From 731cddce6dd110fb2cdee34eddb48599e7251517 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 1 Feb 2022 19:06:27 +0100 Subject: net: mac802154: Convert the symbol duration into nanoseconds Tdsym is often given in the spec as pretty small numbers in microseconds and hence was reflected in the code as symbol_duration and was stored as a u8. Actually, for UWB PHYs, the symbol duration is given in nanoseconds and are as precise as picoseconds. In order to handle better these PHYs, change the type of symbol_duration to u32 and store this value in nanoseconds. All the users of this variable are updated in a mechanical way. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220201180629.93410-3-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 833672d6fbe4..92d4f178caca 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -203,8 +203,8 @@ struct wpan_phy { /* PHY depended MAC PIB values */ - /* 802.15.4 acronym: Tdsym in usec */ - u8 symbol_duration; + /* 802.15.4 acronym: Tdsym in nsec */ + u32 symbol_duration; /* lifs and sifs periods timing */ u16 lifs_period; u16 sifs_period; -- cgit v1.2.3 From 781830c800ddd19566846c634de09fadf37eafde Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 1 Feb 2022 19:06:28 +0100 Subject: net: mac802154: Set durations automatically As depicted in the IEEE 802.15.4 specification, modulation/bands are tight to a number of page/channels so we can for most of them derive the durations automatically. The two locations that must call this new helper to set the variou symbol durations are: - when manually requesting a channel change though the netlink interface - at PHY creation, once the device driver has set the default page/channel If an information is missing, the symbol duration is not touched, a debug message is eventually printed. This keeps the compatibility with the unconverted drivers for which it was too complicated for me to find their precise information. If they initially provided a symbol duration, it would be kept. If they don't, the symbol duration value is left untouched. Once the symbol duration derived, the lifs and sifs durations are updated as well. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220201180629.93410-4-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 92d4f178caca..85f9e8417688 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -415,4 +415,6 @@ static inline const char *wpan_phy_name(struct wpan_phy *phy) return dev_name(&phy->dev); } +void ieee802154_configure_durations(struct wpan_phy *phy); + #endif /* __NET_CFG802154_H */ -- cgit v1.2.3 From dc55e35f9e810f23dd69cfdc91a3d636023f57a2 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Mon, 14 Feb 2022 19:18:14 +0100 Subject: ipc: Store mqueue sysctls in the ipc namespace Right now, the mqueue sysctls take ipc namespaces into account in a rather hacky way. This works in most cases, but does not respect the user namespace. Within the user namespace, the user cannot change the /proc/sys/fs/mqueue/* parametres. This poses a problem in the rootless containers. To solve this I changed the implementation of the mqueue sysctls just like some other sysctls. So far, the changes do not provide additional access to files. This will be done in a future patch. v3: * Don't implemenet set_permissions to keep the current behavior. v2: * Fixed compilation problem if CONFIG_POSIX_MQUEUE_SYSCTL is not specified. Reported-by: kernel test robot Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/b0ccbb2489119f1f20c737cf1930c3a9c4e4243a.1644862280.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/ipc_namespace.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index b75395ec8d52..fa787d97d60a 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -10,6 +10,7 @@ #include #include #include +#include struct user_namespace; @@ -63,6 +64,9 @@ struct ipc_namespace { unsigned int mq_msg_default; unsigned int mq_msgsize_default; + struct ctl_table_set mq_set; + struct ctl_table_header *mq_sysctls; + /* user_ns which owns the ipc ns */ struct user_namespace *user_ns; struct ucounts *ucounts; @@ -169,14 +173,18 @@ static inline void put_ipc_ns(struct ipc_namespace *ns) #ifdef CONFIG_POSIX_MQUEUE_SYSCTL -struct ctl_table_header; -extern struct ctl_table_header *mq_register_sysctl_table(void); +void retire_mq_sysctls(struct ipc_namespace *ns); +bool setup_mq_sysctls(struct ipc_namespace *ns); #else /* CONFIG_POSIX_MQUEUE_SYSCTL */ -static inline struct ctl_table_header *mq_register_sysctl_table(void) +static inline void retire_mq_sysctls(struct ipc_namespace *ns) { - return NULL; +} + +static inline bool setup_mq_sysctls(struct ipc_namespace *ns) +{ + return true; } #endif /* CONFIG_POSIX_MQUEUE_SYSCTL */ -- cgit v1.2.3 From 1f5c135ee509e89e0cc274333a65f73c62cb16e5 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Mon, 14 Feb 2022 19:18:15 +0100 Subject: ipc: Store ipc sysctls in the ipc namespace The ipc sysctls are not available for modification inside the user namespace. Following the mqueue sysctls, we changed the implementation to be more userns friendly. So far, the changes do not provide additional access to files. This will be done in a future patch. Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/be6f9d014276f4dddd0c3aa05a86052856c1c555.1644862280.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/ipc_namespace.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index fa787d97d60a..e3e8c8662b49 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -67,6 +67,9 @@ struct ipc_namespace { struct ctl_table_set mq_set; struct ctl_table_header *mq_sysctls; + struct ctl_table_set ipc_set; + struct ctl_table_header *ipc_sysctls; + /* user_ns which owns the ipc ns */ struct user_namespace *user_ns; struct ucounts *ucounts; @@ -188,4 +191,22 @@ static inline bool setup_mq_sysctls(struct ipc_namespace *ns) } #endif /* CONFIG_POSIX_MQUEUE_SYSCTL */ + +#ifdef CONFIG_SYSVIPC_SYSCTL + +bool setup_ipc_sysctls(struct ipc_namespace *ns); +void retire_ipc_sysctls(struct ipc_namespace *ns); + +#else /* CONFIG_SYSVIPC_SYSCTL */ + +static inline void retire_ipc_sysctls(struct ipc_namespace *ns) +{ +} + +static inline bool setup_ipc_sysctls(struct ipc_namespace *ns) +{ + return true; +} + +#endif /* CONFIG_SYSVIPC_SYSCTL */ #endif -- cgit v1.2.3 From 8733068b9bdbc7a54f02dcc59eb0e4789cd60942 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:17 +0000 Subject: KVM: x86/xen: Make kvm_xen_set_evtchn() reusable from other places Clean it up to return -errno on error consistently, while still being compatible with the return conventions for kvm_arch_set_irq_inatomic() and the kvm_set_irq() callback. We use -ENOTCONN to indicate when the port is masked. No existing users care, except that it's negative. Also allow it to optimise the vCPU lookup. Unless we abuse the lapic map, there is no quick lookup from APIC ID to a vCPU; the logic in kvm_get_vcpu_by_id() will just iterate over all vCPUs till it finds the one it wants. So do that just once and stash the result in the struct kvm_xen_evtchn for next time. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-8-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3f9b22c4983a..252ee4a61b58 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -611,7 +611,8 @@ struct kvm_hv_sint { struct kvm_xen_evtchn { u32 port; - u32 vcpu; + u32 vcpu_id; + int vcpu_idx; u32 priority; }; -- cgit v1.2.3 From 35025735a79eaa894c43837b94fd33c9d6b122df Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:18 +0000 Subject: KVM: x86/xen: Support direct injection of event channel events This adds a KVM_XEN_HVM_EVTCHN_SEND ioctl which allows direct injection of events given an explicit { vcpu, port, priority } in precisely the same form that those fields are given in the IRQ routing table. Userspace is currently able to inject 2-level events purely by setting the bits in the shared_info and vcpu_info, but FIFO event channels are harder to deal with; we will need the kernel to take sole ownership of delivery when we support those. A patch advertising this feature with a new bit in the KVM_CAP_XEN_HVM ioctl will be added in a subsequent patch. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-9-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 91a6fe4e02c0..49cd2e9e0f6a 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1699,6 +1699,9 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_HVM_EVTCHN_SEND _IOW(KVMIO, 0xd0, struct kvm_irq_routing_xen_evtchn) + #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) -- cgit v1.2.3 From 2fd6df2f2b47d4301b1ee0fe9d627d1c061a5988 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Thu, 3 Mar 2022 15:41:19 +0000 Subject: KVM: x86/xen: intercept EVTCHNOP_send from guests Userspace registers a sending @port to either deliver to an @eventfd or directly back to a local event channel port. After binding events the guest or host may wish to bind those events to a particular vcpu. This is usually done for unbound and and interdomain events. Update requests are handled via the KVM_XEN_EVTCHN_UPDATE flag. Unregistered ports are handled by the emulator. Co-developed-by: Ankur Arora Co-developed-By: David Woodhouse Signed-off-by: Joao Martins Signed-off-by: Ankur Arora Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-10-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 49cd2e9e0f6a..623ed2cb228f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1686,6 +1686,32 @@ struct kvm_xen_hvm_attr { struct { __u64 gfn; } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u64 pad[8]; } u; }; @@ -1694,6 +1720,8 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 #define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) -- cgit v1.2.3 From 942c2490c23f2800ad8143f5eb84a79b859aa743 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:21 +0000 Subject: KVM: x86/xen: Add KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID In order to intercept hypercalls such as VCPUOP_set_singleshot_timer, we need to be aware of the Xen CPU numbering. This looks a lot like the Hyper-V handling of vpidx, for obvious reasons. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-12-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 623ed2cb228f..4b65e9f0a4d9 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1747,6 +1747,7 @@ struct kvm_xen_vcpu_attr { __u64 time_blocked; __u64 time_offline; } runstate; + __u32 vcpu_id; } u; }; @@ -1757,6 +1758,8 @@ struct kvm_xen_vcpu_attr { #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { -- cgit v1.2.3 From 536395260582be7443b0b35b0bbb89ffe3947f62 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Thu, 3 Mar 2022 15:41:22 +0000 Subject: KVM: x86/xen: handle PV timers oneshot mode If the guest has offloaded the timer virq, handle the following hypercalls for programming the timer: VCPUOP_set_singleshot_timer VCPUOP_stop_singleshot_timer set_timer_op(timestamp_ns) The event channel corresponding to the timer virq is then used to inject events once timer deadlines are met. For now we back the PV timer with hrtimer. [ dwmw2: Add save/restore, 32-bit compat mode, immediate delivery, don't check timer in kvm_vcpu_has_event() ] Signed-off-by: Joao Martins Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-13-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4b65e9f0a4d9..cb223e425223 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1748,6 +1748,11 @@ struct kvm_xen_vcpu_attr { __u64 time_offline; } runstate; __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; } u; }; @@ -1760,6 +1765,7 @@ struct kvm_xen_vcpu_attr { #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { -- cgit v1.2.3 From 28d1629f751c4a5f9437fbaa0ee4ed81d1a8e587 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:23 +0000 Subject: KVM: x86/xen: Kernel acceleration for XENVER_version Turns out this is a fast path for PV guests because they use it to trigger the event channel upcall. So letting it bounce all the way up to userspace is not great. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-14-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index cb223e425223..4dda3896ed71 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1711,7 +1711,7 @@ struct kvm_xen_hvm_attr { __u32 padding[4]; } deliver; } evtchn; - + __u32 xen_version; __u64 pad[8]; } u; }; @@ -1722,6 +1722,7 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ #define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) -- cgit v1.2.3 From fde0451be8fb3208d4d146b8602d99ee8139e515 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:24 +0000 Subject: KVM: x86/xen: Support per-vCPU event channel upcall via local APIC Windows uses a per-vCPU vector, and it's delivered via the local APIC basically like an MSI (with associated EOI) unlike the traditional guest-wide vector which is just magically asserted by Xen (and in the KVM case by kvm_xen_has_interrupt() / kvm_cpu_get_extint()). Now that the kernel is able to raise event channel events for itself, being able to do so for Windows guests is also going to be useful. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-15-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4dda3896ed71..a9ba690c4f37 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1754,6 +1754,7 @@ struct kvm_xen_vcpu_attr { __u32 priority; __u64 expires_ns; } timer; + __u8 vector; } u; }; @@ -1767,6 +1768,7 @@ struct kvm_xen_vcpu_attr { /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 #define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { -- cgit v1.2.3 From 661a20fab7d156cf6b9a407c946a1e558a633151 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:25 +0000 Subject: KVM: x86/xen: Advertise and document KVM_XEN_HVM_CONFIG_EVTCHN_SEND MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit At the end of the patch series adding this batch of event channel acceleration features, finally add the feature bit which advertises them and document it all. For SCHEDOP_poll we need to wake a polling vCPU when a given port is triggered, even when it's masked — and we want to implement that in the kernel, for efficiency. So we want the kernel to know that it has sole ownership of event channel delivery. Thus, we allow userspace to make the 'promise' by setting the corresponding feature bit in its KVM_XEN_HVM_CONFIG call. As we implement SCHEDOP_poll bypass later, we will do so only if that promise has been made by userspace. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-16-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a9ba690c4f37..ee5cc9e2a837 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1232,6 +1232,7 @@ struct kvm_x86_mce { #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) +#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) struct kvm_xen_hvm_config { __u32 flags; -- cgit v1.2.3 From ffbb61d09fc56c85e28b110494f3788d0ed4d1f8 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 25 Feb 2022 14:53:02 +0000 Subject: KVM: x86: Accept KVM_[GS]ET_TSC_KHZ as a VM ioctl. This sets the default TSC frequency for subsequently created vCPUs. Signed-off-by: David Woodhouse Message-Id: <20220225145304.36166-2-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ee5cc9e2a837..8616af85dc5d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1144,6 +1144,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_MEM_OP_EXTENSION 211 #define KVM_CAP_PMU_CAPABILITY 212 #define KVM_CAP_DISABLE_QUIRKS2 213 +#define KVM_CAP_VM_TSC_CONTROL 214 #ifdef KVM_CAP_IRQ_ROUTING @@ -1471,7 +1472,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2) /* Available with KVM_CAP_PPC_GET_PVINFO */ #define KVM_PPC_GET_PVINFO _IOW(KVMIO, 0xa1, struct kvm_ppc_pvinfo) -/* Available with KVM_CAP_TSC_CONTROL */ +/* Available with KVM_CAP_TSC_CONTROL for a vCPU, or with +* KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */ #define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2) #define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3) /* Available with KVM_CAP_PCI_2_3 */ -- cgit v1.2.3 From 66df0fdb5981052f3ad97c9879eda93712bdefc2 Mon Sep 17 00:00:00 2001 From: Haiyue Wang Date: Sun, 3 Apr 2022 19:53:26 +0800 Subject: bpf: Correct the comment for BTF kind bitfield The commit 8fd886911a6a ("bpf: Add BTF_KIND_FLOAT to uapi") has extended the BTF kind bitfield from 4 to 5 bits, correct the comment. Signed-off-by: Haiyue Wang Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220403115327.205964-1-haiyue.wang@intel.com --- include/uapi/linux/btf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index b0d8fea1951d..a9162a6c0284 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -33,8 +33,8 @@ struct btf_type { /* "info" bits arrangement * bits 0-15: vlen (e.g. # of struct's members) * bits 16-23: unused - * bits 24-27: kind (e.g. int, ptr, array...etc) - * bits 28-30: unused + * bits 24-28: kind (e.g. int, ptr, array...etc) + * bits 29-30: unused * bit 31: kind_flag, currently used by * struct, union and fwd */ -- cgit v1.2.3 From 8bea9af887de4c99a95f93f2ce400ef63e8b4e9b Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 22 Mar 2022 12:50:27 +0200 Subject: iio: adc: ad_sigma_delta: Add sequencer support Some sigma-delta chips support sampling of multiple channels in continuous mode. When the operating with more than one channel enabled, the channel sequencer cycles through the enabled channels in sequential order, from first channel to the last one. If a channel is disabled, it is skipped by the sequencer. If more than one channel is used in continuous mode, instruct the device to append the status to the SPI transfer (1 extra byte) every time we receive a sample. All sigma-delta chips possessing a sampling sequencer have this ability. Inside the status register there will be the number of the converted channel. In this way, even if the CPU won't keep up with the sampling rate, it won't send to userspace wrong channel samples. When multiple channels are enabled in continuous mode, the device needs to perform a measurement on all slots before we can push to userspace the sample. If, during sequencing and data reading, a channel measurement is lost, a desync occurred. In this case, ad_sigma_delta drops the incomplete sample and waits for the device to send the measurement on the first active slot. Co-developed-by: Alexandru Tachici Signed-off-by: Alexandru Tachici Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20220322105029.86389-5-alexandru.tachici@analog.com Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/ad_sigma_delta.h | 38 ++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index c525fd51652f..7852f6c9a714 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -32,26 +32,34 @@ struct iio_dev; /** * struct ad_sigma_delta_info - Sigma Delta driver specific callbacks and options * @set_channel: Will be called to select the current channel, may be NULL. + * @append_status: Will be called to enable status append at the end of the sample, may be NULL. * @set_mode: Will be called to select the current mode, may be NULL. + * @disable_all: Will be called to disable all channels, may be NULL. * @postprocess_sample: Is called for each sampled data word, can be used to * modify or drop the sample data, it, may be NULL. * @has_registers: true if the device has writable and readable registers, false * if there is just one read-only sample data shift register. * @addr_shift: Shift of the register address in the communications register. * @read_mask: Mask for the communications register having the read bit set. + * @status_ch_mask: Mask for the channel number stored in status register. * @data_reg: Address of the data register, if 0 the default address of 0x3 will * be used. * @irq_flags: flags for the interrupt used by the triggered buffer + * @num_slots: Number of sequencer slots */ struct ad_sigma_delta_info { int (*set_channel)(struct ad_sigma_delta *, unsigned int channel); + int (*append_status)(struct ad_sigma_delta *, bool append); int (*set_mode)(struct ad_sigma_delta *, enum ad_sigma_delta_mode mode); + int (*disable_all)(struct ad_sigma_delta *); int (*postprocess_sample)(struct ad_sigma_delta *, unsigned int raw_sample); bool has_registers; unsigned int addr_shift; unsigned int read_mask; + unsigned int status_ch_mask; unsigned int data_reg; unsigned long irq_flags; + unsigned int num_slots; }; /** @@ -76,6 +84,13 @@ struct ad_sigma_delta { uint8_t comm; const struct ad_sigma_delta_info *info; + unsigned int active_slots; + unsigned int current_slot; + unsigned int num_slots; + bool status_appended; + /* map slots to channels in order to know what to expect from devices */ + unsigned int *slots; + uint8_t *samples_buf; /* * DMA (thus cache coherency maintenance) requires the @@ -97,6 +112,29 @@ static inline int ad_sigma_delta_set_channel(struct ad_sigma_delta *sd, return 0; } +static inline int ad_sigma_delta_append_status(struct ad_sigma_delta *sd, bool append) +{ + int ret; + + if (sd->info->append_status) { + ret = sd->info->append_status(sd, append); + if (ret < 0) + return ret; + + sd->status_appended = append; + } + + return 0; +} + +static inline int ad_sigma_delta_disable_all(struct ad_sigma_delta *sd) +{ + if (sd->info->disable_all) + return sd->info->disable_all(sd); + + return 0; +} + static inline int ad_sigma_delta_set_mode(struct ad_sigma_delta *sd, unsigned int mode) { -- cgit v1.2.3 From e87f4152e542610d0b4c6c8548964a68a59d2040 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 23 Mar 2022 20:02:41 +0100 Subject: task_stack, x86/cea: Force-inline stack helpers Force-inline two stack helpers to fix the following objtool warnings: vmlinux.o: warning: objtool: in_task_stack()+0xc: call to task_stack_page() leaves .noinstr.text section vmlinux.o: warning: objtool: in_entry_stack()+0x10: call to cpu_entry_stack() leaves .noinstr.text section Signed-off-by: Borislav Petkov Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220324183607.31717-2-bp@alien8.de --- include/linux/sched/task_stack.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index 892562ebbd3a..5e799a47431e 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -16,7 +16,7 @@ * try_get_task_stack() instead. task_stack_page will return a pointer * that could get freed out from under you. */ -static inline void *task_stack_page(const struct task_struct *task) +static __always_inline void *task_stack_page(const struct task_struct *task) { return task->stack; } -- cgit v1.2.3 From 19c66219e4d5b813ebbd28621cfe9c450659ded7 Mon Sep 17 00:00:00 2001 From: Allen-KH Cheng Date: Fri, 18 Mar 2022 22:45:31 +0800 Subject: arm64: dts: mt8192: Add the mmsys reset bit to reset the dsi0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reset the DSI hardware is needed to prevent different settings between the bootloader and the kernel. Signed-off-by: Allen-KH Cheng Reviewed-by: Nícolas F. R. A. Prado Reviewed-by: AngeloGioacchino Del Regno Acked-by: Rob Herring Link: https://lore.kernel.org/r/20220318144534.17996-20-allen-kh.cheng@mediatek.com Signed-off-by: Matthias Brugger --- include/dt-bindings/reset/mt8192-resets.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/reset/mt8192-resets.h b/include/dt-bindings/reset/mt8192-resets.h index be9a7ca245b9..764ca9910fa9 100644 --- a/include/dt-bindings/reset/mt8192-resets.h +++ b/include/dt-bindings/reset/mt8192-resets.h @@ -27,4 +27,7 @@ #define MT8192_TOPRGU_SW_RST_NUM 23 +/* MMSYS resets */ +#define MT8192_MMSYS_SW0_RST_B_DISP_DSI0 15 + #endif /* _DT_BINDINGS_RESET_CONTROLLER_MT8192 */ -- cgit v1.2.3 From 30ad63e784dd71cbc608a0d039a88e6df12aa258 Mon Sep 17 00:00:00 2001 From: Xiao Yang Date: Thu, 31 Mar 2022 11:24:18 +0800 Subject: IB/uverbs: Move enum ib_raw_packet_caps to uapi This enum is used by ibv_query_device_ex(3) so it should be defined in include/uapi/rdma/ib_user_verbs.h. Link: https://lore.kernel.org/r/20220331032419.313904-1-yangx.jy@fujitsu.com Signed-off-by: Xiao Yang Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 18 +++++++++++------- include/uapi/rdma/ib_user_verbs.h | 7 +++++++ 2 files changed, 18 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 69d883f7fb41..dfd467469622 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1621,19 +1621,23 @@ struct ib_srq { }; enum ib_raw_packet_caps { - /* Strip cvlan from incoming packet and report it in the matching work + /* + * Strip cvlan from incoming packet and report it in the matching work * completion is supported. */ - IB_RAW_PACKET_CAP_CVLAN_STRIPPING = (1 << 0), - /* Scatter FCS field of an incoming packet to host memory is supported. + IB_RAW_PACKET_CAP_CVLAN_STRIPPING = + IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING, + /* + * Scatter FCS field of an incoming packet to host memory is supported. */ - IB_RAW_PACKET_CAP_SCATTER_FCS = (1 << 1), + IB_RAW_PACKET_CAP_SCATTER_FCS = IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS, /* Checksum offloads are supported (for both send and receive). */ - IB_RAW_PACKET_CAP_IP_CSUM = (1 << 2), - /* When a packet is received for an RQ with no receive WQEs, the + IB_RAW_PACKET_CAP_IP_CSUM = IB_UVERBS_RAW_PACKET_CAP_IP_CSUM, + /* + * When a packet is received for an RQ with no receive WQEs, the * packet processing is delayed. */ - IB_RAW_PACKET_CAP_DELAY_DROP = (1 << 3), + IB_RAW_PACKET_CAP_DELAY_DROP = IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP, }; enum ib_wq_type { diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 7ee73a0652f1..ff549695f1ba 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -1298,4 +1298,11 @@ struct ib_uverbs_ex_modify_cq { #define IB_DEVICE_NAME_MAX 64 +enum ib_uverbs_raw_packet_caps { + IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING = 1 << 0, + IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS = 1 << 1, + IB_UVERBS_RAW_PACKET_CAP_IP_CSUM = 1 << 2, + IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP = 1 << 3, +}; + #endif /* IB_USER_VERBS_H */ -- cgit v1.2.3 From f543a3e82bb275349961f8507ee195f34132ffb4 Mon Sep 17 00:00:00 2001 From: Xiao Yang Date: Thu, 31 Mar 2022 11:24:19 +0800 Subject: IB/uverbs: Move part of enum ib_device_cap_flags to uapi 1) Part of enum ib_device_cap_flags are used by ibv_query_device(3) or ibv_query_device_ex(3), so we define them in include/uapi/rdma/ib_user_verbs.h and only expose them to userspace. 2) Reformat enum ib_device_cap_flags by removing the indent before '='. Link: https://lore.kernel.org/r/20220331032419.313904-2-yangx.jy@fujitsu.com Signed-off-by: Xiao Yang Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 104 ++++++++++++++++++++++++-------------- include/uapi/rdma/ib_user_verbs.h | 31 ++++++++++++ 2 files changed, 97 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index dfd467469622..ada4a5226dbd 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -220,21 +220,21 @@ enum rdma_link_layer { }; enum ib_device_cap_flags { - IB_DEVICE_RESIZE_MAX_WR = (1 << 0), - IB_DEVICE_BAD_PKEY_CNTR = (1 << 1), - IB_DEVICE_BAD_QKEY_CNTR = (1 << 2), - IB_DEVICE_RAW_MULTI = (1 << 3), - IB_DEVICE_AUTO_PATH_MIG = (1 << 4), - IB_DEVICE_CHANGE_PHY_PORT = (1 << 5), - IB_DEVICE_UD_AV_PORT_ENFORCE = (1 << 6), - IB_DEVICE_CURR_QP_STATE_MOD = (1 << 7), - IB_DEVICE_SHUTDOWN_PORT = (1 << 8), - /* Not in use, former INIT_TYPE = (1 << 9),*/ - IB_DEVICE_PORT_ACTIVE_EVENT = (1 << 10), - IB_DEVICE_SYS_IMAGE_GUID = (1 << 11), - IB_DEVICE_RC_RNR_NAK_GEN = (1 << 12), - IB_DEVICE_SRQ_RESIZE = (1 << 13), - IB_DEVICE_N_NOTIFY_CQ = (1 << 14), + IB_DEVICE_RESIZE_MAX_WR = IB_UVERBS_DEVICE_RESIZE_MAX_WR, + IB_DEVICE_BAD_PKEY_CNTR = IB_UVERBS_DEVICE_BAD_PKEY_CNTR, + IB_DEVICE_BAD_QKEY_CNTR = IB_UVERBS_DEVICE_BAD_QKEY_CNTR, + IB_DEVICE_RAW_MULTI = IB_UVERBS_DEVICE_RAW_MULTI, + IB_DEVICE_AUTO_PATH_MIG = IB_UVERBS_DEVICE_AUTO_PATH_MIG, + IB_DEVICE_CHANGE_PHY_PORT = IB_UVERBS_DEVICE_CHANGE_PHY_PORT, + IB_DEVICE_UD_AV_PORT_ENFORCE = IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE, + IB_DEVICE_CURR_QP_STATE_MOD = IB_UVERBS_DEVICE_CURR_QP_STATE_MOD, + IB_DEVICE_SHUTDOWN_PORT = IB_UVERBS_DEVICE_SHUTDOWN_PORT, + /* IB_DEVICE_INIT_TYPE = IB_UVERBS_DEVICE_INIT_TYPE, (not in use) */ + IB_DEVICE_PORT_ACTIVE_EVENT = IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT, + IB_DEVICE_SYS_IMAGE_GUID = IB_UVERBS_DEVICE_SYS_IMAGE_GUID, + IB_DEVICE_RC_RNR_NAK_GEN = IB_UVERBS_DEVICE_RC_RNR_NAK_GEN, + IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE, + IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ, /* * This device supports a per-device lkey or stag that can be @@ -243,9 +243,9 @@ enum ib_device_cap_flags { * instead of use the local_dma_lkey flag in the ib_pd structure, * which will always contain a usable lkey. */ - IB_DEVICE_LOCAL_DMA_LKEY = (1 << 15), - /* Reserved, old SEND_W_INV = (1 << 16),*/ - IB_DEVICE_MEM_WINDOW = (1 << 17), + IB_DEVICE_LOCAL_DMA_LKEY = 1 << 15, + /* Reserved, old SEND_W_INV = 1 << 16,*/ + IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW, /* * Devices should set IB_DEVICE_UD_IP_SUM if they support * insertion of UDP and TCP checksum on outgoing UD IPoIB @@ -253,9 +253,9 @@ enum ib_device_cap_flags { * incoming messages. Setting this flag implies that the * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode. */ - IB_DEVICE_UD_IP_CSUM = (1 << 18), - IB_DEVICE_UD_TSO = (1 << 19), - IB_DEVICE_XRC = (1 << 20), + IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM, + IB_DEVICE_UD_TSO = 1 << 19, + IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC, /* * This device supports the IB "base memory management extension", @@ -266,32 +266,60 @@ enum ib_device_cap_flags { * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the * stag. */ - IB_DEVICE_MEM_MGT_EXTENSIONS = (1 << 21), - IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = (1 << 22), - IB_DEVICE_MEM_WINDOW_TYPE_2A = (1 << 23), - IB_DEVICE_MEM_WINDOW_TYPE_2B = (1 << 24), - IB_DEVICE_RC_IP_CSUM = (1 << 25), + IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS, + IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = 1 << 22, + IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A, + IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B, + IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM, /* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */ - IB_DEVICE_RAW_IP_CSUM = (1 << 26), + IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM, /* * Devices should set IB_DEVICE_CROSS_CHANNEL if they * support execution of WQEs that involve synchronization * of I/O operations with single completion queue managed * by hardware. */ - IB_DEVICE_CROSS_CHANNEL = (1 << 27), - IB_DEVICE_MANAGED_FLOW_STEERING = (1 << 29), - IB_DEVICE_INTEGRITY_HANDOVER = (1 << 30), - IB_DEVICE_ON_DEMAND_PAGING = (1ULL << 31), - IB_DEVICE_SG_GAPS_REG = (1ULL << 32), - IB_DEVICE_VIRTUAL_FUNCTION = (1ULL << 33), + IB_DEVICE_CROSS_CHANNEL = 1 << 27, + IB_DEVICE_MANAGED_FLOW_STEERING = + IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING, + IB_DEVICE_INTEGRITY_HANDOVER = 1 << 30, + IB_DEVICE_ON_DEMAND_PAGING = 1ULL << 31, + IB_DEVICE_SG_GAPS_REG = 1ULL << 32, + IB_DEVICE_VIRTUAL_FUNCTION = 1ULL << 33, /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ - IB_DEVICE_RAW_SCATTER_FCS = (1ULL << 34), - IB_DEVICE_RDMA_NETDEV_OPA = (1ULL << 35), + IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS, + IB_DEVICE_RDMA_NETDEV_OPA = 1ULL << 35, /* The device supports padding incoming writes to cacheline. */ - IB_DEVICE_PCI_WRITE_END_PADDING = (1ULL << 36), - IB_DEVICE_ALLOW_USER_UNREG = (1ULL << 37), -}; + IB_DEVICE_PCI_WRITE_END_PADDING = + IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING, + IB_DEVICE_ALLOW_USER_UNREG = 1ULL << 37, +}; + +#define IB_UVERBS_DEVICE_CAP_FLAGS_MASK (IB_UVERBS_DEVICE_RESIZE_MAX_WR | \ + IB_UVERBS_DEVICE_BAD_PKEY_CNTR | \ + IB_UVERBS_DEVICE_BAD_QKEY_CNTR | \ + IB_UVERBS_DEVICE_RAW_MULTI | \ + IB_UVERBS_DEVICE_AUTO_PATH_MIG | \ + IB_UVERBS_DEVICE_CHANGE_PHY_PORT | \ + IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE | \ + IB_UVERBS_DEVICE_CURR_QP_STATE_MOD | \ + IB_UVERBS_DEVICE_SHUTDOWN_PORT | \ + IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT | \ + IB_UVERBS_DEVICE_SYS_IMAGE_GUID | \ + IB_UVERBS_DEVICE_RC_RNR_NAK_GEN | \ + IB_UVERBS_DEVICE_SRQ_RESIZE | \ + IB_UVERBS_DEVICE_N_NOTIFY_CQ | \ + IB_UVERBS_DEVICE_MEM_WINDOW | \ + IB_UVERBS_DEVICE_UD_IP_CSUM | \ + IB_UVERBS_DEVICE_XRC | \ + IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS | \ + IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A | \ + IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B | \ + IB_UVERBS_DEVICE_RC_IP_CSUM | \ + IB_UVERBS_DEVICE_RAW_IP_CSUM | \ + IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING | \ + IB_UVERBS_DEVICE_RAW_SCATTER_FCS | \ + IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING) enum ib_atomic_cap { IB_ATOMIC_NONE, diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index ff549695f1ba..06a4897c4958 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -1298,6 +1298,37 @@ struct ib_uverbs_ex_modify_cq { #define IB_DEVICE_NAME_MAX 64 +enum ib_uverbs_device_cap_flags { + IB_UVERBS_DEVICE_RESIZE_MAX_WR = 1 << 0, + IB_UVERBS_DEVICE_BAD_PKEY_CNTR = 1 << 1, + IB_UVERBS_DEVICE_BAD_QKEY_CNTR = 1 << 2, + IB_UVERBS_DEVICE_RAW_MULTI = 1 << 3, + IB_UVERBS_DEVICE_AUTO_PATH_MIG = 1 << 4, + IB_UVERBS_DEVICE_CHANGE_PHY_PORT = 1 << 5, + IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE = 1 << 6, + IB_UVERBS_DEVICE_CURR_QP_STATE_MOD = 1 << 7, + IB_UVERBS_DEVICE_SHUTDOWN_PORT = 1 << 8, + /* IB_UVERBS_DEVICE_INIT_TYPE = 1 << 9, (not in use) */ + IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT = 1 << 10, + IB_UVERBS_DEVICE_SYS_IMAGE_GUID = 1 << 11, + IB_UVERBS_DEVICE_RC_RNR_NAK_GEN = 1 << 12, + IB_UVERBS_DEVICE_SRQ_RESIZE = 1 << 13, + IB_UVERBS_DEVICE_N_NOTIFY_CQ = 1 << 14, + IB_UVERBS_DEVICE_MEM_WINDOW = 1 << 17, + IB_UVERBS_DEVICE_UD_IP_CSUM = 1 << 18, + IB_UVERBS_DEVICE_XRC = 1 << 20, + IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS = 1 << 21, + IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A = 1 << 23, + IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B = 1 << 24, + IB_UVERBS_DEVICE_RC_IP_CSUM = 1 << 25, + /* Deprecated. Please use IB_UVERBS_RAW_PACKET_CAP_IP_CSUM. */ + IB_UVERBS_DEVICE_RAW_IP_CSUM = 1 << 26, + IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING = 1 << 29, + /* Deprecated. Please use IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS. */ + IB_UVERBS_DEVICE_RAW_SCATTER_FCS = 1ULL << 34, + IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING = 1ULL << 36, +}; + enum ib_uverbs_raw_packet_caps { IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING = 1 << 0, IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS = 1 << 1, -- cgit v1.2.3 From f0e3c6261af183f0c2246cfe691abec78377622c Mon Sep 17 00:00:00 2001 From: Johnson Wang Date: Fri, 1 Apr 2022 16:02:11 +0800 Subject: regulator: mt6366: Add support for MT6366 regulator The MT6366 is a regulator found on boards based on MediaTek MT8186 and probably other SoCs. It is a so called pmic and connects as a slave to SoC using SPI, wrapped inside the pmic-wrapper. Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Johnson Wang Link: https://lore.kernel.org/r/20220401080212.27383-2-johnson.wang@mediatek.com Signed-off-by: Mark Brown --- include/linux/regulator/mt6358-regulator.h | 45 ++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include') diff --git a/include/linux/regulator/mt6358-regulator.h b/include/linux/regulator/mt6358-regulator.h index 1cc304946d09..bdcf83cd719e 100644 --- a/include/linux/regulator/mt6358-regulator.h +++ b/include/linux/regulator/mt6358-regulator.h @@ -48,9 +48,54 @@ enum { MT6358_ID_VLDO28, MT6358_ID_VAUD28, MT6358_ID_VSIM2, + MT6358_ID_VCORE_SSHUB, + MT6358_ID_VSRAM_OTHERS_SSHUB, MT6358_ID_RG_MAX, }; +enum { + MT6366_ID_VDRAM1 = 0, + MT6366_ID_VCORE, + MT6366_ID_VPA, + MT6366_ID_VPROC11, + MT6366_ID_VPROC12, + MT6366_ID_VGPU, + MT6366_ID_VS2, + MT6366_ID_VMODEM, + MT6366_ID_VS1, + MT6366_ID_VDRAM2, + MT6366_ID_VSIM1, + MT6366_ID_VIBR, + MT6366_ID_VRF12, + MT6366_ID_VIO18, + MT6366_ID_VUSB, + MT6366_ID_VCN18, + MT6366_ID_VFE28, + MT6366_ID_VSRAM_PROC11, + MT6366_ID_VCN28, + MT6366_ID_VSRAM_OTHERS, + MT6366_ID_VSRAM_GPU, + MT6366_ID_VXO22, + MT6366_ID_VEFUSE, + MT6366_ID_VAUX18, + MT6366_ID_VMCH, + MT6366_ID_VBIF28, + MT6366_ID_VSRAM_PROC12, + MT6366_ID_VEMC, + MT6366_ID_VIO28, + MT6366_ID_VA12, + MT6366_ID_VRF18, + MT6366_ID_VCN33_BT, + MT6366_ID_VCN33_WIFI, + MT6366_ID_VMC, + MT6366_ID_VAUD28, + MT6366_ID_VSIM2, + MT6366_ID_VCORE_SSHUB, + MT6366_ID_VSRAM_OTHERS_SSHUB, + MT6366_ID_RG_MAX, +}; + #define MT6358_MAX_REGULATOR MT6358_ID_RG_MAX +#define MT6366_MAX_REGULATOR MT6366_ID_RG_MAX #endif /* __LINUX_REGULATOR_MT6358_H */ -- cgit v1.2.3 From caae9458db3aef14b96921cf02c6093340350c4a Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Fri, 11 Feb 2022 17:42:41 +0100 Subject: kunit: Introduce _NULL and _NOT_NULL macros Today, when we want to check if a pointer is NULL and not ERR we have two options: KUNIT_EXPECT_TRUE(test, ptr == NULL); or KUNIT_EXPECT_PTR_NE(test, ptr, (struct mystruct *)NULL); Create a new set of macros that take care of NULL checks. Reviewed-by: Brendan Higgins Reviewed-by: Daniel Latypov Signed-off-by: Ricardo Ribalda Signed-off-by: Shuah Khan --- include/kunit/test.h | 84 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 00b9ff7783ab..e6c18b609b47 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -1218,6 +1218,48 @@ do { \ fmt, \ ##__VA_ARGS__) +/** + * KUNIT_EXPECT_NULL() - Expects that @ptr is null. + * @test: The test context object. + * @ptr: an arbitrary pointer. + * + * Sets an expectation that the value that @ptr evaluates to is null. This is + * semantically equivalent to KUNIT_EXPECT_PTR_EQ(@test, ptr, NULL). + * See KUNIT_EXPECT_TRUE() for more information. + */ +#define KUNIT_EXPECT_NULL(test, ptr) \ + KUNIT_EXPECT_NULL_MSG(test, \ + ptr, \ + NULL) + +#define KUNIT_EXPECT_NULL_MSG(test, ptr, fmt, ...) \ + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + ptr, ==, NULL, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_NOT_NULL() - Expects that @ptr is not null. + * @test: The test context object. + * @ptr: an arbitrary pointer. + * + * Sets an expectation that the value that @ptr evaluates to is not null. This + * is semantically equivalent to KUNIT_EXPECT_PTR_NE(@test, ptr, NULL). + * See KUNIT_EXPECT_TRUE() for more information. + */ +#define KUNIT_EXPECT_NOT_NULL(test, ptr) \ + KUNIT_EXPECT_NOT_NULL_MSG(test, \ + ptr, \ + NULL) + +#define KUNIT_EXPECT_NOT_NULL_MSG(test, ptr, fmt, ...) \ + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + ptr, !=, NULL, \ + fmt, \ + ##__VA_ARGS__) + /** * KUNIT_EXPECT_NOT_ERR_OR_NULL() - Expects that @ptr is not null and not err. * @test: The test context object. @@ -1485,6 +1527,48 @@ do { \ fmt, \ ##__VA_ARGS__) +/** + * KUNIT_ASSERT_NULL() - Asserts that pointers @ptr is null. + * @test: The test context object. + * @ptr: an arbitrary pointer. + * + * Sets an assertion that the values that @ptr evaluates to is null. This is + * the same as KUNIT_EXPECT_NULL(), except it causes an assertion + * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_NULL(test, ptr) \ + KUNIT_ASSERT_NULL_MSG(test, \ + ptr, \ + NULL) + +#define KUNIT_ASSERT_NULL_MSG(test, ptr, fmt, ...) \ + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_ASSERTION, \ + ptr, ==, NULL, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_NOT_NULL() - Asserts that pointers @ptr is not null. + * @test: The test context object. + * @ptr: an arbitrary pointer. + * + * Sets an assertion that the values that @ptr evaluates to is not null. This + * is the same as KUNIT_EXPECT_NOT_NULL(), except it causes an assertion + * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_NOT_NULL(test, ptr) \ + KUNIT_ASSERT_NOT_NULL_MSG(test, \ + ptr, \ + NULL) + +#define KUNIT_ASSERT_NOT_NULL_MSG(test, ptr, fmt, ...) \ + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_ASSERTION, \ + ptr, !=, NULL, \ + fmt, \ + ##__VA_ARGS__) + /** * KUNIT_ASSERT_NOT_ERR_OR_NULL() - Assertion that @ptr is not null and not err. * @test: The test context object. -- cgit v1.2.3 From 61695f8c5d5190db11aece403304f06d22c90597 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Mon, 28 Mar 2022 10:41:42 -0700 Subject: kunit: split resource API from test.h into new resource.h Background: Currently, a reader looking at kunit/test.h will find the file is quite long, and the first meaty comment is a doc comment about struct kunit_resource. Most users will not ever use the KUnit resource API directly. They'll use kunit_kmalloc() and friends, or decide it's simpler to do cleanups via labels (it often can be) instead of figuring out how to use the API. It's also logically separate from everything else in test.h. Removing it from the file doesn't cause any compilation errors (since struct kunit has `struct list_head resources` to store them). This commit: Let's move it into a kunit/resource.h file and give it a separate page in the docs, kunit/api/resource.rst. We include resource.h at the bottom of test.h since * don't want to force existing users to add a new include if they use the API * it accesses `lock` inside `struct kunit` in a inline func * so we can't just forward declare, and the alternatives require uninlining the func, adding hepers to lock/unlock, or other more invasive changes. Now the first big comment in test.h is about kunit_case, which is a lot more relevant to what a new user wants to know. A side effect of this is git blame won't properly track history by default, users need to run $ git blame -L ,1 -C17 include/kunit/resource.h Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/resource.h | 318 +++++++++++++++++++++++++++++++++++++++++++++++ include/kunit/test.h | 303 +------------------------------------------- 2 files changed, 322 insertions(+), 299 deletions(-) create mode 100644 include/kunit/resource.h (limited to 'include') diff --git a/include/kunit/resource.h b/include/kunit/resource.h new file mode 100644 index 000000000000..7ab1fd83972b --- /dev/null +++ b/include/kunit/resource.h @@ -0,0 +1,318 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KUnit resource API for test managed resources (allocations, etc.). + * + * Copyright (C) 2022, Google LLC. + * Author: Daniel Latypov + */ + +#ifndef _KUNIT_RESOURCE_H +#define _KUNIT_RESOURCE_H + +#include + +#include +#include +#include +#include + +struct kunit_resource; + +typedef int (*kunit_resource_init_t)(struct kunit_resource *, void *); +typedef void (*kunit_resource_free_t)(struct kunit_resource *); + +/** + * struct kunit_resource - represents a *test managed resource* + * @data: for the user to store arbitrary data. + * @name: optional name + * @free: a user supplied function to free the resource. Populated by + * kunit_resource_alloc(). + * + * Represents a *test managed resource*, a resource which will automatically be + * cleaned up at the end of a test case. + * + * Resources are reference counted so if a resource is retrieved via + * kunit_alloc_and_get_resource() or kunit_find_resource(), we need + * to call kunit_put_resource() to reduce the resource reference count + * when finished with it. Note that kunit_alloc_resource() does not require a + * kunit_resource_put() because it does not retrieve the resource itself. + * + * Example: + * + * .. code-block:: c + * + * struct kunit_kmalloc_params { + * size_t size; + * gfp_t gfp; + * }; + * + * static int kunit_kmalloc_init(struct kunit_resource *res, void *context) + * { + * struct kunit_kmalloc_params *params = context; + * res->data = kmalloc(params->size, params->gfp); + * + * if (!res->data) + * return -ENOMEM; + * + * return 0; + * } + * + * static void kunit_kmalloc_free(struct kunit_resource *res) + * { + * kfree(res->data); + * } + * + * void *kunit_kmalloc(struct kunit *test, size_t size, gfp_t gfp) + * { + * struct kunit_kmalloc_params params; + * + * params.size = size; + * params.gfp = gfp; + * + * return kunit_alloc_resource(test, kunit_kmalloc_init, + * kunit_kmalloc_free, ¶ms); + * } + * + * Resources can also be named, with lookup/removal done on a name + * basis also. kunit_add_named_resource(), kunit_find_named_resource() + * and kunit_destroy_named_resource(). Resource names must be + * unique within the test instance. + */ +struct kunit_resource { + void *data; + const char *name; + kunit_resource_free_t free; + + /* private: internal use only. */ + struct kref refcount; + struct list_head node; +}; + +/* + * Like kunit_alloc_resource() below, but returns the struct kunit_resource + * object that contains the allocation. This is mostly for testing purposes. + */ +struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + gfp_t internal_gfp, + void *context); + +/** + * kunit_get_resource() - Hold resource for use. Should not need to be used + * by most users as we automatically get resources + * retrieved by kunit_find_resource*(). + * @res: resource + */ +static inline void kunit_get_resource(struct kunit_resource *res) +{ + kref_get(&res->refcount); +} + +/* + * Called when refcount reaches zero via kunit_put_resource(); + * should not be called directly. + */ +static inline void kunit_release_resource(struct kref *kref) +{ + struct kunit_resource *res = container_of(kref, struct kunit_resource, + refcount); + + /* If free function is defined, resource was dynamically allocated. */ + if (res->free) { + res->free(res); + kfree(res); + } +} + +/** + * kunit_put_resource() - When caller is done with retrieved resource, + * kunit_put_resource() should be called to drop + * reference count. The resource list maintains + * a reference count on resources, so if no users + * are utilizing a resource and it is removed from + * the resource list, it will be freed via the + * associated free function (if any). Only + * needs to be used if we alloc_and_get() or + * find() resource. + * @res: resource + */ +static inline void kunit_put_resource(struct kunit_resource *res) +{ + kref_put(&res->refcount, kunit_release_resource); +} + +/** + * kunit_add_resource() - Add a *test managed resource*. + * @test: The test context object. + * @init: a user-supplied function to initialize the result (if needed). If + * none is supplied, the resource data value is simply set to @data. + * If an init function is supplied, @data is passed to it instead. + * @free: a user-supplied function to free the resource (if needed). + * @res: The resource. + * @data: value to pass to init function or set in resource data field. + */ +int kunit_add_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + struct kunit_resource *res, + void *data); + +/** + * kunit_add_named_resource() - Add a named *test managed resource*. + * @test: The test context object. + * @init: a user-supplied function to initialize the resource data, if needed. + * @free: a user-supplied function to free the resource data, if needed. + * @res: The resource. + * @name: name to be set for resource. + * @data: value to pass to init function or set in resource data field. + */ +int kunit_add_named_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + struct kunit_resource *res, + const char *name, + void *data); + +/** + * kunit_alloc_resource() - Allocates a *test managed resource*. + * @test: The test context object. + * @init: a user supplied function to initialize the resource. + * @free: a user supplied function to free the resource. + * @internal_gfp: gfp to use for internal allocations, if unsure, use GFP_KERNEL + * @context: for the user to pass in arbitrary data to the init function. + * + * Allocates a *test managed resource*, a resource which will automatically be + * cleaned up at the end of a test case. See &struct kunit_resource for an + * example. + * + * Note: KUnit needs to allocate memory for a kunit_resource object. You must + * specify an @internal_gfp that is compatible with the use context of your + * resource. + */ +static inline void *kunit_alloc_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + gfp_t internal_gfp, + void *context) +{ + struct kunit_resource *res; + + res = kzalloc(sizeof(*res), internal_gfp); + if (!res) + return NULL; + + if (!kunit_add_resource(test, init, free, res, context)) + return res->data; + + return NULL; +} + +typedef bool (*kunit_resource_match_t)(struct kunit *test, + struct kunit_resource *res, + void *match_data); + +/** + * kunit_resource_instance_match() - Match a resource with the same instance. + * @test: Test case to which the resource belongs. + * @res: The resource. + * @match_data: The resource pointer to match against. + * + * An instance of kunit_resource_match_t that matches a resource whose + * allocation matches @match_data. + */ +static inline bool kunit_resource_instance_match(struct kunit *test, + struct kunit_resource *res, + void *match_data) +{ + return res->data == match_data; +} + +/** + * kunit_resource_name_match() - Match a resource with the same name. + * @test: Test case to which the resource belongs. + * @res: The resource. + * @match_name: The name to match against. + */ +static inline bool kunit_resource_name_match(struct kunit *test, + struct kunit_resource *res, + void *match_name) +{ + return res->name && strcmp(res->name, match_name) == 0; +} + +/** + * kunit_find_resource() - Find a resource using match function/data. + * @test: Test case to which the resource belongs. + * @match: match function to be applied to resources/match data. + * @match_data: data to be used in matching. + */ +static inline struct kunit_resource * +kunit_find_resource(struct kunit *test, + kunit_resource_match_t match, + void *match_data) +{ + struct kunit_resource *res, *found = NULL; + unsigned long flags; + + spin_lock_irqsave(&test->lock, flags); + + list_for_each_entry_reverse(res, &test->resources, node) { + if (match(test, res, (void *)match_data)) { + found = res; + kunit_get_resource(found); + break; + } + } + + spin_unlock_irqrestore(&test->lock, flags); + + return found; +} + +/** + * kunit_find_named_resource() - Find a resource using match name. + * @test: Test case to which the resource belongs. + * @name: match name. + */ +static inline struct kunit_resource * +kunit_find_named_resource(struct kunit *test, + const char *name) +{ + return kunit_find_resource(test, kunit_resource_name_match, + (void *)name); +} + +/** + * kunit_destroy_resource() - Find a kunit_resource and destroy it. + * @test: Test case to which the resource belongs. + * @match: Match function. Returns whether a given resource matches @match_data. + * @match_data: Data passed into @match. + * + * RETURNS: + * 0 if kunit_resource is found and freed, -ENOENT if not found. + */ +int kunit_destroy_resource(struct kunit *test, + kunit_resource_match_t match, + void *match_data); + +static inline int kunit_destroy_named_resource(struct kunit *test, + const char *name) +{ + return kunit_destroy_resource(test, kunit_resource_name_match, + (void *)name); +} + +/** + * kunit_remove_resource() - remove resource from resource list associated with + * test. + * @test: The test context object. + * @res: The resource to be removed. + * + * Note that the resource will not be immediately freed since it is likely + * the caller has a reference to it via alloc_and_get() or find(); + * in this case a final call to kunit_put_resource() is required. + */ +void kunit_remove_resource(struct kunit *test, struct kunit_resource *res); + +#endif /* _KUNIT_RESOURCE_H */ diff --git a/include/kunit/test.h b/include/kunit/test.h index e6c18b609b47..97cd76461886 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -27,78 +27,6 @@ #include -struct kunit_resource; - -typedef int (*kunit_resource_init_t)(struct kunit_resource *, void *); -typedef void (*kunit_resource_free_t)(struct kunit_resource *); - -/** - * struct kunit_resource - represents a *test managed resource* - * @data: for the user to store arbitrary data. - * @name: optional name - * @free: a user supplied function to free the resource. Populated by - * kunit_resource_alloc(). - * - * Represents a *test managed resource*, a resource which will automatically be - * cleaned up at the end of a test case. - * - * Resources are reference counted so if a resource is retrieved via - * kunit_alloc_and_get_resource() or kunit_find_resource(), we need - * to call kunit_put_resource() to reduce the resource reference count - * when finished with it. Note that kunit_alloc_resource() does not require a - * kunit_resource_put() because it does not retrieve the resource itself. - * - * Example: - * - * .. code-block:: c - * - * struct kunit_kmalloc_params { - * size_t size; - * gfp_t gfp; - * }; - * - * static int kunit_kmalloc_init(struct kunit_resource *res, void *context) - * { - * struct kunit_kmalloc_params *params = context; - * res->data = kmalloc(params->size, params->gfp); - * - * if (!res->data) - * return -ENOMEM; - * - * return 0; - * } - * - * static void kunit_kmalloc_free(struct kunit_resource *res) - * { - * kfree(res->data); - * } - * - * void *kunit_kmalloc(struct kunit *test, size_t size, gfp_t gfp) - * { - * struct kunit_kmalloc_params params; - * - * params.size = size; - * params.gfp = gfp; - * - * return kunit_alloc_resource(test, kunit_kmalloc_init, - * kunit_kmalloc_free, ¶ms); - * } - * - * Resources can also be named, with lookup/removal done on a name - * basis also. kunit_add_named_resource(), kunit_find_named_resource() - * and kunit_destroy_named_resource(). Resource names must be - * unique within the test instance. - */ -struct kunit_resource { - void *data; - const char *name; - kunit_resource_free_t free; - - /* private: internal use only. */ - struct kref refcount; - struct list_head node; -}; - struct kunit; /* Size of log associated with test. */ @@ -385,233 +313,6 @@ static inline int kunit_run_all_tests(void) enum kunit_status kunit_suite_has_succeeded(struct kunit_suite *suite); -/* - * Like kunit_alloc_resource() below, but returns the struct kunit_resource - * object that contains the allocation. This is mostly for testing purposes. - */ -struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - gfp_t internal_gfp, - void *context); - -/** - * kunit_get_resource() - Hold resource for use. Should not need to be used - * by most users as we automatically get resources - * retrieved by kunit_find_resource*(). - * @res: resource - */ -static inline void kunit_get_resource(struct kunit_resource *res) -{ - kref_get(&res->refcount); -} - -/* - * Called when refcount reaches zero via kunit_put_resources(); - * should not be called directly. - */ -static inline void kunit_release_resource(struct kref *kref) -{ - struct kunit_resource *res = container_of(kref, struct kunit_resource, - refcount); - - /* If free function is defined, resource was dynamically allocated. */ - if (res->free) { - res->free(res); - kfree(res); - } -} - -/** - * kunit_put_resource() - When caller is done with retrieved resource, - * kunit_put_resource() should be called to drop - * reference count. The resource list maintains - * a reference count on resources, so if no users - * are utilizing a resource and it is removed from - * the resource list, it will be freed via the - * associated free function (if any). Only - * needs to be used if we alloc_and_get() or - * find() resource. - * @res: resource - */ -static inline void kunit_put_resource(struct kunit_resource *res) -{ - kref_put(&res->refcount, kunit_release_resource); -} - -/** - * kunit_add_resource() - Add a *test managed resource*. - * @test: The test context object. - * @init: a user-supplied function to initialize the result (if needed). If - * none is supplied, the resource data value is simply set to @data. - * If an init function is supplied, @data is passed to it instead. - * @free: a user-supplied function to free the resource (if needed). - * @res: The resource. - * @data: value to pass to init function or set in resource data field. - */ -int kunit_add_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - struct kunit_resource *res, - void *data); - -/** - * kunit_add_named_resource() - Add a named *test managed resource*. - * @test: The test context object. - * @init: a user-supplied function to initialize the resource data, if needed. - * @free: a user-supplied function to free the resource data, if needed. - * @res: The resource. - * @name: name to be set for resource. - * @data: value to pass to init function or set in resource data field. - */ -int kunit_add_named_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - struct kunit_resource *res, - const char *name, - void *data); - -/** - * kunit_alloc_resource() - Allocates a *test managed resource*. - * @test: The test context object. - * @init: a user supplied function to initialize the resource. - * @free: a user supplied function to free the resource. - * @internal_gfp: gfp to use for internal allocations, if unsure, use GFP_KERNEL - * @context: for the user to pass in arbitrary data to the init function. - * - * Allocates a *test managed resource*, a resource which will automatically be - * cleaned up at the end of a test case. See &struct kunit_resource for an - * example. - * - * Note: KUnit needs to allocate memory for a kunit_resource object. You must - * specify an @internal_gfp that is compatible with the use context of your - * resource. - */ -static inline void *kunit_alloc_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - gfp_t internal_gfp, - void *context) -{ - struct kunit_resource *res; - - res = kzalloc(sizeof(*res), internal_gfp); - if (!res) - return NULL; - - if (!kunit_add_resource(test, init, free, res, context)) - return res->data; - - return NULL; -} - -typedef bool (*kunit_resource_match_t)(struct kunit *test, - struct kunit_resource *res, - void *match_data); - -/** - * kunit_resource_instance_match() - Match a resource with the same instance. - * @test: Test case to which the resource belongs. - * @res: The resource. - * @match_data: The resource pointer to match against. - * - * An instance of kunit_resource_match_t that matches a resource whose - * allocation matches @match_data. - */ -static inline bool kunit_resource_instance_match(struct kunit *test, - struct kunit_resource *res, - void *match_data) -{ - return res->data == match_data; -} - -/** - * kunit_resource_name_match() - Match a resource with the same name. - * @test: Test case to which the resource belongs. - * @res: The resource. - * @match_name: The name to match against. - */ -static inline bool kunit_resource_name_match(struct kunit *test, - struct kunit_resource *res, - void *match_name) -{ - return res->name && strcmp(res->name, match_name) == 0; -} - -/** - * kunit_find_resource() - Find a resource using match function/data. - * @test: Test case to which the resource belongs. - * @match: match function to be applied to resources/match data. - * @match_data: data to be used in matching. - */ -static inline struct kunit_resource * -kunit_find_resource(struct kunit *test, - kunit_resource_match_t match, - void *match_data) -{ - struct kunit_resource *res, *found = NULL; - unsigned long flags; - - spin_lock_irqsave(&test->lock, flags); - - list_for_each_entry_reverse(res, &test->resources, node) { - if (match(test, res, (void *)match_data)) { - found = res; - kunit_get_resource(found); - break; - } - } - - spin_unlock_irqrestore(&test->lock, flags); - - return found; -} - -/** - * kunit_find_named_resource() - Find a resource using match name. - * @test: Test case to which the resource belongs. - * @name: match name. - */ -static inline struct kunit_resource * -kunit_find_named_resource(struct kunit *test, - const char *name) -{ - return kunit_find_resource(test, kunit_resource_name_match, - (void *)name); -} - -/** - * kunit_destroy_resource() - Find a kunit_resource and destroy it. - * @test: Test case to which the resource belongs. - * @match: Match function. Returns whether a given resource matches @match_data. - * @match_data: Data passed into @match. - * - * RETURNS: - * 0 if kunit_resource is found and freed, -ENOENT if not found. - */ -int kunit_destroy_resource(struct kunit *test, - kunit_resource_match_t match, - void *match_data); - -static inline int kunit_destroy_named_resource(struct kunit *test, - const char *name) -{ - return kunit_destroy_resource(test, kunit_resource_name_match, - (void *)name); -} - -/** - * kunit_remove_resource() - remove resource from resource list associated with - * test. - * @test: The test context object. - * @res: The resource to be removed. - * - * Note that the resource will not be immediately freed since it is likely - * the caller has a reference to it via alloc_and_get() or find(); - * in this case a final call to kunit_put_resource() is required. - */ -void kunit_remove_resource(struct kunit *test, struct kunit_resource *res); - /** * kunit_kmalloc_array() - Like kmalloc_array() except the allocation is *test managed*. * @test: The test context object. @@ -1610,4 +1311,8 @@ do { \ return NULL; \ } +// TODO(dlatypov@google.com): consider eventually migrating users to explicitly +// include resource.h themselves if they need it. +#include + #endif /* _KUNIT_TEST_H */ -- cgit v1.2.3 From 8b023accc8df70e72f7704d29fead7ca914d6837 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Mon, 14 Mar 2022 15:19:03 -0700 Subject: lockdep: Fix -Wunused-parameter for _THIS_IP_ While looking into a bug related to the compiler's handling of addresses of labels, I noticed some uses of _THIS_IP_ seemed unused in lockdep. Drive by cleanup. -Wunused-parameter: kernel/locking/lockdep.c:1383:22: warning: unused parameter 'ip' kernel/locking/lockdep.c:4246:48: warning: unused parameter 'ip' kernel/locking/lockdep.c:4844:19: warning: unused parameter 'ip' Signed-off-by: Nick Desaulniers Signed-off-by: Peter Zijlstra (Intel) Acked-by: Waiman Long Link: https://lore.kernel.org/r/20220314221909.2027027-1-ndesaulniers@google.com --- include/linux/irqflags.h | 4 ++-- include/linux/kvm_host.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 4b140938b03e..5ec0fa71399e 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -20,13 +20,13 @@ #ifdef CONFIG_PROVE_LOCKING extern void lockdep_softirqs_on(unsigned long ip); extern void lockdep_softirqs_off(unsigned long ip); - extern void lockdep_hardirqs_on_prepare(unsigned long ip); + extern void lockdep_hardirqs_on_prepare(void); extern void lockdep_hardirqs_on(unsigned long ip); extern void lockdep_hardirqs_off(unsigned long ip); #else static inline void lockdep_softirqs_on(unsigned long ip) { } static inline void lockdep_softirqs_off(unsigned long ip) { } - static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { } + static inline void lockdep_hardirqs_on_prepare(void) { } static inline void lockdep_hardirqs_on(unsigned long ip) { } static inline void lockdep_hardirqs_off(unsigned long ip) { } #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3f9b22c4983a..e1b2413750c0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -450,7 +450,7 @@ static __always_inline void guest_state_enter_irqoff(void) { instrumentation_begin(); trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); instrumentation_end(); guest_context_enter_irqoff(); -- cgit v1.2.3 From 16edd9b511a13e7760ed4b92ba4e39bacda5c86f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 22 Mar 2022 11:57:08 -0700 Subject: locking: Add lock contention tracepoints This adds two new lock contention tracepoints like below: * lock:contention_begin * lock:contention_end The lock:contention_begin takes a flags argument to classify locks. I found it useful to identify what kind of locks it's tracing like if it's spinning or sleeping, reader-writer lock, real-time, and per-cpu. Move tracepoint definitions into mutex.c so that we can use them without lockdep. Signed-off-by: Namhyung Kim Signed-off-by: Peter Zijlstra (Intel) Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Link: https://lkml.kernel.org/r/20220322185709.141236-2-namhyung@kernel.org --- include/trace/events/lock.h | 61 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 58 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h index d7512129a324..b9b6e3edd518 100644 --- a/include/trace/events/lock.h +++ b/include/trace/events/lock.h @@ -5,11 +5,21 @@ #if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_LOCK_H -#include +#include #include +/* flags for lock:contention_begin */ +#define LCB_F_SPIN (1U << 0) +#define LCB_F_READ (1U << 1) +#define LCB_F_WRITE (1U << 2) +#define LCB_F_RT (1U << 3) +#define LCB_F_PERCPU (1U << 4) + + #ifdef CONFIG_LOCKDEP +#include + TRACE_EVENT(lock_acquire, TP_PROTO(struct lockdep_map *lock, unsigned int subclass, @@ -78,8 +88,53 @@ DEFINE_EVENT(lock, lock_acquired, TP_ARGS(lock, ip) ); -#endif -#endif +#endif /* CONFIG_LOCK_STAT */ +#endif /* CONFIG_LOCKDEP */ + +TRACE_EVENT(contention_begin, + + TP_PROTO(void *lock, unsigned int flags), + + TP_ARGS(lock, flags), + + TP_STRUCT__entry( + __field(void *, lock_addr) + __field(unsigned int, flags) + ), + + TP_fast_assign( + __entry->lock_addr = lock; + __entry->flags = flags; + ), + + TP_printk("%p (flags=%s)", __entry->lock_addr, + __print_flags(__entry->flags, "|", + { LCB_F_SPIN, "SPIN" }, + { LCB_F_READ, "READ" }, + { LCB_F_WRITE, "WRITE" }, + { LCB_F_RT, "RT" }, + { LCB_F_PERCPU, "PERCPU" } + )) +); + +TRACE_EVENT(contention_end, + + TP_PROTO(void *lock, int ret), + + TP_ARGS(lock, ret), + + TP_STRUCT__entry( + __field(void *, lock_addr) + __field(int, ret) + ), + + TP_fast_assign( + __entry->lock_addr = lock; + __entry->ret = ret; + ), + + TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret) +); #endif /* _TRACE_LOCK_H */ -- cgit v1.2.3 From bfe4daf850f45d92dcd3da477f0b0456620294c3 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Tue, 22 Mar 2022 15:15:05 -0700 Subject: perf/core: Add perf_clear_branch_entry_bitfields() helper Make it simpler to reset all the info fields on the perf_branch_entry by adding a helper inline function. The goal is to centralize the initialization to avoid missing a field in case more are added. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220322221517.2510440-2-eranian@google.com --- include/linux/perf_event.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index af97dd427501..a411080d5169 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1063,6 +1063,22 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->txn = 0; } +/* + * Clear all bitfields in the perf_branch_entry. + * The to and from fields are not cleared because they are + * systematically modified by caller. + */ +static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br) +{ + br->mispred = 0; + br->predicted = 0; + br->in_tx = 0; + br->abort = 0; + br->cycles = 0; + br->type = 0; + br->reserved = 0; +} + extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, -- cgit v1.2.3 From dc1f7893a70fe403983bd8492f177bf993940e2c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 30 Mar 2022 13:06:54 +0200 Subject: locking/mutex: Make contention tracepoints more consistent wrt adaptive spinning Have the trace_contention_*() tracepoints consistently include adaptive spinning. In order to differentiate between the spinning and non-spinning states add LCB_F_MUTEX and combine with LCB_F_SPIN. The consequence is that a mutex contention can now triggler multiple _begin() tracepoints before triggering an _end(). Additionally, this fixes one path where mutex would trigger _end() without ever seeing a _begin(). Signed-off-by: Peter Zijlstra (Intel) --- include/trace/events/lock.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h index b9b6e3edd518..9ebd081e057e 100644 --- a/include/trace/events/lock.h +++ b/include/trace/events/lock.h @@ -14,6 +14,7 @@ #define LCB_F_WRITE (1U << 2) #define LCB_F_RT (1U << 3) #define LCB_F_PERCPU (1U << 4) +#define LCB_F_MUTEX (1U << 5) #ifdef CONFIG_LOCKDEP @@ -113,7 +114,8 @@ TRACE_EVENT(contention_begin, { LCB_F_READ, "READ" }, { LCB_F_WRITE, "WRITE" }, { LCB_F_RT, "RT" }, - { LCB_F_PERCPU, "PERCPU" } + { LCB_F_PERCPU, "PERCPU" }, + { LCB_F_MUTEX, "MUTEX" } )) ); -- cgit v1.2.3 From 2a606a18cd672a16343d146a126721b34cc6adbd Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Tue, 22 Mar 2022 15:15:12 -0700 Subject: ACPI: Add perf low power callback Add an optional callback needed by some PMU features, e.g., AMD BRS, to give a chance to the perf_events code to change its state before a CPU goes to low power and after it comes back. The callback is void when the PERF_NEEDS_LOPWR_CB flag is not set. This flag must be set in arch specific perf_event.h header whenever needed. When not set, there is no impact on the ACPI code. Signed-off-by: Stephane Eranian [peterz: build fix] Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220322221517.2510440-9-eranian@google.com --- include/linux/perf_event.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a411080d5169..da759560eec5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1676,4 +1676,10 @@ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, unsigned int cnt); DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); +#ifndef PERF_NEEDS_LOPWR_CB +static inline void perf_lopwr_cb(bool mode) +{ +} +#endif + #endif /* _LINUX_PERF_EVENT_H */ -- cgit v1.2.3 From cfe43f478b79ba45573ca22d52d0d8823be068fa Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Fri, 12 Nov 2021 18:52:01 +0000 Subject: preempt/dynamic: Introduce preemption model accessors CONFIG_PREEMPT{_NONE, _VOLUNTARY} designate either: o The build-time preemption model when !PREEMPT_DYNAMIC o The default boot-time preemption model when PREEMPT_DYNAMIC IOW, using those on PREEMPT_DYNAMIC kernels is meaningless - the actual model could have been set to something else by the "preempt=foo" cmdline parameter. Same problem applies to CONFIG_PREEMPTION. Introduce a set of helpers to determine the actual preemption model used by the live kernel. Suggested-by: Marco Elver Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Marco Elver Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20211112185203.280040-3-valentin.schneider@arm.com --- include/linux/sched.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index d5e3c00b74e1..67f06f72c50e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2117,6 +2117,47 @@ static inline void cond_resched_rcu(void) #endif } +#ifdef CONFIG_PREEMPT_DYNAMIC + +extern bool preempt_model_none(void); +extern bool preempt_model_voluntary(void); +extern bool preempt_model_full(void); + +#else + +static inline bool preempt_model_none(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_NONE); +} +static inline bool preempt_model_voluntary(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); +} +static inline bool preempt_model_full(void) +{ + return IS_ENABLED(CONFIG_PREEMPT); +} + +#endif + +static inline bool preempt_model_rt(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_RT); +} + +/* + * Does the preemption model allow non-cooperative preemption? + * + * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with + * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the + * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the + * PREEMPT_NONE model. + */ +static inline bool preempt_model_preemptible(void) +{ + return preempt_model_full() || preempt_model_rt(); +} + /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, -- cgit v1.2.3 From 900dedd7e47cc3f8d93dfa0ae6ac6cf49eda0c97 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20Povi=C5=A1er?= Date: Thu, 31 Mar 2022 02:04:48 +0200 Subject: ASoC: Introduce snd_soc_of_get_dai_link_cpus MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function is an analogue of snd_soc_of_get_dai_link_codecs to help machine drivers read CPU DAI lists from devicetrees. Signed-off-by: Martin Povišer Link: https://lore.kernel.org/r/20220331000449.41062-5-povik+lin@cutebit.org Signed-off-by: Mark Brown --- include/sound/soc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 7a1650b303f1..d3d3a26e8867 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1263,6 +1263,10 @@ int snd_soc_of_get_dai_link_codecs(struct device *dev, struct device_node *of_node, struct snd_soc_dai_link *dai_link); void snd_soc_of_put_dai_link_codecs(struct snd_soc_dai_link *dai_link); +int snd_soc_of_get_dai_link_cpus(struct device *dev, + struct device_node *of_node, + struct snd_soc_dai_link *dai_link); +void snd_soc_of_put_dai_link_cpus(struct snd_soc_dai_link *dai_link); int snd_soc_add_pcm_runtime(struct snd_soc_card *card, struct snd_soc_dai_link *dai_link); -- cgit v1.2.3 From 9f342904216f378e88008bb0ce1ae200a4b99fe8 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Mon, 28 Mar 2022 20:35:35 +0800 Subject: ASoC: cs35l41: Fix an out-of-bounds access in otp_packed_element_t The CS35L41_NUM_OTP_ELEM is 100, but only 99 entries are defined in the array otp_map_1/2[CS35L41_NUM_OTP_ELEM], this will trigger UBSAN to report a shift-out-of-bounds warning in the cs35l41_otp_unpack() since the last entry in the array will result in GENMASK(-1, 0). UBSAN reports this problem: UBSAN: shift-out-of-bounds in /home/hwang4/build/jammy/jammy/sound/soc/codecs/cs35l41-lib.c:836:8 shift exponent 64 is too large for 64-bit type 'long unsigned int' CPU: 10 PID: 595 Comm: systemd-udevd Not tainted 5.15.0-23-generic #23 Hardware name: LENOVO \x02MFG_IN_GO/\x02MFG_IN_GO, BIOS N3GET19W (1.00 ) 03/11/2022 Call Trace: show_stack+0x52/0x58 dump_stack_lvl+0x4a/0x5f dump_stack+0x10/0x12 ubsan_epilogue+0x9/0x45 __ubsan_handle_shift_out_of_bounds.cold+0x61/0xef ? regmap_unlock_mutex+0xe/0x10 cs35l41_otp_unpack.cold+0x1c6/0x2b2 [snd_soc_cs35l41_lib] cs35l41_hda_probe+0x24f/0x33a [snd_hda_scodec_cs35l41] cs35l41_hda_i2c_probe+0x65/0x90 [snd_hda_scodec_cs35l41_i2c] ? cs35l41_hda_i2c_remove+0x20/0x20 [snd_hda_scodec_cs35l41_i2c] i2c_device_probe+0x252/0x2b0 Fixes: 6450ef559056 ("ASoC: cs35l41: CS35L41 Boosted Smart Amplifier") Reviewed-by: Lucas Tanure Acked-by: Charles Keepax Signed-off-by: Hui Wang Link: https://lore.kernel.org/r/20220328123535.50000-2-hui.wang@canonical.com Signed-off-by: Mark Brown --- include/sound/cs35l41.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index bf7f9a9aeba0..9341130257ea 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -536,7 +536,6 @@ #define CS35L41_MAX_CACHE_REG 36 #define CS35L41_OTP_SIZE_WORDS 32 -#define CS35L41_NUM_OTP_ELEM 100 #define CS35L41_VALID_PDATA 0x80000000 #define CS35L41_NUM_SUPPLIES 2 -- cgit v1.2.3 From 8c756a0a2de17f1535ef885ac7e556e016735eb2 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 31 Mar 2022 15:54:47 +0300 Subject: device property: Convert device_{dma_supported,get_dma_attr} to fwnode Make the device_dma_supported and device_get_dma_attr functions to use the fwnode ops, and move the implementation to ACPI and OF frameworks. Signed-off-by: Sakari Ailus Acked-by: Rob Herring Reviewed-by: Andy Shevchenko Reviewed-by: Heikki Krogerus Signed-off-by: Rafael J. Wysocki --- include/linux/fwnode.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 3a532ba66f6c..6f307f21fc65 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -113,6 +113,9 @@ struct fwnode_operations { bool (*device_is_available)(const struct fwnode_handle *fwnode); const void *(*device_get_match_data)(const struct fwnode_handle *fwnode, const struct device *dev); + bool (*device_dma_supported)(const struct fwnode_handle *fwnode); + enum dev_dma_attr + (*device_get_dma_attr)(const struct fwnode_handle *fwnode); bool (*property_present)(const struct fwnode_handle *fwnode, const char *propname); int (*property_read_int_array)(const struct fwnode_handle *fwnode, -- cgit v1.2.3 From 68b979d068d3d0dceb14c446f664433d96f20a7e Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 31 Mar 2022 15:54:49 +0300 Subject: device property: Add iomap to fwnode operations Add iomap() fwnode operation to implement fwnode_iomap() through fwnode operations, moving the code in fwnode_iomap() to OF framework. Note that the IS_ENABLED(CONFIG_OF_ADDRESS) && is_of_node(fwnode) check is needed for Sparc that has its own implementation of of_iomap anyway. Let the pre-compiler to handle that check. Signed-off-by: Sakari Ailus Reviewed-by: Andy Shevchenko Reviewed-by: Heikki Krogerus Signed-off-by: Rafael J. Wysocki --- include/linux/fwnode.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 6f307f21fc65..ebbc3bf03f95 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -148,6 +148,7 @@ struct fwnode_operations { (*graph_get_port_parent)(struct fwnode_handle *fwnode); int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); + void __iomem *(*iomap)(struct fwnode_handle *fwnode, int index); int (*add_links)(struct fwnode_handle *fwnode); }; -- cgit v1.2.3 From 99c63707bafd15bcf97fbd6bef1c92d5bfa01d28 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 31 Mar 2022 15:54:50 +0300 Subject: device property: Add irq_get to fwnode operation Add irq_get() fwnode operation to implement fwnode_irq_get() through fwnode operations, moving the code in fwnode_irq_get() to OF and ACPI frameworks. Signed-off-by: Sakari Ailus Acked-by: Rob Herring Reviewed-by: Andy Shevchenko Reviewed-by: Heikki Krogerus Signed-off-by: Rafael J. Wysocki --- include/linux/fwnode.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index ebbc3bf03f95..6ab69871b06d 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -149,6 +149,7 @@ struct fwnode_operations { int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); void __iomem *(*iomap)(struct fwnode_handle *fwnode, int index); + int (*irq_get)(const struct fwnode_handle *fwnode, unsigned int index); int (*add_links)(struct fwnode_handle *fwnode); }; -- cgit v1.2.3 From 1be9473e31ab87ad1b6ecf9fd11df461930ede85 Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Tue, 22 Mar 2022 14:03:34 +0000 Subject: module: Move livepatch support to a separate file No functional change. This patch migrates livepatch support (i.e. used during module add/or load and remove/or deletion) from core module code into kernel/module/livepatch.c. At the moment it contains code to persist Elf information about a given livepatch module, only. The new file was added to MAINTAINERS. Reviewed-by: Petr Mladek Tested-by: Petr Mladek Signed-off-by: Aaron Tomlin Signed-off-by: Luis Chamberlain --- include/linux/module.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 1e135fd5c076..7ec9715de7dc 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -663,17 +663,14 @@ static inline bool module_requested_async_probing(struct module *module) return module && module->async_probe_requested; } -#ifdef CONFIG_LIVEPATCH static inline bool is_livepatch_module(struct module *mod) { +#ifdef CONFIG_LIVEPATCH return mod->klp; -} -#else /* !CONFIG_LIVEPATCH */ -static inline bool is_livepatch_module(struct module *mod) -{ +#else return false; +#endif } -#endif /* CONFIG_LIVEPATCH */ bool is_module_sig_enforced(void); void set_module_sig_enforced(void); -- cgit v1.2.3 From 0c1e42805c25c87eb7a6f3b18bdbf3b3b7840aff Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Tue, 22 Mar 2022 14:03:37 +0000 Subject: module: Move extra signature support out of core code No functional change. This patch migrates additional module signature check code from core module code into kernel/module/signing.c. Reviewed-by: Christophe Leroy Signed-off-by: Aaron Tomlin Signed-off-by: Luis Chamberlain --- include/linux/module.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 7ec9715de7dc..5e2059f3afc7 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -672,7 +672,6 @@ static inline bool is_livepatch_module(struct module *mod) #endif } -bool is_module_sig_enforced(void); void set_module_sig_enforced(void); #else /* !CONFIG_MODULES... */ @@ -799,10 +798,6 @@ static inline bool module_requested_async_probing(struct module *module) return false; } -static inline bool is_module_sig_enforced(void) -{ - return false; -} static inline void set_module_sig_enforced(void) { @@ -854,11 +849,18 @@ static inline bool retpoline_module_ok(bool has_retpoline) #endif #ifdef CONFIG_MODULE_SIG +bool is_module_sig_enforced(void); + static inline bool module_sig_ok(struct module *module) { return module->sig_ok; } #else /* !CONFIG_MODULE_SIG */ +static inline bool is_module_sig_enforced(void) +{ + return false; +} + static inline bool module_sig_ok(struct module *module) { return true; -- cgit v1.2.3 From f64205a42046d3802c423fa2059e7fca39af127c Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Tue, 22 Mar 2022 14:03:43 +0000 Subject: module: Move kdb module related code out of main kdb code No functional change. This patch migrates the kdb 'lsmod' command support out of main kdb code into its own file under kernel/module. In addition to the above, a minor style warning i.e. missing a blank line after declarations, was resolved too. The new file was added to MAINTAINERS. Finally we remove linux/module.h as it is entirely redundant. Reviewed-by: Daniel Thompson Acked-by: Daniel Thompson Signed-off-by: Aaron Tomlin Signed-off-by: Luis Chamberlain --- include/linux/kdb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index ea0f5e580fac..07dfb6a20a1c 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -222,5 +222,6 @@ enum { extern int kdbgetintenv(const char *, int *); extern int kdb_set(int, const char **); +int kdb_lsmod(int argc, const char **argv); #endif /* !_KDB_H */ -- cgit v1.2.3 From 01dc0386efb769056257410ba5754558384006a7 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 23 Feb 2022 13:02:14 +0100 Subject: module: Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC to allow architectures to request having modules data in vmalloc area instead of module area. This is required on powerpc book3s/32 in order to set data non executable, because it is not possible to set executability on page basis, this is done per 256 Mbytes segments. The module area has exec right, vmalloc area has noexec. This can also be useful on other powerpc/32 in order to maximize the chance of code being close enough to kernel core to avoid branch trampolines. Cc: Jason Wessel Acked-by: Daniel Thompson Cc: Douglas Anderson Signed-off-by: Christophe Leroy [mcgrof: rebased in light of kernel/module/kdb.c move] Signed-off-by: Luis Chamberlain --- include/linux/module.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 5e2059f3afc7..46d4d5f2516e 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -422,6 +422,9 @@ struct module { /* Core layout: rbtree is accessed frequently, so keep together. */ struct module_layout core_layout __module_layout_align; struct module_layout init_layout; +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + struct module_layout data_layout; +#endif /* Arch-specific module values */ struct mod_arch_specific arch; @@ -569,6 +572,11 @@ bool is_module_text_address(unsigned long addr); static inline bool within_module_core(unsigned long addr, const struct module *mod) { +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + if ((unsigned long)mod->data_layout.base <= addr && + addr < (unsigned long)mod->data_layout.base + mod->data_layout.size) + return true; +#endif return (unsigned long)mod->core_layout.base <= addr && addr < (unsigned long)mod->core_layout.base + mod->core_layout.size; } -- cgit v1.2.3 From baa914cd81f51f4e4f3bae5bb59764b32ad8c353 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Tue, 5 Apr 2022 16:22:20 +0900 Subject: firewire: add kernel API to access CYCLE_TIME register 1394 OHCI specification defined Isochronous Cycle Timer Register to get value of CYCLE_TIME register defined by IEEE 1394 for CSR architecture defined by ISO/IEC 13213. Unit driver can calculate packet time by compute with the value of CYCLE_TIME and timeStamp field in descriptor of each isochronous and asynchronous context. The resolution of CYCLE_TIME is 49.576 MHz, while the one of timeStamp is 8,000 Hz. Current implementation of Linux FireWire subsystem allows the driver to get the value of CYCLE_TIMER CSR register by transaction service. The transaction service has overhead in regard of access to MMIO register. This commit adds kernel API for unit driver to access the register directly. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20220405072221.226217-3-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/linux/firewire.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 07967a450eaa..2f467c52bdec 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -150,6 +150,8 @@ static inline void fw_card_put(struct fw_card *card) kref_put(&card->kref, fw_card_release); } +int fw_card_read_cycle_time(struct fw_card *card, u32 *cycle_time); + struct fw_attribute_group { struct attribute_group *groups[2]; struct attribute_group group; -- cgit v1.2.3 From b2405aa948b95afc5246fa56fc05c3512cd6185c Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Tue, 5 Apr 2022 16:22:21 +0900 Subject: firewire: add kernel API to access packet structure in request structure for AR context In 1394 OHCI specification, descriptor of Asynchronous Receive DMA context has timeStamp field in its trailer quadlet. The field is written by the host controller for the time to receive asynchronous request subaction in isochronous cycle time. In Linux FireWire subsystem, the value of field is stored to fw_packet structure and copied to fw_request structure as the part. The fw_request structure is hidden from unit driver and passed as opaque pointer when calling registered handler. It's inconvenient to the unit driver which needs timestamp of packet. This commit adds kernel API to pick up timestamp from opaque pointer to fw_request structure. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20220405072221.226217-4-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/linux/firewire.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 2f467c52bdec..980019053e54 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -354,6 +354,7 @@ void fw_core_remove_address_handler(struct fw_address_handler *handler); void fw_send_response(struct fw_card *card, struct fw_request *request, int rcode); int fw_get_request_speed(struct fw_request *request); +u32 fw_request_get_timestamp(const struct fw_request *request); void fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode, int destination_id, int generation, int speed, unsigned long long offset, void *payload, size_t length, -- cgit v1.2.3 From bc8cb02976cd602b8d7631a6f4a54a9cf305d38c Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 5 Apr 2022 14:54:15 +0100 Subject: ASoC: soc.h: Add SOC_SINGLE_S_TLV() macro Add a convenience macro for defining a single (mono) TLV control with a signed value. This can already be done by using SOC_DOUBLE_R_S_TLV() with the same address for left and right registers, but a dedicated macro is more readable. Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20220405135419.1230088-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index d3d3a26e8867..55fb6a6d7d25 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -176,6 +176,8 @@ .get = snd_soc_get_volsw, .put = snd_soc_put_volsw, \ .private_value = SOC_DOUBLE_R_S_VALUE(reg_left, reg_right, xshift, \ xmin, xmax, xsign_bit, xinvert) } +#define SOC_SINGLE_S_TLV(xname, xreg, xshift, xmin, xmax, xsign_bit, xinvert, tlv_array) \ + SOC_DOUBLE_R_S_TLV(xname, xreg, xreg, xshift, xmin, xmax, xsign_bit, xinvert, tlv_array) #define SOC_SINGLE_S8_TLV(xname, xreg, xmin, xmax, tlv_array) \ { .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = (xname), \ .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \ -- cgit v1.2.3 From 1ef34dd2b90d78a9830398441801658ef86eee9d Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 5 Apr 2022 14:54:16 +0100 Subject: ASoC: soc-utils: Add helper to calculate BCLK from TDM info Add a helper function snd_soc_tdm_params_to_bclk() to calculate the bclk from params info and the tdm sots configuration. When using a TDM frame of N slots of width W bits: bclk = sample_rate * N * W As a convenience to simplify calling code, if the slot count or slot width are 0 a value will be obtained from the params. This allows calling code to use this one function to handle cases of TDM where only one parameter is fixed, or I2S where the slot width is fixed (for example to set a 32-bit slot for 24-bit samples). Also as a convenience the slot count can optionally be rounded up to a multiple. This is mainly useful for I2S systems, since I2S has two phases of LRCLK the number of slots is always a multiple of 2. Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20220405135419.1230088-3-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 55fb6a6d7d25..2d3261799d2c 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -487,6 +487,8 @@ int snd_soc_calc_frame_size(int sample_size, int channels, int tdm_slots); int snd_soc_params_to_frame_size(struct snd_pcm_hw_params *params); int snd_soc_calc_bclk(int fs, int sample_size, int channels, int tdm_slots); int snd_soc_params_to_bclk(struct snd_pcm_hw_params *parms); +int snd_soc_tdm_params_to_bclk(struct snd_pcm_hw_params *params, + int tdm_width, int tdm_slots, int slot_multiple); /* set runtime hw params */ int snd_soc_set_runtime_hwparams(struct snd_pcm_substream *substream, -- cgit v1.2.3 From 72661ff7662acc00d51976d4b2d2d13eb5628385 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 5 Apr 2022 14:54:18 +0100 Subject: ASoC: dt-bindings: cs35l45: Cirrus Logic CS35L45 Smart Amp This adds the schema binding for the Cirrus Logic CS35L45 Smart Amp and associated header file. Signed-off-by: Richard Fitzgerald Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20220405135419.1230088-5-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/dt-bindings/sound/cs35l45.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/dt-bindings/sound/cs35l45.h (limited to 'include') diff --git a/include/dt-bindings/sound/cs35l45.h b/include/dt-bindings/sound/cs35l45.h new file mode 100644 index 000000000000..076da4b2c28d --- /dev/null +++ b/include/dt-bindings/sound/cs35l45.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* + * cs35l45.h -- CS35L45 ALSA SoC audio driver DT bindings header + * + * Copyright 2022 Cirrus Logic, Inc. + */ + +#ifndef DT_CS35L45_H +#define DT_CS35L45_H + +/* + * cirrus,asp-sdout-hiz-ctrl + * + * TX_HIZ_UNUSED: TX pin high-impedance during unused slots. + * TX_HIZ_DISABLED: TX pin high-impedance when all channels disabled. + */ +#define CS35L45_ASP_TX_HIZ_UNUSED 0x1 +#define CS35L45_ASP_TX_HIZ_DISABLED 0x2 + +#endif /* DT_CS35L45_H */ -- cgit v1.2.3 From a8e2512efc65892a1cbf608d9c03c8bcbe5a623a Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Fri, 1 Apr 2022 15:06:04 +0100 Subject: PM: core: Add NS varients of EXPORT[_GPL]_SIMPLE_DEV_PM_OPS and runtime pm equiv As more drivers start to use namespaces, we need to have varients of these useful macros that allow the export to be in a particular namespace. Signed-off-by: Jonathan Cameron Cc: Paul Cercueil Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 14 +++++++++----- include/linux/pm_runtime.h | 10 ++++++++-- 2 files changed, 17 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index e65b3ab28377..ffe941958501 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -368,13 +368,13 @@ const struct dev_pm_ops name = { \ #ifdef CONFIG_PM #define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn, sec) \ + runtime_resume_fn, idle_fn, sec, ns) \ _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ runtime_resume_fn, idle_fn); \ - _EXPORT_SYMBOL(name, sec) + __EXPORT_SYMBOL(name, sec, ns) #else #define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn, sec) \ + runtime_resume_fn, idle_fn, sec, ns) \ static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ resume_fn, runtime_suspend_fn, \ runtime_resume_fn, idle_fn) @@ -391,9 +391,13 @@ static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL) #define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "") + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", "") #define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl") + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", "") +#define EXPORT_NS_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", #ns) +#define EXPORT_NS_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", #ns) /* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 2bff6a10095d..9e4d056967c6 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -41,10 +41,16 @@ #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "") + suspend_fn, resume_fn, idle_fn, "", "") #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "_gpl") + suspend_fn, resume_fn, idle_fn, "_gpl", "") +#define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "", #ns) +#define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "_gpl", #ns) #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; -- cgit v1.2.3 From 0b5c21bbc01e92745ca1ca4f6fd87d878fa3ea5e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 4 Apr 2022 11:38:47 +0200 Subject: net: ensure net_todo_list is processed quickly In [1], Will raised a potential issue that the cfg80211 code, which does (from a locking perspective) rtnl_lock() wiphy_lock() rtnl_unlock() might be suspectible to ABBA deadlocks, because rtnl_unlock() calls netdev_run_todo(), which might end up calling rtnl_lock() again, which could then deadlock (see the comment in the code added here for the scenario). Some back and forth and thinking ensued, but clearly this can't happen if the net_todo_list is empty at the rtnl_unlock() here. Clearly, the code here cannot actually put an entry on it, and all other users of rtnl_unlock() will empty it since that will always go through netdev_run_todo(), emptying the list. So the only other way to get there would be to add to the list and then unlock the RTNL without going through rtnl_unlock(), which is only possible through __rtnl_unlock(). However, this isn't exported and not used in many places, and none of them seem to be able to unregister before using it. Therefore, add a WARN_ON() in the code to ensure this invariant won't be broken, so that the cfg80211 (or any similar) code stays safe. [1] https://lore.kernel.org/r/Yjzpo3TfZxtKPMAG@google.com Signed-off-by: Johannes Berg Link: https://lore.kernel.org/r/20220404113847.0ee02e4a70da.Ic73d206e217db20fd22dcec14fe5442ca732804b@changeid Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 59e27a2b7bf0..b6a1e7f643da 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3894,7 +3894,8 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern int netdev_budget; extern unsigned int netdev_budget_usecs; -/* Called by rtnetlink.c:rtnl_unlock() */ +/* Used by rtnetlink.c:__rtnl_unlock()/rtnl_unlock() */ +extern struct list_head net_todo_list; void netdev_run_todo(void); static inline void __dev_put(struct net_device *dev) -- cgit v1.2.3 From 40379a0084c2f65eb62c102f5bbf5cdc14a50410 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 4 Apr 2022 15:08:15 +0300 Subject: net/mlx5_fpga: Drop INNOVA TLS support Mellanox INNOVA TLS cards are EOL in May, 2018 [1]. As such, the code is unmaintained, untested and not in-use by any upstream/distro oriented customers. In order to reduce code complexity, drop the kernel code. [1] https://network.nvidia.com/related-docs/eol/LCR-000286.pdf Link: https://lore.kernel.org/r/b88add368def721ea9d054cb69def72d9e3f67aa.1649073691.git.leonro@nvidia.com Reviewed-by: Tariq Toukan Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc_fpga.h | 63 -------------------------------------- 1 file changed, 63 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index 07d77323f78a..e3d824f6a309 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -54,7 +54,6 @@ enum { enum { MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC = 0x2, - MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS = 0x3, }; struct mlx5_ifc_fpga_shell_caps_bits { @@ -387,27 +386,6 @@ struct mlx5_ifc_fpga_destroy_qp_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_tls_extended_cap_bits { - u8 aes_gcm_128[0x1]; - u8 aes_gcm_256[0x1]; - u8 reserved_at_2[0x1e]; - u8 reserved_at_20[0x20]; - u8 context_capacity_total[0x20]; - u8 context_capacity_rx[0x20]; - u8 context_capacity_tx[0x20]; - u8 reserved_at_a0[0x10]; - u8 tls_counter_size[0x10]; - u8 tls_counters_addr_low[0x20]; - u8 tls_counters_addr_high[0x20]; - u8 rx[0x1]; - u8 tx[0x1]; - u8 tls_v12[0x1]; - u8 tls_v13[0x1]; - u8 lro[0x1]; - u8 ipv6[0x1]; - u8 reserved_at_106[0x1a]; -}; - struct mlx5_ifc_ipsec_extended_cap_bits { u8 encapsulation[0x20]; @@ -572,45 +550,4 @@ struct mlx5_ifc_fpga_ipsec_sa { __be16 vid; /* only 12 bits, rest is reserved */ __be16 reserved2; } __packed; - -enum fpga_tls_cmds { - CMD_SETUP_STREAM = 0x1001, - CMD_TEARDOWN_STREAM = 0x1002, - CMD_RESYNC_RX = 0x1003, -}; - -#define MLX5_TLS_1_2 (0) - -#define MLX5_TLS_ALG_AES_GCM_128 (0) -#define MLX5_TLS_ALG_AES_GCM_256 (1) - -struct mlx5_ifc_tls_cmd_bits { - u8 command_type[0x20]; - u8 ipv6[0x1]; - u8 direction_sx[0x1]; - u8 tls_version[0x2]; - u8 reserved[0x1c]; - u8 swid[0x20]; - u8 src_port[0x10]; - u8 dst_port[0x10]; - union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6; - union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6; - u8 tls_rcd_sn[0x40]; - u8 tcp_sn[0x20]; - u8 tls_implicit_iv[0x20]; - u8 tls_xor_iv[0x40]; - u8 encryption_key[0x100]; - u8 alg[4]; - u8 reserved2[0x1c]; - u8 reserved3[0x4a0]; -}; - -struct mlx5_ifc_tls_resp_bits { - u8 syndrome[0x20]; - u8 stream_id[0x20]; - u8 reserved[0x40]; -}; - -#define MLX5_TLS_COMMAND_SIZE (0x100) - #endif /* MLX5_IFC_FPGA_H */ -- cgit v1.2.3 From 0276bd3a94c072de3f69b5afe6224e488cc76635 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 5 Apr 2022 17:15:16 +0200 Subject: IB/mlx5: Fix undefined behavior due to shift overflowing the constant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix: drivers/infiniband/hw/mlx5/main.c: In function ‘translate_eth_legacy_proto_oper’: drivers/infiniband/hw/mlx5/main.c:370:2: error: case label does not reduce to an integer constant case MLX5E_PROT_MASK(MLX5E_50GBASE_KR2): ^~~~ See https://lore.kernel.org/r/YkwQ6%2BtIH8GQpuct@zn.tnic for the gory details as to why it triggers with older gccs only. Link: https://lore.kernel.org/all/20220405151517.29753-11-bp@alien8.de Signed-off-by: Borislav Petkov Cc: Leon Romanovsky Cc: Saeed Mahameed Cc: linux-rdma@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/port.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 28a928b0684b..e96ee1e348cb 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -141,7 +141,7 @@ enum mlx5_ptys_width { MLX5_PTYS_WIDTH_12X = 1 << 4, }; -#define MLX5E_PROT_MASK(link_mode) (1 << link_mode) +#define MLX5E_PROT_MASK(link_mode) (1U << link_mode) #define MLX5_GET_ETH_PROTO(reg, out, ext, field) \ (ext ? MLX5_GET(reg, out, ext_##field) : \ MLX5_GET(reg, out, field)) -- cgit v1.2.3 From a285909f471d6703a04b2b3942c352e27131c92b Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 6 Apr 2022 15:00:03 +0900 Subject: mm/slub, kunit: Make slub_kunit unaffected by user specified flags slub_kunit does not expect other debugging flags to be set when running tests. When SLAB_RED_ZONE flag is set globally, test fails because the flag affects number of errors reported. To make slub_kunit unaffected by user specified debugging flags, introduce SLAB_NO_USER_FLAGS to ignore them. With this flag, only flags specified in the code are used and others are ignored. Suggested-by: Vlastimil Babka Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/Yk0sY9yoJhFEXWOg@hyeyoo --- include/linux/slab.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 373b3ef99f4e..11ceddcae9f4 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -112,6 +112,13 @@ #define SLAB_KASAN 0 #endif +/* + * Ignore user specified debugging flags. + * Intended for caches created for self-tests so they have only flags + * specified in the code and other flags are ignored. + */ +#define SLAB_NO_USER_FLAGS ((slab_flags_t __force)0x10000000U) + /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) -- cgit v1.2.3 From a5f1783be29adae15666fd803efd7d2979130869 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 2 Mar 2022 12:02:22 +0100 Subject: lib/stackdepot: allow requesting early initialization dynamically In a later patch we want to add stackdepot support for object owner tracking in slub caches, which is enabled by slub_debug boot parameter. This creates a bootstrap problem as some caches are created early in boot when slab_is_available() is false and thus stack_depot_init() tries to use memblock. But, as reported by Hyeonggon Yoo [1] we are already beyond memblock_free_all(). Ideally memblock allocation should fail, yet it succeeds, but later the system crashes, which is a separately handled issue. To resolve this boostrap issue in a robust way, this patch adds another way to request stack_depot_early_init(), which happens at a well-defined point of time. In addition to build-time CONFIG_STACKDEPOT_ALWAYS_INIT, code that's e.g. processing boot parameters (which happens early enough) can call a new function stack_depot_want_early_init(), which sets a flag that stack_depot_early_init() will check. In this patch we also convert page_owner to this approach. While it doesn't have the bootstrap issue as slub, it's also a functionality enabled by a boot param and can thus request stack_depot_early_init() with memblock allocation instead of later initialization with kvmalloc(). As suggested by Mike, make stack_depot_early_init() only attempt memblock allocation and stack_depot_init() only attempt kvmalloc(). Also change the latter to kvcalloc(). In both cases we can lose the explicit array zeroing, which the allocations do already. As suggested by Marco, provide empty implementations of the init functions for !CONFIG_STACKDEPOT builds to simplify the callers. [1] https://lore.kernel.org/all/YhnUcqyeMgCrWZbd@ip-172-31-19-208.ap-northeast-1.compute.internal/ Reported-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Suggested-by: Mike Rapoport Suggested-by: Marco Elver Signed-off-by: Vlastimil Babka Reviewed-by: Marco Elver Reviewed-and-tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Mike Rapoport Acked-by: David Rientjes --- include/linux/stackdepot.h | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 17f992fe6355..bc2797955de9 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -20,18 +20,36 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, gfp_t gfp_flags, bool can_alloc); /* - * Every user of stack depot has to call this during its own init when it's - * decided that it will be calling stack_depot_save() later. + * Every user of stack depot has to call stack_depot_init() during its own init + * when it's decided that it will be calling stack_depot_save() later. This is + * recommended for e.g. modules initialized later in the boot process, when + * slab_is_available() is true. * * The alternative is to select STACKDEPOT_ALWAYS_INIT to have stack depot * enabled as part of mm_init(), for subsystems where it's known at compile time * that stack depot will be used. + * + * Another alternative is to call stack_depot_want_early_init(), when the + * decision to use stack depot is taken e.g. when evaluating kernel boot + * parameters, which precedes the enablement point in mm_init(). + * + * stack_depot_init() and stack_depot_want_early_init() can be called regardless + * of CONFIG_STACKDEPOT and are no-op when disabled. The actual save/fetch/print + * functions should only be called from code that makes sure CONFIG_STACKDEPOT + * is enabled. */ +#ifdef CONFIG_STACKDEPOT int stack_depot_init(void); -#ifdef CONFIG_STACKDEPOT_ALWAYS_INIT -static inline int stack_depot_early_init(void) { return stack_depot_init(); } +void __init stack_depot_want_early_init(void); + +/* This is supposed to be called only from mm_init() */ +int __init stack_depot_early_init(void); #else +static inline int stack_depot_init(void) { return 0; } + +static inline void stack_depot_want_early_init(void) { } + static inline int stack_depot_early_init(void) { return 0; } #endif -- cgit v1.2.3 From f742b90e61bb53b27771f64bdae05db03a6ab1f2 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Thu, 24 Feb 2022 10:55:49 -0600 Subject: x86/mm: Extend cc_attr to include AMD SEV-SNP The CC_ATTR_GUEST_SEV_SNP can be used by the guest to query whether the SNP (Secure Nested Paging) feature is active. Signed-off-by: Brijesh Singh Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220307213356.2797205-10-brijesh.singh@amd.com --- include/linux/cc_platform.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index efd8205282da..d08dd65b5c43 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -72,6 +72,14 @@ enum cc_attr { * Examples include TDX guest & SEV. */ CC_ATTR_GUEST_UNROLL_STRING_IO, + + /** + * @CC_ATTR_SEV_SNP: Guest SNP is active. + * + * The platform/OS is running as a guest/virtual machine and actively + * using AMD SEV-SNP features. + */ + CC_ATTR_GUEST_SEV_SNP, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM -- cgit v1.2.3 From f4b41f062c424209e3939a81e6da022e049a45f2 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 4 Apr 2022 18:30:22 +0200 Subject: net: remove noblock parameter from skb_recv_datagram() skb_recv_datagram() has two parameters 'flags' and 'noblock' that are merged inside skb_recv_datagram() by 'flags | (noblock ? MSG_DONTWAIT : 0)' As 'flags' may contain MSG_DONTWAIT as value most callers split the 'flags' into 'flags' and 'noblock' with finally obsolete bit operations like this: skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &rc); And this is not even done consistently with the 'flags' parameter. This patch removes the obsolete and costly splitting into two parameters and only performs bit operations when really needed on the caller side. One missing conversion thankfully reported by kernel test robot. I missed to enable kunit tests to build the mctp code. Reported-by: kernel test robot Signed-off-by: Oliver Hartkopp Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3a30cae8b0a5..2394441fa3dd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3836,8 +3836,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); -struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, - int *err); +struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, -- cgit v1.2.3 From 1ee375d77bb944321c969b456aa73994566cecf6 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Mon, 4 Apr 2022 10:54:47 -0700 Subject: net, uapi: remove inclusion of arpa/inet.h In include/uapi/linux/tipc_config.h, there's a comment that it includes arpa/inet.h for ntohs; but ntohs is not defined in any UAPI header. For now, reuse the definitions from include/linux/byteorder/generic.h, since the various conversion functions do exist in UAPI headers: include/uapi/linux/byteorder/big_endian.h include/uapi/linux/byteorder/little_endian.h We would like to get to the point where we can build UAPI header tests with -nostdinc, meaning that kernel UAPI headers should not have a circular dependency on libc headers. Link: https://android-review.googlesource.com/c/platform/bionic/+/2048127 Suggested-by: Jakub Kicinski Signed-off-by: Nick Desaulniers Signed-off-by: David S. Miller --- include/uapi/linux/tipc_config.h | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h index 4dfc05651c98..c00adf2fe868 100644 --- a/include/uapi/linux/tipc_config.h +++ b/include/uapi/linux/tipc_config.h @@ -43,10 +43,6 @@ #include #include -#ifndef __KERNEL__ -#include /* for ntohs etc. */ -#endif - /* * Configuration * @@ -269,33 +265,33 @@ static inline int TLV_OK(const void *tlv, __u16 space) */ return (space >= TLV_SPACE(0)) && - (ntohs(((struct tlv_desc *)tlv)->tlv_len) <= space); + (__be16_to_cpu(((struct tlv_desc *)tlv)->tlv_len) <= space); } static inline int TLV_CHECK(const void *tlv, __u16 space, __u16 exp_type) { return TLV_OK(tlv, space) && - (ntohs(((struct tlv_desc *)tlv)->tlv_type) == exp_type); + (__be16_to_cpu(((struct tlv_desc *)tlv)->tlv_type) == exp_type); } static inline int TLV_GET_LEN(struct tlv_desc *tlv) { - return ntohs(tlv->tlv_len); + return __be16_to_cpu(tlv->tlv_len); } static inline void TLV_SET_LEN(struct tlv_desc *tlv, __u16 len) { - tlv->tlv_len = htons(len); + tlv->tlv_len = __cpu_to_be16(len); } static inline int TLV_CHECK_TYPE(struct tlv_desc *tlv, __u16 type) { - return (ntohs(tlv->tlv_type) == type); + return (__be16_to_cpu(tlv->tlv_type) == type); } static inline void TLV_SET_TYPE(struct tlv_desc *tlv, __u16 type) { - tlv->tlv_type = htons(type); + tlv->tlv_type = __cpu_to_be16(type); } static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len) @@ -305,8 +301,8 @@ static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len) tlv_len = TLV_LENGTH(len); tlv_ptr = (struct tlv_desc *)tlv; - tlv_ptr->tlv_type = htons(type); - tlv_ptr->tlv_len = htons(tlv_len); + tlv_ptr->tlv_type = __cpu_to_be16(type); + tlv_ptr->tlv_len = __cpu_to_be16(tlv_len); if (len && data) { memcpy(TLV_DATA(tlv_ptr), data, len); memset((char *)TLV_DATA(tlv_ptr) + len, 0, TLV_SPACE(len) - tlv_len); @@ -348,7 +344,7 @@ static inline void *TLV_LIST_DATA(struct tlv_list_desc *list) static inline void TLV_LIST_STEP(struct tlv_list_desc *list) { - __u16 tlv_space = TLV_ALIGN(ntohs(list->tlv_ptr->tlv_len)); + __u16 tlv_space = TLV_ALIGN(__be16_to_cpu(list->tlv_ptr->tlv_len)); list->tlv_ptr = (struct tlv_desc *)((char *)list->tlv_ptr + tlv_space); list->tlv_space -= tlv_space; @@ -404,9 +400,9 @@ static inline int TCM_SET(void *msg, __u16 cmd, __u16 flags, msg_len = TCM_LENGTH(data_len); tcm_hdr = (struct tipc_cfg_msg_hdr *)msg; - tcm_hdr->tcm_len = htonl(msg_len); - tcm_hdr->tcm_type = htons(cmd); - tcm_hdr->tcm_flags = htons(flags); + tcm_hdr->tcm_len = __cpu_to_be32(msg_len); + tcm_hdr->tcm_type = __cpu_to_be16(cmd); + tcm_hdr->tcm_flags = __cpu_to_be16(flags); if (data_len && data) { memcpy(TCM_DATA(msg), data, data_len); memset((char *)TCM_DATA(msg) + data_len, 0, TCM_SPACE(data_len) - msg_len); -- cgit v1.2.3 From fe696ccb277d332dc4e625b5b20b988b04d16c04 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 3 Apr 2022 15:53:54 -0700 Subject: gpu: host1x: Fix a kernel-doc warning Add @cache description to eliminate a kernel-doc warning. include/linux/host1x.h:104: warning: Function parameter or member 'cache' not described in 'host1x_client' Fixes: 1f39b1dfa53c ("drm/tegra: Implement buffer object cache") Signed-off-by: Randy Dunlap Cc: Thierry Reding Cc: linux-tegra@vger.kernel.org Cc: David Airlie Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Signed-off-by: Thierry Reding --- include/linux/host1x.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index e8dc5bc41f79..00278853eadf 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -81,6 +81,7 @@ struct host1x_client_ops { * @parent: pointer to parent structure * @usecount: reference count for this structure * @lock: mutex for mutually exclusive concurrency + * @cache: host1x buffer object cache */ struct host1x_client { struct list_head list; -- cgit v1.2.3 From 804775dfc2885e93a0a4b35db1914c2cc25172b5 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 5 Apr 2022 21:57:47 +0200 Subject: net: ethernet: mtk_eth_soc: add support for Wireless Ethernet Dispatch (WED) The Wireless Ethernet Dispatch subsystem on the MT7622 SoC can be configured to intercept and handle access to the DMA queues and PCIe interrupts for a MT7615/MT7915 wireless card. It can manage the internal WDMA (Wireless DMA) controller, which allows ethernet packets to be passed from the packet switch engine (PSE) to the wireless card, bypassing the CPU entirely. This can be used to implement hardware flow offloading from ethernet to WLAN. Signed-off-by: Felix Fietkau Signed-off-by: David S. Miller --- include/linux/soc/mediatek/mtk_wed.h | 131 +++++++++++++++++++++++++++++++++++ 1 file changed, 131 insertions(+) create mode 100644 include/linux/soc/mediatek/mtk_wed.h (limited to 'include') diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h new file mode 100644 index 000000000000..7e00cca06709 --- /dev/null +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -0,0 +1,131 @@ +#ifndef __MTK_WED_H +#define __MTK_WED_H + +#include +#include +#include +#include + +#define MTK_WED_TX_QUEUES 2 + +struct mtk_wed_hw; +struct mtk_wdma_desc; + +struct mtk_wed_ring { + struct mtk_wdma_desc *desc; + dma_addr_t desc_phys; + int size; + + u32 reg_base; + void __iomem *wpdma; +}; + +struct mtk_wed_device { +#ifdef CONFIG_NET_MEDIATEK_SOC_WED + const struct mtk_wed_ops *ops; + struct device *dev; + struct mtk_wed_hw *hw; + bool init_done, running; + int wdma_idx; + int irq; + + struct mtk_wed_ring tx_ring[MTK_WED_TX_QUEUES]; + struct mtk_wed_ring txfree_ring; + struct mtk_wed_ring tx_wdma[MTK_WED_TX_QUEUES]; + + struct { + int size; + void **pages; + struct mtk_wdma_desc *desc; + dma_addr_t desc_phys; + } buf_ring; + + /* filled by driver: */ + struct { + struct pci_dev *pci_dev; + + u32 wpdma_phys; + + u16 token_start; + unsigned int nbuf; + + u32 (*init_buf)(void *ptr, dma_addr_t phys, int token_id); + int (*offload_enable)(struct mtk_wed_device *wed); + void (*offload_disable)(struct mtk_wed_device *wed); + } wlan; +#endif +}; + +struct mtk_wed_ops { + int (*attach)(struct mtk_wed_device *dev); + int (*tx_ring_setup)(struct mtk_wed_device *dev, int ring, + void __iomem *regs); + int (*txfree_ring_setup)(struct mtk_wed_device *dev, + void __iomem *regs); + void (*detach)(struct mtk_wed_device *dev); + + void (*stop)(struct mtk_wed_device *dev); + void (*start)(struct mtk_wed_device *dev, u32 irq_mask); + void (*reset_dma)(struct mtk_wed_device *dev); + + u32 (*reg_read)(struct mtk_wed_device *dev, u32 reg); + void (*reg_write)(struct mtk_wed_device *dev, u32 reg, u32 val); + + u32 (*irq_get)(struct mtk_wed_device *dev, u32 mask); + void (*irq_set_mask)(struct mtk_wed_device *dev, u32 mask); +}; + +extern const struct mtk_wed_ops __rcu *mtk_soc_wed_ops; + +static inline int +mtk_wed_device_attach(struct mtk_wed_device *dev) +{ + int ret = -ENODEV; + +#ifdef CONFIG_NET_MEDIATEK_SOC_WED + rcu_read_lock(); + dev->ops = rcu_dereference(mtk_soc_wed_ops); + if (dev->ops) + ret = dev->ops->attach(dev); + else + rcu_read_unlock(); + + if (ret) + dev->ops = NULL; +#endif + + return ret; +} + +#ifdef CONFIG_NET_MEDIATEK_SOC_WED +#define mtk_wed_device_active(_dev) !!(_dev)->ops +#define mtk_wed_device_detach(_dev) (_dev)->ops->detach(_dev) +#define mtk_wed_device_start(_dev, _mask) (_dev)->ops->start(_dev, _mask) +#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) \ + (_dev)->ops->tx_ring_setup(_dev, _ring, _regs) +#define mtk_wed_device_txfree_ring_setup(_dev, _regs) \ + (_dev)->ops->txfree_ring_setup(_dev, _regs) +#define mtk_wed_device_reg_read(_dev, _reg) \ + (_dev)->ops->reg_read(_dev, _reg) +#define mtk_wed_device_reg_write(_dev, _reg, _val) \ + (_dev)->ops->reg_write(_dev, _reg, _val) +#define mtk_wed_device_irq_get(_dev, _mask) \ + (_dev)->ops->irq_get(_dev, _mask) +#define mtk_wed_device_irq_set_mask(_dev, _mask) \ + (_dev)->ops->irq_set_mask(_dev, _mask) +#else +static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) +{ + return false; +} +#define mtk_wed_device_detach(_dev) do {} while (0) +#define mtk_wed_device_start(_dev, _mask) do {} while (0) +#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_txfree_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_reg_read(_dev, _reg) 0 +#define mtk_wed_device_reg_write(_dev, _reg, _val) do {} while (0) +#define mtk_wed_device_irq_get(_dev, _mask) 0 +#define mtk_wed_device_irq_set_mask(_dev, _mask) do {} while (0) +#endif + +#endif -- cgit v1.2.3 From a333215e10cb5d3b1e0685ca117f0e9452215485 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 5 Apr 2022 21:57:48 +0200 Subject: net: ethernet: mtk_eth_soc: implement flow offloading to WED devices This allows hardware flow offloading from Ethernet to WLAN on MT7622 SoC Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: Felix Fietkau Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b6a1e7f643da..7b2a0b739684 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -862,6 +862,7 @@ enum net_device_path_type { DEV_PATH_BRIDGE, DEV_PATH_PPPOE, DEV_PATH_DSA, + DEV_PATH_MTK_WDMA, }; struct net_device_path { @@ -887,6 +888,12 @@ struct net_device_path { int port; u16 proto; } dsa; + struct { + u8 wdma_idx; + u8 queue; + u16 wcid; + u8 bss; + } mtk_wdma; }; }; -- cgit v1.2.3 From 3e9c4584336149146fe15cb5703fc10a2ca2d2a0 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 24 Mar 2022 11:30:25 +0100 Subject: gpu: host1x: Do not use mapping cache for job submissions Buffer mappings used in job submissions are usually small and not rapidly reused as opposed to framebuffers (which are usually large and rapidly reused, for example when page-flipping between double-buffered framebuffers). Avoid going through the mapping cache for these buffers since the cache would also lead to leaks if nobody is ever releasing the cache's last reference. For DRM/KMS these last references are dropped when the framebuffers are removed and therefore no longer needed. While at it, also add a note about the need to explicitly remove the final reference to the mapping in the cache. Reviewed-by: Jon Hunter Tested-by: Jon Hunter Signed-off-by: Thierry Reding --- include/linux/host1x.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 00278853eadf..c0bf4e581fe9 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -31,6 +31,11 @@ u64 host1x_get_dma_mask(struct host1x *host1x); * struct host1x_bo_cache - host1x buffer object cache * @mappings: list of mappings * @lock: synchronizes accesses to the list of mappings + * + * Note that entries are not periodically evicted from this cache and instead need to be + * explicitly released. This is used primarily for DRM/KMS where the cache's reference is + * released when the last reference to a buffer object represented by a mapping in this + * cache is dropped. */ struct host1x_bo_cache { struct list_head mappings; -- cgit v1.2.3 From 71f69ffa0129bf04205edf0e7dc73dc4777b2588 Mon Sep 17 00:00:00 2001 From: Ashish Singhal Date: Wed, 9 Mar 2022 00:00:26 +0530 Subject: arm64: tegra: Add QSPI controllers on Tegra234 This adds the QSPI controllers on the Tegra234 SoC and populates the SPI NOR flash device for the Jetson AGX Orin platform. Signed-off-by: Ashish Singhal Signed-off-by: Jon Hunter Signed-off-by: Krishna Yarlagadda Reviewed-by: Jon Hunter Acked-by: Rob Herring Signed-off-by: Thierry Reding --- include/dt-bindings/clock/tegra234-clock.h | 8 ++++++++ include/dt-bindings/reset/tegra234-reset.h | 2 ++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/tegra234-clock.h b/include/dt-bindings/clock/tegra234-clock.h index 8cae969e8cba..bd4c3086a2da 100644 --- a/include/dt-bindings/clock/tegra234-clock.h +++ b/include/dt-bindings/clock/tegra234-clock.h @@ -140,6 +140,14 @@ #define TEGRA234_CLK_PEX2_C9_CORE 173U /** @brief output of gate CLK_ENB_PEX2_CORE_10 */ #define TEGRA234_CLK_PEX2_C10_CORE 187U +/** @brief CLK_RST_CONTROLLER_CLK_SOURCE_QSPI0 switch divider output */ +#define TEGRA234_CLK_QSPI0_2X_PM 192U +/** @brief CLK_RST_CONTROLLER_CLK_SOURCE_QSPI1 switch divider output */ +#define TEGRA234_CLK_QSPI1_2X_PM 193U +/** @brief output of the divider QSPI_CLK_DIV2_SEL in CLK_RST_CONTROLLER_CLK_SOURCE_QSPI0 */ +#define TEGRA234_CLK_QSPI0_PM 194U +/** @brief output of the divider QSPI_CLK_DIV2_SEL in CLK_RST_CONTROLLER_CLK_SOURCE_QSPI1 */ +#define TEGRA234_CLK_QSPI1_PM 195U /** @brief CLK_RST_CONTROLLER_CLK_SOURCE_SDMMC_LEGACY_TM switch divider output */ #define TEGRA234_CLK_SDMMC_LEGACY_TM 219U /** @brief output of gate CLK_ENB_PEX0_CORE_0 */ diff --git a/include/dt-bindings/reset/tegra234-reset.h b/include/dt-bindings/reset/tegra234-reset.h index 1362cd5e03f0..547ca3b60caa 100644 --- a/include/dt-bindings/reset/tegra234-reset.h +++ b/include/dt-bindings/reset/tegra234-reset.h @@ -40,6 +40,8 @@ #define TEGRA234_RESET_PWM6 73U #define TEGRA234_RESET_PWM7 74U #define TEGRA234_RESET_PWM8 75U +#define TEGRA234_RESET_QSPI0 76U +#define TEGRA234_RESET_QSPI1 77U #define TEGRA234_RESET_SDMMC4 85U #define TEGRA234_RESET_UARTA 100U #define TEGRA234_RESET_PEX0_CORE_0 116U -- cgit v1.2.3 From e945c653c8e972d1b81a88e474d79f801b60213a Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 4 Apr 2022 12:26:42 -0300 Subject: RDMA: Split kernel-only global device caps from uverbs device caps Split out flags from ib_device::device_cap_flags that are only used internally to the kernel into kernel_cap_flags that is not part of the uapi. This limits the device_cap_flags to being the same bitmap that will be copied to userspace. This cleanly splits out the uverbs flags from the kernel flags to avoid confusion in the flags bitmap. Add some short comments describing which each of the kernel flags is connected to. Remove unused kernel flags. Link: https://lore.kernel.org/r/0-v2-22c19e565eef+139a-kern_caps_jgg@nvidia.com Reviewed-by: Christoph Hellwig Reviewed-by: Max Gurtovoy Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 88 ++++++++++++++++----------------------- include/rdma/opa_vnic.h | 3 +- include/uapi/rdma/ib_user_verbs.h | 4 ++ 3 files changed, 42 insertions(+), 53 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index ada4a5226dbd..b3bb4dd068b6 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -236,14 +236,6 @@ enum ib_device_cap_flags { IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE, IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ, - /* - * This device supports a per-device lkey or stag that can be - * used without performing a memory registration for the local - * memory. Note that ULPs should never check this flag, but - * instead of use the local_dma_lkey flag in the ib_pd structure, - * which will always contain a usable lkey. - */ - IB_DEVICE_LOCAL_DMA_LKEY = 1 << 15, /* Reserved, old SEND_W_INV = 1 << 16,*/ IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW, /* @@ -254,7 +246,6 @@ enum ib_device_cap_flags { * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode. */ IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM, - IB_DEVICE_UD_TSO = 1 << 19, IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC, /* @@ -267,59 +258,53 @@ enum ib_device_cap_flags { * stag. */ IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS, - IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = 1 << 22, IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A, IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B, IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM, /* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */ IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM, - /* - * Devices should set IB_DEVICE_CROSS_CHANNEL if they - * support execution of WQEs that involve synchronization - * of I/O operations with single completion queue managed - * by hardware. - */ - IB_DEVICE_CROSS_CHANNEL = 1 << 27, IB_DEVICE_MANAGED_FLOW_STEERING = IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING, - IB_DEVICE_INTEGRITY_HANDOVER = 1 << 30, - IB_DEVICE_ON_DEMAND_PAGING = 1ULL << 31, - IB_DEVICE_SG_GAPS_REG = 1ULL << 32, - IB_DEVICE_VIRTUAL_FUNCTION = 1ULL << 33, /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS, - IB_DEVICE_RDMA_NETDEV_OPA = 1ULL << 35, /* The device supports padding incoming writes to cacheline. */ IB_DEVICE_PCI_WRITE_END_PADDING = IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING, - IB_DEVICE_ALLOW_USER_UNREG = 1ULL << 37, -}; - -#define IB_UVERBS_DEVICE_CAP_FLAGS_MASK (IB_UVERBS_DEVICE_RESIZE_MAX_WR | \ - IB_UVERBS_DEVICE_BAD_PKEY_CNTR | \ - IB_UVERBS_DEVICE_BAD_QKEY_CNTR | \ - IB_UVERBS_DEVICE_RAW_MULTI | \ - IB_UVERBS_DEVICE_AUTO_PATH_MIG | \ - IB_UVERBS_DEVICE_CHANGE_PHY_PORT | \ - IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE | \ - IB_UVERBS_DEVICE_CURR_QP_STATE_MOD | \ - IB_UVERBS_DEVICE_SHUTDOWN_PORT | \ - IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT | \ - IB_UVERBS_DEVICE_SYS_IMAGE_GUID | \ - IB_UVERBS_DEVICE_RC_RNR_NAK_GEN | \ - IB_UVERBS_DEVICE_SRQ_RESIZE | \ - IB_UVERBS_DEVICE_N_NOTIFY_CQ | \ - IB_UVERBS_DEVICE_MEM_WINDOW | \ - IB_UVERBS_DEVICE_UD_IP_CSUM | \ - IB_UVERBS_DEVICE_XRC | \ - IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS | \ - IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A | \ - IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B | \ - IB_UVERBS_DEVICE_RC_IP_CSUM | \ - IB_UVERBS_DEVICE_RAW_IP_CSUM | \ - IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING | \ - IB_UVERBS_DEVICE_RAW_SCATTER_FCS | \ - IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING) +}; + +enum ib_kernel_cap_flags { + /* + * This device supports a per-device lkey or stag that can be + * used without performing a memory registration for the local + * memory. Note that ULPs should never check this flag, but + * instead of use the local_dma_lkey flag in the ib_pd structure, + * which will always contain a usable lkey. + */ + IBK_LOCAL_DMA_LKEY = 1 << 0, + /* IB_QP_CREATE_INTEGRITY_EN is supported to implement T10-PI */ + IBK_INTEGRITY_HANDOVER = 1 << 1, + /* IB_ACCESS_ON_DEMAND is supported during reg_user_mr() */ + IBK_ON_DEMAND_PAGING = 1 << 2, + /* IB_MR_TYPE_SG_GAPS is supported */ + IBK_SG_GAPS_REG = 1 << 3, + /* Driver supports RDMA_NLDEV_CMD_DELLINK */ + IBK_ALLOW_USER_UNREG = 1 << 4, + + /* ipoib will use IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK */ + IBK_BLOCK_MULTICAST_LOOPBACK = 1 << 5, + /* iopib will use IB_QP_CREATE_IPOIB_UD_LSO for its QPs */ + IBK_UD_TSO = 1 << 6, + /* iopib will use the device ops: + * get_vf_config + * get_vf_guid + * get_vf_stats + * set_vf_guid + * set_vf_link_state + */ + IBK_VIRTUAL_FUNCTION = 1 << 7, + /* ipoib will use IB_QP_CREATE_NETDEV_USE for its QPs */ + IBK_RDMA_NETDEV_OPA = 1 << 8, +}; enum ib_atomic_cap { IB_ATOMIC_NONE, @@ -417,6 +402,7 @@ struct ib_device_attr { int max_qp; int max_qp_wr; u64 device_cap_flags; + u64 kernel_cap_flags; int max_send_sge; int max_recv_sge; int max_sge_rd; @@ -4344,7 +4330,7 @@ static inline int ib_check_mr_access(struct ib_device *ib_dev, return -EINVAL; if (flags & IB_ACCESS_ON_DEMAND && - !(ib_dev->attrs.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING)) + !(ib_dev->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING)) return -EINVAL; return 0; } diff --git a/include/rdma/opa_vnic.h b/include/rdma/opa_vnic.h index cbe3c2811455..f3d5377b217a 100644 --- a/include/rdma/opa_vnic.h +++ b/include/rdma/opa_vnic.h @@ -90,8 +90,7 @@ struct opa_vnic_stats { static inline bool rdma_cap_opa_vnic(struct ib_device *device) { - return !!(device->attrs.device_cap_flags & - IB_DEVICE_RDMA_NETDEV_OPA); + return !!(device->attrs.kernel_cap_flags & IBK_RDMA_NETDEV_OPA); } #endif /* _OPA_VNIC_H */ diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 06a4897c4958..7dd903d932e5 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -1298,6 +1298,10 @@ struct ib_uverbs_ex_modify_cq { #define IB_DEVICE_NAME_MAX 64 +/* + * bits 9, 15, 16, 19, 22, 27, 30, 31, 32, 33, 35 and 37 may be set by old + * kernels and should not be used. + */ enum ib_uverbs_device_cap_flags { IB_UVERBS_DEVICE_RESIZE_MAX_WR = 1 << 0, IB_UVERBS_DEVICE_BAD_PKEY_CNTR = 1 << 1, -- cgit v1.2.3 From 40570375356c874b1578e05c1dcc3ff7c1322dbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Apr 2022 16:35:38 -0700 Subject: tcp: add accessors to read/set tp->snd_cwnd We had various bugs over the years with code breaking the assumption that tp->snd_cwnd is greater than zero. Lately, syzbot reported the WARN_ON_ONCE(!tp->prior_cwnd) added in commit 8b8a321ff72c ("tcp: fix zero cwnd in tcp_cwnd_reduction") can trigger, and without a repro we would have to spend considerable time finding the bug. Instead of complaining too late, we want to catch where and when tp->snd_cwnd is set to an illegal value. Signed-off-by: Eric Dumazet Suggested-by: Yuchung Cheng Cc: Neal Cardwell Acked-by: Yuchung Cheng Link: https://lore.kernel.org/r/20220405233538.947344-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 19 +++++++++++++++---- include/trace/events/tcp.h | 2 +- 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 70ca4a5e330a..54aa2f02bb63 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1207,9 +1207,20 @@ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) #define TCP_INFINITE_SSTHRESH 0x7fffffff +static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp) +{ + return tp->snd_cwnd; +} + +static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val) +{ + WARN_ON_ONCE((int)val <= 0); + tp->snd_cwnd = val; +} + static inline bool tcp_in_slow_start(const struct tcp_sock *tp) { - return tp->snd_cwnd < tp->snd_ssthresh; + return tcp_snd_cwnd(tp) < tp->snd_ssthresh; } static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) @@ -1235,8 +1246,8 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk) return tp->snd_ssthresh; else return max(tp->snd_ssthresh, - ((tp->snd_cwnd >> 1) + - (tp->snd_cwnd >> 2))); + ((tcp_snd_cwnd(tp) >> 1) + + (tcp_snd_cwnd(tp) >> 2))); } /* Use define here intentionally to get WARN_ON location shown at the caller */ @@ -1278,7 +1289,7 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) - return tp->snd_cwnd < 2 * tp->max_packets_out; + return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out; return tp->is_cwnd_limited; } diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 521059d8dc0a..edcd6369de10 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -279,7 +279,7 @@ TRACE_EVENT(tcp_probe, __entry->data_len = skb->len - __tcp_hdrlen(th); __entry->snd_nxt = tp->snd_nxt; __entry->snd_una = tp->snd_una; - __entry->snd_cwnd = tp->snd_cwnd; + __entry->snd_cwnd = tcp_snd_cwnd(tp); __entry->snd_wnd = tp->snd_wnd; __entry->rcv_wnd = tp->rcv_wnd; __entry->ssthresh = tcp_current_ssthresh(sk); -- cgit v1.2.3 From a60707d74bd1d119cf7bcc5101cda912fc46d5e3 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:57 +0800 Subject: sched: Move child_runs_first sysctls to fair.c move child_runs_first sysctls to fair.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c1076b5e17fb..1d2ff3cd1728 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -14,8 +14,6 @@ extern unsigned long sysctl_hung_task_timeout_secs; enum { sysctl_hung_task_timeout_secs = 0 }; #endif -extern unsigned int sysctl_sched_child_runs_first; - enum sched_tunable_scaling { SCHED_TUNABLESCALING_NONE, SCHED_TUNABLESCALING_LOG, -- cgit v1.2.3 From f5ef06d58be8311a9425e6a54a053ecb350952f3 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:58 +0800 Subject: sched: Move schedstats sysctls to core.c move schedstats sysctls to core.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 1d2ff3cd1728..6c7a6850559b 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -64,8 +64,6 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) extern unsigned int sysctl_sched_energy_aware; -- cgit v1.2.3 From d9ab0e63fa7f8405fbb19e28c5191e0880a7f2db Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:59 +0800 Subject: sched: Move rt_period/runtime sysctls to rt.c move rt_period/runtime sysctls to rt.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 6c7a6850559b..4391c1307945 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,15 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -/* - * control realtime throttling: - * - * /proc/sys/kernel/sched_rt_period_us - * /proc/sys/kernel/sched_rt_runtime_us - */ -extern unsigned int sysctl_sched_rt_period; -extern int sysctl_sched_rt_runtime; - extern unsigned int sysctl_sched_dl_period_max; extern unsigned int sysctl_sched_dl_period_min; @@ -58,8 +49,6 @@ extern int sched_rr_timeslice; int sched_rr_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int sched_rt_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, -- cgit v1.2.3 From 84227c12888b1105725cd2de14705b029bcbb4b2 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:00 +0800 Subject: sched: Move deadline_period sysctls to deadline.c move deadline_period sysctls to deadline.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 4391c1307945..7da9b94c5e1c 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,9 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -extern unsigned int sysctl_sched_dl_period_max; -extern unsigned int sysctl_sched_dl_period_min; - #ifdef CONFIG_UCLAMP_TASK extern unsigned int sysctl_sched_uclamp_util_min; extern unsigned int sysctl_sched_uclamp_util_max; -- cgit v1.2.3 From dafd7a9dad22fadcb290b24dff54e2eae3b89776 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:01 +0800 Subject: sched: Move rr_timeslice sysctls to rt.c move rr_timeslice sysctls to rt.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 7da9b94c5e1c..3d307e512d1f 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -41,11 +41,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default; extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -extern int sysctl_sched_rr_timeslice; -extern int sched_rr_timeslice; - -int sched_rr_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, -- cgit v1.2.3 From 3267e0156c3341ac25b37a0f60551cdae1634b60 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:02 +0800 Subject: sched: Move uclamp_util sysctls to core.c move uclamp_util sysctls to core.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 3d307e512d1f..0934b21a57a4 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,18 +31,10 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -#ifdef CONFIG_UCLAMP_TASK -extern unsigned int sysctl_sched_uclamp_util_min; -extern unsigned int sysctl_sched_uclamp_util_max; -extern unsigned int sysctl_sched_uclamp_util_min_rt_default; -#endif - #ifdef CONFIG_CFS_BANDWIDTH extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3 From d4ae80ffa64f87b9c355692b680b603add084e96 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:03 +0800 Subject: sched: Move cfs_bandwidth_slice sysctls to fair.c move cfs_bandwidth_slice sysctls to fair.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 0934b21a57a4..198f77c8a873 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,10 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -#ifdef CONFIG_CFS_BANDWIDTH -extern unsigned int sysctl_sched_cfs_bandwidth_slice; -#endif - int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3 From 8a0441415b3f9b9a920a6a5086580ea3daa7b884 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:04 +0800 Subject: sched: Move energy_aware sysctls to topology.c move energy_aware sysctls to topology.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 198f77c8a873..e650946816d0 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -34,10 +34,4 @@ extern int sysctl_numa_balancing_mode; int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) -extern unsigned int sysctl_sched_energy_aware; -int sched_energy_aware_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - #endif /* _LINUX_SCHED_SYSCTL_H */ -- cgit v1.2.3 From 06d177662fb86b80c7fc2290667b9a14cb0bd925 Mon Sep 17 00:00:00 2001 From: tangmeng Date: Thu, 17 Feb 2022 12:23:21 +0800 Subject: kernel/reboot: move reboot sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the poweroff_cmd and ctrl-alt-del sysctls to its own file, kernel/reboot.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/reboot.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index af907a3d68d1..a2429648d831 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -71,12 +71,8 @@ extern void kernel_restart(char *cmd); extern void kernel_halt(void); extern void kernel_power_off(void); -extern int C_A_D; /* for sysctl */ void ctrl_alt_del(void); -#define POWEROFF_CMD_PATH_LEN 256 -extern char poweroff_cmd[POWEROFF_CMD_PATH_LEN]; - extern void orderly_poweroff(bool force); extern void orderly_reboot(void); void hw_protection_shutdown(const char *reason, int ms_until_forced); -- cgit v1.2.3 From 43fe219aa56a2fdd8f0623c9470a32b14b0617a5 Mon Sep 17 00:00:00 2001 From: sujiaxun Date: Thu, 17 Feb 2022 18:51:48 -0800 Subject: mm: move oom_kill sysctls to their own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the oom_kill sysctls to their own file, mm/oom_kill.c [sfr@canb.auug.org.au: null-terminate the array] Link: https://lkml.kernel.org/r/20220216193202.28838626@canb.auug.org.au Link: https://lkml.kernel.org/r/20220215093203.31032-1-sujiaxun@uniontech.com Signed-off-by: sujiaxun Signed-off-by: Stephen Rothwell Cc: Kees Cook Cc: Iurii Zaikin Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Luis Chamberlain --- include/linux/oom.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/oom.h b/include/linux/oom.h index 2db9a1432511..02d1e7bbd8cd 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -123,8 +123,4 @@ extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); -/* sysctls */ -extern int sysctl_oom_dump_tasks; -extern int sysctl_oom_kill_allocating_task; -extern int sysctl_panic_on_oom; #endif /* _INCLUDE_LINUX_OOM_H */ -- cgit v1.2.3 From aa779e5102195e1d9ade95dcbc0bfbd8f916eb59 Mon Sep 17 00:00:00 2001 From: zhanglianjie Date: Thu, 17 Feb 2022 18:51:51 -0800 Subject: mm: move page-writeback sysctls to their own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the page-writeback sysctls to its own file. [akpm@linux-foundation.org: coding-style cleanups] akpm@linux-foundation.org: fix CONFIG_SYSCTL=n warnings] Link: https://lkml.kernel.org/r/20220129012955.26594-1-zhanglianjie@uniontech.com Signed-off-by: zhanglianjie Cc: Kees Cook Cc: Iurii Zaikin Cc: Luis Chamberlain Signed-off-by: Andrew Morton Signed-off-by: Luis Chamberlain --- include/linux/writeback.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fec248ab1fec..dc2b94e6a94f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -345,28 +345,13 @@ void wb_domain_exit(struct wb_domain *dom); extern struct wb_domain global_wb_domain; /* These are exported to sysctl. */ -extern int dirty_background_ratio; -extern unsigned long dirty_background_bytes; -extern int vm_dirty_ratio; -extern unsigned long vm_dirty_bytes; extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; -extern int vm_highmem_is_dirtyable; extern int laptop_mode; -int dirty_background_ratio_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int dirty_background_bytes_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int dirty_ratio_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int dirty_bytes_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int dirtytime_interval_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); -- cgit v1.2.3 From f79c9b8ae8bde10126586c1bb55b5fd027276d8e Mon Sep 17 00:00:00 2001 From: tangmeng Date: Fri, 18 Feb 2022 18:58:57 +0800 Subject: kernel/lockdep: move lockdep sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the prove_locking and lock_stat sysctls to its own file, kernel/lockdep.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/lockdep.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 467b94257105..37951c17908e 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -16,10 +16,6 @@ struct task_struct; -/* for sysctl */ -extern int prove_locking; -extern int lock_stat; - #ifdef CONFIG_LOCKDEP #include -- cgit v1.2.3 From 9df918698408fd914493aba0b7858fef50eba63a Mon Sep 17 00:00:00 2001 From: tangmeng Date: Fri, 18 Feb 2022 18:59:12 +0800 Subject: kernel/panic: move panic sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the oops_all_cpu_backtrace sysctl to its own file, kernel/panic.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/panic.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/panic.h b/include/linux/panic.h index f5844908a089..e71161da69c4 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -15,12 +15,6 @@ extern void oops_enter(void); extern void oops_exit(void); extern bool oops_may_print(void); -#ifdef CONFIG_SMP -extern unsigned int sysctl_oops_all_cpu_backtrace; -#else -#define sysctl_oops_all_cpu_backtrace 0 -#endif /* CONFIG_SMP */ - extern int panic_timeout; extern unsigned long panic_print; extern int panic_on_oops; -- cgit v1.2.3 From 801b501439d1b366d524dee4fc1e6b3473a95b9a Mon Sep 17 00:00:00 2001 From: tangmeng Date: Fri, 18 Feb 2022 18:59:23 +0800 Subject: kernel/acct: move acct sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the acct sysctl to its own file, kernel/acct.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/acct.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/acct.h b/include/linux/acct.h index bc70e81895c0..2718c4854815 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -21,7 +21,6 @@ #ifdef CONFIG_BSD_PROCESS_ACCT struct pid_namespace; -extern int acct_parm[]; /* for sysctl */ extern void acct_collect(long exitcode, int group_dead); extern void acct_process(void); extern void acct_exit_ns(struct pid_namespace *); -- cgit v1.2.3 From 1186618a6a35d43a865448472a261184b608d13c Mon Sep 17 00:00:00 2001 From: tangmeng Date: Fri, 18 Feb 2022 18:59:36 +0800 Subject: kernel/delayacct: move delayacct sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the delayacct sysctl to its own file, kernel/delayacct.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/delayacct.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 3e03d010bd2e..6b16a6930a19 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -61,9 +61,6 @@ extern int delayacct_on; /* Delay accounting turned on/off */ extern struct kmem_cache *delayacct_cache; extern void delayacct_init(void); -extern int sysctl_delayacct(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); - extern void __delayacct_tsk_init(struct task_struct *); extern void __delayacct_tsk_exit(struct task_struct *); extern void __delayacct_blkio_start(void); -- cgit v1.2.3 From d772cc2c321900f3f463a124eebeb7218e66dda6 Mon Sep 17 00:00:00 2001 From: tangmeng Date: Fri, 18 Feb 2022 18:59:49 +0800 Subject: kernel/do_mount_initrd: move real_root_dev sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the real_root_dev sysctl to its own file, kernel/do_mount_initrd.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/initrd.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 1bbe9af48dc3..f1a1f4c92ded 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -29,8 +29,6 @@ static inline void wait_for_initramfs(void) {} extern phys_addr_t phys_initrd_start; extern unsigned long phys_initrd_size; -extern unsigned int real_root_dev; - extern char __initramfs_start[]; extern unsigned long __initramfs_size; -- cgit v1.2.3 From 8e4e83b2278bdfb55cb2b13de07cf0a721ce8af7 Mon Sep 17 00:00:00 2001 From: Wei Xiao Date: Wed, 23 Feb 2022 19:11:53 +0800 Subject: ftrace: move sysctl_ftrace_enabled to ftrace.c This moves ftrace_enabled to trace/ftrace.c. We move sysctls to places where features actually belong to improve the readability of the code and reduce the risk of code merge conflicts. At the same time, the proc-sysctl maintainers do not want to know what sysctl knobs you wish to add for your owner piece of code, we just care about the core logic. Signed-off-by: Wei Xiao Acked-by: Steven Rostedt (Google) Signed-off-by: Luis Chamberlain --- include/linux/ftrace.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 4816b7e11047..088b915853dd 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -101,9 +101,6 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val #ifdef CONFIG_FUNCTION_TRACER extern int ftrace_enabled; -extern int -ftrace_enable_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS -- cgit v1.2.3 From 51454ea42c1ab4e0c2828bb0d4d53957976980de Mon Sep 17 00:00:00 2001 From: Niels Dossche Date: Mon, 4 Apr 2022 01:15:24 +0200 Subject: ipv6: fix locking issues with loops over idev->addr_list idev->addr_list needs to be protected by idev->lock. However, it is not always possible to do so while iterating and performing actions on inet6_ifaddr instances. For example, multiple functions (like addrconf_{join,leave}_anycast) eventually call down to other functions that acquire the idev->lock. The current code temporarily unlocked the idev->lock during the loops, which can cause race conditions. Moving the locks up is also not an appropriate solution as the ordering of lock acquisition will be inconsistent with for example mc_lock. This solution adds an additional field to inet6_ifaddr that is used to temporarily add the instances to a temporary list while holding idev->lock. The temporary list can then be traversed without holding idev->lock. This change was done in two places. In addrconf_ifdown, the list_for_each_entry_safe variant of the list loop is also no longer necessary as there is no deletion within that specific loop. Suggested-by: Paolo Abeni Signed-off-by: Niels Dossche Acked-by: Paolo Abeni Link: https://lore.kernel.org/r/20220403231523.45843-1-dossche.niels@gmail.com Signed-off-by: Jakub Kicinski --- include/net/if_inet6.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 4cfdef6ca4f6..c8490729b4ae 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -64,6 +64,14 @@ struct inet6_ifaddr { struct hlist_node addr_lst; struct list_head if_list; + /* + * Used to safely traverse idev->addr_list in process context + * if the idev->lock needed to protect idev->addr_list cannot be held. + * In that case, add the items to this list temporarily and iterate + * without holding idev->lock. + * See addrconf_ifdown and dev_forward_change. + */ + struct list_head if_list_aux; struct list_head tmp_list; struct inet6_ifaddr *ifpub; -- cgit v1.2.3 From 5ea98e01ab524cbc53dad8aebd27b434ebe5d074 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 7 Mar 2022 15:33:39 -0600 Subject: x86/boot: Add Confidential Computing type to setup_data While launching encrypted guests, the hypervisor may need to provide some additional information during the guest boot. When booting under an EFI-based BIOS, the EFI configuration table contains an entry for the confidential computing blob that contains the required information. To support booting encrypted guests on non-EFI VMs, the hypervisor needs to pass this additional information to the guest kernel using a different method. For this purpose, introduce SETUP_CC_BLOB type in setup_data to hold the physical address of the confidential computing blob location. The boot loader or hypervisor may choose to use this method instead of an EFI configuration table. The CC blob location scanning should give preference to a setup_data blob over an EFI configuration table. In AMD SEV-SNP, the CC blob contains the address of the secrets and CPUID pages. The secrets page includes information such as a VM to PSP communication key and the CPUID page contains PSP-filtered CPUID values. Define the AMD SEV confidential computing blob structure. While at it, define the EFI GUID for the confidential computing blob. [ bp: Massage commit message, mark struct __packed. ] Signed-off-by: Brijesh Singh Signed-off-by: Borislav Petkov Acked-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20220307213356.2797205-30-brijesh.singh@amd.com --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index ccd4d3f91c98..984aa688997a 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -390,6 +390,7 @@ void efi_native_runtime_setup(void); #define EFI_CERT_SHA256_GUID EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28) #define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) #define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) +#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) /* * This GUID is used to pass to the kernel proper the struct screen_info -- cgit v1.2.3 From fce96cf0443083e37455eff8f78fd240c621dae3 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 7 Mar 2022 15:33:53 -0600 Subject: virt: Add SEV-SNP guest driver The SEV-SNP specification provides the guest a mechanism to communicate with the PSP without risk from a malicious hypervisor who wishes to read, alter, drop or replay the messages sent. The driver uses snp_issue_guest_request() to issue GHCB SNP_GUEST_REQUEST or SNP_EXT_GUEST_REQUEST NAE events to submit the request to PSP. The PSP requires that all communication should be encrypted using key specified through a struct snp_guest_platform_data descriptor. Userspace can use SNP_GET_REPORT ioctl() to query the guest attestation report. See SEV-SNP spec section Guest Messages for more details. [ bp: Remove the "what" from the commit message, massage. ] Signed-off-by: Brijesh Singh Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220307213356.2797205-44-brijesh.singh@amd.com --- include/uapi/linux/sev-guest.h | 50 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) create mode 100644 include/uapi/linux/sev-guest.h (limited to 'include') diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h new file mode 100644 index 000000000000..38f11d723c68 --- /dev/null +++ b/include/uapi/linux/sev-guest.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Userspace interface for AMD SEV and SNP guest driver. + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh + * + * SEV API specification is available at: https://developer.amd.com/sev/ + */ + +#ifndef __UAPI_LINUX_SEV_GUEST_H_ +#define __UAPI_LINUX_SEV_GUEST_H_ + +#include + +struct snp_report_req { + /* user data that should be included in the report */ + __u8 user_data[64]; + + /* The vmpl level to be included in the report */ + __u32 vmpl; + + /* Must be zero filled */ + __u8 rsvd[28]; +}; + +struct snp_report_resp { + /* response data, see SEV-SNP spec for the format */ + __u8 data[4000]; +}; + +struct snp_guest_request_ioctl { + /* message version number (must be non-zero) */ + __u8 msg_version; + + /* Request and response structure address */ + __u64 req_data; + __u64 resp_data; + + /* firmware error code on failure (see psp-sev.h) */ + __u64 fw_err; +}; + +#define SNP_GUEST_REQ_IOC_TYPE 'S' + +/* Get SNP attestation report */ +#define SNP_GET_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x0, struct snp_guest_request_ioctl) + +#endif /* __UAPI_LINUX_SEV_GUEST_H_ */ -- cgit v1.2.3 From 68de0b2f938642079c0c853b219bdb88c4dc4d13 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Thu, 24 Feb 2022 10:56:23 -0600 Subject: virt: sevguest: Add support to derive key The SNP_GET_DERIVED_KEY ioctl interface can be used by the SNP guest to ask the firmware to provide a key derived from a root key. The derived key may be used by the guest for any purposes it chooses, such as a sealing key or communicating with the external entities. See SEV-SNP firmware spec for more information. [ bp: No need to memset "req" - it will get overwritten. ] Signed-off-by: Brijesh Singh Signed-off-by: Borislav Petkov Reviewed-by: Liam Merwick Link: https://lore.kernel.org/r/20220307213356.2797205-45-brijesh.singh@amd.com --- include/uapi/linux/sev-guest.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h index 38f11d723c68..598367f12064 100644 --- a/include/uapi/linux/sev-guest.h +++ b/include/uapi/linux/sev-guest.h @@ -30,6 +30,20 @@ struct snp_report_resp { __u8 data[4000]; }; +struct snp_derived_key_req { + __u32 root_key_select; + __u32 rsvd; + __u64 guest_field_select; + __u32 vmpl; + __u32 guest_svn; + __u64 tcb_version; +}; + +struct snp_derived_key_resp { + /* response data, see SEV-SNP spec for the format */ + __u8 data[64]; +}; + struct snp_guest_request_ioctl { /* message version number (must be non-zero) */ __u8 msg_version; @@ -47,4 +61,7 @@ struct snp_guest_request_ioctl { /* Get SNP attestation report */ #define SNP_GET_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x0, struct snp_guest_request_ioctl) +/* Get a derived key from the root */ +#define SNP_GET_DERIVED_KEY _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x1, struct snp_guest_request_ioctl) + #endif /* __UAPI_LINUX_SEV_GUEST_H_ */ -- cgit v1.2.3 From d80b494f712317493d464a55652698c4d1b7bb0f Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 7 Mar 2022 15:33:55 -0600 Subject: virt: sevguest: Add support to get extended report Version 2 of GHCB specification defines Non-Automatic-Exit (NAE) to get extended guest report which is similar to the SNP_GET_REPORT ioctl. The main difference is related to the additional data that will be returned. That additional data returned is a certificate blob that can be used by the SNP guest user. The certificate blob layout is defined in the GHCB specification. The driver simply treats the blob as a opaque data and copies it to userspace. [ bp: Massage commit message, cast 1st arg of access_ok() ] Signed-off-by: Brijesh Singh Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220307213356.2797205-46-brijesh.singh@amd.com --- include/uapi/linux/sev-guest.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h index 598367f12064..256aaeff7e65 100644 --- a/include/uapi/linux/sev-guest.h +++ b/include/uapi/linux/sev-guest.h @@ -56,6 +56,16 @@ struct snp_guest_request_ioctl { __u64 fw_err; }; +struct snp_ext_report_req { + struct snp_report_req data; + + /* where to copy the certificate blob */ + __u64 certs_address; + + /* length of the certificate blob */ + __u32 certs_len; +}; + #define SNP_GUEST_REQ_IOC_TYPE 'S' /* Get SNP attestation report */ @@ -64,4 +74,7 @@ struct snp_guest_request_ioctl { /* Get a derived key from the root */ #define SNP_GET_DERIVED_KEY _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x1, struct snp_guest_request_ioctl) +/* Get SNP extended report as defined in the GHCB specification version 2. */ +#define SNP_GET_EXT_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x2, struct snp_guest_request_ioctl) + #endif /* __UAPI_LINUX_SEV_GUEST_H_ */ -- cgit v1.2.3 From bae1a962ac2c5e6be08319ff3f7d6df542584fce Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Wed, 6 Apr 2022 02:29:33 +0300 Subject: x86/topology: Disable CPU online/offline control for TDX guests Unlike regular VMs, TDX guests use the firmware hand-off wakeup method to wake up the APs during the boot process. This wakeup model uses a mailbox to communicate with firmware to bring up the APs. As per the design, this mailbox can only be used once for the given AP, which means after the APs are booted, the same mailbox cannot be used to offline/online the given AP. More details about this requirement can be found in Intel TDX Virtual Firmware Design Guide, sec titled "AP initialization in OS" and in sec titled "Hotplug Device". Since the architecture does not support any method of offlining the CPUs, disable CPU hotplug support in the kernel. Since this hotplug disable feature can be re-used by other VM guests, add a new CC attribute CC_ATTR_HOTPLUG_DISABLED and use it to disable the hotplug support. Attempt to offline CPU will fail with -EOPNOTSUPP. Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Reviewed-by: Andi Kleen Reviewed-by: Tony Luck Reviewed-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20220405232939.73860-25-kirill.shutemov@linux.intel.com --- include/linux/cc_platform.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index efd8205282da..691494bbaf5a 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -72,6 +72,16 @@ enum cc_attr { * Examples include TDX guest & SEV. */ CC_ATTR_GUEST_UNROLL_STRING_IO, + + /** + * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled. + * + * The platform/OS is running as a guest/virtual machine does not + * support CPU hotplug feature. + * + * Examples include TDX Guest. + */ + CC_ATTR_HOTPLUG_DISABLED, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM -- cgit v1.2.3 From ccc706353d1b89d8ff1726e575dd4a10f8550fb7 Mon Sep 17 00:00:00 2001 From: Rohit Agarwal Date: Wed, 16 Mar 2022 11:37:14 +0530 Subject: dt-bindings: power: Add rpm power domain bindings for SDX65 Add RPM power domain bindings for the SDX65 SoC. Signed-off-by: Rohit Agarwal Acked-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/1647410837-22537-4-git-send-email-quic_rohiagar@quicinc.com --- include/dt-bindings/power/qcom-rpmpd.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/qcom-rpmpd.h b/include/dt-bindings/power/qcom-rpmpd.h index c002cc6ddf55..0a8978d0c78c 100644 --- a/include/dt-bindings/power/qcom-rpmpd.h +++ b/include/dt-bindings/power/qcom-rpmpd.h @@ -20,6 +20,14 @@ #define SDX55_MX 1 #define SDX55_CX 2 +/* SDX65 Power Domain Indexes */ +#define SDX65_MSS 0 +#define SDX65_MX 1 +#define SDX65_MX_AO 2 +#define SDX65_CX 3 +#define SDX65_CX_AO 4 +#define SDX65_MXC 5 + /* SM6350 Power Domain Indexes */ #define SM6350_CX 0 #define SM6350_GFX 1 -- cgit v1.2.3 From 6264f58ca0e54e41d63c2d00334a48bac28fbf30 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Apr 2022 14:37:54 -0700 Subject: net: extract a few internals from netdevice.h There's a number of functions and static variables used under net/core/ but not from the outside. We currently dump most of them into netdevice.h. That bad for many reasons: - netdevice.h is very cluttered, hard to figure out what the APIs are; - netdevice.h is very long; - we have to touch netdevice.h more which causes expensive incremental builds. Create a header under net/core/ and move some declarations. The new header is also a bit of a catch-all but that's fine, if we create more specific headers people will likely over-think where their declaration fit best. And end up putting them in netdevice.h, again. More work should be done on splitting netdevice.h into more targeted headers, but that'd be more time consuming so small steps. Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 72 ++--------------------------------------------- 1 file changed, 2 insertions(+), 70 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7b2a0b739684..7e7b2a72e473 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -59,7 +59,8 @@ struct dsa_port; struct ip_tunnel_parm; struct macsec_context; struct macsec_ops; - +struct netdev_name_node; +struct sd_flow_limit; struct sfp_bus; /* 802.11 specific */ struct wireless_dev; @@ -1020,16 +1021,6 @@ struct dev_ifalias { struct devlink; struct tlsdev_ops; -struct netdev_name_node { - struct hlist_node hlist; - struct list_head list; - struct net_device *dev; - const char *name; -}; - -int netdev_name_node_alt_create(struct net_device *dev, const char *name); -int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); - struct netdev_net_notifier { struct list_head list; struct notifier_block *nb; @@ -2975,7 +2966,6 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); -int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); @@ -3034,19 +3024,6 @@ static inline bool dev_has_header(const struct net_device *dev) return dev->header_ops && dev->header_ops->create; } -#ifdef CONFIG_NET_FLOW_LIMIT -#define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */ -struct sd_flow_limit { - u64 count; - unsigned int num_buckets; - unsigned int history_head; - u16 history[FLOW_LIMIT_HISTORY]; - u8 buckets[]; -}; - -extern int netdev_flow_limit_table_len; -#endif /* CONFIG_NET_FLOW_LIMIT */ - /* * Incoming packets are placed on per-CPU queues */ @@ -3770,7 +3747,6 @@ int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); void __dev_notify_flags(struct net_device *, unsigned int old_flags, unsigned int gchanges); -int dev_change_name(struct net_device *, const char *); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int __dev_change_net_namespace(struct net_device *dev, struct net *net, @@ -3782,13 +3758,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, return __dev_change_net_namespace(dev, net, pat, 0); } int __dev_set_mtu(struct net_device *, int); -int dev_validate_mtu(struct net_device *dev, int mtu, - struct netlink_ext_ack *extack); -int dev_set_mtu_ext(struct net_device *dev, int mtu, - struct netlink_ext_ack *extack); int dev_set_mtu(struct net_device *, int); -int dev_change_tx_queue_len(struct net_device *, unsigned long); -void dev_set_group(struct net_device *, int); int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack); int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, @@ -3796,24 +3766,13 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); -int dev_change_carrier(struct net_device *, bool new_carrier); -int dev_get_phys_port_id(struct net_device *dev, - struct netdev_phys_item_id *ppid); -int dev_get_phys_port_name(struct net_device *dev, - char *name, size_t len); int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); -int dev_change_proto_down(struct net_device *dev, bool proto_down); -void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, - u32 value); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); -int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, - int fd, int expected_fd, u32 flags); int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); @@ -3898,13 +3857,6 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, bool dev_nit_active(struct net_device *dev); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); -extern int netdev_budget; -extern unsigned int netdev_budget_usecs; - -/* Used by rtnetlink.c:__rtnl_unlock()/rtnl_unlock() */ -extern struct list_head net_todo_list; -void netdev_run_todo(void); - static inline void __dev_put(struct net_device *dev) { if (dev) { @@ -4021,10 +3973,7 @@ static inline void dev_replace_track(struct net_device *odev, * called netif_lowerlayer_*() because they represent the state of any * kind of lower layer not just hardware media. */ - -void linkwatch_init_dev(struct net_device *dev); void linkwatch_fire_event(struct net_device *dev); -void linkwatch_forget_dev(struct net_device *dev); /** * netif_carrier_ok - test if carrier present @@ -4470,9 +4419,6 @@ int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); -void dev_addr_flush(struct net_device *dev); -int dev_addr_init(struct net_device *dev); -void dev_addr_check(struct net_device *dev); /* Functions used for unicast addresses handling */ int dev_uc_add(struct net_device *dev, const unsigned char *addr); @@ -4562,7 +4508,6 @@ static inline void __dev_mc_unsync(struct net_device *dev, /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); -void __dev_set_rx_mode(struct net_device *dev); int dev_set_promiscuity(struct net_device *dev, int inc); int dev_set_allmulti(struct net_device *dev, int inc); void netdev_state_change(struct net_device *dev); @@ -4580,11 +4525,6 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); extern int netdev_max_backlog; -extern int netdev_tstamp_prequeue; -extern int netdev_unregister_timeout_secs; -extern int weight_p; -extern int dev_weight_rx_bias; -extern int dev_weight_tx_bias; extern int dev_rx_weight; extern int dev_tx_weight; extern int gro_normal_batch; @@ -4772,12 +4712,6 @@ static inline void netdev_rx_csum_fault(struct net_device *dev, void net_enable_timestamp(void); void net_disable_timestamp(void); -#ifdef CONFIG_PROC_FS -int __init dev_proc_init(void); -#else -#define dev_proc_init() 0 -#endif - static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, bool more) @@ -4813,8 +4747,6 @@ extern const struct kobj_ns_type_operations net_ns_type_operations; const char *netdev_drivername(const struct net_device *dev); -void linkwatch_run_queue(void); - static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { -- cgit v1.2.3 From 794c24e9921f32ded4422833a990ccf11dc3c00e Mon Sep 17 00:00:00 2001 From: Jeffrey Ji Date: Wed, 6 Apr 2022 17:26:00 +0000 Subject: net-core: rx_otherhost_dropped to core_stats Increment rx_otherhost_dropped counter when packet dropped due to mismatched dest MAC addr. An example when this drop can occur is when manually crafting raw packets that will be consumed by a user space application via a tap device. For testing purposes local traffic was generated using trafgen for the client and netcat to start a server Tested: Created 2 netns, sent 1 packet using trafgen from 1 to the other with "{eth(daddr=$INCORRECT_MAC...}", verified that iproute2 showed the counter was incremented. (Also had to modify iproute2 to show the stat, additional patch for that coming next.) Signed-off-by: Jeffrey Ji Reviewed-by: Brian Vazquez Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220406172600.1141083-1-jeffreyjilinux@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 ++ include/uapi/linux/if_link.h | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7e7b2a72e473..28ea4f8269d4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -203,6 +203,7 @@ struct net_device_core_stats { local_t rx_dropped; local_t tx_dropped; local_t rx_nohandler; + local_t rx_otherhost_dropped; } __aligned(4 * sizeof(local_t)); #include @@ -3837,6 +3838,7 @@ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) DEV_CORE_STATS_INC(rx_nohandler) +DEV_CORE_STATS_INC(rx_otherhost_dropped) static __always_inline int ____dev_forward_skb(struct net_device *dev, struct sk_buff *skb, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index cc284c048e69..d1e600816b82 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -211,6 +211,9 @@ struct rtnl_link_stats { * @rx_nohandler: Number of packets received on the interface * but dropped by the networking stack because the device is * not designated to receive packets (e.g. backup link in a bond). + * + * @rx_otherhost_dropped: Number of packets dropped due to mismatch + * in destination MAC address. */ struct rtnl_link_stats64 { __u64 rx_packets; @@ -243,6 +246,8 @@ struct rtnl_link_stats64 { __u64 rx_compressed; __u64 tx_compressed; __u64 rx_nohandler; + + __u64 rx_otherhost_dropped; }; /* Subset of link stats useful for in-HW collection. Meaning of the fields is as -- cgit v1.2.3 From 15fcdf6ae116d1e8da4ff76c6fd82514f5ea501b Mon Sep 17 00:00:00 2001 From: Ping Gan Date: Wed, 6 Apr 2022 09:09:56 +0800 Subject: tcp: Add tracepoint for tcp_set_ca_state The congestion status of a tcp flow may be updated since there is congestion between tcp sender and receiver. It makes sense to add tracepoint for congestion status set function to summate cc status duration and evaluate the performance of network and congestion algorithm. the backgound of this patch is below. Link: https://github.com/iovisor/bcc/pull/3899 Signed-off-by: Ping Gan Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220406010956.19656-1-jacky_gam_2001@163.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 12 +++--------- include/trace/events/tcp.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 54aa2f02bb63..6d50a662bf89 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1139,15 +1139,6 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk) return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } -static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - - if (icsk->icsk_ca_ops->set_state) - icsk->icsk_ca_ops->set_state(sk, ca_state); - icsk->icsk_ca_state = ca_state; -} - static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1156,6 +1147,9 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) icsk->icsk_ca_ops->cwnd_event(sk, event); } +/* From tcp_cong.c */ +void tcp_set_ca_state(struct sock *sk, const u8 ca_state); + /* From tcp_rate.c */ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb); void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index edcd6369de10..901b440238d5 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -371,6 +371,51 @@ DEFINE_EVENT(tcp_event_skb, tcp_bad_csum, TP_ARGS(skb) ); +TRACE_EVENT(tcp_cong_state_set, + + TP_PROTO(struct sock *sk, const u8 ca_state), + + TP_ARGS(sk, ca_state), + + TP_STRUCT__entry( + __field(const void *, skaddr) + __field(__u16, sport) + __field(__u16, dport) + __array(__u8, saddr, 4) + __array(__u8, daddr, 4) + __array(__u8, saddr_v6, 16) + __array(__u8, daddr_v6, 16) + __field(__u8, cong_state) + ), + + TP_fast_assign( + struct inet_sock *inet = inet_sk(sk); + __be32 *p32; + + __entry->skaddr = sk; + + __entry->sport = ntohs(inet->inet_sport); + __entry->dport = ntohs(inet->inet_dport); + + p32 = (__be32 *) __entry->saddr; + *p32 = inet->inet_saddr; + + p32 = (__be32 *) __entry->daddr; + *p32 = inet->inet_daddr; + + TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, + sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); + + __entry->cong_state = ca_state; + ), + + TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", + __entry->sport, __entry->dport, + __entry->saddr, __entry->daddr, + __entry->saddr_v6, __entry->daddr_v6, + __entry->cong_state) +); + #endif /* _TRACE_TCP_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 73c919d314ad57be900437fd329990b1d846b763 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Tue, 15 Mar 2022 17:44:51 +0800 Subject: crypto: sm4 - export sm4 constant arrays Export the constant arrays fk, ck, sbox of the SM4 algorithm, and add the 'crypto_sm4_' prefix, where sbox is used in the SM4 NEON implementation for the tbl/tbx instruction to replace the S-BOX, and the fk, ck arrays are used in the SM4 CE implementation. Use the sm4ekey instruction to speed up key expansion operations. Signed-off-by: Tianjia Zhang Signed-off-by: Herbert Xu --- include/crypto/sm4.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/crypto/sm4.h b/include/crypto/sm4.h index 709f286e7b25..9656a9a40326 100644 --- a/include/crypto/sm4.h +++ b/include/crypto/sm4.h @@ -21,6 +21,10 @@ struct sm4_ctx { u32 rkey_dec[SM4_RKEY_WORDS]; }; +extern const u32 crypto_sm4_fk[]; +extern const u32 crypto_sm4_ck[]; +extern const u8 crypto_sm4_sbox[]; + /** * sm4_expandkey - Expands the SM4 key as described in GB/T 32907-2016 * @ctx: The location where the computed key will be stored. -- cgit v1.2.3 From bdae79651453df0bca20963fc2ab970146ef2a37 Mon Sep 17 00:00:00 2001 From: Shuai Xue Date: Tue, 8 Mar 2022 22:40:51 +0800 Subject: efi/cper: Add a cper_mem_err_status_str() to decode error description Introduce a new helper function cper_mem_err_status_str() to decode the error status value into a human readable string. [ bp: Massage. ] Signed-off-by: Shuai Xue Signed-off-by: Borislav Petkov Acked-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20220308144053.49090-2-xueshuai@linux.alibaba.com --- include/linux/cper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cper.h b/include/linux/cper.h index 6a511a1078ca..5b1dd27b317d 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -558,6 +558,7 @@ extern const char *const cper_proc_error_type_strs[4]; u64 cper_next_record_id(void); const char *cper_severity_str(unsigned int); const char *cper_mem_err_type_str(unsigned int); +const char *cper_mem_err_status_str(u64 status); void cper_print_bits(const char *prefix, unsigned int bits, const char * const strs[], unsigned int strs_size); void cper_mem_err_pack(const struct cper_sec_mem_err *, -- cgit v1.2.3 From ed27b5df3877458eb24615fd9c202178660db009 Mon Sep 17 00:00:00 2001 From: Shuai Xue Date: Tue, 8 Mar 2022 22:40:52 +0800 Subject: EDAC/ghes: Unify CPER memory error location reporting Switch the GHES EDAC memory error reporting functions to use the common CPER ones and get rid of code duplication. [ bp: - rewrite commit message, remove useless text - rip out useless reformatting - align function params on the opening brace - rename function to a more descriptive name - drop useless function exports - handle buffer lengths properly when printing other detail - remove useless casting ] Signed-off-by: Shuai Xue Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220308144053.49090-3-xueshuai@linux.alibaba.com --- include/linux/cper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cper.h b/include/linux/cper.h index 5b1dd27b317d..eacb7dd7b3af 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -569,5 +569,7 @@ void cper_print_proc_arm(const char *pfx, const struct cper_sec_proc_arm *proc); void cper_print_proc_ia(const char *pfx, const struct cper_sec_proc_ia *proc); +int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); +int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); #endif -- cgit v1.2.3 From 9027ce0b071a1bbd046682907fc2e23ca3592883 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 23 Mar 2022 14:22:01 +0100 Subject: netfilter: ecache: move to separate structure This makes it easier for a followup patch to only expose ecache related parts of nf_conntrack_net structure. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index b08b70989d2c..69e6c6a218be 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -43,6 +43,11 @@ union nf_conntrack_expect_proto { /* insert expect proto private data here */ }; +struct nf_conntrack_net_ecache { + struct delayed_work dwork; + struct netns_ct *ct_net; +}; + struct nf_conntrack_net { /* only used when new connection is allocated: */ atomic_t count; @@ -58,8 +63,7 @@ struct nf_conntrack_net { struct ctl_table_header *sysctl_header; #endif #ifdef CONFIG_NF_CONNTRACK_EVENTS - struct delayed_work ecache_dwork; - struct netns_ct *ct_net; + struct nf_conntrack_net_ecache ecache; #endif }; -- cgit v1.2.3 From c3f6bb74137c68b515b7e2ff123a80611e801013 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 7 Apr 2022 20:38:16 -0700 Subject: tls: rx: don't store the record type in socket context Original TLS implementation was handling one record at a time. It stashed the type of the record inside tls context (per socket structure) for convenience. When async crypto support was added [1] the author had to use skb->cb to store the type per-message. The use of skb->cb overlaps with strparser, however, so a hybrid approach was taken where type is stored in context while parsing (since we parse a message at a time) but once parsed its copied to skb->cb. Recently a workaround for sockmaps [2] exposed the previously private struct _strp_msg and started a trend of adding user fields directly in strparser's header. This is cleaner than storing information about an skb in the context. This change is not strictly necessary, but IMHO the ownership of the context field is confusing. Information naturally belongs to the skb. [1] commit 94524d8fc965 ("net/tls: Add support for async decryption of tls records") [2] commit b2c4618162ec ("bpf, sockmap: sk_skb data_end access incorrect when src_reg = dst_reg") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/strparser.h | 3 +++ include/net/tls.h | 10 +++------- 2 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/strparser.h b/include/net/strparser.h index 732b7097d78e..c271543076cf 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -70,6 +70,9 @@ struct sk_skb_cb { * when dst_reg == src_reg. */ u64 temp_reg; + struct tls_msg { + u8 control; + } tls; }; static inline struct strp_msg *strp_msg(struct sk_buff *skb) diff --git a/include/net/tls.h b/include/net/tls.h index b6968a5b5538..c3717cd1f1cd 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -117,11 +117,6 @@ struct tls_rec { u8 aead_req_ctx[]; }; -struct tls_msg { - struct strp_msg rxm; - u8 control; -}; - struct tx_work { struct delayed_work work; struct sock *sk; @@ -152,7 +147,6 @@ struct tls_sw_context_rx { void (*saved_data_ready)(struct sock *sk); struct sk_buff *recv_pkt; - u8 control; u8 async_capable:1; u8 decrypted:1; atomic_t decrypt_pending; @@ -411,7 +405,9 @@ void tls_free_partial_record(struct sock *sk, struct tls_context *ctx); static inline struct tls_msg *tls_msg(struct sk_buff *skb) { - return (struct tls_msg *)strp_msg(skb); + struct sk_skb_cb *scb = (struct sk_skb_cb *)skb->cb; + + return &scb->tls; } static inline bool tls_is_partially_sent_record(struct tls_context *ctx) -- cgit v1.2.3 From 7dc59c33d62c4520a119051d4486c214ef5caa23 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 7 Apr 2022 20:38:17 -0700 Subject: tls: rx: don't store the decryption status in socket context Similar justification to previous change, the information about decryption status belongs in the skb. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/strparser.h | 1 + include/net/tls.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/strparser.h b/include/net/strparser.h index c271543076cf..a191486eb1e4 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -72,6 +72,7 @@ struct sk_skb_cb { u64 temp_reg; struct tls_msg { u8 control; + u8 decrypted; } tls; }; diff --git a/include/net/tls.h b/include/net/tls.h index c3717cd1f1cd..f040edc97c50 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -148,7 +148,6 @@ struct tls_sw_context_rx { struct sk_buff *recv_pkt; u8 async_capable:1; - u8 decrypted:1; atomic_t decrypt_pending; /* protect crypto_wait with decrypt_pending*/ spinlock_t decrypt_compl_lock; -- cgit v1.2.3 From a8340cc02beed4ffbb5e7b1b0eadca445323fc6a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 7 Apr 2022 20:38:19 -0700 Subject: tls: rx: use a define for tag length TLS 1.3 has to strip padding, and it starts out 16 bytes from the end of the record. Make it clear this is because of the auth tag. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/tls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index f040edc97c50..a01c264e5f15 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -64,6 +64,7 @@ #define TLS_AAD_SPACE_SIZE 13 #define MAX_IV_SIZE 16 +#define TLS_TAG_SIZE 16 #define TLS_MAX_REC_SEQ_SIZE 8 /* For CCM mode, the full 16-bytes of IV is made of '4' fields of given sizes. -- cgit v1.2.3 From c2ccf84ecb715bb81dc7f51e69d680a95bf055ae Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 7 Apr 2022 10:35:22 +0300 Subject: net/sched: act_api: Add extack to offload_act_setup() callback The callback is used by various actions to populate the flow action structure prior to offload. Pass extack to this callback so that the various actions will be able to report accurate error messages to user space. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- include/net/act_api.h | 3 ++- include/net/pkt_cls.h | 6 ++++-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 3049cb69c025..9cf6870b526e 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -134,7 +134,8 @@ struct tc_action_ops { (*get_psample_group)(const struct tc_action *a, tc_action_priv_destructor *destructor); int (*offload_act_setup)(struct tc_action *act, void *entry_data, - u32 *index_inc, bool bind); + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack); }; struct tc_action_net { diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a3b57a93228a..8cf001aed858 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -547,10 +547,12 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } int tc_setup_offload_action(struct flow_action *flow_action, - const struct tcf_exts *exts); + const struct tcf_exts *exts, + struct netlink_ext_ack *extack); void tc_cleanup_offload_action(struct flow_action *flow_action); int tc_setup_action(struct flow_action *flow_action, - struct tc_action *actions[]); + struct tc_action *actions[], + struct netlink_ext_ack *extack); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop, bool rtnl_held); -- cgit v1.2.3 From 69642c2ab2f553fd8c4c121fcdf3b3054c727e86 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 7 Apr 2022 10:35:23 +0300 Subject: net/sched: act_gact: Add extack messages for offload failure For better error reporting to user space, add extack messages when gact action offload fails. Example: # echo 1 > /sys/kernel/tracing/events/netlink/netlink_extack/enable # tc filter add dev dummy0 ingress pref 1 proto all matchall skip_sw action continue Error: cls_matchall: Failed to setup flow action. We have an error talking to the kernel # cat /sys/kernel/tracing/trace_pipe tc-181 [002] b..1. 105.493450: netlink_extack: msg=act_gact: Offload of "continue" action is not supported tc-181 [002] ..... 105.493466: netlink_extack: msg=cls_matchall: Failed to setup flow action # tc filter add dev dummy0 ingress pref 1 proto all matchall skip_sw action reclassify Error: cls_matchall: Failed to setup flow action. We have an error talking to the kernel # cat /sys/kernel/tracing/trace_pipe tc-183 [002] b..1. 124.126477: netlink_extack: msg=act_gact: Offload of "reclassify" action is not supported tc-183 [002] ..... 124.126489: netlink_extack: msg=cls_matchall: Failed to setup flow action # tc filter add dev dummy0 ingress pref 1 proto all matchall skip_sw action pipe action drop Error: cls_matchall: Failed to setup flow action. We have an error talking to the kernel # cat /sys/kernel/tracing/trace_pipe tc-185 [002] b..1. 137.097791: netlink_extack: msg=act_gact: Offload of "pipe" action is not supported tc-185 [002] ..... 137.097804: netlink_extack: msg=cls_matchall: Failed to setup flow action Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- include/net/tc_act/tc_gact.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index eb8f01c819e6..832efd40e023 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -59,4 +59,19 @@ static inline u32 tcf_gact_goto_chain_index(const struct tc_action *a) return READ_ONCE(a->tcfa_action) & TC_ACT_EXT_VAL_MASK; } +static inline bool is_tcf_gact_continue(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_UNSPEC, false); +} + +static inline bool is_tcf_gact_reclassify(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_RECLASSIFY, false); +} + +static inline bool is_tcf_gact_pipe(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_PIPE, false); +} + #endif /* __NET_TC_GACT_H */ -- cgit v1.2.3 From a9c64939b669b3c83cc54738d1986430e6beaff2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 7 Apr 2022 10:35:28 +0300 Subject: net/sched: act_skbedit: Add extack messages for offload failure For better error reporting to user space, add extack messages when skbedit action offload fails. Example: # echo 1 > /sys/kernel/tracing/events/netlink/netlink_extack/enable # tc filter add dev dummy0 ingress pref 1 proto all matchall skip_sw action skbedit queue_mapping 1234 Error: cls_matchall: Failed to setup flow action. We have an error talking to the kernel # cat /sys/kernel/tracing/trace_pipe tc-185 [002] b..1. 31.802414: netlink_extack: msg=act_skbedit: Offload not supported when "queue_mapping" option is used tc-185 [002] ..... 31.802418: netlink_extack: msg=cls_matchall: Failed to setup flow action # tc filter add dev dummy0 ingress pref 1 proto all matchall skip_sw action skbedit inheritdsfield Error: cls_matchall: Failed to setup flow action. We have an error talking to the kernel # cat /sys/kernel/tracing/trace_pipe tc-187 [002] b..1. 45.985145: netlink_extack: msg=act_skbedit: Offload not supported when "inheritdsfield" option is used tc-187 [002] ..... 45.985160: netlink_extack: msg=cls_matchall: Failed to setup flow action Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- include/net/tc_act/tc_skbedit.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 00bfee70609e..cab8229b9bed 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -94,4 +94,16 @@ static inline u32 tcf_skbedit_priority(const struct tc_action *a) return priority; } +/* Return true iff action is queue_mapping */ +static inline bool is_tcf_skbedit_queue_mapping(const struct tc_action *a) +{ + return is_tcf_skbedit_with_flag(a, SKBEDIT_F_QUEUE_MAPPING); +} + +/* Return true iff action is inheritdsfield */ +static inline bool is_tcf_skbedit_inheritdsfield(const struct tc_action *a) +{ + return is_tcf_skbedit_with_flag(a, SKBEDIT_F_INHERITDSFIELD); +} + #endif /* __NET_TC_SKBEDIT_H */ -- cgit v1.2.3 From 85ebb1a6bd62147ebcfa70500d513331a8daf9e0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 1 Apr 2022 13:35:52 +0300 Subject: gpiolib: Introduce for_each_gpiochip_node() loop helper Introduce for_each_gpiochip_node() loop helper which iterates over the GPIO controller child nodes of a given device. Signed-off-by: Andy Shevchenko Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Acked-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..bfc91f122d5f 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -3,13 +3,14 @@ #define __LINUX_GPIO_DRIVER_H #include -#include #include #include #include #include #include #include +#include +#include struct gpio_desc; struct of_phandle_args; @@ -750,4 +751,8 @@ static inline void gpiochip_unlock_as_irq(struct gpio_chip *gc, } #endif /* CONFIG_GPIOLIB */ +#define for_each_gpiochip_node(dev, child) \ + device_for_each_child_node(dev, child) \ + if (!fwnode_property_present(child, "gpio-controller")) {} else + #endif /* __LINUX_GPIO_DRIVER_H */ -- cgit v1.2.3 From 0b19dde90ad004592792a928c75e80612be3e2e8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 1 Apr 2022 13:35:53 +0300 Subject: gpiolib: Introduce gpiochip_node_count() helper The gpiochip_node_count() helper iterates over the device child nodes that have the "gpio-controller" property set. It returns the number of such nodes under a given device. Signed-off-by: Andy Shevchenko Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Acked-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index bfc91f122d5f..12de0b22b4ef 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -755,4 +755,15 @@ static inline void gpiochip_unlock_as_irq(struct gpio_chip *gc, device_for_each_child_node(dev, child) \ if (!fwnode_property_present(child, "gpio-controller")) {} else +static inline unsigned int gpiochip_node_count(struct device *dev) +{ + struct fwnode_handle *child; + unsigned int count = 0; + + for_each_gpiochip_node(dev, child) + count++; + + return count; +} + #endif /* __LINUX_GPIO_DRIVER_H */ -- cgit v1.2.3 From 2fa33b3518a8da0a5345b7ae0064223b5e4e156f Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:36 +0300 Subject: net/mlx5_fpga: Drop INNOVA IPsec support Mellanox INNOVA IPsec cards are EOL in Nov, 2019 [1]. As such, the code is unmaintained, untested and not in-use by any upstream/distro oriented customers. In order to reduce code complexity, drop the kernel code. [1] https://network.nvidia.com/related-docs/eol/LCR-000535.pdf Link: https://lore.kernel.org/r/2afe88ec5020a491079eacf6fe3c89b64d65195c.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc_fpga.h | 148 ------------------------------------- 1 file changed, 148 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index e3d824f6a309..45c7c0d67635 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -386,68 +386,6 @@ struct mlx5_ifc_fpga_destroy_qp_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_ipsec_extended_cap_bits { - u8 encapsulation[0x20]; - - u8 reserved_0[0x12]; - u8 v2_command[0x1]; - u8 udp_encap[0x1]; - u8 rx_no_trailer[0x1]; - u8 ipv4_fragment[0x1]; - u8 ipv6[0x1]; - u8 esn[0x1]; - u8 lso[0x1]; - u8 transport_and_tunnel_mode[0x1]; - u8 tunnel_mode[0x1]; - u8 transport_mode[0x1]; - u8 ah_esp[0x1]; - u8 esp[0x1]; - u8 ah[0x1]; - u8 ipv4_options[0x1]; - - u8 auth_alg[0x20]; - - u8 enc_alg[0x20]; - - u8 sa_cap[0x20]; - - u8 reserved_1[0x10]; - u8 number_of_ipsec_counters[0x10]; - - u8 ipsec_counters_addr_low[0x20]; - u8 ipsec_counters_addr_high[0x20]; -}; - -struct mlx5_ifc_ipsec_counters_bits { - u8 dec_in_packets[0x40]; - - u8 dec_out_packets[0x40]; - - u8 dec_bypass_packets[0x40]; - - u8 enc_in_packets[0x40]; - - u8 enc_out_packets[0x40]; - - u8 enc_bypass_packets[0x40]; - - u8 drop_dec_packets[0x40]; - - u8 failed_auth_dec_packets[0x40]; - - u8 drop_enc_packets[0x40]; - - u8 success_add_sa[0x40]; - - u8 fail_add_sa[0x40]; - - u8 success_delete_sa[0x40]; - - u8 fail_delete_sa[0x40]; - - u8 dropped_cmd[0x40]; -}; - enum { MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RETRY_COUNTER_EXPIRED = 0x1, MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RNR_EXPIRED = 0x2, @@ -464,90 +402,4 @@ struct mlx5_ifc_fpga_qp_error_event_bits { u8 reserved_at_c0[0x8]; u8 fpga_qpn[0x18]; }; -enum mlx5_ifc_fpga_ipsec_response_syndrome { - MLX5_FPGA_IPSEC_RESPONSE_SUCCESS = 0, - MLX5_FPGA_IPSEC_RESPONSE_ILLEGAL_REQUEST = 1, - MLX5_FPGA_IPSEC_RESPONSE_SADB_ISSUE = 2, - MLX5_FPGA_IPSEC_RESPONSE_WRITE_RESPONSE_ISSUE = 3, -}; - -struct mlx5_ifc_fpga_ipsec_cmd_resp { - __be32 syndrome; - union { - __be32 sw_sa_handle; - __be32 flags; - }; - u8 reserved[24]; -} __packed; - -enum mlx5_ifc_fpga_ipsec_cmd_opcode { - MLX5_FPGA_IPSEC_CMD_OP_ADD_SA = 0, - MLX5_FPGA_IPSEC_CMD_OP_DEL_SA = 1, - MLX5_FPGA_IPSEC_CMD_OP_ADD_SA_V2 = 2, - MLX5_FPGA_IPSEC_CMD_OP_DEL_SA_V2 = 3, - MLX5_FPGA_IPSEC_CMD_OP_MOD_SA_V2 = 4, - MLX5_FPGA_IPSEC_CMD_OP_SET_CAP = 5, -}; - -enum mlx5_ifc_fpga_ipsec_cap { - MLX5_FPGA_IPSEC_CAP_NO_TRAILER = BIT(0), -}; - -struct mlx5_ifc_fpga_ipsec_cmd_cap { - __be32 cmd; - __be32 flags; - u8 reserved[24]; -} __packed; - -enum mlx5_ifc_fpga_ipsec_sa_flags { - MLX5_FPGA_IPSEC_SA_ESN_EN = BIT(0), - MLX5_FPGA_IPSEC_SA_ESN_OVERLAP = BIT(1), - MLX5_FPGA_IPSEC_SA_IPV6 = BIT(2), - MLX5_FPGA_IPSEC_SA_DIR_SX = BIT(3), - MLX5_FPGA_IPSEC_SA_SPI_EN = BIT(4), - MLX5_FPGA_IPSEC_SA_SA_VALID = BIT(5), - MLX5_FPGA_IPSEC_SA_IP_ESP = BIT(6), - MLX5_FPGA_IPSEC_SA_IP_AH = BIT(7), -}; - -enum mlx5_ifc_fpga_ipsec_sa_enc_mode { - MLX5_FPGA_IPSEC_SA_ENC_MODE_NONE = 0, - MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_128_AUTH_128 = 1, - MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_256_AUTH_128 = 3, -}; - -struct mlx5_ifc_fpga_ipsec_sa_v1 { - __be32 cmd; - u8 key_enc[32]; - u8 key_auth[32]; - __be32 sip[4]; - __be32 dip[4]; - union { - struct { - __be32 reserved; - u8 salt_iv[8]; - __be32 salt; - } __packed gcm; - struct { - u8 salt[16]; - } __packed cbc; - }; - __be32 spi; - __be32 sw_sa_handle; - __be16 tfclen; - u8 enc_mode; - u8 reserved1[2]; - u8 flags; - u8 reserved2[2]; -}; - -struct mlx5_ifc_fpga_ipsec_sa { - struct mlx5_ifc_fpga_ipsec_sa_v1 ipsec_sa_v1; - __be16 udp_sp; - __be16 udp_dp; - u8 reserved1[4]; - __be32 esn; - __be16 vid; /* only 12 bits, rest is reserved */ - __be16 reserved2; -} __packed; #endif /* MLX5_IFC_FPGA_H */ -- cgit v1.2.3 From de8bdb476908e64805df4bfbad20618cbb1f9ffa Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:42 +0300 Subject: RDMA/mlx5: Drop crypto flow steering API The mlx5 flow steering crypto API was intended to be used in FPGA devices, which is not supported for years already. The removal of mlx5 crypto FPGA code together with inability to configure encryption keys makes the low steering API completely unusable. So delete the code, so any ESP flow steering requests will fail with not supported error, as it is happening now anyway as no device support this type of API. Link: https://lore.kernel.org/r/634a5face7734381463d809bfb89850f6998deac.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/accel.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index dacf69516002..af67d51308cf 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -111,10 +111,6 @@ struct mlx5_accel_esp_xfrm { struct mlx5_accel_esp_xfrm_attrs attrs; }; -enum { - MLX5_ACCEL_XFRM_FLAG_REQUIRE_METADATA = 1UL << 0, -}; - enum mlx5_accel_ipsec_cap { MLX5_ACCEL_IPSEC_CAP_DEVICE = 1 << 0, MLX5_ACCEL_IPSEC_CAP_REQUIRED_METADATA = 1 << 1, @@ -132,8 +128,7 @@ u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev); struct mlx5_accel_esp_xfrm * mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, - const struct mlx5_accel_esp_xfrm_attrs *attrs, - u32 flags); + const struct mlx5_accel_esp_xfrm_attrs *attrs); void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm); int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, const struct mlx5_accel_esp_xfrm_attrs *attrs); @@ -144,8 +139,10 @@ static inline u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev) { ret static inline struct mlx5_accel_esp_xfrm * mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, - const struct mlx5_accel_esp_xfrm_attrs *attrs, - u32 flags) { return ERR_PTR(-EOPNOTSUPP); } + const struct mlx5_accel_esp_xfrm_attrs *attrs) +{ + return ERR_PTR(-EOPNOTSUPP); +} static inline void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm) {} static inline int -- cgit v1.2.3 From 32313c6ae622ed7aa553fa1ee22d8e5f24146f0e Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:43 +0300 Subject: RDMA/core: Delete IPsec flow action logic from the core The removal of mlx5 flow steering logic, left the kernel without any RDMA drivers that implements flow action callbacks supplied by RDMA/core. Any user access to them caused to EOPNOTSUPP error, which can be achieved by simply removing ioctl implementation. Link: https://lore.kernel.org/r/a638e376314a2eb1c66f597c0bbeeab2e5de7faf.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Acked-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky --- include/rdma/ib_verbs.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 69d883f7fb41..11ee4eaf84bd 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2497,15 +2497,7 @@ struct ib_device_ops { struct ib_flow_attr *flow_attr, struct ib_udata *udata); int (*destroy_flow)(struct ib_flow *flow_id); - struct ib_flow_action *(*create_flow_action_esp)( - struct ib_device *device, - const struct ib_flow_action_attrs_esp *attr, - struct uverbs_attr_bundle *attrs); int (*destroy_flow_action)(struct ib_flow_action *action); - int (*modify_flow_action_esp)( - struct ib_flow_action *action, - const struct ib_flow_action_attrs_esp *attr, - struct uverbs_attr_bundle *attrs); int (*set_vf_link_state)(struct ib_device *device, int vf, u32 port, int state); int (*get_vf_config)(struct ib_device *device, int vf, u32 port, -- cgit v1.2.3 From 2451da081a343e079d9f5a7b063fcdf0bc439aa8 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:46 +0300 Subject: net/mlx5: Unify device IPsec capabilities check Merge two different function to one in order to provide coherent picture if the device is IPsec capable or not. Link: https://lore.kernel.org/r/8f10ea06ad19c6f651e9fb33921009658f01e1d5.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/accel.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index af67d51308cf..9145e2d37c0e 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -124,7 +124,7 @@ enum mlx5_accel_ipsec_cap { #ifdef CONFIG_MLX5_ACCEL -u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev); +u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev); struct mlx5_accel_esp_xfrm * mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, @@ -135,7 +135,10 @@ int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, #else -static inline u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev) { return 0; } +static inline u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) +{ + return 0; +} static inline struct mlx5_accel_esp_xfrm * mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, -- cgit v1.2.3 From 54deb0e77561973f4ca4515e18ab972c281eea1d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:48 +0300 Subject: net/mlx5: Remove not-needed IPsec config In current code, the CONFIG_MLX5_IPSEC and CONFIG_MLX5_EN_IPSEC are the same. So remove useless indirection. Link: https://lore.kernel.org/r/fd14492cbc01a0d51a5bfedde02bcd2154123fde.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/accel.h | 4 ++-- include/linux/mlx5/driver.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 9145e2d37c0e..73e4d50a9f02 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -122,7 +122,7 @@ enum mlx5_accel_ipsec_cap { MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN = 1 << 7, }; -#ifdef CONFIG_MLX5_ACCEL +#ifdef CONFIG_MLX5_EN_IPSEC u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev); @@ -152,5 +152,5 @@ static inline int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; } -#endif /* CONFIG_MLX5_ACCEL */ +#endif /* CONFIG_MLX5_EN_IPSEC */ #endif /* __MLX5_ACCEL_H__ */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 9424503eb8d3..5af53c035949 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -778,7 +778,7 @@ struct mlx5_core_dev { #ifdef CONFIG_MLX5_FPGA struct mlx5_fpga_device *fpga; #endif -#ifdef CONFIG_MLX5_ACCEL +#ifdef CONFIG_MLX5_EN_IPSEC const struct mlx5_accel_ipsec_ops *ipsec_ops; #endif struct mlx5_clock clock; -- cgit v1.2.3 From f2b41b32cde8453a0a26875261f0e26809c2805a Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:51 +0300 Subject: net/mlx5: Remove ipsec_ops function table There is only one IPsec implementation and ipsec_ops is not needed at all in this situation. Together with removal of ipsec_ops, we can drop the entry checks as these functions are called for IPsec devices only. Link: https://lore.kernel.org/r/bc8dd1c8a77b65dbf5e2cf92c813ffaca2505c5f.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5af53c035949..ff47d49d8be4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -777,9 +777,6 @@ struct mlx5_core_dev { } roce; #ifdef CONFIG_MLX5_FPGA struct mlx5_fpga_device *fpga; -#endif -#ifdef CONFIG_MLX5_EN_IPSEC - const struct mlx5_accel_ipsec_ops *ipsec_ops; #endif struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; -- cgit v1.2.3 From 2984287c4c19949d7eb451dcad0bd5c54a2a376f Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:52 +0300 Subject: net/mlx5: Remove not-implemented IPsec capabilities Clean a capabilities enum to remove not-implemented bits. Link: https://lore.kernel.org/r/1044bb7b779107ff38e48e3f6553421104f3f819.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/accel.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 73e4d50a9f02..0f2596297f6a 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -113,13 +113,10 @@ struct mlx5_accel_esp_xfrm { enum mlx5_accel_ipsec_cap { MLX5_ACCEL_IPSEC_CAP_DEVICE = 1 << 0, - MLX5_ACCEL_IPSEC_CAP_REQUIRED_METADATA = 1 << 1, - MLX5_ACCEL_IPSEC_CAP_ESP = 1 << 2, - MLX5_ACCEL_IPSEC_CAP_IPV6 = 1 << 3, - MLX5_ACCEL_IPSEC_CAP_LSO = 1 << 4, - MLX5_ACCEL_IPSEC_CAP_RX_NO_TRAILER = 1 << 5, - MLX5_ACCEL_IPSEC_CAP_ESN = 1 << 6, - MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN = 1 << 7, + MLX5_ACCEL_IPSEC_CAP_ESP = 1 << 1, + MLX5_ACCEL_IPSEC_CAP_IPV6 = 1 << 2, + MLX5_ACCEL_IPSEC_CAP_LSO = 1 << 3, + MLX5_ACCEL_IPSEC_CAP_ESN = 1 << 4, }; #ifdef CONFIG_MLX5_EN_IPSEC -- cgit v1.2.3 From efaa0227f6c6a5073951b20cf2f8c63c4155306c Mon Sep 17 00:00:00 2001 From: tangmeng Date: Tue, 15 Feb 2022 14:50:19 +0800 Subject: timers: Move timer sysctl into the timer code This is part of the effort to reduce kernel/sysctl.c to only contain the core logic. Signed-off-by: tangmeng Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220215065019.7520-1-tangmeng@uniontech.com --- include/linux/timer.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index fda13c9d1256..648f00105f58 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -196,14 +196,6 @@ extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -struct ctl_table; - -extern unsigned int sysctl_timer_migration; -int timer_migration_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); unsigned long round_jiffies(unsigned long j); -- cgit v1.2.3 From a8b6d6708bb682108d8c899bc0cb7873240daf8a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:28 +0100 Subject: iio: core: Enhance the kernel doc of modes and currentmodes iio_dev entries Let's provide more details about these two variables because their understanding may not be straightforward for someone not used to the IIO subsystem internal logic. The different modes will soon be also be more documented for the same reason. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-2-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index faf00f2c0be6..f191b80466cd 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -488,8 +488,15 @@ struct iio_buffer_setup_ops { /** * struct iio_dev - industrial I/O device - * @modes: [DRIVER] operating modes supported by device - * @currentmode: [INTERN] current operating mode + * @modes: [DRIVER] bitmask listing all the operating modes + * supported by the IIO device. This list should be + * initialized before registering the IIO device. It can + * also be filed up by the IIO core, as a result of + * enabling particular features in the driver + * (see iio_triggered_event_setup()). + * @currentmode: [INTERN] operating mode currently in use, may be + * eventually checked by device drivers but should be + * considered read-only as this is a core internal bit * @dev: [DRIVER] device structure, should be assigned a parent * and owner * @buffer: [DRIVER] any buffer present -- cgit v1.2.3 From 474010127e2505fc463236470908e1ff5ddb3578 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:33 +0100 Subject: iio: st_sensors: Add a local lock for protecting odr Right now the (framework) mlock lock is (ab)used for multiple purposes: 1- protecting concurrent accesses over the odr local cache 2- avoid changing samplig frequency whilst buffer is running Let's start by handling situation #1 with a local lock. Suggested-by: Jonathan Cameron Cc: Denis Ciocca Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-7-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 22f67845cdd3..db4a1b260348 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -237,6 +237,7 @@ struct st_sensor_settings { * @hw_irq_trigger: if we're using the hardware interrupt on the sensor. * @hw_timestamp: Latest timestamp from the interrupt handler, when in use. * @buffer_data: Data used by buffer part. + * @odr_lock: Local lock for preventing concurrent ODR accesses/changes */ struct st_sensor_data { struct iio_trigger *trig; @@ -261,6 +262,8 @@ struct st_sensor_data { s64 hw_timestamp; char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned; + + struct mutex odr_lock; }; #ifdef CONFIG_IIO_BUFFER -- cgit v1.2.3 From 2f53b4adfede66f1bc1c8bb7efd7ced2bad1191a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:36 +0100 Subject: iio: Un-inline iio_buffer_enabled() As we are going to hide the currentmode inside the opaque structure, this helper would soon need to call a non-inline function which would simply drop the benefit of having the helper defined inline in a header. One alternative is to move this helper in the core as there is no more interest in defining it inline in a header. We will pay the minor cost either way. Let's do like the iio_device_id() helper which also refers to the opaque structure and gets defined in the core. Suggested-by: Jonathan Cameron Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-10-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index f191b80466cd..faabb852128a 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -550,6 +550,7 @@ struct iio_dev { }; int iio_device_id(struct iio_dev *indio_dev); +bool iio_buffer_enabled(struct iio_dev *indio_dev); const struct iio_chan_spec *iio_find_channel_from_si(struct iio_dev *indio_dev, int si); @@ -679,16 +680,6 @@ struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv); __printf(2, 3) struct iio_trigger *devm_iio_trigger_alloc(struct device *parent, const char *fmt, ...); -/** - * iio_buffer_enabled() - helper function to test if the buffer is enabled - * @indio_dev: IIO device structure for device - **/ -static inline bool iio_buffer_enabled(struct iio_dev *indio_dev) -{ - return indio_dev->currentmode - & (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE | - INDIO_BUFFER_SOFTWARE); -} /** * iio_get_debugfs_dentry() - helper function to get the debugfs_dentry -- cgit v1.2.3 From 8c576f87ad7eb639b8bd4472a9bb830e0696dda5 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:37 +0100 Subject: iio: core: Hide read accesses to iio_dev->currentmode In order to later move this variable within the opaque structure, let's create a helper for accessing it in read-only mode. This helper will be exposed to device drivers and kept accessible for the few that could need it. The write access to this variable however should be fully reserved to the core so in a second step we will hide this variable into the opaque structure. Cc: Eugen Hristev Cc: Nicolas Ferre Cc: Alexandre Belloni Cc: Ludovic Desroches Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-11-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index faabb852128a..31098ffa7dc9 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -550,6 +550,7 @@ struct iio_dev { }; int iio_device_id(struct iio_dev *indio_dev); +int iio_device_get_current_mode(struct iio_dev *indio_dev); bool iio_buffer_enabled(struct iio_dev *indio_dev); const struct iio_chan_spec -- cgit v1.2.3 From 51570c9d4b3a678f77a50ac139f67290e946ec86 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:38 +0100 Subject: iio: core: Move the currentmode entry to the opaque structure This entry should, under no situation, be modified by device drivers. Now that we have limited its read access to device drivers really needing it and did so through a dedicated helper, we can easily move this variable to the opaque structure in order to prevent any further modification from non-authorized code (out of the core, basically). Signed-off-by: Miquel Raynal Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20220207143840.707510-12-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-opaque.h | 4 ++++ include/linux/iio/iio.h | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 2be12b7b5dc5..6b3586b3f952 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -7,6 +7,9 @@ * struct iio_dev_opaque - industrial I/O device opaque information * @indio_dev: public industrial I/O device information * @id: used to identify device internally + * @currentmode: operating mode currently in use, may be eventually + * checked by device drivers but should be considered + * read-only as this is a core internal bit * @driver_module: used to make it harder to undercut users * @info_exist_lock: lock to prevent use during removal * @trig_readonly: mark the current trigger immutable @@ -36,6 +39,7 @@ */ struct iio_dev_opaque { struct iio_dev indio_dev; + int currentmode; int id; struct module *driver_module; struct mutex info_exist_lock; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 31098ffa7dc9..85cb924debd9 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -494,9 +494,6 @@ struct iio_buffer_setup_ops { * also be filed up by the IIO core, as a result of * enabling particular features in the driver * (see iio_triggered_event_setup()). - * @currentmode: [INTERN] operating mode currently in use, may be - * eventually checked by device drivers but should be - * considered read-only as this is a core internal bit * @dev: [DRIVER] device structure, should be assigned a parent * and owner * @buffer: [DRIVER] any buffer present @@ -523,7 +520,6 @@ struct iio_buffer_setup_ops { */ struct iio_dev { int modes; - int currentmode; struct device dev; struct iio_buffer *buffer; -- cgit v1.2.3 From f67c6c73cb07a4778425a2064640333ef7bfa42b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:39 +0100 Subject: iio: core: Simplify the registration of kfifo buffers Among all the users of the kfifo buffers, no one uses the INDIO_BUFFER_HARDWARE mode. So let's take this as a general rule and simplify a little bit the internals - overall the documentation - by eliminating unused specific cases. Use the INDIO_BUFFER_SOFTWARE mode by default with kfifo buffers, which will basically mimic what all the "non direct" modes do. Cc: Benson Leung Cc: Guenter Roeck Cc: Jyoti Bhayana Cc: Jean-Baptiste Maneyrol Cc: Lorenzo Bianconi Cc: Michael Hennerich Cc: Greg Kroah-Hartman Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-13-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/kfifo_buf.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/iio/kfifo_buf.h b/include/linux/iio/kfifo_buf.h index ccd2ceae7b25..8a83fb58232d 100644 --- a/include/linux/iio/kfifo_buf.h +++ b/include/linux/iio/kfifo_buf.h @@ -12,11 +12,10 @@ void iio_kfifo_free(struct iio_buffer *r); int devm_iio_kfifo_buffer_setup_ext(struct device *dev, struct iio_dev *indio_dev, - int mode_flags, const struct iio_buffer_setup_ops *setup_ops, const struct attribute **buffer_attrs); -#define devm_iio_kfifo_buffer_setup(dev, indio_dev, mode_flags, setup_ops) \ - devm_iio_kfifo_buffer_setup_ext((dev), (indio_dev), (mode_flags), (setup_ops), NULL) +#define devm_iio_kfifo_buffer_setup(dev, indio_dev, setup_ops) \ + devm_iio_kfifo_buffer_setup_ext((dev), (indio_dev), (setup_ops), NULL) #endif -- cgit v1.2.3 From 37943f047bfb88ba4dfc7a522563f57c86d088a0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 8 Apr 2022 11:31:27 -0700 Subject: tls: rx: simplify async wait Since we are protected from async completions by decrypt_compl_lock we can drop the async_notify and reinit the completion before we start waiting. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/tls.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index a01c264e5f15..6fe78361c8c8 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -152,7 +152,6 @@ struct tls_sw_context_rx { atomic_t decrypt_pending; /* protect crypto_wait with decrypt_pending*/ spinlock_t decrypt_compl_lock; - bool async_notify; }; struct tls_record_info { -- cgit v1.2.3 From 4f1a22ee7b576a38dc5705837c9b0de0c7b5b064 Mon Sep 17 00:00:00 2001 From: John Garry Date: Fri, 8 Apr 2022 17:04:12 +0800 Subject: libata: Improve ATA queued command allocation Improve ATA queued command allocation as follows: - For attaining a qc tag for a SAS host we need to allocate a bit in ata_port.sas_tag_allocated bitmap. However we already have a unique tag per device in range [0, ATA_MAX_QUEUE -1] in the scsi cmnd budget token, so just use that instead. - It is a bit pointless to have ata_qc_new_init() in libata-core.c since it pokes scsi internals, so inline it in ata_scsi_qc_new() (in libata-scsi.c). Also update Doc accordingly. - Use standard SCSI helpers set_host_byte() and set_status_byte() in ata_scsi_qc_new(). Christoph Hellwig originally contributed the change to inline ata_qc_new_init(). Signed-off-by: John Garry Reviewed-by: Christoph Hellwig Signed-off-by: Damien Le Moal --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 9b1d3d8b1252..16107122e587 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -820,7 +820,6 @@ struct ata_port { unsigned int cbl; /* cable type; ATA_CBL_xxx */ struct ata_queued_cmd qcmd[ATA_MAX_QUEUE + 1]; - unsigned long sas_tag_allocated; /* for sas tag allocation only */ u64 qc_active; int nr_active_links; /* #links with active qcs */ unsigned int sas_last_tag; /* track next tag hw expects */ -- cgit v1.2.3 From c1b8a56755ee121f9fa374de9eec36c91a7da25f Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 7 Apr 2022 14:20:49 +0800 Subject: net: sock: introduce sock_queue_rcv_skb_reason() In order to report the reasons of skb drops in 'sock_queue_rcv_skb()', introduce the function 'sock_queue_rcv_skb_reason()'. As the return value of 'sock_queue_rcv_skb()' is used as the error code, we can't make it as drop reason and have to pass extra output argument. 'sock_queue_rcv_skb()' is used in many places, so we can't change it directly. Introduce the new function 'sock_queue_rcv_skb_reason()' and make 'sock_queue_rcv_skb()' an inline call to it. Reviewed-by: Hao Peng Reviewed-by: Jiang Biao Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/sock.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index c4b91fc19b9c..1a988e605f09 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2392,7 +2392,14 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, void (*destructor)(struct sock *sk, struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); + +int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason *reason); + +static inline int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + return sock_queue_rcv_skb_reason(sk, skb, NULL); +} int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); struct sk_buff *sock_dequeue_err_skb(struct sock *sk); -- cgit v1.2.3 From 9f8ed577c28813410614b418bad42285840c1a00 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 7 Apr 2022 14:20:50 +0800 Subject: net: skb: rename SKB_DROP_REASON_PTYPE_ABSENT As David Ahern suggested, the reasons for skb drops should be more general and not be code based. Therefore, rename SKB_DROP_REASON_PTYPE_ABSENT to SKB_DROP_REASON_UNHANDLED_PROTO, which is used for the cases of no L3 protocol handler, no L4 protocol handler, version extensions, etc. From previous discussion, now we have the aim to make these reasons more abstract and users based, avoiding code based. Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 8 +++----- include/trace/events/skb.h | 2 +- 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2394441fa3dd..173bc35a10a3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -408,11 +408,9 @@ enum skb_drop_reason { */ SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */ - SKB_DROP_REASON_PTYPE_ABSENT, /* not packet_type found to handle - * the skb. For an etner packet, - * this means that L3 protocol is - * not supported - */ + SKB_DROP_REASON_UNHANDLED_PROTO, /* protocol not implemented + * or not supported + */ SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation * error */ diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index e1670e1e4934..85abd7cbd221 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -50,7 +50,7 @@ EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \ EM(SKB_DROP_REASON_XDP, XDP) \ EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS) \ - EM(SKB_DROP_REASON_PTYPE_ABSENT, PTYPE_ABSENT) \ + EM(SKB_DROP_REASON_UNHANDLED_PROTO, UNHANDLED_PROTO) \ EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM) \ EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \ EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT) \ -- cgit v1.2.3 From b384c95a861eebf47e88695cf6a29f34e0b10b0f Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 7 Apr 2022 14:20:52 +0800 Subject: net: icmp: add skb drop reasons to icmp protocol Replace kfree_skb() used in icmp_rcv() and icmpv6_rcv() with kfree_skb_reason(). In order to get the reasons of the skb drops after icmp message handle, we change the return type of 'handler()' in 'struct icmp_control' from 'bool' to 'enum skb_drop_reason'. This may change its original intention, as 'false' means failure, but 'SKB_NOT_DROPPED_YET' means success now. Therefore, all 'handler' and the call of them need to be handled. Following 'handler' functions are involved: icmp_unreach() icmp_redirect() icmp_echo() icmp_timestamp() icmp_discard() And following new drop reasons are added: SKB_DROP_REASON_ICMP_CSUM SKB_DROP_REASON_INVALID_PROTO The reason 'INVALID_PROTO' is introduced for the case that the packet doesn't follow rfc 1122 and is dropped. This is not a common case, and I believe we can locate the problem from the data in the packet. For now, this 'INVALID_PROTO' is used for the icmp broadcasts with wrong types. Maybe there should be a document file for these reasons. For example, list all the case that causes the 'UNHANDLED_PROTO' and 'INVALID_PROTO' drop reason. Therefore, users can locate their problems according to the document. Reviewed-by: Hao Peng Reviewed-by: Jiang Biao Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ include/net/ping.h | 2 +- include/trace/events/skb.h | 2 ++ 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 173bc35a10a3..9b81ba497665 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -442,6 +442,11 @@ enum skb_drop_reason { SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented * at tun/tap, e.g., check_filter() */ + SKB_DROP_REASON_ICMP_CSUM, /* ICMP checksum error */ + SKB_DROP_REASON_INVALID_PROTO, /* the packet doesn't follow RFC + * 2211, such as a broadcasts + * ICMP_TIMESTAMP + */ SKB_DROP_REASON_MAX, }; diff --git a/include/net/ping.h b/include/net/ping.h index 2fe78874318c..b68fbfdb606f 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -76,7 +76,7 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, void *user_icmph, size_t icmph_len); int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -bool ping_rcv(struct sk_buff *skb); +enum skb_drop_reason ping_rcv(struct sk_buff *skb); #ifdef CONFIG_PROC_FS void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family); diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 85abd7cbd221..42647114fffe 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -61,6 +61,8 @@ EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC) \ EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER) \ EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ + EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \ + EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 2e2ac4a3327479f7e2744cdd88a5c823f2057bad Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Wed, 6 Apr 2022 22:15:20 +0200 Subject: tty: goldfish: Introduce gf_ioread32()/gf_iowrite32() The goldfish TTY device was clearly defined as having little-endian registers, but the switch to __raw_{read,write}l(() broke its driver when running on big-endian kernels (if anyone ever tried this). The m68k qemu implementation got this wrong, and assumed native-endian registers. While this is a bug in qemu, it is probably impossible to fix that since there is no way of knowing which other operating systems have started relying on that bug over the years. Hence revert commit da31de35cd2f ("tty: goldfish: use __raw_writel()/__raw_readl()", and define gf_ioread32()/gf_iowrite32() to be able to use accessors defined by the architecture. Cc: stable@vger.kernel.org # v5.11+ Fixes: da31de35cd2fb78f ("tty: goldfish: use __raw_writel()/__raw_readl()") Signed-off-by: Laurent Vivier Link: https://lore.kernel.org/r/20220406201523.243733-2-laurent@vivier.eu [geert: Add rationale based on Arnd's comments] Signed-off-by: Geert Uytterhoeven --- include/linux/goldfish.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/goldfish.h b/include/linux/goldfish.h index 12be1601fd84..bcc17f95b906 100644 --- a/include/linux/goldfish.h +++ b/include/linux/goldfish.h @@ -8,14 +8,21 @@ /* Helpers for Goldfish virtual platform */ +#ifndef gf_ioread32 +#define gf_ioread32 ioread32 +#endif +#ifndef gf_iowrite32 +#define gf_iowrite32 iowrite32 +#endif + static inline void gf_write_ptr(const void *ptr, void __iomem *portl, void __iomem *porth) { const unsigned long addr = (unsigned long)ptr; - __raw_writel(lower_32_bits(addr), portl); + gf_iowrite32(lower_32_bits(addr), portl); #ifdef CONFIG_64BIT - __raw_writel(upper_32_bits(addr), porth); + gf_iowrite32(upper_32_bits(addr), porth); #endif } @@ -23,9 +30,9 @@ static inline void gf_write_dma_addr(const dma_addr_t addr, void __iomem *portl, void __iomem *porth) { - __raw_writel(lower_32_bits(addr), portl); + gf_iowrite32(lower_32_bits(addr), portl); #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT - __raw_writel(upper_32_bits(addr), porth); + gf_iowrite32(upper_32_bits(addr), porth); #endif } -- cgit v1.2.3 From c92e7ef16400bf035e8b49c7dd091bfce4f99773 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Wed, 6 Apr 2022 22:15:22 +0200 Subject: clocksource/drivers: Add a goldfish-timer clocksource Add a clocksource based on the goldfish-rtc device. Move the timer register definition to This kernel implementation is based on the QEMU upstream implementation: https://git.qemu.org/?p=qemu.git;a=blob_plain;f=hw/rtc/goldfish_rtc.c goldfish-timer is a high-precision signed 64-bit nanosecond timer. It is part of the 'goldfish' virtual hardware platform used to run some emulated Android systems under QEMU. This timer only supports oneshot event. Signed-off-by: Laurent Vivier Acked-by: Daniel Lezcano Link: https://lore.kernel.org/r/20220406201523.243733-4-laurent@vivier.eu Signed-off-by: Geert Uytterhoeven --- include/clocksource/timer-goldfish.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/clocksource/timer-goldfish.h (limited to 'include') diff --git a/include/clocksource/timer-goldfish.h b/include/clocksource/timer-goldfish.h new file mode 100644 index 000000000000..05a3a4f610d6 --- /dev/null +++ b/include/clocksource/timer-goldfish.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * goldfish-timer clocksource + * Registers definition for the goldfish-timer device + */ + +#ifndef _CLOCKSOURCE_TIMER_GOLDFISH_H +#define _CLOCKSOURCE_TIMER_GOLDFISH_H + +/* + * TIMER_TIME_LOW get low bits of current time and update TIMER_TIME_HIGH + * TIMER_TIME_HIGH get high bits of time at last TIMER_TIME_LOW read + * TIMER_ALARM_LOW set low bits of alarm and activate it + * TIMER_ALARM_HIGH set high bits of next alarm + * TIMER_IRQ_ENABLED enable alarm interrupt + * TIMER_CLEAR_ALARM disarm an existing alarm + * TIMER_ALARM_STATUS alarm status (running or not) + * TIMER_CLEAR_INTERRUPT clear interrupt + */ +#define TIMER_TIME_LOW 0x00 +#define TIMER_TIME_HIGH 0x04 +#define TIMER_ALARM_LOW 0x08 +#define TIMER_ALARM_HIGH 0x0c +#define TIMER_IRQ_ENABLED 0x10 +#define TIMER_CLEAR_ALARM 0x14 +#define TIMER_ALARM_STATUS 0x18 +#define TIMER_CLEAR_INTERRUPT 0x1c + +extern int goldfish_timer_init(int irq, void __iomem *base); + +#endif /* _CLOCKSOURCE_TIMER_GOLDFISH_H */ -- cgit v1.2.3 From e5c95ca094cfe59a4013d711f87ff034cba30f80 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Mon, 4 Apr 2022 23:01:08 +0200 Subject: mac80211: Improve confusing comment around tx_info clearing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The comment above the ieee80211_tx_info_clear_status() helper was somewhat confusing as to which fields it was or wasn't clearing. So replace it by something that is hopefully more, well, clear. Signed-off-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20220404210108.2684907-1-toke@toke.dk Signed-off-by: Johannes Berg --- include/net/mac80211.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 382ebb862ea8..db992f71604d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1201,9 +1201,9 @@ static inline struct ieee80211_rx_status *IEEE80211_SKB_RXCB(struct sk_buff *skb * in the TX status but the rate control information (it does clear * the count since you need to fill that in anyway). * - * NOTE: You can only use this function if you do NOT use - * info->driver_data! Use info->rate_driver_data - * instead if you need only the less space that allows. + * NOTE: While the rates array is kept intact, this will wipe all of the + * driver_data fields in info, so it's up to the driver to restore + * any fields it needs after calling this helper. */ static inline void ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) -- cgit v1.2.3 From 6d945a33f2b0aa24fc210dadaa0af3e8218e7002 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 25 Mar 2022 11:42:41 +0100 Subject: mac80211: introduce BSS color collision detection Add ieee80211_rx_check_bss_color_collision routine in order to introduce BSS color collision detection in mac80211 if it is not supported in HW/FW (e.g. for mt7915 chipset). Add IEEE80211_HW_DETECTS_COLOR_COLLISION flag to let the driver notify BSS color collision detection is supported in HW/FW. Set this for ath11k which apparently didn't need this code. Tested-by: Peter Chiu Co-developed-by: Ryder Lee Signed-off-by: Ryder Lee Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/a05eeeb1841a84560dc5aaec77894fcb69a54f27.1648204871.git.lorenzo@kernel.org [clarify commit message a bit, move flag to mac80211] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index db992f71604d..0943b2626f4d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2434,6 +2434,9 @@ struct ieee80211_txq { * usage and 802.11 frames with %RX_FLAG_ONLY_MONITOR set for monitor to * the stack. * + * @IEEE80211_HW_DETECTS_COLOR_COLLISION: HW/driver has support for BSS color + * collision detection and doesn't need it in software. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2489,6 +2492,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD, IEEE80211_HW_SUPPORTS_RX_DECAP_OFFLOAD, IEEE80211_HW_SUPPORTS_CONC_MON_RX_DECAP, + IEEE80211_HW_DETECTS_COLOR_COLLISION, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS -- cgit v1.2.3 From 2d7991fe867974a8e5065ee9691451a406b9320d Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 11 Mar 2022 16:23:22 -0700 Subject: dmaengine: idxd: update IAA definitions for user header Add additional structure definitions for Intel In-memory Analytics Accelerator (IAA/IAX). See specification (1) for more details. 1: https://cdrdv2.intel.com/v1/dl/getContent/721858 Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/164704100212.1373038.18362680016033557757.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index a8f0ff75c430..bce7c43657d5 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -53,6 +53,11 @@ enum idxd_scmd_stat { /* IAX */ #define IDXD_OP_FLAG_RD_SRC2_AECS 0x010000 +#define IDXD_OP_FLAG_RD_SRC2_2ND 0x020000 +#define IDXD_OP_FLAG_WR_SRC2_AECS_COMP 0x040000 +#define IDXD_OP_FLAG_WR_SRC2_AECS_OVFL 0x080000 +#define IDXD_OP_FLAG_SRC2_STS 0x100000 +#define IDXD_OP_FLAG_CRC_RFC3720 0x200000 /* Opcode */ enum dsa_opcode { @@ -81,6 +86,18 @@ enum iax_opcode { IAX_OPCODE_MEMMOVE, IAX_OPCODE_DECOMPRESS = 0x42, IAX_OPCODE_COMPRESS, + IAX_OPCODE_CRC64, + IAX_OPCODE_ZERO_DECOMP_32 = 0x48, + IAX_OPCODE_ZERO_DECOMP_16, + IAX_OPCODE_DECOMP_32 = 0x4c, + IAX_OPCODE_DECOMP_16, + IAX_OPCODE_SCAN = 0x50, + IAX_OPCODE_SET_MEMBER, + IAX_OPCODE_EXTRACT, + IAX_OPCODE_SELECT, + IAX_OPCODE_RLE_BURST, + IAX_OPCDE_FIND_UNIQUE, + IAX_OPCODE_EXPAND, }; /* Completion record status */ @@ -120,6 +137,7 @@ enum iax_completion_status { IAX_COMP_NONE = 0, IAX_COMP_SUCCESS, IAX_COMP_PAGE_FAULT_IR = 0x04, + IAX_COMP_ANALYTICS_ERROR = 0x0a, IAX_COMP_OUTBUF_OVERFLOW, IAX_COMP_BAD_OPCODE = 0x10, IAX_COMP_INVALID_FLAGS, @@ -140,7 +158,10 @@ enum iax_completion_status { IAX_COMP_WATCHDOG, IAX_COMP_INVALID_COMP_FLAG = 0x30, IAX_COMP_INVALID_FILTER_FLAG, - IAX_COMP_INVALID_NUM_ELEMS = 0x33, + IAX_COMP_INVALID_INPUT_SIZE, + IAX_COMP_INVALID_NUM_ELEMS, + IAX_COMP_INVALID_SRC1_WIDTH, + IAX_COMP_INVALID_INVERT_OUT, }; #define DSA_COMP_STATUS_MASK 0x7f @@ -319,8 +340,12 @@ struct iax_completion_record { uint32_t output_size; uint8_t output_bits; uint8_t rsvd3; - uint16_t rsvd4; - uint64_t rsvd5[4]; + uint16_t xor_csum; + uint32_t crc; + uint32_t min; + uint32_t max; + uint32_t sum; + uint64_t rsvd4[2]; } __attribute__((packed)); struct iax_raw_completion_record { -- cgit v1.2.3 From 52126d4c03798cc55aa927fea4c776ab26b5a5f0 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 6 Feb 2022 10:47:45 +0100 Subject: dmaengine: Remove a useless mutex According to lib/idr.c, The IDA handles its own locking. It is safe to call any of the IDA functions without synchronisation in your code. so the 'chan_mutex' mutex can just be removed. It is here only to protect some ida_alloc()/ida_free() calls. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/7180452c1d77b039e27b6f9418e0e7d9dd33c431.1644140845.git.christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 842d4f7ca752..6db9e03afd0b 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -870,7 +870,6 @@ struct dma_device { struct device *dev; struct module *owner; struct ida chan_ida; - struct mutex chan_mutex; /* to protect chan_ida */ u32 src_addr_widths; u32 dst_addr_widths; -- cgit v1.2.3 From 046d2e7c50e3087a32a85fd384c21f896dbccf83 Mon Sep 17 00:00:00 2001 From: Sriram R Date: Mon, 4 Apr 2022 21:11:23 +0530 Subject: mac80211: prepare sta handling for MLO support Currently in mac80211 each STA object is represented using sta_info datastructure with the associated STA specific information and drivers access ieee80211_sta part of it. With MLO (Multi Link Operation) support being added in 802.11be standard, though the association is logically with a single Multi Link capable STA, at the physical level communication can happen via different advertised links (uniquely identified by Channel, operating class, BSSID) and hence the need to handle multiple link STA parameters within a composite sta_info object called the MLD STA. The different link STA part of MLD STA are identified using the link address which can be same or different as the MLD STA address and unique link id based on the link vif. To support extension of such a model, the sta_info datastructure is modified to hold multiple link STA objects with link specific params currently within sta_info moved to this new structure. Similarly this is done for ieee80211_sta as well which will be accessed within mac80211 as well as by drivers, hence trivial driver changes are expected to support this. For current non MLO supported drivers, only one link STA is present and link information is accessed via 'deflink' member. For MLO drivers, we still need to define the APIs etc. to get the correct link ID and access the correct part of the station info. Currently in mac80211, all link STA info are accessed directly via deflink. These will be updated to access via link pointers indexed by link id with MLO support patches, with link id being 0 for non MLO supported cases. Except for couple of macro related changes, below spatch takes care of updating mac80211 and driver code to access to the link STA info via deflink. @ieee80211_sta@ struct ieee80211_sta *s; struct sta_info *si; identifier var = {supp_rates, ht_cap, vht_cap, he_cap, he_6ghz_capa, eht_cap, rx_nss, bandwidth, txpwr}; @@ ( s-> - var + deflink.var | si->sta. - var + deflink.var ) @sta_info@ struct sta_info *si; identifier var = {gtk, pcpu_rx_stats, rx_stats, rx_stats_avg, status_stats, tx_stats, cur_max_bandwidth}; @@ ( si-> - var + deflink.var ) Signed-off-by: Sriram R Link: https://lore.kernel.org/r/1649086883-13246-1-git-send-email-quic_srirrama@quicinc.com [remove MLO-drivers notes from commit message, not clear yet; run spatch] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 80 ++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 58 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 0943b2626f4d..75880fc70700 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2056,6 +2056,45 @@ struct ieee80211_sta_txpwr { enum nl80211_tx_power_setting type; }; +#define MAX_STA_LINKS 15 + +/** + * struct ieee80211_link_sta - station Link specific info + * All link specific info for a STA link for a non MLD STA(single) + * or a MLD STA(multiple entries) are stored here. + * + * @addr: MAC address of the Link STA. For non-MLO STA this is same as the addr + * in ieee80211_sta. For MLO Link STA this addr can be same or different + * from addr in ieee80211_sta (representing MLD STA addr) + * @supp_rates: Bitmap of supported rates + * @ht_cap: HT capabilities of this STA; restricted to our own capabilities + * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities + * @he_cap: HE capabilities of this STA + * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities + * @eht_cap: EHT capabilities of this STA + * @bandwidth: current bandwidth the station can receive with + * @rx_nss: in HT/VHT, the maximum number of spatial streams the + * station can receive at the moment, changed by operating mode + * notifications and capabilities. The value is only valid after + * the station moves to associated state. + * @txpwr: the station tx power configuration + * + */ +struct ieee80211_link_sta { + u8 addr[ETH_ALEN]; + + u32 supp_rates[NUM_NL80211_BANDS]; + struct ieee80211_sta_ht_cap ht_cap; + struct ieee80211_sta_vht_cap vht_cap; + struct ieee80211_sta_he_cap he_cap; + struct ieee80211_he_6ghz_capa he_6ghz_capa; + struct ieee80211_sta_eht_cap eht_cap; + + u8 rx_nss; + enum ieee80211_sta_rx_bandwidth bandwidth; + struct ieee80211_sta_txpwr txpwr; +}; + /** * struct ieee80211_sta - station table entry * @@ -2065,15 +2104,11 @@ struct ieee80211_sta_txpwr { * either be protected by rcu_read_lock() explicitly or implicitly, * or you must take good care to not use such a pointer after a * call to your sta_remove callback that removed it. + * This also represents the MLD STA in case of MLO association + * and holds pointers to various link STA's * * @addr: MAC address * @aid: AID we assigned to the station if we're an AP - * @supp_rates: Bitmap of supported rates (per band) - * @ht_cap: HT capabilities of this STA; restricted to our own capabilities - * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities - * @he_cap: HE capabilities of this STA - * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities - * @eht_cap: EHT capabilities of this STA * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU * that this station is allowed to transmit to us. * Can be modified by driver. @@ -2085,11 +2120,6 @@ struct ieee80211_sta_txpwr { * if wme is supported. The bits order is like in * IEEE80211_WMM_IE_STA_QOSINFO_AC_*. * @max_sp: max Service Period. Only valid if wme is supported. - * @bandwidth: current bandwidth the station can receive with - * @rx_nss: in HT/VHT, the maximum number of spatial streams the - * station can receive at the moment, changed by operating mode - * notifications and capabilities. The value is only valid after - * the station moves to associated state. * @smps_mode: current SMPS mode (off, static or dynamic) * @rates: rate control selection table * @tdls: indicates whether the STA is a TDLS peer @@ -2102,25 +2132,28 @@ struct ieee80211_sta_txpwr { * @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not. * @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control. * @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID - * @txpwr: the station tx power configuration * @txq: per-TID data TX queues (if driver uses the TXQ abstraction); note that * the last entry (%IEEE80211_NUM_TIDS) is used for non-data frames + * @multi_link_sta: Identifies if this sta is a MLD STA + * @deflink: This holds the default link STA information, for non MLO STA all link + * specific STA information is accessed through @deflink or through + * link[0] which points to address of @deflink. For MLO Link STA + * the first added link STA will point to deflink. + * @link: reference to Link Sta entries. For Non MLO STA, except 1st link, + * i.e link[0] all links would be assigned to NULL by default and + * would access link information via @deflink or link[0]. For MLO + * STA, first link STA being added will point its link pointer to + * @deflink address and remaining would be allocated and the address + * would be assigned to link[link_id] where link_id is the id assigned + * by the AP. */ struct ieee80211_sta { - u32 supp_rates[NUM_NL80211_BANDS]; u8 addr[ETH_ALEN]; u16 aid; - struct ieee80211_sta_ht_cap ht_cap; - struct ieee80211_sta_vht_cap vht_cap; - struct ieee80211_sta_he_cap he_cap; - struct ieee80211_he_6ghz_capa he_6ghz_capa; - struct ieee80211_sta_eht_cap eht_cap; u16 max_rx_aggregation_subframes; bool wme; u8 uapsd_queues; u8 max_sp; - u8 rx_nss; - enum ieee80211_sta_rx_bandwidth bandwidth; enum ieee80211_smps_mode smps_mode; struct ieee80211_sta_rates __rcu *rates; bool tdls; @@ -2147,10 +2180,13 @@ struct ieee80211_sta { bool support_p2p_ps; u16 max_rc_amsdu_len; u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS]; - struct ieee80211_sta_txpwr txpwr; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; + bool multi_link_sta; + struct ieee80211_link_sta deflink; + struct ieee80211_link_sta *link[MAX_STA_LINKS]; + /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; @@ -6371,7 +6407,7 @@ static inline int rate_supported(struct ieee80211_sta *sta, enum nl80211_band band, int index) { - return (sta == NULL || sta->supp_rates[band] & BIT(index)); + return (sta == NULL || sta->deflink.supp_rates[band] & BIT(index)); } static inline s8 -- cgit v1.2.3 From 95ebe80d99de3cb849c522a1f768e5e8befa0b7c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 20 Jan 2022 13:16:18 -0800 Subject: srcu: Fix s/is/if/ typo in srcu_node comment This commit fixed a typo in the srcu_node structure's ->srcu_have_cbs comment. While in the area, redo a couple of comments to take advantage of 100-character line lengths. Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index cb1f4351e8ba..4025840ba9a3 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -47,11 +47,9 @@ struct srcu_data { */ struct srcu_node { spinlock_t __private lock; - unsigned long srcu_have_cbs[4]; /* GP seq for children */ - /* having CBs, but only */ - /* is > ->srcu_gq_seq. */ - unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs */ - /* have CBs for given GP? */ + unsigned long srcu_have_cbs[4]; /* GP seq for children having CBs, but only */ + /* if greater than ->srcu_gq_seq. */ + unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs have CBs for given GP? */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ struct srcu_node *srcu_parent; /* Next up in tree. */ int grplo; /* Least CPU for node. */ -- cgit v1.2.3 From 994f706872e6ce080506bd795ecf783d5b617de6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 24 Jan 2022 09:46:57 -0800 Subject: srcu: Make Tree SRCU able to operate without snp_node array This commit makes Tree SRCU able to operate without an snp_node array, that is, when the srcu_data structures' ->mynode pointers are NULL. This can result in high contention on the srcu_struct structure's ->lock, but only when there are lots of call_srcu(), synchronize_srcu(), and synchronize_srcu_expedited() calls. Note that when there is no snp_node array, all SRCU callbacks use CPU 0's callback queue. This is optimal in the common case of low update-side load because it removes the need to search each CPU for the single callback that made the grace period happen. Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 4025840ba9a3..8d1da136a93a 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -63,8 +63,9 @@ struct srcu_struct { struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ + int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t __private lock; /* Protect counters */ + spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ @@ -83,6 +84,17 @@ struct srcu_struct { struct lockdep_map dep_map; }; +/* Values for size state variable (->srcu_size_state). */ +#define SRCU_SIZE_SMALL 0 +#define SRCU_SIZE_ALLOC 1 +#define SRCU_SIZE_WAIT_BARRIER 2 +#define SRCU_SIZE_WAIT_CALL 3 +#define SRCU_SIZE_WAIT_CBS1 4 +#define SRCU_SIZE_WAIT_CBS2 5 +#define SRCU_SIZE_WAIT_CBS3 6 +#define SRCU_SIZE_WAIT_CBS4 7 +#define SRCU_SIZE_BIG 8 + /* Values for state variable (bottom bits of ->srcu_gp_seq). */ #define SRCU_STATE_IDLE 0 #define SRCU_STATE_SCAN1 1 -- cgit v1.2.3 From 2ec303113d978931ef368886c4c6bc854493e8bf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Jan 2022 16:13:52 -0800 Subject: srcu: Dynamically allocate srcu_node array This commit shrinks the srcu_struct structure by converting its ->node field from a fixed-size compile-time array to a pointer to a dynamically allocated array. In kernels built with large values of NR_CPUS that boot on systems with smaller numbers of CPUs, this can save significant memory. [ paulmck: Apply kernel test robot feedback. ] Reported-by: A cast of thousands Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 8d1da136a93a..8501b6b45941 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -60,7 +60,7 @@ struct srcu_node { * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ + struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ int srcu_size_state; /* Small-to-big transition state. */ -- cgit v1.2.3 From db8f1471c61336477e2bf74dcb00e67d650e6dea Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 26 Jan 2022 10:03:54 -0500 Subject: srcu: Use export for srcu_struct defined by DEFINE_STATIC_SRCU() If an srcu_struct structure defined by tree SRCU's DEFINE_STATIC_SRCU() is used by a module, sparse will give the following diagnostic: sparse: symbol '__srcu_struct_nodes_srcu' was not declared. Should it be static? The problem is that a within-module DEFINE_STATIC_SRCU() must define a non-static srcu_struct because it is exported by referencing it in a special '__section("___srcu_struct_ptrs")'. This reference is needed so that module load and unloading can invoke init_srcu_struct() and cleanup_srcu_struct(), respectively. Unfortunately, sparse is unaware of '__section("___srcu_struct_ptrs")', resulting in the above false-positive diagnostic. To avoid this false positive, this commit therefore creates a prototype of the srcu_struct with an "extern" keyword. Signed-off-by: Alexander Aring Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 8501b6b45941..44e998643f48 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -131,6 +131,7 @@ struct srcu_struct { #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ is_static struct srcu_struct name; \ + extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else -- cgit v1.2.3 From 46470cf85d2b61abd37c6f66c4dacc1bc510d10f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 Jan 2022 13:20:49 -0800 Subject: srcu: Prevent cleanup_srcu_struct() from freeing non-dynamic ->sda When an srcu_struct structure is created (but not in a kernel module) by DEFINE_SRCU() and friends, the per-CPU srcu_data structure is statically allocated. In all other cases, that structure is obtained from alloc_percpu(), in which case cleanup_srcu_struct() must invoke free_percpu() on the resulting ->sda pointer in the srcu_struct pointer. Which it does. Except that it also invokes free_percpu() on the ->sda pointer referencing the statically allocated per-CPU srcu_data structures. Which free_percpu() is surprisingly OK with. This commit nevertheless stops cleanup_srcu_struct() from freeing statically allocated per-CPU srcu_data structures. Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 44e998643f48..44bd204498a1 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -73,6 +73,7 @@ struct srcu_struct { unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ + bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ struct completion srcu_barrier_completion; -- cgit v1.2.3 From 9f2e91d94c91558e3764fe4e01c5e6281a90f239 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 Jan 2022 20:32:05 -0800 Subject: srcu: Add contention-triggered addition of srcu_node tree This commit instruments the acquisitions of the srcu_struct structure's ->lock, enabling the initiation of a transition from SRCU_SIZE_SMALL to SRCU_SIZE_BIG when sufficient contention is experienced. The instrumentation counts the number of trylock failures within the confines of a single jiffy. If that number exceeds the value specified by the srcutree.small_contention_lim kernel boot parameter (which defaults to 100), and if the value specified by the srcutree.convert_to_big kernel boot parameter has the 0x10 bit set (defaults to 0), then a transition will be automatically initiated. By default, there will never be any transitions, so that none of the srcu_struct structures ever gains an srcu_node array. The useful values for srcutree.convert_to_big are: 0x00: Never convert. 0x01: Always convert at init_srcu_struct() time. 0x02: Convert when rcutorture prints its first round of statistics. 0x03: Decide conversion approach at boot given system size. 0x10: Convert if contention is encountered. 0x12: Convert if contention is encountered or when rcutorture prints its first round of statistics, whichever comes first. The value 0x11 acts the same as 0x01 because the conversion happens before there is any chance of contention. [ paulmck: Apply "static" feedback from kernel test robot. ] Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 44bd204498a1..1b9ff4ed37e4 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -72,6 +72,8 @@ struct srcu_struct { unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ + unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ + unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ -- cgit v1.2.3 From 5d90070816534882b9158f14154b7e2cdef1194a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 4 Mar 2022 10:41:44 -0800 Subject: rcu-tasks: Make Tasks RCU account for userspace execution The main Tasks RCU quiescent state is voluntary context switch. However, userspace execution is also a valid quiescent state, and is a valuable one for userspace applications that spin repeatedly executing light-weight non-sleeping system calls. Currently, such an application can delay a Tasks RCU grace period for many tens of seconds. This commit therefore enlists the aid of the scheduler-clock interrupt to provide a Tasks RCU quiescent state when it interrupted a task executing in userspace. [ paulmck: Apply feedback from kernel test robot. ] Cc: Martin KaFai Lau Cc: Neil Spring Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e7c39c200e2b..1a32036c918c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -196,6 +196,7 @@ void synchronize_rcu_tasks_rude(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ +#define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu -- cgit v1.2.3 From bd6c375b92c3f367e184d164e12952e4b9d9fb4f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 15 Mar 2022 16:33:38 +0100 Subject: rcutorture: Call preempt_schedule() through static call/key The rcutorture test suite sometimess triggers a random scheduler preemption call while simulating a read delay. Unfortunately, its direct call to preempt_schedule() bypasses the static call/key filter used by CONFIG_PREEMPT_DYNAMIC. This breaks the no-preempt assumption when the dynamic preemption mode is "none". For example, rcu_blocking_is_gp() is fooled and abbreviates grace periods when the CPU runs in no-preempt UP mode. Fix this by making torture_preempt_schedule() call __preempt_schedule(), which uses the static call/key. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/torture.h b/include/linux/torture.h index 63fa4196e51c..7038104463e4 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -118,7 +118,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); _torture_stop_kthread("Stopping " #n " task", &(tp)) #ifdef CONFIG_PREEMPTION -#define torture_preempt_schedule() preempt_schedule() +#define torture_preempt_schedule() __preempt_schedule() #else #define torture_preempt_schedule() do { } while (0) #endif -- cgit v1.2.3 From a28c1ab312712c26a8d004af1f68628d625dafac Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Sat, 9 Apr 2022 22:13:56 +0300 Subject: ata: libata-core: fix parameter type in ata_xfer_mode2shift() The data transfer mode that corresponds to the 'xfer_mode' parameter for ata_xfer_mode2shift() is a 8-bit *unsigned* value. Using *unsigned long* to declare the parameter leads to a problematic implicit *int* to *unsigned long* cast and was most probably a result of a copy/paste mistake -- use the 'u8' type instead, as in ata_xfer_mode2mask()... Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Signed-off-by: Sergey Shtylyov Signed-off-by: Damien Le Moal --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 16107122e587..732de9014626 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1110,7 +1110,7 @@ extern void ata_unpack_xfermask(unsigned long xfer_mask, unsigned long *udma_mask); extern u8 ata_xfer_mask2mode(unsigned long xfer_mask); extern unsigned long ata_xfer_mode2mask(u8 xfer_mode); -extern int ata_xfer_mode2shift(unsigned long xfer_mode); +extern int ata_xfer_mode2shift(u8 xfer_mode); extern const char *ata_mode_string(unsigned long xfer_mask); extern unsigned long ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); -- cgit v1.2.3 From 888ade8f90d7dbbdc8552ae9b23d311f9e61ab0e Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 8 Apr 2022 22:08:37 +0200 Subject: ipv4: Use dscp_t in struct fib_rt_info Use the new dscp_t type to replace the tos field of struct fib_rt_info. This ensures ECN bits are ignored and makes it compatible with the fa_dscp field of struct fib_alias. This also allows sparse to flag potential incorrect uses of DSCP and ECN bits. Signed-off-by: Guillaume Nault Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/ip_fib.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 6a82bcb8813b..f08ba531ac08 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -212,7 +212,7 @@ struct fib_rt_info { u32 tb_id; __be32 dst; int dst_len; - u8 tos; + dscp_t dscp; u8 type; u8 offload:1, trap:1, -- cgit v1.2.3 From 568a3f33b4273833f1b1e4a39d4a3410c4770c32 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 8 Apr 2022 22:08:40 +0200 Subject: ipv4: Use dscp_t in struct fib_entry_notifier_info Use the new dscp_t type to replace the tos field of struct fib_entry_notifier_info. This ensures ECN bits are ignored and makes it compatible with the dscp field of struct fib_rt_info. This also allows sparse to flag potential incorrect uses of DSCP and ECN bits. Signed-off-by: Guillaume Nault Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/ip_fib.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index f08ba531ac08..a378eff827c7 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -225,7 +225,7 @@ struct fib_entry_notifier_info { u32 dst; int dst_len; struct fib_info *fi; - u8 tos; + dscp_t dscp; u8 type; u32 tb_id; }; -- cgit v1.2.3 From b33115bd05afda6fe16fdd142779a9ff95d63317 Mon Sep 17 00:00:00 2001 From: Mohan Kumar Date: Mon, 11 Apr 2022 13:02:09 +0530 Subject: ALSA: hda: Jack detection poll in suspend state HDA Jack detection logic doesn't work when the HDACODEC in runtime suspended state as unsol event won't be triggered during D3 state. As pulseaudio server in userspace rely on the jack mixer control status to show the audio devices in gui and any display sink device hotplug event during D3 state will never updates the jack status which will result in no audio device option available in userspace settings. The possible option available to resolve this issue is to run Jack polling worker thread even after codec suspend state. The choice can be made based on compromise between power saving or Jack detection in suspend state. Signed-off-by: Mohan Kumar Link: https://lore.kernel.org/r/20220411073210.23445-2-mkumard@nvidia.com Signed-off-by: Takashi Iwai --- include/sound/hda_codec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index 77426ff58338..b7be300b6b18 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -59,6 +59,9 @@ struct hda_bus { unsigned int no_response_fallback:1; /* don't fallback at RIRB error */ unsigned int bus_probing :1; /* during probing process */ unsigned int keep_power:1; /* keep power up for notification */ + unsigned int jackpoll_in_suspend:1; /* keep jack polling during + * runtime suspend + */ int primary_dig_out_type; /* primary digital out PCM type */ unsigned int mixer_assigned; /* codec addr for mixer name */ -- cgit v1.2.3 From 1b6a6fc5280e97559287b61eade2d4b363e836f2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Amadeusz=20S=C5=82awi=C5=84ski?= Date: Tue, 12 Apr 2022 11:16:28 +0200 Subject: ALSA: jack: Access input_dev under mutex MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is possible when using ASoC that input_dev is unregistered while calling snd_jack_report, which causes NULL pointer dereference. In order to prevent this serialize access to input_dev using mutex lock. Signed-off-by: Amadeusz Sławiński Reviewed-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220412091628.3056922-1-amadeuszx.slawinski@linux.intel.com Signed-off-by: Takashi Iwai --- include/sound/jack.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/jack.h b/include/sound/jack.h index 1181f536557e..1ed90e2109e9 100644 --- a/include/sound/jack.h +++ b/include/sound/jack.h @@ -62,6 +62,7 @@ struct snd_jack { const char *id; #ifdef CONFIG_SND_JACK_INPUT_DEV struct input_dev *input_dev; + struct mutex input_dev_lock; int registered; int type; char name[100]; -- cgit v1.2.3 From 9b30501949f773777f3632d891e6defbb363daf5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alvin=20=C5=A0ipraga?= Date: Thu, 17 Mar 2022 23:35:58 +0100 Subject: dt-bindings: imx: add clock bindings for i.MX8MN GPT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The i.MX8MN has a General Purpose Timer (GPT) just like the i.MX8MM, which already has such bindings. Add the relevant bindings for the Nano SoC too. Signed-off-by: Alvin Šipraga Acked-by: Krzysztof Kozlowski Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20220317223600.175894-1-alvin@pqrs.dk Signed-off-by: Abel Vesa --- include/dt-bindings/clock/imx8mn-clock.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/imx8mn-clock.h b/include/dt-bindings/clock/imx8mn-clock.h index 01e8bab1d767..07b8a282c268 100644 --- a/include/dt-bindings/clock/imx8mn-clock.h +++ b/include/dt-bindings/clock/imx8mn-clock.h @@ -243,6 +243,20 @@ #define IMX8MN_CLK_M7_CORE 221 -#define IMX8MN_CLK_END 222 +#define IMX8MN_CLK_GPT_3M 222 +#define IMX8MN_CLK_GPT1 223 +#define IMX8MN_CLK_GPT1_ROOT 224 +#define IMX8MN_CLK_GPT2 225 +#define IMX8MN_CLK_GPT2_ROOT 226 +#define IMX8MN_CLK_GPT3 227 +#define IMX8MN_CLK_GPT3_ROOT 228 +#define IMX8MN_CLK_GPT4 229 +#define IMX8MN_CLK_GPT4_ROOT 230 +#define IMX8MN_CLK_GPT5 231 +#define IMX8MN_CLK_GPT5_ROOT 232 +#define IMX8MN_CLK_GPT6 233 +#define IMX8MN_CLK_GPT6_ROOT 234 + +#define IMX8MN_CLK_END 235 #endif -- cgit v1.2.3 From ec095263a965720e1ca39db1d9c5cd47846c789b Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 11 Apr 2022 14:49:55 +0200 Subject: net: remove noblock parameter from recvmsg() entities The internal recvmsg() functions have two parameters 'flags' and 'noblock' that were merged inside skb_recv_datagram(). As a follow up patch to commit f4b41f062c42 ("net: remove noblock parameter from skb_recv_datagram()") this patch removes the separate 'noblock' parameter for recvmsg(). Analogue to the referenced patch for skb_recv_datagram() the 'flags' and 'noblock' parameters are unnecessarily split up with e.g. err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &addr_len); or in err = INDIRECT_CALL_2(sk->sk_prot->recvmsg, tcp_recvmsg, udp_recvmsg, sk, msg, size, flags & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &addr_len); instead of simply using only flags all the time and check for MSG_DONTWAIT where needed (to preserve for the formerly separated no(n)block condition). Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/r/20220411124955.154876-1-socketcan@hartkopp.net Signed-off-by: Paolo Abeni --- include/net/ping.h | 2 +- include/net/sctp/sctp.h | 2 +- include/net/sock.h | 3 +-- include/net/tcp.h | 2 +- include/net/tls.h | 2 +- include/net/udp.h | 8 ++++---- 6 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ping.h b/include/net/ping.h index b68fbfdb606f..e4ff3911cbf5 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -71,7 +71,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info); int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd, struct sk_buff *); -int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, +int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, void *user_icmph, size_t icmph_len); diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index bf3716fe83e0..a04999ee99b0 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -103,7 +103,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, struct sctp_association *asoc); extern struct percpu_counter sctp_sockets_allocated; int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *); -struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *); +struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int *); typedef int (*sctp_callback_t)(struct sctp_endpoint *, struct sctp_transport *, void *); void sctp_transport_walk_start(struct rhashtable_iter *iter); diff --git a/include/net/sock.h b/include/net/sock.h index 1a988e605f09..a01d6c421aa2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1202,8 +1202,7 @@ struct proto { int (*sendmsg)(struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, - int *addr_len); + size_t len, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); int (*bind)(struct sock *sk, diff --git a/include/net/tcp.h b/include/net/tcp.h index 6d50a662bf89..679b1964d494 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -407,7 +407,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); -int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, +int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); int tcp_set_window_clamp(struct sock *sk, int val); diff --git a/include/net/tls.h b/include/net/tls.h index 6fe78361c8c8..b59f0a63292b 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -371,7 +371,7 @@ void tls_sw_free_resources_rx(struct sock *sk); void tls_sw_release_resources_rx(struct sock *sk); void tls_sw_free_ctx_rx(struct tls_context *tls_ctx); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int nonblock, int flags, int *addr_len); + int flags, int *addr_len); bool tls_sw_sock_is_readable(struct sock *sk); ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, diff --git a/include/net/udp.h b/include/net/udp.h index f1c2a88c9005..b83a00330566 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -250,14 +250,14 @@ void udp_destruct_sock(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); -struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, - int noblock, int *off, int *err); +struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int *off, + int *err); static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, - int noblock, int *err) + int *err) { int off = 0; - return __skb_recv_udp(sk, flags, noblock, &off, err); + return __skb_recv_udp(sk, flags, &off, err); } int udp_v4_early_demux(struct sk_buff *skb); -- cgit v1.2.3 From 4185b27b3bef9ce724a3dafd8193c935e845fcdc Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Wed, 23 Feb 2022 22:52:47 +0530 Subject: dt-bindings: clock: Add YAML schemas for LPASS clocks on SC7280 The LPASS(Low Power Audio Subsystem) clock provider have a bunch of generic properties that are needed in a device tree. Also add clock ids for LPASS core clocks and audio clock IDs for LPASS client to request for the clocks. Reviewed-by: Rob Herring Reviewed-by: Stephen Boyd Signed-off-by: Taniya Das Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220223172248.18877-1-tdas@codeaurora.org --- .../dt-bindings/clock/qcom,lpassaudiocc-sc7280.h | 43 ++++++++++++++++++++++ .../dt-bindings/clock/qcom,lpasscorecc-sc7280.h | 26 +++++++++++++ 2 files changed, 69 insertions(+) create mode 100644 include/dt-bindings/clock/qcom,lpassaudiocc-sc7280.h create mode 100644 include/dt-bindings/clock/qcom,lpasscorecc-sc7280.h (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,lpassaudiocc-sc7280.h b/include/dt-bindings/clock/qcom,lpassaudiocc-sc7280.h new file mode 100644 index 000000000000..20ef2ea673f3 --- /dev/null +++ b/include/dt-bindings/clock/qcom,lpassaudiocc-sc7280.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_LPASS_AUDIO_CC_SC7280_H +#define _DT_BINDINGS_CLK_QCOM_LPASS_AUDIO_CC_SC7280_H + +/* LPASS_AUDIO_CC clocks */ +#define LPASS_AUDIO_CC_PLL 0 +#define LPASS_AUDIO_CC_PLL_OUT_AUX2 1 +#define LPASS_AUDIO_CC_PLL_OUT_AUX2_DIV_CLK_SRC 2 +#define LPASS_AUDIO_CC_PLL_OUT_MAIN_DIV_CLK_SRC 3 +#define LPASS_AUDIO_CC_CDIV_RX_MCLK_DIV_CLK_SRC 4 +#define LPASS_AUDIO_CC_CODEC_MEM0_CLK 5 +#define LPASS_AUDIO_CC_CODEC_MEM1_CLK 6 +#define LPASS_AUDIO_CC_CODEC_MEM2_CLK 7 +#define LPASS_AUDIO_CC_CODEC_MEM_CLK 8 +#define LPASS_AUDIO_CC_EXT_MCLK0_CLK 9 +#define LPASS_AUDIO_CC_EXT_MCLK0_CLK_SRC 10 +#define LPASS_AUDIO_CC_EXT_MCLK1_CLK 11 +#define LPASS_AUDIO_CC_EXT_MCLK1_CLK_SRC 12 +#define LPASS_AUDIO_CC_RX_MCLK_2X_CLK 13 +#define LPASS_AUDIO_CC_RX_MCLK_CLK 14 +#define LPASS_AUDIO_CC_RX_MCLK_CLK_SRC 15 + +/* LPASS_AON_CC clocks */ +#define LPASS_AON_CC_PLL 0 +#define LPASS_AON_CC_PLL_OUT_EVEN 1 +#define LPASS_AON_CC_PLL_OUT_MAIN_CDIV_DIV_CLK_SRC 2 +#define LPASS_AON_CC_PLL_OUT_ODD 3 +#define LPASS_AON_CC_AUDIO_HM_H_CLK 4 +#define LPASS_AON_CC_CDIV_TX_MCLK_DIV_CLK_SRC 5 +#define LPASS_AON_CC_MAIN_RCG_CLK_SRC 6 +#define LPASS_AON_CC_TX_MCLK_2X_CLK 7 +#define LPASS_AON_CC_TX_MCLK_CLK 8 +#define LPASS_AON_CC_TX_MCLK_RCG_CLK_SRC 9 +#define LPASS_AON_CC_VA_MEM0_CLK 10 + +/* LPASS_AON_CC power domains */ +#define LPASS_AON_CC_LPASS_AUDIO_HM_GDSC 0 + +#endif diff --git a/include/dt-bindings/clock/qcom,lpasscorecc-sc7280.h b/include/dt-bindings/clock/qcom,lpasscorecc-sc7280.h new file mode 100644 index 000000000000..28ed2a07aacc --- /dev/null +++ b/include/dt-bindings/clock/qcom,lpasscorecc-sc7280.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_LPASS_CORE_CC_SC7280_H +#define _DT_BINDINGS_CLK_QCOM_LPASS_CORE_CC_SC7280_H + +/* LPASS_CORE_CC clocks */ +#define LPASS_CORE_CC_DIG_PLL 0 +#define LPASS_CORE_CC_DIG_PLL_OUT_MAIN_DIV_CLK_SRC 1 +#define LPASS_CORE_CC_DIG_PLL_OUT_ODD 2 +#define LPASS_CORE_CC_CORE_CLK 3 +#define LPASS_CORE_CC_CORE_CLK_SRC 4 +#define LPASS_CORE_CC_EXT_IF0_CLK_SRC 5 +#define LPASS_CORE_CC_EXT_IF0_IBIT_CLK 6 +#define LPASS_CORE_CC_EXT_IF1_CLK_SRC 7 +#define LPASS_CORE_CC_EXT_IF1_IBIT_CLK 8 +#define LPASS_CORE_CC_LPM_CORE_CLK 9 +#define LPASS_CORE_CC_LPM_MEM0_CORE_CLK 10 +#define LPASS_CORE_CC_SYSNOC_MPORT_CORE_CLK 11 + +/* LPASS_CORE_CC power domains */ +#define LPASS_CORE_CC_LPASS_CORE_HM_GDSC 0 + +#endif -- cgit v1.2.3 From f7f207375d4e6eb9acc78d312eed8806b37d101a Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:13 +0100 Subject: ALSA: cs35l41: Unify hardware configuration Both ASoC and HDA require to configure the GPIOs and Boost, so create a single shared struct for hardware configuration. Signed-off-by: Lucas Tanure Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220413083728.10730-2-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 41 +++++++++++++++++++++++++++++++---------- 1 file changed, 31 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index bf7f9a9aeba0..abcf850f7110 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -701,9 +701,6 @@ #define CS35L41_GPIO1_CTRL_SHIFT 16 #define CS35L41_GPIO2_CTRL_MASK 0x07000000 #define CS35L41_GPIO2_CTRL_SHIFT 24 -#define CS35L41_GPIO_CTRL_OPEN_INT 2 -#define CS35L41_GPIO_CTRL_ACTV_LO 4 -#define CS35L41_GPIO_CTRL_ACTV_HI 5 #define CS35L41_GPIO_POL_MASK 0x1000 #define CS35L41_GPIO_POL_SHIFT 12 @@ -735,19 +732,43 @@ enum cs35l41_clk_ids { CS35L41_CLKID_MCLK = 4, }; -struct cs35l41_irq_cfg { - bool irq_pol_inv; - bool irq_out_en; - int irq_src_sel; +enum cs35l41_gpio1_func { + CS35L41_GPIO1_HIZ, + CS35L41_GPIO1_GPIO, + CS35L41_GPIO1_MDSYNC, + CS35L41_GPIO1_MCLK, + CS35L41_GPIO1_PDM_CLK, + CS35L41_GPIO1_PDM_DATA, }; -struct cs35l41_platform_data { +enum cs35l41_gpio2_func { + CS35L41_GPIO2_HIZ, + CS35L41_GPIO2_GPIO, + CS35L41_GPIO2_INT_OPEN_DRAIN, + CS35L41_GPIO2_MCLK, + CS35L41_GPIO2_INT_PUSH_PULL_LOW, + CS35L41_GPIO2_INT_PUSH_PULL_HIGH, + CS35L41_GPIO2_PDM_CLK, + CS35L41_GPIO2_PDM_DATA, +}; + +struct cs35l41_gpio_cfg { + bool pol_inv; + bool out_en; + unsigned int func; +}; + +struct cs35l41_hw_cfg { int bst_ind; int bst_ipk; int bst_cap; int dout_hiz; - struct cs35l41_irq_cfg irq_config1; - struct cs35l41_irq_cfg irq_config2; + struct cs35l41_gpio_cfg gpio1; + struct cs35l41_gpio_cfg gpio2; + unsigned int spk_pos; + + /* Don't put the AMP in reset if VSPK can not be turned off */ + bool vspk_always_on; }; struct cs35l41_otp_packed_element_t { -- cgit v1.2.3 From 2603c974b45dbfeece80474ee32173756aac3ba1 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:14 +0100 Subject: ALSA: cs35l41: Check hw_config before using it The driver can receive an empty hw_config, so mark as valid if successfully read from device tree/ACPI or set by the driver itself. Platforms not marked with a valid hw config will not be supported. Signed-off-by: Lucas Tanure Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220413083728.10730-3-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index abcf850f7110..4200379e0c26 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -538,7 +538,6 @@ #define CS35L41_OTP_SIZE_WORDS 32 #define CS35L41_NUM_OTP_ELEM 100 -#define CS35L41_VALID_PDATA 0x80000000 #define CS35L41_NUM_SUPPLIES 2 #define CS35L41_SCLK_MSTR_MASK 0x10 @@ -753,12 +752,14 @@ enum cs35l41_gpio2_func { }; struct cs35l41_gpio_cfg { + bool valid; bool pol_inv; bool out_en; unsigned int func; }; struct cs35l41_hw_cfg { + bool valid; int bst_ind; int bst_ipk; int bst_cap; -- cgit v1.2.3 From fcad8950a50dec5962b1b7b18a285daf7c137178 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:15 +0100 Subject: ALSA: cs35l41: Move cs35l41_gpio_config to shared lib ASoC and HDA can use a single function to configure the chip gpios. Signed-off-by: Lucas Tanure Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220413083728.10730-4-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index 4200379e0c26..e312eb1f6e48 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -798,5 +798,6 @@ int cs35l41_set_channels(struct device *dev, struct regmap *reg, unsigned int rx_num, unsigned int *rx_slot); int cs35l41_boost_config(struct device *dev, struct regmap *regmap, int boost_ind, int boost_cap, int boost_ipk); +int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); #endif /* __CS35L41_H */ -- cgit v1.2.3 From b8388a1aba32bef84884c06c8270efa9eec91267 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:18 +0100 Subject: ALSA: hda: cs35l41: Add Boost type flag Replace vspk_always_on by a enum that better characterizes the boost type, as there is 3 types of boost hardware. And with the new boost type other parts of the driver can better handle the configuration of the chip. Signed-off-by: Lucas Tanure Link: https://lore.kernel.org/r/20220413083728.10730-7-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index e312eb1f6e48..64d98cbd5c0e 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -725,6 +725,12 @@ #define CS35L41_SPI_MAX_FREQ 4000000 #define CS35L41_REGSTRIDE 4 +enum cs35l41_boost_type { + CS35L41_INT_BOOST, + CS35L41_EXT_BOOST, + CS35L41_EXT_BOOST_NO_VSPK_SWITCH, +}; + enum cs35l41_clk_ids { CS35L41_CLKID_SCLK = 0, CS35L41_CLKID_LRCLK = 1, @@ -768,8 +774,7 @@ struct cs35l41_hw_cfg { struct cs35l41_gpio_cfg gpio2; unsigned int spk_pos; - /* Don't put the AMP in reset if VSPK can not be turned off */ - bool vspk_always_on; + enum cs35l41_boost_type bst_type; }; struct cs35l41_otp_packed_element_t { -- cgit v1.2.3 From 5fdb68a7618e3c25816d458e07fd102803493400 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:22 +0100 Subject: ALSA: hda: cs35l41: Move boost config to initialization code Having CS35L41_PWR_CTRL2 on cs35l41_hda_config overwrites the boost configuration for internal boost. So move it to the initialization part and use regmap_update_bits to only change the correct bits. Signed-off-by: Lucas Tanure Link: https://lore.kernel.org/r/20220413083728.10730-11-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index 64d98cbd5c0e..7d892c97b1e8 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -661,6 +661,7 @@ #define CS35L41_GLOBAL_EN_SHIFT 0 #define CS35L41_BST_EN_MASK 0x0030 #define CS35L41_BST_EN_SHIFT 4 +#define CS35L41_BST_DIS_FET_OFF 0x00 #define CS35L41_BST_EN_DEFAULT 0x2 #define CS35L41_AMP_EN_SHIFT 0 #define CS35L41_AMP_EN_MASK 1 -- cgit v1.2.3 From 5577dd2329d03ef88a7c87c17d4c127f3d666192 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:26 +0100 Subject: ALSA: hda: cs35l41: Move external boost handling to lib for ASoC use To add support for external boost for ASoC move the HDA external boost implementation to the shared lib. Signed-off-by: Lucas Tanure Link: https://lore.kernel.org/r/20220413083728.10730-15-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index 7d892c97b1e8..ac629f852f2a 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -805,5 +805,9 @@ int cs35l41_set_channels(struct device *dev, struct regmap *reg, int cs35l41_boost_config(struct device *dev, struct regmap *regmap, int boost_ind, int boost_cap, int boost_ipk); int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); +int cs35l41_init_boost(struct device *dev, struct regmap *regmap, + struct cs35l41_hw_cfg *hw_cfg); +bool cs35l41_safe_reset(struct regmap *regmap, enum cs35l41_boost_type b_type); +int cs35l41_global_enable(struct regmap *regmap, enum cs35l41_boost_type b_type, int enable); #endif /* __CS35L41_H */ -- cgit v1.2.3 From bb06c203f86766fc2c37cbce0e20e9daae786f6e Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:28 +0100 Subject: ASoC: cs35l41: Support external boost Add support for external boost voltage, where GPIO1 must control a switch to isolate CS35L41 from the external Boost Voltage Signed-off-by: Lucas Tanure Acked-by: Charles Keepax Acked-by: Mark Brown Link: https://lore.kernel.org/r/20220413083728.10730-17-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index ac629f852f2a..dbe8d9c0191b 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -701,6 +701,8 @@ #define CS35L41_GPIO1_CTRL_SHIFT 16 #define CS35L41_GPIO2_CTRL_MASK 0x07000000 #define CS35L41_GPIO2_CTRL_SHIFT 24 +#define CS35L41_GPIO_LVL_SHIFT 15 +#define CS35L41_GPIO_LVL_MASK BIT(CS35L41_GPIO_LVL_SHIFT) #define CS35L41_GPIO_POL_MASK 0x1000 #define CS35L41_GPIO_POL_SHIFT 12 @@ -802,8 +804,6 @@ int cs35l41_register_errata_patch(struct device *dev, struct regmap *reg, unsign int cs35l41_set_channels(struct device *dev, struct regmap *reg, unsigned int tx_num, unsigned int *tx_slot, unsigned int rx_num, unsigned int *rx_slot); -int cs35l41_boost_config(struct device *dev, struct regmap *regmap, int boost_ind, int boost_cap, - int boost_ipk); int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); int cs35l41_init_boost(struct device *dev, struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); -- cgit v1.2.3 From eb2789785428e2dbc3d5f413b16c67ff90d828c1 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 2 Apr 2022 08:30:34 +0100 Subject: dt-bindings: clock: Add R9A07G043 CPG Clock and Reset Definitions Define RZ/G2UL (R9A07G043U) Clock Pulse Generator Core Clock and module clock outputs, as listed in Table 7.1.4.2 ("Clock List r0.51") and also add Reset definitions referring to registers CPG_RST_* in Section 7.2.3 ("Register configuration") of the RZ/G2UL Hardware User's Manual (Rev. 0.51, Nov. 2021). Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Acked-by: Rob Herring Link: https://lore.kernel.org/r/20220402073037.23947-3-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/clock/r9a07g043-cpg.h | 184 ++++++++++++++++++++++++++++++ 1 file changed, 184 insertions(+) create mode 100644 include/dt-bindings/clock/r9a07g043-cpg.h (limited to 'include') diff --git a/include/dt-bindings/clock/r9a07g043-cpg.h b/include/dt-bindings/clock/r9a07g043-cpg.h new file mode 100644 index 000000000000..27e232733096 --- /dev/null +++ b/include/dt-bindings/clock/r9a07g043-cpg.h @@ -0,0 +1,184 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + * + * Copyright (C) 2022 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_CLOCK_R9A07G043_CPG_H__ +#define __DT_BINDINGS_CLOCK_R9A07G043_CPG_H__ + +#include + +/* R9A07G043 CPG Core Clocks */ +#define R9A07G043_CLK_I 0 +#define R9A07G043_CLK_I2 1 +#define R9A07G043_CLK_S0 2 +#define R9A07G043_CLK_SPI0 3 +#define R9A07G043_CLK_SPI1 4 +#define R9A07G043_CLK_SD0 5 +#define R9A07G043_CLK_SD1 6 +#define R9A07G043_CLK_M0 7 +#define R9A07G043_CLK_M2 8 +#define R9A07G043_CLK_M3 9 +#define R9A07G043_CLK_HP 10 +#define R9A07G043_CLK_TSU 11 +#define R9A07G043_CLK_ZT 12 +#define R9A07G043_CLK_P0 13 +#define R9A07G043_CLK_P1 14 +#define R9A07G043_CLK_P2 15 +#define R9A07G043_CLK_AT 16 +#define R9A07G043_OSCCLK 17 +#define R9A07G043_CLK_P0_DIV2 18 + +/* R9A07G043 Module Clocks */ +#define R9A07G043_CA55_SCLK 0 /* RZ/G2UL Only */ +#define R9A07G043_CA55_PCLK 1 /* RZ/G2UL Only */ +#define R9A07G043_CA55_ATCLK 2 /* RZ/G2UL Only */ +#define R9A07G043_CA55_GICCLK 3 /* RZ/G2UL Only */ +#define R9A07G043_CA55_PERICLK 4 /* RZ/G2UL Only */ +#define R9A07G043_CA55_ACLK 5 /* RZ/G2UL Only */ +#define R9A07G043_CA55_TSCLK 6 /* RZ/G2UL Only */ +#define R9A07G043_GIC600_GICCLK 7 /* RZ/G2UL Only */ +#define R9A07G043_IA55_CLK 8 /* RZ/G2UL Only */ +#define R9A07G043_IA55_PCLK 9 /* RZ/G2UL Only */ +#define R9A07G043_MHU_PCLK 10 /* RZ/G2UL Only */ +#define R9A07G043_SYC_CNT_CLK 11 +#define R9A07G043_DMAC_ACLK 12 +#define R9A07G043_DMAC_PCLK 13 +#define R9A07G043_OSTM0_PCLK 14 +#define R9A07G043_OSTM1_PCLK 15 +#define R9A07G043_OSTM2_PCLK 16 +#define R9A07G043_MTU_X_MCK_MTU3 17 +#define R9A07G043_POE3_CLKM_POE 18 +#define R9A07G043_WDT0_PCLK 19 +#define R9A07G043_WDT0_CLK 20 +#define R9A07G043_WDT2_PCLK 21 /* RZ/G2UL Only */ +#define R9A07G043_WDT2_CLK 22 /* RZ/G2UL Only */ +#define R9A07G043_SPI_CLK2 23 +#define R9A07G043_SPI_CLK 24 +#define R9A07G043_SDHI0_IMCLK 25 +#define R9A07G043_SDHI0_IMCLK2 26 +#define R9A07G043_SDHI0_CLK_HS 27 +#define R9A07G043_SDHI0_ACLK 28 +#define R9A07G043_SDHI1_IMCLK 29 +#define R9A07G043_SDHI1_IMCLK2 30 +#define R9A07G043_SDHI1_CLK_HS 31 +#define R9A07G043_SDHI1_ACLK 32 +#define R9A07G043_ISU_ACLK 33 /* RZ/G2UL Only */ +#define R9A07G043_ISU_PCLK 34 /* RZ/G2UL Only */ +#define R9A07G043_CRU_SYSCLK 35 /* RZ/G2UL Only */ +#define R9A07G043_CRU_VCLK 36 /* RZ/G2UL Only */ +#define R9A07G043_CRU_PCLK 37 /* RZ/G2UL Only */ +#define R9A07G043_CRU_ACLK 38 /* RZ/G2UL Only */ +#define R9A07G043_LCDC_CLK_A 39 /* RZ/G2UL Only */ +#define R9A07G043_LCDC_CLK_P 40 /* RZ/G2UL Only */ +#define R9A07G043_LCDC_CLK_D 41 /* RZ/G2UL Only */ +#define R9A07G043_SSI0_PCLK2 42 +#define R9A07G043_SSI0_PCLK_SFR 43 +#define R9A07G043_SSI1_PCLK2 44 +#define R9A07G043_SSI1_PCLK_SFR 45 +#define R9A07G043_SSI2_PCLK2 46 +#define R9A07G043_SSI2_PCLK_SFR 47 +#define R9A07G043_SSI3_PCLK2 48 +#define R9A07G043_SSI3_PCLK_SFR 49 +#define R9A07G043_SRC_CLKP 50 /* RZ/G2UL Only */ +#define R9A07G043_USB_U2H0_HCLK 51 +#define R9A07G043_USB_U2H1_HCLK 52 +#define R9A07G043_USB_U2P_EXR_CPUCLK 53 +#define R9A07G043_USB_PCLK 54 +#define R9A07G043_ETH0_CLK_AXI 55 +#define R9A07G043_ETH0_CLK_CHI 56 +#define R9A07G043_ETH1_CLK_AXI 57 +#define R9A07G043_ETH1_CLK_CHI 58 +#define R9A07G043_I2C0_PCLK 59 +#define R9A07G043_I2C1_PCLK 60 +#define R9A07G043_I2C2_PCLK 61 +#define R9A07G043_I2C3_PCLK 62 +#define R9A07G043_SCIF0_CLK_PCK 63 +#define R9A07G043_SCIF1_CLK_PCK 64 +#define R9A07G043_SCIF2_CLK_PCK 65 +#define R9A07G043_SCIF3_CLK_PCK 66 +#define R9A07G043_SCIF4_CLK_PCK 67 +#define R9A07G043_SCI0_CLKP 68 +#define R9A07G043_SCI1_CLKP 69 +#define R9A07G043_IRDA_CLKP 70 +#define R9A07G043_RSPI0_CLKB 71 +#define R9A07G043_RSPI1_CLKB 72 +#define R9A07G043_RSPI2_CLKB 73 +#define R9A07G043_CANFD_PCLK 74 +#define R9A07G043_GPIO_HCLK 75 +#define R9A07G043_ADC_ADCLK 76 +#define R9A07G043_ADC_PCLK 77 +#define R9A07G043_TSU_PCLK 78 + +/* R9A07G043 Resets */ +#define R9A07G043_CA55_RST_1_0 0 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_1_1 1 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_3_0 2 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_3_1 3 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_4 4 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_5 5 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_6 6 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_7 7 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_8 8 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_9 9 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_10 10 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_11 11 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_12 12 /* RZ/G2UL Only */ +#define R9A07G043_GIC600_GICRESET_N 13 /* RZ/G2UL Only */ +#define R9A07G043_GIC600_DBG_GICRESET_N 14 /* RZ/G2UL Only */ +#define R9A07G043_IA55_RESETN 15 /* RZ/G2UL Only */ +#define R9A07G043_MHU_RESETN 16 /* RZ/G2UL Only */ +#define R9A07G043_DMAC_ARESETN 17 +#define R9A07G043_DMAC_RST_ASYNC 18 +#define R9A07G043_SYC_RESETN 19 +#define R9A07G043_OSTM0_PRESETZ 20 +#define R9A07G043_OSTM1_PRESETZ 21 +#define R9A07G043_OSTM2_PRESETZ 22 +#define R9A07G043_MTU_X_PRESET_MTU3 23 +#define R9A07G043_POE3_RST_M_REG 24 +#define R9A07G043_WDT0_PRESETN 25 +#define R9A07G043_WDT2_PRESETN 26 /* RZ/G2UL Only */ +#define R9A07G043_SPI_RST 27 +#define R9A07G043_SDHI0_IXRST 28 +#define R9A07G043_SDHI1_IXRST 29 +#define R9A07G043_ISU_ARESETN 30 /* RZ/G2UL Only */ +#define R9A07G043_ISU_PRESETN 31 /* RZ/G2UL Only */ +#define R9A07G043_CRU_CMN_RSTB 32 /* RZ/G2UL Only */ +#define R9A07G043_CRU_PRESETN 33 /* RZ/G2UL Only */ +#define R9A07G043_CRU_ARESETN 34 /* RZ/G2UL Only */ +#define R9A07G043_LCDC_RESET_N 35 /* RZ/G2UL Only */ +#define R9A07G043_SSI0_RST_M2_REG 36 +#define R9A07G043_SSI1_RST_M2_REG 37 +#define R9A07G043_SSI2_RST_M2_REG 38 +#define R9A07G043_SSI3_RST_M2_REG 39 +#define R9A07G043_SRC_RST 40 /* RZ/G2UL Only */ +#define R9A07G043_USB_U2H0_HRESETN 41 +#define R9A07G043_USB_U2H1_HRESETN 42 +#define R9A07G043_USB_U2P_EXL_SYSRST 43 +#define R9A07G043_USB_PRESETN 44 +#define R9A07G043_ETH0_RST_HW_N 45 +#define R9A07G043_ETH1_RST_HW_N 46 +#define R9A07G043_I2C0_MRST 47 +#define R9A07G043_I2C1_MRST 48 +#define R9A07G043_I2C2_MRST 49 +#define R9A07G043_I2C3_MRST 50 +#define R9A07G043_SCIF0_RST_SYSTEM_N 51 +#define R9A07G043_SCIF1_RST_SYSTEM_N 52 +#define R9A07G043_SCIF2_RST_SYSTEM_N 53 +#define R9A07G043_SCIF3_RST_SYSTEM_N 54 +#define R9A07G043_SCIF4_RST_SYSTEM_N 55 +#define R9A07G043_SCI0_RST 56 +#define R9A07G043_SCI1_RST 57 +#define R9A07G043_IRDA_RST 58 +#define R9A07G043_RSPI0_RST 59 +#define R9A07G043_RSPI1_RST 60 +#define R9A07G043_RSPI2_RST 61 +#define R9A07G043_CANFD_RSTP_N 62 +#define R9A07G043_CANFD_RSTC_N 63 +#define R9A07G043_GPIO_RSTN 64 +#define R9A07G043_GPIO_PORT_RESETN 65 +#define R9A07G043_GPIO_SPARE_RESETN 66 +#define R9A07G043_ADC_PRESETN 67 +#define R9A07G043_ADC_ADRST_N 68 +#define R9A07G043_TSU_PRESETN 69 + +#endif /* __DT_BINDINGS_CLOCK_R9A07G043_CPG_H__ */ -- cgit v1.2.3 From 1a95e04e29a116c3424988c70c441ca8ec2779ff Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 12 Apr 2022 11:24:00 +0100 Subject: net: phylink: remove phylink_helper_basex_speed() As there are now no users of phylink_helper_basex_speed(), we can remove this obsolete functionality. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/phylink.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 223781622b33..6d06896fc20d 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -160,11 +160,6 @@ struct phylink_mac_ops { * clearing unsupported speeds and duplex settings. The port modes * should not be cleared; phylink_set_port_modes() will help with this. * - * If the @state->interface mode is %PHY_INTERFACE_MODE_1000BASEX - * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode - * based on @state->advertising and/or @state->speed and update - * @state->interface accordingly. See phylink_helper_basex_speed(). - * * When @config->supported_interfaces has been set, phylink will iterate * over the supported interfaces to determine the full capability of the * MAC. The validation function must not print errors if @state->interface @@ -579,7 +574,6 @@ int phylink_speed_up(struct phylink *pl); #define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) void phylink_set_port_modes(unsigned long *bits); -void phylink_helper_basex_speed(struct phylink_link_state *state); void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, u16 bmsr, u16 lpa); -- cgit v1.2.3 From 12dc5c2cb7b269c5a1c6d02844f40bfce942a7a6 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:51 +0300 Subject: net: rtnetlink: add msg kind names Add rtnl kind names instead of using raw values. We'll need to check for DEL kind later to validate bulk flag support. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 9f48733bfd21..78712b51f3da 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -13,6 +13,13 @@ enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = 1, }; +enum rtnl_kinds { + RTNL_KIND_NEW, + RTNL_KIND_DEL, + RTNL_KIND_GET, + RTNL_KIND_SET +}; + void rtnl_register(int protocol, int msgtype, rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); int rtnl_register_module(struct module *owner, int protocol, int msgtype, -- cgit v1.2.3 From 2e9ea3e30f696fd438319c07836422bb0bbb4608 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:52 +0300 Subject: net: rtnetlink: add helper to extract msg type's kind Add a helper which extracts the msg type's kind using the kind mask (0x3). Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 78712b51f3da..c51c5ff7f7e2 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -19,6 +19,12 @@ enum rtnl_kinds { RTNL_KIND_GET, RTNL_KIND_SET }; +#define RTNL_KIND_MASK 0x3 + +static inline enum rtnl_kinds rtnl_msgtype_kind(int msgtype) +{ + return msgtype & RTNL_KIND_MASK; +} void rtnl_register(int protocol, int msgtype, rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); -- cgit v1.2.3 From 0569e31f1bc2f50613ba4c219f3ecc0d1174d841 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:53 +0300 Subject: net: rtnetlink: use BIT for flag values Use BIT to define flag values. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index c51c5ff7f7e2..0bf622409aaa 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -10,7 +10,7 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { - RTNL_FLAG_DOIT_UNLOCKED = 1, + RTNL_FLAG_DOIT_UNLOCKED = BIT(0), }; enum rtnl_kinds { -- cgit v1.2.3 From 545528d788556c724eeb5400757f828ef27782a8 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:54 +0300 Subject: net: netlink: add NLM_F_BULK delete request modifier Add a new delete request modifier called NLM_F_BULK which, when supported, would cause the request to delete multiple objects. The flag is a convenient way to signal that a multiple delete operation is requested which can be gradually added to different delete requests. In order to make sure older kernels will error out if the operation is not supported instead of doing something unintended we have to break a required condition when implementing support for this flag, f.e. for neighbors we will omit the mandatory mac address attribute. Initially it will be used to add flush with filtering support for bridge fdbs, but it also opens the door to add similar support to others. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 4c0cde075c27..855dffb4c1c3 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -72,6 +72,7 @@ struct nlmsghdr { /* Modifiers to DELETE request */ #define NLM_F_NONREC 0x100 /* Do not delete recursively */ +#define NLM_F_BULK 0x200 /* Delete multiple objects */ /* Flags for ACK message */ #define NLM_F_CAPPED 0x100 /* request was capped */ -- cgit v1.2.3 From a6cec0bcd34264be8887791594be793b3f12719f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:55 +0300 Subject: net: rtnetlink: add bulk delete support flag Add a new rtnl flag (RTNL_FLAG_BULK_DEL_SUPPORTED) which is used to verify that the delete operation allows bulk object deletion. Also emit a warning if anyone tries to set it for non-delete kind. Suggested-by: David Ahern Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 0bf622409aaa..bf8bb3357825 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -10,7 +10,8 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { - RTNL_FLAG_DOIT_UNLOCKED = BIT(0), + RTNL_FLAG_DOIT_UNLOCKED = BIT(0), + RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1), }; enum rtnl_kinds { -- cgit v1.2.3 From 1306d5362a591493a2d07f685ed2cc480dcda320 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:56 +0300 Subject: net: add ndo_fdb_del_bulk Add a new netdev op called ndo_fdb_del_bulk, it will be later used for driver-specific bulk delete implementation dispatched from rtnetlink. The first user will be the bridge, we need it to signal to rtnetlink from the driver that we support bulk delete operation (NLM_F_BULK). Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 28ea4f8269d4..a602f29365b0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1260,6 +1260,10 @@ struct netdev_net_notifier { * struct net_device *dev, * const unsigned char *addr, u16 vid) * Deletes the FDB entry from dev coresponding to addr. + * int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[], + * struct net_device *dev, + * u16 vid, + * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, struct net_device *filter_dev, * int *idx) @@ -1510,6 +1514,11 @@ struct net_device_ops { struct net_device *dev, const unsigned char *addr, u16 vid); + int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + u16 vid, + struct netlink_ext_ack *extack); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, -- cgit v1.2.3 From ea2c0f9e3fc2f94f090d693b7235c02af1289629 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:52:00 +0300 Subject: net: rtnetlink: add ndm flags and state mask attributes Add ndm flags/state masks which will be used for bulk delete filtering. All of these are used by the bridge and vxlan drivers. Also minimal attr policy validation is added, it is up to ndo_fdb_del_bulk implementers to further validate them. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/neighbour.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index db05fb55055e..39c565e460c7 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -32,6 +32,8 @@ enum { NDA_NH_ID, NDA_FDB_EXT_ATTRS, NDA_FLAGS_EXT, + NDA_NDM_STATE_MASK, + NDA_NDM_FLAGS_MASK, __NDA_MAX }; -- cgit v1.2.3 From d6d3146ce532268ad0ffd8d92d2b7492898decf1 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:52 +0800 Subject: skb: add some helpers for skb drop reasons In order to simply the definition and assignment for 'enum skb_drop_reason', introduce some helpers. SKB_DR() is used to define a variable of type 'enum skb_drop_reason' with the 'SKB_DROP_REASON_NOT_SPECIFIED' initial value. SKB_DR_SET() is used to set the value of the variable. Seems it is a little useless? But it makes the code shorter. SKB_DR_OR() is used to set the value of the variable if it is not set yet, which means its value is SKB_DROP_REASON_NOT_SPECIFIED. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9b81ba497665..0cbd6ada957c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -450,6 +450,18 @@ enum skb_drop_reason { SKB_DROP_REASON_MAX, }; +#define SKB_DR_INIT(name, reason) \ + enum skb_drop_reason name = SKB_DROP_REASON_##reason +#define SKB_DR(name) \ + SKB_DR_INIT(name, NOT_SPECIFIED) +#define SKB_DR_SET(name, reason) \ + (name = SKB_DROP_REASON_##reason) +#define SKB_DR_OR(name, reason) \ + do { \ + if (name == SKB_DROP_REASON_NOT_SPECIFIED) \ + SKB_DR_SET(name, reason); \ + } while (0) + /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. -- cgit v1.2.3 From c4eb664191b4a5ff6856478f903924176697719e Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:53 +0800 Subject: net: ipv4: add skb drop reasons to ip_error() Eventually, I find out the handler function for inputting route lookup fail: ip_error(). The drop reasons we used in ip_error() are almost corresponding to IPSTATS_MIB_*, and following new reasons are introduced: SKB_DROP_REASON_IP_INADDRERRORS SKB_DROP_REASON_IP_INNOROUTES Isn't the name SKB_DROP_REASON_IP_HOSTUNREACH and SKB_DROP_REASON_IP_NETUNREACH more accurate? To make them corresponding to IPSTATS_MIB_*, we keep their name still. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ include/trace/events/skb.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0cbd6ada957c..886e83ac4b70 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -447,6 +447,12 @@ enum skb_drop_reason { * 2211, such as a broadcasts * ICMP_TIMESTAMP */ + SKB_DROP_REASON_IP_INADDRERRORS, /* host unreachable, corresponding + * to IPSTATS_MIB_INADDRERRORS + */ + SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding + * to IPSTATS_MIB_INADDRERRORS + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 42647114fffe..0acac7e5a019 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -63,6 +63,8 @@ EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \ EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ + EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \ + EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 2edc1a383fda8d2f580216292dfd9daeae691e47 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:55 +0800 Subject: net: ip: add skb drop reasons to ip forwarding Replace kfree_skb() which is used in ip6_forward() and ip_forward() with kfree_skb_reason(). The new drop reason 'SKB_DROP_REASON_PKT_TOO_BIG' is introduced for the case that the length of the packet exceeds MTU and can't fragment. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ include/trace/events/skb.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 886e83ac4b70..0ef11df1bc67 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -453,6 +453,9 @@ enum skb_drop_reason { SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding * to IPSTATS_MIB_INADDRERRORS */ + SKB_DROP_REASON_PKT_TOO_BIG, /* packet size is too big (maybe exceed + * the MTU) + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 0acac7e5a019..2da72a9a5764 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -65,6 +65,7 @@ EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \ EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \ + EM(SKB_DROP_REASON_PKT_TOO_BIG, PKT_TOO_BIG) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 1ad6d548e2a452f21bcee4606ee4ec7afcde5f37 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:56 +0800 Subject: net: icmp: introduce function icmpv6_param_prob_reason() In order to add the skb drop reasons support to icmpv6_param_prob(), introduce the function icmpv6_param_prob_reason() and make icmpv6_param_prob() an inline call to it. This new function will be used in the following patches. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 9055cb380ee2..db0f4fcfdaf4 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -79,8 +79,9 @@ extern int icmpv6_init(void); extern int icmpv6_err_convert(u8 type, u8 code, int *err); extern void icmpv6_cleanup(void); -extern void icmpv6_param_prob(struct sk_buff *skb, - u8 code, int pos); +extern void icmpv6_param_prob_reason(struct sk_buff *skb, + u8 code, int pos, + enum skb_drop_reason reason); struct flowi6; struct in6_addr; @@ -91,6 +92,12 @@ extern void icmpv6_flow_init(struct sock *sk, const struct in6_addr *daddr, int oif); +static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) +{ + icmpv6_param_prob_reason(skb, code, pos, + SKB_DROP_REASON_NOT_SPECIFIED); +} + static inline bool icmpv6_is_err(int type) { switch (type) { -- cgit v1.2.3 From bdc21a4d286c6917fe966fd765de99411095b1b4 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Mon, 21 Mar 2022 09:57:22 +0000 Subject: PM: EM: Add .get_cost() callback The Energy Model (EM) supports devices which report abstract power scale, not only real Watts. The primary goal for EM is to enable the Energy Aware Scheduler (EAS) for a given platform. Some of the platforms might not be able to deliver proper power values. The only information that they might have is the relative efficiency between CPU types. Thus, it makes sense to remove some restrictions in the EM framework and introduce a mechanism which would support those platforms. What is crucial for EAS to operate is the 'cost' field in the EM. The 'cost' is calculated internally in EM framework based on knowledge from 'power' values. The 'cost' values must be strictly increasing. The existing API with its 'power' value size restrictions cannot guarantee that the 'cost' will meet this requirement. Since the platform is missing this detailed information, but has only efficiency details, introduce a new custom callback in the EM framework. The new callback would allow to provide the 'cost' values which reflect efficiency of the CPUs. This would allow to provide EAS information which has different relation than what would be forced by the EM internal formulas calculating 'cost' values. Thanks to this new callback it is possible to create a system view for EAS which has no overlapping performance states across many Performance Domains. Signed-off-by: Lukasz Luba Reviewed-by: Ionela Voinescu Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 9f3c400bc52d..0a3a5663177b 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -114,9 +114,30 @@ struct em_data_callback { */ int (*active_power)(unsigned long *power, unsigned long *freq, struct device *dev); + + /** + * get_cost() - Provide the cost at the given performance state of + * a device + * @dev : Device for which we do this operation (can be a CPU) + * @freq : Frequency at the performance state in kHz + * @cost : The cost value for the performance state + * (modified) + * + * In case of CPUs, the cost is the one of a single CPU in the domain. + * It is expected to fit in the [0, EM_MAX_POWER] range due to internal + * usage in EAS calculation. + * + * Return 0 on success, or appropriate error value in case of failure. + */ + int (*get_cost)(struct device *dev, unsigned long freq, + unsigned long *cost); }; -#define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } #define EM_SET_ACTIVE_POWER_CB(em_cb, cb) ((em_cb).active_power = cb) +#define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) \ + { .active_power = _active_power_cb, \ + .get_cost = _cost_cb } +#define EM_DATA_CB(_active_power_cb) \ + EM_ADV_DATA_CB(_active_power_cb, NULL) struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); @@ -264,6 +285,7 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) #else struct em_data_callback {}; +#define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) { } #define EM_DATA_CB(_active_power_cb) { } #define EM_SET_ACTIVE_POWER_CB(em_cb, cb) do { } while (0) -- cgit v1.2.3 From fc3a9a9858478ab5f8441765a3f9552a0ceba10c Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Mon, 21 Mar 2022 09:57:23 +0000 Subject: PM: EM: Add artificial EM flag The Energy Model (EM) can be used on platforms which are missing real power information. Those platforms would implement .get_cost() which populates needed values for the Energy Aware Scheduler (EAS). The EAS doesn't use 'power' fields from EM, but other frameworks might use them. Thus, to avoid miss-usage of this specific type of EM, introduce a new flags which can be checked by other frameworks. Signed-off-by: Pierre Gondois Signed-off-by: Lukasz Luba Reviewed-by: Ionela Voinescu Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 0a3a5663177b..92e82a322859 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -67,11 +67,16 @@ struct em_perf_domain { * * EM_PERF_DOMAIN_SKIP_INEFFICIENCIES: Skip inefficient states when estimating * energy consumption. + * + * EM_PERF_DOMAIN_ARTIFICIAL: The power values are artificial and might be + * created by platform missing real power information */ #define EM_PERF_DOMAIN_MILLIWATTS BIT(0) #define EM_PERF_DOMAIN_SKIP_INEFFICIENCIES BIT(1) +#define EM_PERF_DOMAIN_ARTIFICIAL BIT(2) #define em_span_cpus(em) (to_cpumask((em)->cpus)) +#define em_is_artificial(em) ((em)->flags & EM_PERF_DOMAIN_ARTIFICIAL) #ifdef CONFIG_ENERGY_MODEL #define EM_MAX_POWER 0xFFFF -- cgit v1.2.3 From 75a3a99a5a9886af13be44e640cb415ebda80db2 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Mon, 21 Mar 2022 09:57:25 +0000 Subject: PM: EM: Change the order of arguments in the .active_power() callback The .active_power() callback passes the device pointer when it's called. Aligned with a convetion present in other subsystems and pass the 'dev' as a first argument. It looks more cleaner. Adjust all affected drivers which implement that API callback. Suggested-by: Ionela Voinescu Signed-off-by: Lukasz Luba Reviewed-by: Ionela Voinescu Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 92e82a322859..8419bffb4398 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -101,11 +101,11 @@ struct em_data_callback { /** * active_power() - Provide power at the next performance state of * a device + * @dev : Device for which we do this operation (can be a CPU) * @power : Active power at the performance state * (modified) * @freq : Frequency at the performance state in kHz * (modified) - * @dev : Device for which we do this operation (can be a CPU) * * active_power() must find the lowest performance state of 'dev' above * 'freq' and update 'power' and 'freq' to the matching active power @@ -117,8 +117,8 @@ struct em_data_callback { * * Return 0 on success. */ - int (*active_power)(unsigned long *power, unsigned long *freq, - struct device *dev); + int (*active_power)(struct device *dev, unsigned long *power, + unsigned long *freq); /** * get_cost() - Provide the cost at the given performance state of -- cgit v1.2.3 From ce1cb680ff1c5b88505f878137796b1723e00193 Mon Sep 17 00:00:00 2001 From: David Cohen Date: Thu, 24 Mar 2022 08:07:30 +0000 Subject: PM: sleep: enable dynamic debug support within pm_pr_dbg() Currently pm_pr_dbg() is used to filter kernel pm debug messages based on pm_debug_messages_on flag. The problem is if we enable/disable this flag it will affect all pm_pr_dbg() calls at once, so we can't individually control them. This patch changes pm_pr_dbg() implementation as such: - If pm_debug_messages_on is enabled, print the message. - If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is enabled, only print the messages explicitly enabled on /sys/kernel/debug/dynamic_debug/control. - If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is disabled, don't print the message. Signed-off-by: David Cohen Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 44 +++++++++++++++++++++++++++++++++++++++----- 1 file changed, 39 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 300273ff40cc..70f2921e2e70 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -542,22 +542,56 @@ static inline void unlock_system_sleep(void) {} #ifdef CONFIG_PM_SLEEP_DEBUG extern bool pm_print_times_enabled; extern bool pm_debug_messages_on; -extern __printf(2, 3) void __pm_pr_dbg(bool defer, const char *fmt, ...); +static inline int pm_dyn_debug_messages_on(void) +{ +#ifdef CONFIG_DYNAMIC_DEBUG + return 1; +#else + return 0; +#endif +} +#ifndef pr_fmt +#define pr_fmt(fmt) "PM: " fmt +#endif +#define __pm_pr_dbg(fmt, ...) \ + do { \ + if (pm_debug_messages_on) \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + else if (pm_dyn_debug_messages_on()) \ + pr_debug(fmt, ##__VA_ARGS__); \ + } while (0) +#define __pm_deferred_pr_dbg(fmt, ...) \ + do { \ + if (pm_debug_messages_on) \ + printk_deferred(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + } while (0) #else #define pm_print_times_enabled (false) #define pm_debug_messages_on (false) #include -#define __pm_pr_dbg(defer, fmt, ...) \ - no_printk(KERN_DEBUG fmt, ##__VA_ARGS__) +#define __pm_pr_dbg(fmt, ...) \ + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) +#define __pm_deferred_pr_dbg(fmt, ...) \ + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif +/** + * pm_pr_dbg - print pm sleep debug messages + * + * If pm_debug_messages_on is enabled, print message. + * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is enabled, + * print message only from instances explicitly enabled on dynamic debug's + * control. + * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is disabled, + * don't print message. + */ #define pm_pr_dbg(fmt, ...) \ - __pm_pr_dbg(false, fmt, ##__VA_ARGS__) + __pm_pr_dbg(fmt, ##__VA_ARGS__) #define pm_deferred_pr_dbg(fmt, ...) \ - __pm_pr_dbg(true, fmt, ##__VA_ARGS__) + __pm_deferred_pr_dbg(fmt, ##__VA_ARGS__) #ifdef CONFIG_PM_AUTOSLEEP -- cgit v1.2.3 From cf6ba0750a22a54f5101986401271429995cc4a0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 4 Apr 2022 17:21:50 +0200 Subject: ACPI: bus: Introduce acpi_dev_for_each_child() Introduce a wrapper around device_for_each_child() to iterate over the children of a given ACPI device object. This function will be used in subsequent change sets. Signed-off-by: Rafael J. Wysocki Reviewed-by: Mika Westerberg --- include/acpi/acpi_bus.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index c4b78c21d793..c616f3d8506b 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -481,6 +481,8 @@ void acpi_initialize_hp_context(struct acpi_device *adev, extern struct bus_type acpi_bus_type; int acpi_bus_for_each_dev(int (*fn)(struct device *, void *), void *data); +int acpi_dev_for_each_child(struct acpi_device *adev, + int (*fn)(struct device *, void *), void *data); /* * Events -- cgit v1.2.3 From b7dd6298db81ea6dd902f1787eaf9a43228e2707 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 4 Apr 2022 17:23:13 +0200 Subject: ACPI: PM: Introduce acpi_dev_power_up_children_with_adr() Introduce a function powering up all of the children of a given ACPI device object that are power-manageable and hold valid _ADR ACPI objects so as to make it possible to prepare the corresponding "physical" devices for enumeration carried out by a bus type driver, like PCI. This function will be used in a subsequent change set. Signed-off-by: Rafael J. Wysocki Reviewed-by: Mika Westerberg --- include/acpi/acpi_bus.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index c616f3d8506b..b44aaffedb91 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -524,6 +524,7 @@ int acpi_device_fix_up_power(struct acpi_device *device); int acpi_bus_update_power(acpi_handle handle, int *state_p); int acpi_device_update_power(struct acpi_device *device, int *state_p); bool acpi_bus_power_manageable(acpi_handle handle); +void acpi_dev_power_up_children_with_adr(struct acpi_device *adev); int acpi_device_power_add_dependent(struct acpi_device *adev, struct device *dev); void acpi_device_power_remove_dependent(struct acpi_device *adev, -- cgit v1.2.3 From 1227418989346af3af179742cf42ce842e0ad484 Mon Sep 17 00:00:00 2001 From: Dov Murik Date: Tue, 12 Apr 2022 21:21:24 +0000 Subject: efi: Save location of EFI confidential computing area Confidential computing (coco) hardware such as AMD SEV (Secure Encrypted Virtualization) allows a guest owner to inject secrets into the VMs memory without the host/hypervisor being able to read them. Firmware support for secret injection is available in OVMF, which reserves a memory area for secret injection and includes a pointer to it the in EFI config table entry LINUX_EFI_COCO_SECRET_TABLE_GUID. If EFI exposes such a table entry, uefi_init() will keep a pointer to the EFI config table entry in efi.coco_secret, so it can be used later by the kernel (specifically drivers/virt/coco/efi_secret). It will also appear in the kernel log as "CocoSecret=ADDRESS"; for example: [ 0.000000] efi: EFI v2.70 by EDK II [ 0.000000] efi: CocoSecret=0x7f22e680 SMBIOS=0x7f541000 ACPI=0x7f77e000 ACPI 2.0=0x7f77e014 MEMATTR=0x7ea0c018 The new functionality can be enabled with CONFIG_EFI_COCO_SECRET=y. Signed-off-by: Dov Murik Reviewed-by: Gerd Hoffmann Link: https://lore.kernel.org/r/20220412212127.154182-2-dovmurik@linux.ibm.com Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index ccd4d3f91c98..771d4cd06b56 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -405,6 +405,7 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) #define LINUX_EFI_INITRD_MEDIA_GUID EFI_GUID(0x5568e427, 0x68fc, 0x4f3d, 0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68) #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) +#define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) @@ -596,6 +597,7 @@ extern struct efi { unsigned long tpm_log; /* TPM2 Event Log table */ unsigned long tpm_final_log; /* TPM2 Final Events Log table */ unsigned long mokvar_table; /* MOK variable config table */ + unsigned long coco_secret; /* Confidential computing secret table */ efi_get_time_t *get_time; efi_set_time_t *set_time; @@ -1335,4 +1337,12 @@ extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } #endif +struct linux_efi_coco_secret_area { + u64 base_pa; + u64 size; +}; + +/* Header of a populated EFI secret area */ +#define EFI_SECRET_TABLE_HEADER_GUID EFI_GUID(0x1e74f542, 0x71dd, 0x4d66, 0x96, 0x3e, 0xef, 0x42, 0x87, 0xff, 0x17, 0x3b) + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From aa480379d8bdb33920d68acfd90f823c8af32578 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Fri, 4 Mar 2022 07:36:37 +0100 Subject: efi: Add missing prototype for efi_capsule_setup_info Fixes "no previous declaration for 'efi_capsule_setup_info'" warnings under W=1. Fixes: 2959c95d510c ("efi/capsule: Add support for Quark security header") Signed-off-by: Jan Kiszka Link: https://lore.kernel.org/r/c28d3f86-dd72-27d1-e2c2-40971b8da6bd@siemens.com Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index 771d4cd06b56..fd266198f9d8 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -213,6 +213,8 @@ struct capsule_info { size_t page_bytes_remain; }; +int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, + size_t hdr_bytes); int __efi_capsule_setup_info(struct capsule_info *cap_info); /* -- cgit v1.2.3 From c24a950ec7d60c4da91dc3f273295c7f438b531e Mon Sep 17 00:00:00 2001 From: Peter Gonda Date: Thu, 7 Apr 2022 14:02:33 -0700 Subject: KVM, SEV: Add KVM_EXIT_SHUTDOWN metadata for SEV-ES If an SEV-ES guest requests termination, exit to userspace with KVM_EXIT_SYSTEM_EVENT and a dedicated SEV_TERM type instead of -EINVAL so that userspace can take appropriate action. See AMD's GHCB spec section '4.1.13 Termination Request' for more details. Suggested-by: Sean Christopherson Suggested-by: Paolo Bonzini Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Peter Gonda Reported-by: kernel test robot Message-Id: <20220407210233.782250-1-pgonda@google.com> [Add documentatino. - Paolo] Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 8616af85dc5d..dd1d8167e71f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -444,8 +444,11 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_SHUTDOWN 1 #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 +#define KVM_SYSTEM_EVENT_SEV_TERM 4 +#define KVM_SYSTEM_EVENT_NDATA_VALID (1u << 31) __u32 type; - __u64 flags; + __u32 ndata; + __u64 data[16]; } system_event; /* KVM_EXIT_S390_STSI */ struct { -- cgit v1.2.3 From 002752af7b89b74c64fe6bec8c5fde3d3a7810d8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 8 Apr 2022 21:48:40 +0300 Subject: device property: Allow error pointer to be passed to fwnode APIs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some of the fwnode APIs might return an error pointer instead of NULL or valid fwnode handle. The result of such API call may be considered optional and hence the test for it is usually done in a form of fwnode = fwnode_find_reference(...); if (IS_ERR(fwnode)) ...error handling... Nevertheless the resulting fwnode may have bumped the reference count and hence caller of the above API is obliged to call fwnode_handle_put(). Since fwnode may be not valid either as NULL or error pointer the check has to be performed there. This approach uglifies the code and adds a point of making a mistake, i.e. forgetting about error point case. To prevent this, allow an error pointer to be passed to the fwnode APIs. Fixes: 83b34afb6b79 ("device property: Introduce fwnode_find_reference()") Reported-by: Nuno Sá Tested-by: Nuno Sá Acked-by: Nuno Sá Reviewed-by: Sakari Ailus Reviewed-by: Heikki Krogerus Signed-off-by: Andy Shevchenko Tested-by: Michael Walle Signed-off-by: Rafael J. Wysocki --- include/linux/fwnode.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 6ab69871b06d..9a81c4410b9f 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -153,12 +153,12 @@ struct fwnode_operations { int (*add_links)(struct fwnode_handle *fwnode); }; -#define fwnode_has_op(fwnode, op) \ - ((fwnode) && (fwnode)->ops && (fwnode)->ops->op) +#define fwnode_has_op(fwnode, op) \ + (!IS_ERR_OR_NULL(fwnode) && (fwnode)->ops && (fwnode)->ops->op) + #define fwnode_call_int_op(fwnode, op, ...) \ - (fwnode ? (fwnode_has_op(fwnode, op) ? \ - (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \ - -EINVAL) + (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : (IS_ERR_OR_NULL(fwnode) ? -EINVAL : -ENXIO)) #define fwnode_call_bool_op(fwnode, op, ...) \ (fwnode_has_op(fwnode, op) ? \ -- cgit v1.2.3 From 87ffea09470d94c93dd6a5a22d4b2216b395d1ea Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 8 Apr 2022 21:48:41 +0300 Subject: device property: Introduce fwnode_for_each_parent_node() In a few cases the functionality of fwnode_for_each_parent_node() is already in use. Introduce a common helper macro for it. It may be used by others as well in the future. Signed-off-by: Andy Shevchenko Reviewed-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/property.h b/include/linux/property.h index 4cd4b326941f..15d6863ae962 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -83,9 +83,14 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, const char *fwnode_get_name(const struct fwnode_handle *fwnode); const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode); + struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); -struct fwnode_handle *fwnode_get_next_parent( - struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); + +#define fwnode_for_each_parent_node(fwnode, parent) \ + for (parent = fwnode_get_parent(fwnode); parent; \ + parent = fwnode_get_next_parent(parent)) + struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode); unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, -- cgit v1.2.3 From 022fe6bc8f3bd0f2b1f9bc778bacc38020dfd420 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 8 Apr 2022 21:48:42 +0300 Subject: device property: Drop 'test' prefix in parameters of fwnode_is_ancestor_of() The part 'is' in the function name implies the test against something. Drop unnecessary 'test' prefix in the fwnode_is_ancestor_of() parameters. No functional change intended. Signed-off-by: Andy Shevchenko Reviewed-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/property.h b/include/linux/property.h index 15d6863ae962..fc24d45632eb 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -95,8 +95,7 @@ struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode); unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, unsigned int depth); -bool fwnode_is_ancestor_of(struct fwnode_handle *test_ancestor, - struct fwnode_handle *test_child); +bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_child_node( const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_available_child_node( -- cgit v1.2.3 From 62b32fd961cf2d8b2c9fdcd8d58abeb184bb439b Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 11 Apr 2022 20:47:00 +0200 Subject: ACPICA: Add support for the Windows 11 _OSI string ACPICA commit f2e9fb8345b9146a67f8c63474b65ccfc06d962a See https://github.com/microsoft_docs/windows-driver-docs/commit/a061e31fd77c20cc8e6eb0234e5d3a83e417f48 Link: https://github.com/acpica/acpica/commit/f2e9fb83 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actypes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 02c1fa16e638..362037fc63a6 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -1303,6 +1303,7 @@ typedef enum { #define ACPI_OSI_WIN_10_RS5 0x13 #define ACPI_OSI_WIN_10_19H1 0x14 #define ACPI_OSI_WIN_10_20H1 0x15 +#define ACPI_OSI_WIN_11 0x16 /* Definitions of getopt */ -- cgit v1.2.3 From a95d2fb08538f29f6e9f54a803dffc303b5263cd Mon Sep 17 00:00:00 2001 From: Lawrence Hileman Date: Mon, 11 Apr 2022 20:47:40 +0200 Subject: ACPICA: Add the subtable CFMWS to the CEDT table ACPICA commit 19b11f91660b1a38a8e9655b0b1a4ad51ec4db1e Link: https://github.com/acpica/acpica/commit/19b11f91 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl1.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 159070edd031..0ccda7b7814d 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -373,6 +373,10 @@ struct acpi_cedt_cfmws { u32 interleave_targets[]; }; +struct acpi_cedt_cfmws_target_element { + u32 interleave_target; +}; + /* Values for Interleave Arithmetic field above */ #define ACPI_CEDT_CFMWS_ARITHMETIC_MODULO (0) -- cgit v1.2.3 From 90037551c68d08facd6fb56a971352a9cd189c44 Mon Sep 17 00:00:00 2001 From: Piotr Maziarz Date: Mon, 11 Apr 2022 20:48:21 +0200 Subject: ACPICA: iASL: NHLT: Treat Terminator as specific_config ACPICA commit 23a659e190cf3ed0edd46cddf12bbbcfeaa09396 specific_config has 4 bytes of size and then an amount of bytes specified by size. All of the terminators that I've seen had a size equal to 4, but theoretically it can vary. Link: https://github.com/acpica/acpica/commit/23a659e1 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 16847c8d9d5f..a57853f2bb0b 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -1689,11 +1689,6 @@ struct acpi_nhlt_linux_specific_data_b { u8 specific_data[18]; }; -struct acpi_nhlt_table_terminator { - u32 terminator_value; - u32 terminator_signature; -}; - /******************************************************************************* * * PCCT - Platform Communications Channel Table (ACPI 5.0) -- cgit v1.2.3 From ab1ba87bd71a507286781b8a7f5c64e1eb7a2d34 Mon Sep 17 00:00:00 2001 From: Piotr Maziarz Date: Mon, 11 Apr 2022 20:49:08 +0200 Subject: ACPICA: iASL: NHLT: Fix parsing undocumented bytes at the end of Endpoint Descriptor ACPICA commit 961221a76814ffa0ecc92219ddf857579b0f7d54 Undocumented bytes at the end of Endpoint Descriptor can be present independently of Linux-specific structures. Their size can also vary. Link: https://github.com/acpica/acpica/commit/961221a7 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index a57853f2bb0b..757db244e220 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -1685,10 +1685,6 @@ struct acpi_nhlt_linux_specific_data { u8 device_port_id; }; -struct acpi_nhlt_linux_specific_data_b { - u8 specific_data[18]; -}; - /******************************************************************************* * * PCCT - Platform Communications Channel Table (ACPI 5.0) -- cgit v1.2.3 From 8bd24835db1781685f9abd0d1b628eaaac20d7c1 Mon Sep 17 00:00:00 2001 From: Piotr Maziarz Date: Mon, 11 Apr 2022 20:50:25 +0200 Subject: ACPICA: iASL: NHLT: Rename linux specific strucures to device_info ACPICA commit 68c7e542075319d57129467872fcbe98906f2b2c Those structures aren't used by Linux drivers, and in other NHLT related tools they are called device_info. Link: https://github.com/acpica/acpica/commit/68c7e542 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 757db244e220..fe6d01aedb1f 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -1673,13 +1673,13 @@ struct acpi_nhlt_render_feedback_device_specific_config { u16 feedback_valid_bits_per_sample; }; -/* Linux-specific structures */ +/* Non documented structures */ -struct acpi_nhlt_linux_specific_count { +struct acpi_nhlt_device_info_count { u8 structure_count; }; -struct acpi_nhlt_linux_specific_data { +struct acpi_nhlt_device_info { u8 device_id[16]; u8 device_instance_id; u8 device_port_id; -- cgit v1.2.3 From 487ea80a2848b7147eede3b73a4ee160c150f567 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Mon, 11 Apr 2022 20:54:22 +0200 Subject: ACPICA: Update copyright notices to the year 2022 ACPICA commit 738d7b0726e6c0458ef93c0a01c0377490888d1e Affects all source modules and utility signons. Link: https://github.com/acpica/acpica/commit/738d7b07 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/acbuffer.h | 2 +- include/acpi/acconfig.h | 2 +- include/acpi/acexcep.h | 2 +- include/acpi/acnames.h | 2 +- include/acpi/acoutput.h | 2 +- include/acpi/acpi.h | 2 +- include/acpi/acpiosxf.h | 2 +- include/acpi/acpixf.h | 2 +- include/acpi/acrestyp.h | 2 +- include/acpi/actbl.h | 2 +- include/acpi/actbl1.h | 2 +- include/acpi/actbl2.h | 2 +- include/acpi/actbl3.h | 2 +- include/acpi/actypes.h | 2 +- include/acpi/acuuid.h | 2 +- include/acpi/platform/acenv.h | 2 +- include/acpi/platform/acenvex.h | 2 +- include/acpi/platform/acgcc.h | 2 +- include/acpi/platform/acgccex.h | 2 +- include/acpi/platform/acintel.h | 2 +- include/acpi/platform/aclinux.h | 2 +- include/acpi/platform/aclinuxex.h | 2 +- 22 files changed, 22 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/acpi/acbuffer.h b/include/acpi/acbuffer.h index 3e8d969b22fe..8cbfcbca7b7e 100644 --- a/include/acpi/acbuffer.h +++ b/include/acpi/acbuffer.h @@ -3,7 +3,7 @@ * * Name: acbuffer.h - Support for buffers returned by ACPI predefined names * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h index 0362cbb72359..c3ae3ea88e17 100644 --- a/include/acpi/acconfig.h +++ b/include/acpi/acconfig.h @@ -3,7 +3,7 @@ * * Name: acconfig.h - Global configuration constants * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h index ea3b1c41bc79..28943c900be7 100644 --- a/include/acpi/acexcep.h +++ b/include/acpi/acexcep.h @@ -3,7 +3,7 @@ * * Name: acexcep.h - Exception codes returned by the ACPI subsystem * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h index 30869ab77fba..6f22e92b1744 100644 --- a/include/acpi/acnames.h +++ b/include/acpi/acnames.h @@ -3,7 +3,7 @@ * * Name: acnames.h - Global names and strings * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h index 5a3875744678..73781aae2119 100644 --- a/include/acpi/acoutput.h +++ b/include/acpi/acoutput.h @@ -3,7 +3,7 @@ * * Name: acoutput.h -- debug output * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpi.h b/include/acpi/acpi.h index 6f6282a862bc..416e59bcf149 100644 --- a/include/acpi/acpi.h +++ b/include/acpi/acpi.h @@ -3,7 +3,7 @@ * * Name: acpi.h - Master public include file used to interface to ACPICA * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h index 690c369b717a..52844cc5eeb5 100644 --- a/include/acpi/acpiosxf.h +++ b/include/acpi/acpiosxf.h @@ -5,7 +5,7 @@ * interfaces must be implemented by OSL to interface the * ACPI components to the host operating system. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 7417731472b7..56362c419cd4 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -3,7 +3,7 @@ * * Name: acpixf.h - External interfaces to the ACPI subsystem * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acrestyp.h b/include/acpi/acrestyp.h index 8e2319bbd0a2..a7fb8ddb3dc6 100644 --- a/include/acpi/acrestyp.h +++ b/include/acpi/acrestyp.h @@ -3,7 +3,7 @@ * * Name: acrestyp.h - Defines, types, and structures for resource descriptors * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h index f9cda909f92c..c6af579f74f4 100644 --- a/include/acpi/actbl.h +++ b/include/acpi/actbl.h @@ -3,7 +3,7 @@ * * Name: actbl.h - Basic ACPI Table Definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 0ccda7b7814d..9f1acc6ff15b 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -3,7 +3,7 @@ * * Name: actbl1.h - Additional ACPI table definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index fe6d01aedb1f..6db7525588c5 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -3,7 +3,7 @@ * * Name: actbl2.h - ACPI Table Definitions (tables not in ACPI spec) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h index edbf1ad8206d..7b9571e00cc4 100644 --- a/include/acpi/actbl3.h +++ b/include/acpi/actbl3.h @@ -3,7 +3,7 @@ * * Name: actbl3.h - ACPI Table Definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 362037fc63a6..d62f36bc90b2 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -3,7 +3,7 @@ * * Name: actypes.h - Common data types for the entire ACPI subsystem * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acuuid.h b/include/acpi/acuuid.h index bc24388ce94e..8f1e7c489df5 100644 --- a/include/acpi/acuuid.h +++ b/include/acpi/acuuid.h @@ -3,7 +3,7 @@ * * Name: acuuid.h - ACPI-related UUID/GUID definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h index e8958e0d1646..03eb3d977075 100644 --- a/include/acpi/platform/acenv.h +++ b/include/acpi/platform/acenv.h @@ -3,7 +3,7 @@ * * Name: acenv.h - Host and compiler configuration * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h index 277fe2fa4d9b..3a6b1db9a984 100644 --- a/include/acpi/platform/acenvex.h +++ b/include/acpi/platform/acenvex.h @@ -3,7 +3,7 @@ * * Name: acenvex.h - Extra host and compiler configuration * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h index 33ad282bd338..ac80111f503c 100644 --- a/include/acpi/platform/acgcc.h +++ b/include/acpi/platform/acgcc.h @@ -3,7 +3,7 @@ * * Name: acgcc.h - GCC specific defines, etc. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acgccex.h b/include/acpi/platform/acgccex.h index 738d52865e0a..302ea1b724b9 100644 --- a/include/acpi/platform/acgccex.h +++ b/include/acpi/platform/acgccex.h @@ -3,7 +3,7 @@ * * Name: acgccex.h - Extra GCC specific defines, etc. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acintel.h b/include/acpi/platform/acintel.h index 550fe9a8cd6c..85b1ae86ee63 100644 --- a/include/acpi/platform/acintel.h +++ b/include/acpi/platform/acintel.h @@ -3,7 +3,7 @@ * * Name: acintel.h - VC specific defines, etc. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index cec41e004ecf..a5550dd4d507 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -3,7 +3,7 @@ * * Name: aclinux.h - OS specific defines, etc. for Linux * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h index 5f642b07ad64..28c72744decf 100644 --- a/include/acpi/platform/aclinuxex.h +++ b/include/acpi/platform/aclinuxex.h @@ -3,7 +3,7 @@ * * Name: aclinuxex.h - Extra OS specific defines, etc. for Linux * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ -- cgit v1.2.3 From 45882a817d4bae5a3b63c3861cb62b9b9a025de5 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Mon, 11 Apr 2022 20:55:10 +0200 Subject: ACPICA: Removed some tabs and // comments ACPICA commit 0914618b553d6f3366e568409cebf2656891ca69 Automated cleanup; No functional changes. Link: https://github.com/acpica/acpica/commit/0914618b Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl1.h | 12 ++++++------ include/acpi/actbl2.h | 40 ++++++++++++++++++++-------------------- include/acpi/actypes.h | 16 ++++++++-------- 3 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 9f1acc6ff15b..15c78678c5d3 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -379,15 +379,15 @@ struct acpi_cedt_cfmws_target_element { /* Values for Interleave Arithmetic field above */ -#define ACPI_CEDT_CFMWS_ARITHMETIC_MODULO (0) +#define ACPI_CEDT_CFMWS_ARITHMETIC_MODULO (0) /* Values for Restrictions field above */ -#define ACPI_CEDT_CFMWS_RESTRICT_TYPE2 (1) -#define ACPI_CEDT_CFMWS_RESTRICT_TYPE3 (1<<1) -#define ACPI_CEDT_CFMWS_RESTRICT_VOLATILE (1<<2) -#define ACPI_CEDT_CFMWS_RESTRICT_PMEM (1<<3) -#define ACPI_CEDT_CFMWS_RESTRICT_FIXED (1<<4) +#define ACPI_CEDT_CFMWS_RESTRICT_TYPE2 (1) +#define ACPI_CEDT_CFMWS_RESTRICT_TYPE3 (1<<1) +#define ACPI_CEDT_CFMWS_RESTRICT_VOLATILE (1<<2) +#define ACPI_CEDT_CFMWS_RESTRICT_PMEM (1<<3) +#define ACPI_CEDT_CFMWS_RESTRICT_FIXED (1<<4) /******************************************************************************* * diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 6db7525588c5..fda066de5764 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -978,8 +978,8 @@ struct acpi_madt_multiproc_wakeup { u64 base_address; }; -#define ACPI_MULTIPROC_WAKEUP_MB_OS_SIZE 2032 -#define ACPI_MULTIPROC_WAKEUP_MB_FIRMWARE_SIZE 2048 +#define ACPI_MULTIPROC_WAKEUP_MB_OS_SIZE 2032 +#define ACPI_MULTIPROC_WAKEUP_MB_FIRMWARE_SIZE 2048 struct acpi_madt_multiproc_wakeup_mailbox { u16 command; @@ -1597,7 +1597,7 @@ struct acpi_nhlt_mic_device_specific_config { /* Values for array_type_ext above */ -#define ACPI_NHLT_ARRAY_TYPE_RESERVED 0x09 // 9 and below are reserved +#define ACPI_NHLT_ARRAY_TYPE_RESERVED 0x09 /* 9 and below are reserved */ #define ACPI_NHLT_SMALL_LINEAR_2ELEMENT 0x0A #define ACPI_NHLT_BIG_LINEAR_2ELEMENT 0x0B #define ACPI_NHLT_FIRST_GEOMETRY_LINEAR_4ELEMENT 0x0C @@ -1617,17 +1617,17 @@ struct acpi_nhlt_vendor_mic_count { struct acpi_nhlt_vendor_mic_config { u8 type; u8 panel; - u16 speaker_position_distance; // mm - u16 horizontal_offset; // mm - u16 vertical_offset; // mm - u8 frequency_low_band; // 5*hz - u8 frequency_high_band; // 500*hz - u16 direction_angle; // -180 - + 180 - u16 elevation_angle; // -180 - + 180 - u16 work_vertical_angle_begin; // -180 - + 180 with 2 deg step - u16 work_vertical_angle_end; // -180 - + 180 with 2 deg step - u16 work_horizontal_angle_begin; // -180 - + 180 with 2 deg step - u16 work_horizontal_angle_end; // -180 - + 180 with 2 deg step + u16 speaker_position_distance; /* mm */ + u16 horizontal_offset; /* mm */ + u16 vertical_offset; /* mm */ + u8 frequency_low_band; /* 5*Hz */ + u8 frequency_high_band; /* 500*Hz */ + u16 direction_angle; /* -180 - + 180 */ + u16 elevation_angle; /* -180 - + 180 */ + u16 work_vertical_angle_begin; /* -180 - + 180 with 2 deg step */ + u16 work_vertical_angle_end; /* -180 - + 180 with 2 deg step */ + u16 work_horizontal_angle_begin; /* -180 - + 180 with 2 deg step */ + u16 work_horizontal_angle_end; /* -180 - + 180 with 2 deg step */ }; /* Values for Type field above */ @@ -1638,9 +1638,9 @@ struct acpi_nhlt_vendor_mic_config { #define ACPI_NHLT_MIC_SUPER_CARDIOID 3 #define ACPI_NHLT_MIC_HYPER_CARDIOID 4 #define ACPI_NHLT_MIC_8_SHAPED 5 -#define ACPI_NHLT_MIC_RESERVED6 6 // 6 is reserved +#define ACPI_NHLT_MIC_RESERVED6 6 /* 6 is reserved */ #define ACPI_NHLT_MIC_VENDOR_DEFINED 7 -#define ACPI_NHLT_MIC_RESERVED 8 // 8 and above are reserved +#define ACPI_NHLT_MIC_RESERVED 8 /* 8 and above are reserved */ /* Values for Panel field above */ @@ -1650,12 +1650,12 @@ struct acpi_nhlt_vendor_mic_config { #define ACPI_NHLT_MIC_POSITION_RIGHT 3 #define ACPI_NHLT_MIC_POSITION_FRONT 4 #define ACPI_NHLT_MIC_POSITION_BACK 5 -#define ACPI_NHLT_MIC_POSITION_RESERVED 6 // 6 and above are reserved +#define ACPI_NHLT_MIC_POSITION_RESERVED 6 /* 6 and above are reserved */ struct acpi_nhlt_vendor_mic_device_specific_config { struct acpi_nhlt_mic_device_specific_config mic_array_device_config; u8 number_of_microphones; - struct acpi_nhlt_vendor_mic_config mic_config[]; // indexed by number_of_microphones + struct acpi_nhlt_vendor_mic_config mic_config[]; /* Indexed by number_of_microphones */ }; /* Microphone SNR and Sensitivity extension */ @@ -1668,8 +1668,8 @@ struct acpi_nhlt_mic_snr_sensitivity_extension { /* Render device with feedback */ struct acpi_nhlt_render_feedback_device_specific_config { - u8 feedback_virtual_slot; // render slot in case of capture - u16 feedback_channels; // informative only + u8 feedback_virtual_slot; /* Render slot in case of capture */ + u16 feedback_channels; /* Informative only */ u16 feedback_valid_bits_per_sample; }; diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index d62f36bc90b2..3491e454b2ab 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -539,14 +539,14 @@ typedef u64 acpi_integer; * Can be used with access_width of struct acpi_generic_address and access_size of * struct acpi_resource_generic_register. */ -#define ACPI_ACCESS_BIT_SHIFT 2 -#define ACPI_ACCESS_BYTE_SHIFT -1 -#define ACPI_ACCESS_BIT_MAX (31 - ACPI_ACCESS_BIT_SHIFT) -#define ACPI_ACCESS_BYTE_MAX (31 - ACPI_ACCESS_BYTE_SHIFT) -#define ACPI_ACCESS_BIT_DEFAULT (8 - ACPI_ACCESS_BIT_SHIFT) -#define ACPI_ACCESS_BYTE_DEFAULT (8 - ACPI_ACCESS_BYTE_SHIFT) -#define ACPI_ACCESS_BIT_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BIT_SHIFT)) -#define ACPI_ACCESS_BYTE_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BYTE_SHIFT)) +#define ACPI_ACCESS_BIT_SHIFT 2 +#define ACPI_ACCESS_BYTE_SHIFT -1 +#define ACPI_ACCESS_BIT_MAX (31 - ACPI_ACCESS_BIT_SHIFT) +#define ACPI_ACCESS_BYTE_MAX (31 - ACPI_ACCESS_BYTE_SHIFT) +#define ACPI_ACCESS_BIT_DEFAULT (8 - ACPI_ACCESS_BIT_SHIFT) +#define ACPI_ACCESS_BYTE_DEFAULT (8 - ACPI_ACCESS_BYTE_SHIFT) +#define ACPI_ACCESS_BIT_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BIT_SHIFT)) +#define ACPI_ACCESS_BYTE_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BYTE_SHIFT)) /******************************************************************************* * -- cgit v1.2.3 From aa29b2083e11722a0ceedfa2a87de74cc7cfa676 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 11 Apr 2022 20:56:15 +0200 Subject: ACPICA: Headers: Replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ACPICA commit 98835f452c698b015d4da999944405ecb90da670 There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.16/process/deprecated.html#zero-length-and-one-element-arrays Link: https://github.com/acpica/acpica/commit/98835f45 Link: https://github.com/KSPP/linux/issues/78 Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: Rafael J. Wysocki Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index fda066de5764..3e92d15a0cd6 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -2310,7 +2310,7 @@ struct acpi_table_rgrt { u16 version; u8 image_type; u8 reserved; - u8 image[0]; + u8 image[]; }; /* image_type values */ -- cgit v1.2.3 From 1c5d62f5dd979dbe7f4b16a5bd3c64fbecb7d92a Mon Sep 17 00:00:00 2001 From: Besar Wicaksono Date: Mon, 11 Apr 2022 20:58:04 +0200 Subject: ACPICA: Add support for ARM Performance Monitoring Unit Table. ACPICA commit 002165ecc0a3dc703bb24c789aaa02fdada01675 The specification of this table is described in "ARM Performance Monitoring Unit Architecture 1.0 Platform Design Document" ARM DEN0117. This patch adds the necessary types and support for compiling/disassembling APMT. Link: https://github.com/acpica/acpica/commit/002165ec Signed-off-by: Besar Wicaksono Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 80 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 3e92d15a0cd6..8298b106aa40 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -25,6 +25,7 @@ * the wrong signature. */ #define ACPI_SIG_AGDI "AGDI" /* Arm Generic Diagnostic Dump and Reset Device Interface */ +#define ACPI_SIG_APMT "APMT" /* Arm Performance Monitoring Unit table */ #define ACPI_SIG_BDAT "BDAT" /* BIOS Data ACPI Table */ #define ACPI_SIG_IORT "IORT" /* IO Remapping Table */ #define ACPI_SIG_IVRS "IVRS" /* I/O Virtualization Reporting Structure */ @@ -258,6 +259,85 @@ struct acpi_table_agdi { #define ACPI_AGDI_SIGNALING_MODE (1) +/******************************************************************************* + * + * APMT - ARM Performance Monitoring Unit Table + * + * Conforms to: + * ARM Performance Monitoring Unit Architecture 1.0 Platform Design Document + * ARM DEN0117 v1.0 November 25, 2021 + * + ******************************************************************************/ + +struct acpi_table_apmt { + struct acpi_table_header header; /* Common ACPI table header */ +}; + +#define ACPI_APMT_NODE_ID_LENGTH 4 + +/* + * APMT subtables + */ +struct acpi_apmt_node { + u16 length; + u8 flags; + u8 type; + u32 id; + u64 inst_primary; + u32 inst_secondary; + u64 base_address0; + u64 base_address1; + u32 ovflw_irq; + u32 reserved; + u32 ovflw_irq_flags; + u32 proc_affinity; + u32 impl_id; +}; + +/* Masks for Flags field above */ + +#define ACPI_APMT_FLAGS_DUAL_PAGE (1<<0) +#define ACPI_APMT_FLAGS_AFFINITY (1<<1) +#define ACPI_APMT_FLAGS_ATOMIC (1<<2) + +/* Values for Flags dual page field above */ + +#define ACPI_APMT_FLAGS_DUAL_PAGE_NSUPP (0<<0) +#define ACPI_APMT_FLAGS_DUAL_PAGE_SUPP (1<<0) + +/* Values for Flags processor affinity field above */ +#define ACPI_APMT_FLAGS_AFFINITY_PROC (0<<1) +#define ACPI_APMT_FLAGS_AFFINITY_PROC_CONTAINER (1<<1) + +/* Values for Flags 64-bit atomic field above */ +#define ACPI_APMT_FLAGS_ATOMIC_NSUPP (0<<2) +#define ACPI_APMT_FLAGS_ATOMIC_SUPP (1<<2) + +/* Values for Type field above */ + +enum acpi_apmt_node_type { + ACPI_APMT_NODE_TYPE_MC = 0x00, + ACPI_APMT_NODE_TYPE_SMMU = 0x01, + ACPI_APMT_NODE_TYPE_PCIE_ROOT = 0x02, + ACPI_APMT_NODE_TYPE_ACPI = 0x03, + ACPI_APMT_NODE_TYPE_CACHE = 0x04, + ACPI_APMT_NODE_TYPE_COUNT +}; + +/* Masks for ovflw_irq_flags field above */ + +#define ACPI_APMT_OVFLW_IRQ_FLAGS_MODE (1<<0) +#define ACPI_APMT_OVFLW_IRQ_FLAGS_TYPE (1<<1) + +/* Values for ovflw_irq_flags mode field above */ + +#define ACPI_APMT_OVFLW_IRQ_FLAGS_MODE_LEVEL (0<<0) +#define ACPI_APMT_OVFLW_IRQ_FLAGS_MODE_EDGE (1<<0) + +/* Values for ovflw_irq_flags type field above */ + +#define ACPI_APMT_OVFLW_IRQ_FLAGS_TYPE_WIRED (0<<1) + /******************************************************************************* * * BDAT - BIOS Data ACPI Table -- cgit v1.2.3 From da6a9bbedc79c49ba94a6ca746580a9b43931641 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Mon, 11 Apr 2022 21:00:45 +0200 Subject: ACPICA: iASL/MADT: Add OEM-defined subtable ACPICA commit 4450b89b596a2b54b0cdfe2357b49a63445c2e03 Adds support for the "reserved for OEM use" subtable (types 0x80 to 0xFF). Link: https://github.com/acpica/acpica/commit/4450b89b Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 8298b106aa40..42b5753dd78c 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -842,7 +842,8 @@ enum acpi_madt_type { ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR = 14, ACPI_MADT_TYPE_GENERIC_TRANSLATOR = 15, ACPI_MADT_TYPE_MULTIPROC_WAKEUP = 16, - ACPI_MADT_TYPE_RESERVED = 17 /* 17 and greater are reserved */ + ACPI_MADT_TYPE_RESERVED = 17, /* 17 to 0x7F are reserved */ + ACPI_MADT_TYPE_OEM_RESERVED = 0x80 /* 0x80 to 0xFF are reserved for OEM use */ }; /* @@ -1072,6 +1073,12 @@ struct acpi_madt_multiproc_wakeup_mailbox { #define ACPI_MP_WAKE_COMMAND_WAKEUP 1 +/* 17: OEM data */ + +struct acpi_madt_oem_data { + u8 oem_data[0]; +}; + /* * Common flags fields for MADT subtables */ -- cgit v1.2.3 From 4fd147530edd44439a099dda6b22f1a390f306ab Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Mon, 11 Apr 2022 21:02:33 +0200 Subject: ACPICA: IORT: Updates for revision E.d ACPICA commit 87a2e39b8abdfedfb86b0a105708e37e895becd9 IORT revision is now updated to E.d (ARM DEN 0049E.d) and contains a few additions like, -Added descriptor in the root complex node for specifying PASID width supported by the root complex. -Updated RMR node Flags field. -Introduced memory access attributes in the RMR node. Please note that IORT Rev E.c is deprecated and not supported. Link: https://github.com/acpica/acpica/commit/87a2e39b Signed-off-by: Shameer Kolothum Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 42b5753dd78c..655102bc6d14 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -357,7 +357,7 @@ struct acpi_table_bdat { * IORT - IO Remapping Table * * Conforms to "IO Remapping Table System Software on ARM Platforms", - * Document number: ARM DEN 0049E.b, Feb 2021 + * Document number: ARM DEN 0049E.d, Feb 2022 * ******************************************************************************/ @@ -454,7 +454,8 @@ struct acpi_iort_root_complex { u32 ats_attribute; u32 pci_segment_number; u8 memory_address_limit; /* Memory address size limit */ - u8 reserved[3]; /* Reserved, must be zero */ + u16 pasid_capabilities; /* PASID Capabilities */ + u8 reserved[1]; /* Reserved, must be zero */ }; /* Masks for ats_attribute field above */ @@ -463,6 +464,9 @@ struct acpi_iort_root_complex { #define ACPI_IORT_PRI_SUPPORTED (1<<1) /* The root complex PRI support */ #define ACPI_IORT_PASID_FWD_SUPPORTED (1<<2) /* The root complex PASID forward support */ +/* Masks for pasid_capabilities field above */ +#define ACPI_IORT_PASID_MAX_WIDTH (0x1F) /* Bits 0-4 */ + struct acpi_iort_smmu { u64 base_address; /* SMMU base address */ u64 span; /* Length of memory range */ @@ -538,6 +542,25 @@ struct acpi_iort_rmr { u32 rmr_offset; }; +/* Masks for Flags field above */ +#define ACPI_IORT_RMR_REMAP_PERMITTED (1) +#define ACPI_IORT_RMR_ACCESS_PRIVILEGE (1<<1) + +/* + * Macro to access the Access Attributes in flags field above: + * Access Attributes is encoded in bits 9:2 + */ +#define ACPI_IORT_RMR_ACCESS_ATTRIBUTES(flags) (((flags) >> 2) & 0xFF) + +/* Values for above Access Attributes */ + +#define ACPI_IORT_RMR_ATTR_DEVICE_NGNRNE 0x00 +#define ACPI_IORT_RMR_ATTR_DEVICE_NGNRE 0x01 +#define ACPI_IORT_RMR_ATTR_DEVICE_NGRE 0x02 +#define ACPI_IORT_RMR_ATTR_DEVICE_GRE 0x03 +#define ACPI_IORT_RMR_ATTR_NORMAL_NC 0x04 +#define ACPI_IORT_RMR_ATTR_NORMAL_IWB_OWB 0x05 + struct acpi_iort_rmr_desc { u64 base_address; u64 length; -- cgit v1.2.3 From 0076ca940e3f1a1eae6b5e39b6594c96934713a2 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Mon, 11 Apr 2022 21:04:03 +0200 Subject: ACPICA: Update version to 20220331 ACPICA commit ada5b805eaa7480930082af9bc3d689c6f181329 Version 20220331. Link: https://github.com/acpica/acpica/commit/ada5b805 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/acpixf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 56362c419cd4..67c0b9e734b6 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -12,7 +12,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20211217 +#define ACPI_CA_VERSION 0x20220331 #include #include -- cgit v1.2.3 From a090931524d03a4975c84b89a32210420d852313 Mon Sep 17 00:00:00 2001 From: Liu Xinpeng Date: Tue, 12 Apr 2022 11:05:19 +0800 Subject: ACPI: APEI: Fix missing ERST record id Read a record is cleared by others, but the deleted record cache entry is still created by erst_get_record_id_next. When next enumerate the records, get the cached deleted record, then erst_read() return -ENOENT and try to get next record, loop back to first ID will return 0 in function __erst_record_id_cache_add_one and then set record_id as APEI_ERST_INVALID_RECORD_ID, finished this time read operation. It will result in read the records just in the cache hereafter. This patch cleared the deleted record cache, fix the issue that "./erst-inject -p" shows record counts not equal to "./erst-inject -n". A reproducer of the problem(retry many times): [root@localhost erst-inject]# ./erst-inject -c 0xaaaaa00011 [root@localhost erst-inject]# ./erst-inject -p rc: 273 rcd sig: CPER rcd id: 0xaaaaa00012 rc: 273 rcd sig: CPER rcd id: 0xaaaaa00013 rc: 273 rcd sig: CPER rcd id: 0xaaaaa00014 [root@localhost erst-inject]# ./erst-inject -i 0xaaaaa000006 [root@localhost erst-inject]# ./erst-inject -i 0xaaaaa000007 [root@localhost erst-inject]# ./erst-inject -i 0xaaaaa000008 [root@localhost erst-inject]# ./erst-inject -p rc: 273 rcd sig: CPER rcd id: 0xaaaaa00012 rc: 273 rcd sig: CPER rcd id: 0xaaaaa00013 rc: 273 rcd sig: CPER rcd id: 0xaaaaa00014 [root@localhost erst-inject]# ./erst-inject -n total error record count: 6 Signed-off-by: Liu Xinpeng Reviewed-by: Tony Luck Signed-off-by: Rafael J. Wysocki --- include/acpi/apei.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/acpi/apei.h b/include/acpi/apei.h index afaca3a075e8..dc60f7db5524 100644 --- a/include/acpi/apei.h +++ b/include/acpi/apei.h @@ -46,6 +46,8 @@ int erst_get_record_id_next(int *pos, u64 *record_id); void erst_get_record_id_end(void); ssize_t erst_read(u64 record_id, struct cper_record_header *record, size_t buflen); +ssize_t erst_read_record(u64 record_id, struct cper_record_header *record, + size_t buflen, size_t recordlen, const guid_t *creatorid); int erst_clear(u64 record_id); int arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, void *data); -- cgit v1.2.3 From 4e140f59d285c1ca1e5c81b4c13e27366865bd09 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 10 Jan 2022 23:15:27 +0000 Subject: mm/usercopy: Check kmap addresses properly If you are copying to an address in the kmap region, you may not copy across a page boundary, no matter what the size of the underlying allocation. You can't kmap() a slab page because slab pages always come from low memory. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220110231530.665970-2-willy@infradead.org --- include/linux/highmem-internal.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index a77be5630209..337bd9f32921 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -149,6 +149,11 @@ static inline void totalhigh_pages_add(long count) atomic_long_add(count, &_totalhigh_pages); } +static inline bool is_kmap_addr(const void *x) +{ + unsigned long addr = (unsigned long)x; + return addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP); +} #else /* CONFIG_HIGHMEM */ static inline struct page *kmap_to_page(void *addr) @@ -234,6 +239,11 @@ static inline void __kunmap_atomic(void *addr) static inline unsigned int nr_free_highpages(void) { return 0; } static inline unsigned long totalhigh_pages(void) { return 0UL; } +static inline bool is_kmap_addr(const void *x) +{ + return false; +} + #endif /* CONFIG_HIGHMEM */ /* -- cgit v1.2.3 From e6f3b3c9c109ed57230996cf4a4c1b8ae7e36a81 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Tue, 5 Apr 2022 15:16:18 -0700 Subject: cfi: Use __builtin_function_start Clang 14 added support for the __builtin_function_start function, which allows us to implement the function_nocfi macro without architecture-specific inline assembly and in a way that also works with static initializers. Change CONFIG_CFI_CLANG to depend on Clang >= 14, define function_nocfi using __builtin_function_start, and remove the arm64 inline assembly implementation. Link: https://github.com/llvm/llvm-project/commit/ec2e26eaf63558934f5b73a6e530edc453cf9508 Link: https://github.com/ClangBuiltLinux/linux/issues/1353 Signed-off-by: Sami Tolvanen Reviewed-by: Nick Desaulniers Reviewed-by: Mark Rutland Tested-by: Mark Rutland Acked-by: Will Deacon # arm64 Reviewed-by: Nathan Chancellor Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220405221618.633743-1-samitolvanen@google.com --- include/linux/compiler-clang.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index babb1347148c..c84fec767445 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -69,6 +69,16 @@ #define __nocfi __attribute__((__no_sanitize__("cfi"))) #define __cficanonical __attribute__((__cfi_canonical_jump_table__)) +#if defined(CONFIG_CFI_CLANG) +/* + * With CONFIG_CFI_CLANG, the compiler replaces function address + * references with the address of the function's CFI jump table + * entry. The function_nocfi macro always returns the address of the + * actual function instead. + */ +#define function_nocfi(x) __builtin_function_start(x) +#endif + /* * Turn individual warnings and errors on and off locally, depending * on version. -- cgit v1.2.3 From 63cec1389e116ae0e2a15e612a5b49651e04be3f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 4 Apr 2022 18:09:14 -0700 Subject: fscrypt: split up FS_CRYPTO_BLOCK_SIZE FS_CRYPTO_BLOCK_SIZE is neither the filesystem block size nor the granularity of encryption. Rather, it defines two logically separate constraints that both arise from the block size of the AES cipher: - The alignment required for the lengths of file contents blocks - The minimum input/output length for the filenames encryption modes Since there are way too many things called the "block size", and the connection with the AES block size is not easily understood, split FS_CRYPTO_BLOCK_SIZE into two constants FSCRYPT_CONTENTS_ALIGNMENT and FSCRYPT_FNAME_MIN_MSG_LEN that more clearly describe what they are. Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20220405010914.18519-1-ebiggers@kernel.org --- include/linux/fscrypt.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 50d92d805bd8..efc7f96e5e26 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -18,7 +18,17 @@ #include #include -#define FS_CRYPTO_BLOCK_SIZE 16 +/* + * The lengths of all file contents blocks must be divisible by this value. + * This is needed to ensure that all contents encryption modes will work, as + * some of the supported modes don't support arbitrarily byte-aligned messages. + * + * Since the needed alignment is 16 bytes, most filesystems will meet this + * requirement naturally, as typical block sizes are powers of 2. However, if a + * filesystem can generate arbitrarily byte-aligned block lengths (e.g., via + * compression), then it will need to pad to this alignment before encryption. + */ +#define FSCRYPT_CONTENTS_ALIGNMENT 16 union fscrypt_policy; struct fscrypt_info; -- cgit v1.2.3 From 9554e908fb5d02e48a681d1eca180225bf109e83 Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Fri, 25 Mar 2022 11:39:51 -0400 Subject: ELF: Remove elf_core_copy_kernel_regs() x86-32 was the last architecture that implemented separate user and kernel registers. Signed-off-by: Brian Gerst Signed-off-by: Borislav Petkov Reviewed-by: Thomas Gleixner Acked-by: Andy Lutomirski Acked-by: Michael Ellerman Link: https://lore.kernel.org/r/20220325153953.162643-3-brgerst@gmail.com --- include/linux/elfcore.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index f8e206e82476..346a8b56cdc8 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -84,15 +84,6 @@ static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *re #endif } -static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_regs *regs) -{ -#ifdef ELF_CORE_COPY_KERNEL_REGS - ELF_CORE_COPY_KERNEL_REGS((*elfregs), regs); -#else - elf_core_copy_regs(elfregs, regs); -#endif -} - static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs) { #if defined (ELF_CORE_COPY_TASK_REGS) -- cgit v1.2.3 From 64b97df995f0c943be469a019d6117c89e2131bc Mon Sep 17 00:00:00 2001 From: Lech Perczak Date: Wed, 13 Apr 2022 03:44:14 +0200 Subject: cdc_ether: export usbnet_cdc_zte_rx_fixup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit bfe9b9d2df66 ("cdc_ether: Improve ZTE MF823/831/910 handling") introduces a workaround for certain ZTE modems reporting invalid MAC addresses over CDC-ECM. The same issue was present on their RNDIS interface,which was fixed in commit a5a18bdf7453 ("rndis_host: Set valid random MAC on buggy devices"). However, internal modem of ZTE MF286R router, on its RNDIS interface, also exhibits a second issue fixed already in CDC-ECM, of the device not respecting configured random MAC address. In order to share the fixup for this with rndis_host driver, export the workaround function, which will be re-used in the following commit in rndis_host. Cc: Kristian Evensen Cc: Bjørn Mork Cc: Oliver Neukum Signed-off-by: Lech Perczak Signed-off-by: Paolo Abeni --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 8336e86ce606..1b4d72d5e891 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -214,6 +214,7 @@ extern int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf) extern int usbnet_cdc_bind(struct usbnet *, struct usb_interface *); extern void usbnet_cdc_unbind(struct usbnet *, struct usb_interface *); extern void usbnet_cdc_status(struct usbnet *, struct urb *); +extern int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb); /* CDC and RNDIS support the same host-chosen packet filters for IN transfers */ #define DEFAULT_FILTER (USB_CDC_PACKET_TYPE_BROADCAST \ -- cgit v1.2.3 From 36e747972d8b4c09e6e3275e31a3acba46e2c4d2 Mon Sep 17 00:00:00 2001 From: Lech Perczak Date: Wed, 13 Apr 2022 03:44:15 +0200 Subject: rndis_host: enable the bogus MAC fixup for ZTE devices from cdc_ether MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Certain ZTE modems, namely: MF823. MF831, MF910, built-in modem from MF286R, expose both CDC-ECM and RNDIS network interfaces. They have a trait of ignoring the locally-administered MAC address configured on the interface both in CDC-ECM and RNDIS part, and this leads to dropping of incoming traffic by the host. However, the workaround was only present in CDC-ECM, and MF286R explicitly requires it in RNDIS mode. Re-use the workaround in rndis_host as well, to fix operation of MF286R module, some versions of which expose only the RNDIS interface. Do so by introducing new flag, RNDIS_DRIVER_DATA_DST_MAC_FIXUP, and testing for it in rndis_rx_fixup. This is required, as RNDIS uses frame batching, and all of the packets inside the batch need the fixup. This might introduce a performance penalty, because test is done for every returned Ethernet frame. Apply the workaround to both "flavors" of RNDIS interfaces, as older ZTE modems, like MF823 found in the wild, report the USB_CLASS_COMM class interfaces, while MF286R reports USB_CLASS_WIRELESS_CONTROLLER. Suggested-by: Bjørn Mork Cc: Kristian Evensen Cc: Oliver Neukum Signed-off-by: Lech Perczak Signed-off-by: Paolo Abeni --- include/linux/usb/rndis_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb/rndis_host.h b/include/linux/usb/rndis_host.h index 809bccd08455..cc42db51bbba 100644 --- a/include/linux/usb/rndis_host.h +++ b/include/linux/usb/rndis_host.h @@ -197,6 +197,7 @@ struct rndis_keepalive_c { /* IN (optionally OUT) */ /* Flags for driver_info::data */ #define RNDIS_DRIVER_DATA_POLL_STATUS 1 /* poll status before control */ +#define RNDIS_DRIVER_DATA_DST_MAC_FIXUP 2 /* device ignores configured MAC address */ extern void rndis_status(struct usbnet *dev, struct urb *urb); extern int -- cgit v1.2.3 From fde33ca4cb2bae6472714123b451475fdfd9995c Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 11 Apr 2022 16:01:15 +0200 Subject: tracing/timer: Add missing argument documentation of trace points Documentation of trace points timer_start, timer_expire_entry and hrtimer_start lack always the last argument. Add it to keep implementation and documentation in sync. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Acked-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20220411140115.24185-1-anna-maria@linutronix.de --- include/trace/events/timer.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 6ad031c71be7..2e713a7d9aa3 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -48,6 +48,7 @@ DEFINE_EVENT(timer_class, timer_init, * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time + * @flags: the timers flags */ TRACE_EVENT(timer_start, @@ -84,6 +85,7 @@ TRACE_EVENT(timer_start, /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list + * @baseclk: value of timer_base::clk when timer expires * * Allows to determine the timer latency. */ @@ -190,7 +192,8 @@ TRACE_EVENT(hrtimer_init, /** * hrtimer_start - called when the hrtimer is started - * @hrtimer: pointer to struct hrtimer + * @hrtimer: pointer to struct hrtimer + * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_start, -- cgit v1.2.3 From 3dc6ffae2da201284cb24af66af77ee0bbb2efaa Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Thu, 14 Apr 2022 11:18:03 +0200 Subject: timekeeping: Introduce fast accessor to clock tai Introduce fast/NMI safe accessor to clock tai for tracing. The Linux kernel tracing infrastructure has support for using different clocks to generate timestamps for trace events. Especially in TSN networks it's useful to have TAI as trace clock, because the application scheduling is done in accordance to the network time, which is based on TAI. With a tai trace_clock in place, it becomes very convenient to correlate network activity with Linux kernel application traces. Use the same implementation as ktime_get_boot_fast_ns() does by reading the monotonic time and adding the TAI offset. The same limitations as for the fast boot implementation apply. The TAI offset may change at run time e.g., by setting the time or using adjtimex() with an offset. However, these kind of offset changes are rare events. Nevertheless, the user has to be aware and deal with it in post processing. An alternative approach would be to use the same implementation as ktime_get_real_fast_ns() does. However, this requires to add an additional u64 member to the tk_read_base struct. This struct together with a seqcount is designed to fit into a single cache line on 64 bit architectures. Adding a new member would violate this constraint. Signed-off-by: Kurt Kanzenbach Signed-off-by: Thomas Gleixner Cc: Steven Rostedt Link: https://lore.kernel.org/r/20220414091805.89667-2-kurt@linutronix.de --- include/linux/timekeeping.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 78a98bdff76d..fe1e467ba046 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -177,6 +177,7 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); +extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* -- cgit v1.2.3 From 19aed2d6cdb72a7c92909832b9480d9cadebeef9 Mon Sep 17 00:00:00 2001 From: Akihiko Odaki Date: Fri, 8 Apr 2022 13:11:14 +0900 Subject: ASoC: soc-card: Create jack kcontrol without pins snd_soc_card_jack_new() allowed to create jack kcontrol without pins, but did not create kcontrols. The jack would not have kcontrols if pins were not going to be added. This renames the old snd_soc_card_jack_new() to snd_soc_card_jack_new_pins() for use when pins are provided or will be added later. The new snd_soc_card_jack_new() appropriately creates a jack for use without pins and adds a kcontrol. Signed-off-by: Akihiko Odaki Link: https://lore.kernel.org/r/20220408041114.6024-1-akihiko.odaki@gmail.com Signed-off-by: Mark Brown --- include/sound/soc-card.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/soc-card.h b/include/sound/soc-card.h index 4f2cc4fb56b7..df08573bd80c 100644 --- a/include/sound/soc-card.h +++ b/include/sound/soc-card.h @@ -16,8 +16,11 @@ enum snd_soc_card_subclass { struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card, const char *name); int snd_soc_card_jack_new(struct snd_soc_card *card, const char *id, int type, - struct snd_soc_jack *jack, - struct snd_soc_jack_pin *pins, unsigned int num_pins); + struct snd_soc_jack *jack); +int snd_soc_card_jack_new_pins(struct snd_soc_card *card, const char *id, + int type, struct snd_soc_jack *jack, + struct snd_soc_jack_pin *pins, + unsigned int num_pins); int snd_soc_card_suspend_pre(struct snd_soc_card *card); int snd_soc_card_suspend_post(struct snd_soc_card *card); -- cgit v1.2.3 From af47d8033fc731f19600efd27ba4a7d0fdfcc77c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 14 Apr 2022 21:42:48 +0300 Subject: gpiolib: Introduce a helper to get first GPIO controller node Introduce a helper to get first GPIO controller node which drivers may want to use. Signed-off-by: Andy Shevchenko Tested-by: Marek Szyprowski --- include/linux/gpio/driver.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 12de0b22b4ef..83e2d72e51bb 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -766,4 +766,14 @@ static inline unsigned int gpiochip_node_count(struct device *dev) return count; } +static inline struct fwnode_handle *gpiochip_node_get_first(struct device *dev) +{ + struct fwnode_handle *fwnode; + + for_each_gpiochip_node(dev, fwnode) + return fwnode; + + return NULL; +} + #endif /* __LINUX_GPIO_DRIVER_H */ -- cgit v1.2.3 From f1724d397c60d296c0805c95a46ae7fc7163b70c Mon Sep 17 00:00:00 2001 From: Kai Ye Date: Sat, 9 Apr 2022 16:03:18 +0800 Subject: crypto: hisilicon/qm - add register checking for ACC Add register detection function to accelerator. Provided a tool that user can checking differential register through Debugfs. e.g. cd /sys/kernel/debug/hisi_zip//zip_dfx cat diff_regs Signed-off-by: Longfang Liu Signed-off-by: Kai Ye Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 177f7b7cd414..39acc0316a60 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -168,6 +168,12 @@ enum qm_vf_state { QM_NOT_READY, }; +struct dfx_diff_registers { + u32 *regs; + u32 reg_offset; + u32 reg_len; +}; + struct qm_dfx { atomic64_t err_irq_cnt; atomic64_t aeq_irq_cnt; @@ -190,6 +196,8 @@ struct qm_debug { struct dentry *debug_root; struct dentry *qm_d; struct debugfs_file files[DEBUG_FILE_NUM]; + struct dfx_diff_registers *qm_diff_regs; + struct dfx_diff_registers *acc_diff_regs; }; struct qm_shaper_factor { @@ -448,6 +456,12 @@ int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen); int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs); void hisi_qm_dev_err_init(struct hisi_qm *qm); void hisi_qm_dev_err_uninit(struct hisi_qm *qm); +int hisi_qm_diff_regs_init(struct hisi_qm *qm, + struct dfx_diff_registers *dregs, int reg_len); +void hisi_qm_diff_regs_uninit(struct hisi_qm *qm, int reg_len); +void hisi_qm_acc_diff_regs_dump(struct hisi_qm *qm, struct seq_file *s, + struct dfx_diff_registers *dregs, int regs_len); + pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev, pci_channel_state_t state); pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev); -- cgit v1.2.3 From a888ccd6c66683a49977ba6a2b91fe52fbec9367 Mon Sep 17 00:00:00 2001 From: Kai Ye Date: Sat, 9 Apr 2022 16:03:25 +0800 Subject: crypto: hisilicon/qm - add last word dumping for ACC Add last word dumping function during acc engines controller reset. The last words are reported to the printed information during the reset. The dmesg information included qm debugging registers and engine debugging registers. It can help to improve debugging capability. Signed-off-by: Kai Ye Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 39acc0316a60..e5522eaf88fd 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -196,6 +196,9 @@ struct qm_debug { struct dentry *debug_root; struct dentry *qm_d; struct debugfs_file files[DEBUG_FILE_NUM]; + unsigned int *qm_last_words; + /* ACC engines recoreding last regs */ + unsigned int *last_words; struct dfx_diff_registers *qm_diff_regs; struct dfx_diff_registers *acc_diff_regs; }; @@ -251,6 +254,7 @@ struct hisi_qm_err_ini { void (*open_sva_prefetch)(struct hisi_qm *qm); void (*close_sva_prefetch)(struct hisi_qm *qm); void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts); + void (*show_last_dfx_regs)(struct hisi_qm *qm); void (*err_info_init)(struct hisi_qm *qm); }; -- cgit v1.2.3 From f6f586102add59d57bcc6eea06fdeaae11bb17a1 Mon Sep 17 00:00:00 2001 From: Eric Tremblay Date: Wed, 30 Mar 2022 12:46:40 +0200 Subject: serial: 8250: Handle UART without interrupt on TEMT using em485 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce the UART_CAP_NOTEMT capability. The capability indicates that the UART doesn't have an interrupt available on TEMT. In the case where the device does not support it, we calculate the maximum time it could take for the transmitter to empty the shift register. When we get in the situation where we get the THRE interrupt, we check if the TEMT bit is set. If it's not, we start the a timer and recall __stop_tx() after the delay. The transmit sequence is a bit modified when the capability is set. The new timer is used between the last interrupt(THRE) and a potential stop_tx timer. Signed-off-by: Giulio Benetti [moved to use added UART_CAP_TEMT] Signed-off-by: Heiko Stuebner [moved to use added UART_CAP_NOTEMT, improve timeout] Signed-off-by: Eric Tremblay [rebased to v5.17, making use of tty_get_frame_size] Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20220330104642.229507-2-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index ff84a3ed10ea..de135852107c 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -79,7 +79,9 @@ struct uart_8250_ops { struct uart_8250_em485 { struct hrtimer start_tx_timer; /* "rs485 start tx" timer */ struct hrtimer stop_tx_timer; /* "rs485 stop tx" timer */ + struct hrtimer no_temt_timer; /* "rs485 no TEMT interrupt" timer */ struct hrtimer *active_timer; /* pointer to active timer */ + unsigned long no_temt_delay; /* Delay for no_temt_timer */ struct uart_8250_port *port; /* for hrtimer callbacks */ unsigned int tx_stopped:1; /* tx is currently stopped */ }; -- cgit v1.2.3 From f3c5264f452a5b0ac1de1f2f657efbabdea3c76a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 12 Apr 2022 18:31:58 +0200 Subject: net: page_pool: introduce ethtool stats Introduce page_pool APIs to report stats through ethtool and reduce duplicated code in each driver. Signed-off-by: Lorenzo Bianconi Reviewed-by: Jakub Kicinski Reviewed-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/net/page_pool.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index ea5fb70e5101..813c93499f20 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -117,6 +117,10 @@ struct page_pool_stats { struct page_pool_recycle_stats recycle_stats; }; +int page_pool_ethtool_stats_get_count(void); +u8 *page_pool_ethtool_stats_get_strings(u8 *data); +u64 *page_pool_ethtool_stats_get(u64 *data, void *stats); + /* * Drivers that wish to harvest page pool stats and report them to users * (perhaps via ethtool, debugfs, or another mechanism) can allocate a @@ -124,6 +128,23 @@ struct page_pool_stats { */ bool page_pool_get_stats(struct page_pool *pool, struct page_pool_stats *stats); +#else + +static inline int page_pool_ethtool_stats_get_count(void) +{ + return 0; +} + +static inline u8 *page_pool_ethtool_stats_get_strings(u8 *data) +{ + return data; +} + +static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats) +{ + return data; +} + #endif struct page_pool { -- cgit v1.2.3 From 4dc84c06a343fcb95fd5a0acb537aefa4ebdd1b0 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Tue, 12 Apr 2022 10:01:19 +0800 Subject: net: ethtool: extend ringparam set/get APIs for tx_push Currently tx push is a standard driver feature which controls use of a fast path descriptor push. So this patch extends the ringparam APIs and data structures to support set/get tx push by ethtool -G/g. Signed-off-by: Jie Wang Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 4 ++++ include/uapi/linux/ethtool_netlink.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 4af58459a1e7..99dc7bfbcd3c 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -71,11 +71,13 @@ enum { * struct kernel_ethtool_ringparam - RX/TX ring configuration * @rx_buf_len: Current length of buffers on the rx ring. * @tcp_data_split: Scatter packet headers and data to separate buffers + * @tx_push: The flag of tx push mode * @cqe_size: Size of TX/RX completion queue event */ struct kernel_ethtool_ringparam { u32 rx_buf_len; u8 tcp_data_split; + u8 tx_push; u32 cqe_size; }; @@ -83,10 +85,12 @@ struct kernel_ethtool_ringparam { * enum ethtool_supported_ring_param - indicator caps for setting ring params * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len * @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size + * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), ETHTOOL_RING_USE_CQE_SIZE = BIT(1), + ETHTOOL_RING_USE_TX_PUSH = BIT(2), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 979850221b8d..d2fb4f7be61b 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -338,6 +338,7 @@ enum { ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ ETHTOOL_A_RINGS_CQE_SIZE, /* u32 */ + ETHTOOL_A_RINGS_TX_PUSH, /* u8 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, -- cgit v1.2.3 From f9a2fb73318eb4dbf8cd84866b8b0dd012d8b116 Mon Sep 17 00:00:00 2001 From: Arun Ajith S Date: Fri, 15 Apr 2022 08:34:02 +0000 Subject: net/ipv6: Introduce accept_unsolicited_na knob to implement router-side changes for RFC9131 Add a new neighbour cache entry in STALE state for routers on receiving an unsolicited (gratuitous) neighbour advertisement with target link-layer-address option specified. This is similar to the arp_accept configuration for IPv4. A new sysctl endpoint is created to turn on this behaviour: /proc/sys/net/ipv6/conf/interface/accept_unsolicited_na. Signed-off-by: Arun Ajith S Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 16870f86c74d..918bfea4ef5f 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -61,6 +61,7 @@ struct ipv6_devconf { __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; __s32 drop_unsolicited_na; + __s32 accept_unsolicited_na; struct ipv6_stable_secret { bool initialized; struct in6_addr secret; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index d4178dace0bf..549ddeaf788b 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -194,6 +194,7 @@ enum { DEVCONF_IOAM6_ID, DEVCONF_IOAM6_ID_WIDE, DEVCONF_NDISC_EVICT_NOCARRIER, + DEVCONF_ACCEPT_UNSOLICITED_NA, DEVCONF_MAX }; -- cgit v1.2.3 From da40b613f89c43c58986e6f30560ad6573a4d569 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:41 -0700 Subject: tcp: add drop reason support to tcp_validate_incoming() Creates four new drop reasons for the following cases: 1) packet being rejected by RFC 7323 PAWS check 2) packet being rejected by SEQUENCE check 3) Invalid RST packet 4) Invalid SYN packet Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ include/trace/events/skb.h | 5 +++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0ef11df1bc67..a903da1fa0ed 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -381,6 +381,12 @@ enum skb_drop_reason { * the ofo queue, corresponding to * LINUX_MIB_TCPOFOMERGE */ + SKB_DROP_REASON_TCP_RFC7323_PAWS, /* PAWS check, corresponding to + * LINUX_MIB_PAWSESTABREJECTED + */ + SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */ + SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */ + SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 2da72a9a5764..820dacd14bad 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -37,6 +37,11 @@ EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ + EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \ + EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \ + TCP_INVALID_SEQUENCE) \ + EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \ + EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From 669da7a71890b2b2a31a7e9571c0fdf1123e26ef Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:43 -0700 Subject: tcp: add drop reasons to tcp_rcv_state_process() Add basic support for drop reasons in tcp_rcv_state_process() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ include/trace/events/skb.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a903da1fa0ed..6f1410b5ff13 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -387,6 +387,9 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */ SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */ SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */ + SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */ + SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */ + SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 820dacd14bad..fbe21ad038bc 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -42,6 +42,9 @@ TCP_INVALID_SEQUENCE) \ EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \ EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \ + EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \ + EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \ + EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From 4b506af9c5b8de0da34097d50d9448dfb33d70c3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:44 -0700 Subject: tcp: add two drop reasons for tcp_ack() Add TCP_TOO_OLD_ACK and TCP_ACK_UNSENT_DATA drop reasons so that tcp_rcv_established() can report them. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ include/trace/events/skb.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f1410b5ff13..9ff5557b1909 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -390,6 +390,8 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */ SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */ SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ + SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ + SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index fbe21ad038bc..eab0b09223f3 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -45,6 +45,9 @@ EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \ EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \ EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \ + EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \ + EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \ + TCP_ACK_UNSENT_DATA) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From e7c89ae4078eab24af71ba26b91642e819a4bd7f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:45 -0700 Subject: tcp: add drop reason support to tcp_prune_ofo_queue() Add one reason for packets dropped from OFO queue because of memory pressure. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9ff5557b1909..ad15ad208b56 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -392,6 +392,7 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ + SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index eab0b09223f3..73d7a6e594cb 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -48,6 +48,8 @@ EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \ EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \ TCP_ACK_UNSENT_DATA) \ + EM(SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, \ + TCP_OFO_QUEUE_PRUNE) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From 8fbf195798b56e1e87f62d01be636a6425c304c2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:48 -0700 Subject: tcp: add drop reason support to tcp_ofo_queue() packets in OFO queue might be redundant, and dropped. tcp_drop() is no longer needed. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ad15ad208b56..84d78df60453 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -393,6 +393,7 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */ + SKB_DROP_REASON_TCP_OFO_DROP, /* data already in receive queue */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 73d7a6e594cb..a477bf907498 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -37,6 +37,7 @@ EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ + EM(SKB_DROP_REASON_TCP_OFO_DROP, TCP_OFO_DROP) \ EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \ EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \ TCP_INVALID_SEQUENCE) \ -- cgit v1.2.3 From 0df71650c051ab106c921de257f4b38e9e3dd251 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 24 Mar 2022 16:35:24 -0400 Subject: block: allow using the per-cpu bio cache from bio_alloc_bioset Replace the BIO_PERCPU_CACHE bio-internal flag with a REQ_ALLOC_CACHE one that can be passed to bio_alloc / bio_alloc_bioset, and implement the percpu cache allocation logic in a helper called from bio_alloc_bioset. This allows any bio_alloc_bioset user to use the percpu caches instead of having the functionality tied to struct kiocb. Signed-off-by: Mike Snitzer [hch: refactored a bit] Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220324203526.62306-2-snitzer@kernel.org Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 -- include/linux/blk_types.h | 3 ++- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 278cc81cc1e7..0fe8a51a0778 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -405,8 +405,6 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask, struct bio_set *bs); -struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, - unsigned short nr_vecs, unsigned int opf, struct bio_set *bs); struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); extern void bio_put(struct bio *); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1973ef9bd40f..4968cb17b13b 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -329,7 +329,6 @@ enum { BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ - BIO_PERCPU_CACHE, /* can participate in per-cpu alloc cache */ BIO_FLAG_LAST }; @@ -414,6 +413,7 @@ enum req_flag_bits { __REQ_NOUNMAP, /* do not free blocks when zeroing */ __REQ_POLLED, /* caller polls for completion using bio_poll */ + __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ /* for driver use */ __REQ_DRV, @@ -439,6 +439,7 @@ enum req_flag_bits { #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_POLLED (1ULL << __REQ_POLLED) +#define REQ_ALLOC_CACHE (1ULL << __REQ_ALLOC_CACHE) #define REQ_DRV (1ULL << __REQ_DRV) #define REQ_SWAP (1ULL << __REQ_SWAP) -- cgit v1.2.3 From b53f3dcd705e52a07bd0311870dbfb6842e88c91 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 24 Mar 2022 16:35:25 -0400 Subject: block: allow use of per-cpu bio alloc cache by block drivers Refine per-cpu bio alloc cache interfaces so that DM and other block drivers can properly create and use the cache: DM uses bioset_init_from_src() to do its final bioset initialization, so must update bioset_init_from_src() to set BIOSET_PERCPU_CACHE if %src bioset has a cache. Also move bio_clear_polled() to include/linux/bio.h to allow users outside of block core. Signed-off-by: Mike Snitzer Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220324203526.62306-3-snitzer@kernel.org Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 0fe8a51a0778..8e87f3065042 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -780,6 +780,12 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } +static inline void bio_clear_polled(struct bio *bio) +{ + /* can't support alloc cache if we turn off polling */ + bio->bi_opf &= ~(REQ_POLLED | REQ_ALLOC_CACHE); +} + struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, unsigned int opf, gfp_t gfp); -- cgit v1.2.3 From 066ff571011d8416e903d3d4f1f41e0b5eb91e1d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 6 Apr 2022 08:12:27 +0200 Subject: block: turn bio_kmalloc into a simple kmalloc wrapper Remove the magic autofree semantics and require the callers to explicitly call bio_init to initialize the bio. This allows bio_free to catch accidental bio_put calls on bio_init()ed bios as well. Signed-off-by: Christoph Hellwig Acked-by: Coly Li Acked-by: Mike Snitzer Link: https://lore.kernel.org/r/20220406061228.410163-5-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 8e87f3065042..49eff01fb829 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -405,7 +405,7 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask, struct bio_set *bs); -struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); +struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask); extern void bio_put(struct bio *); struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, -- cgit v1.2.3 From 817e8b51eb3d927ce6d56ecf9f48bc3c5b26168b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:33 +0200 Subject: target: pass a block_device to target_configure_unmap_from_queue The SCSI target drivers is a consumer of the block layer and shoul d generally work on struct block_device. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-3-hch@lst.de Signed-off-by: Jens Axboe --- include/target/target_core_backend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 675f3a1fe613..773963a1e0b5 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -14,7 +14,7 @@ #define TRANSPORT_FLAG_PASSTHROUGH_ALUA 0x2 #define TRANSPORT_FLAG_PASSTHROUGH_PGR 0x4 -struct request_queue; +struct block_device; struct scatterlist; struct target_backend_ops { @@ -117,7 +117,7 @@ sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd, bool target_sense_desc_format(struct se_device *dev); sector_t target_to_linux_sector(struct se_device *dev, sector_t lb); bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, - struct request_queue *q); + struct block_device *bdev); static inline bool target_dev_configured(struct se_device *se_dev) { -- cgit v1.2.3 From 10f0d2a517796b8f6dc04fb0cc3e49003ae6b0bc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:42 +0200 Subject: block: add a bdev_nonrot helper Add a helper to check the nonrot flag based on the block_device instead of having to poke into the block layer internal request_queue. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: David Sterba [btrfs] Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-12-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60d016138997..3a9578e14a6b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1326,6 +1326,11 @@ static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) return 0; } +static inline bool bdev_nonrot(struct block_device *bdev) +{ + return blk_queue_nonrot(bdev_get_queue(bdev)); +} + static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 08e688fdb8f7e862092ae64cee20bc8b463d1046 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:43 +0200 Subject: block: add a bdev_write_cache helper Add a helper to check the write cache flag based on the block_device instead of having to poke into the block layer internal request_queue. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: David Sterba [btrfs] Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-13-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3a9578e14a6b..807a49aa5a27 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1331,6 +1331,11 @@ static inline bool bdev_nonrot(struct block_device *bdev) return blk_queue_nonrot(bdev_get_queue(bdev)); } +static inline bool bdev_write_cache(struct block_device *bdev) +{ + return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); +} + static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From a557e82e5a01826f902bd94fc925c03f253cb712 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:44 +0200 Subject: block: add a bdev_fua helper Add a helper to check the FUA flag based on the block_device instead of having to poke into the block layer internal request_queue. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-14-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 807a49aa5a27..075b16d4560e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -602,7 +602,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) -#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) @@ -1336,6 +1335,11 @@ static inline bool bdev_write_cache(struct block_device *bdev) return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); } +static inline bool bdev_fua(struct block_device *bdev) +{ + return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); +} + static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 36d254893aa6a6e204075c3cce94bb572ac32c04 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:45 +0200 Subject: block: add a bdev_stable_writes helper Add a helper to check the stable writes flag based on the block_device instead of having to poke into the block layer internal request_queue. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-15-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 075b16d4560e..a433798c3343 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1330,6 +1330,12 @@ static inline bool bdev_nonrot(struct block_device *bdev) return blk_queue_nonrot(bdev_get_queue(bdev)); } +static inline bool bdev_stable_writes(struct block_device *bdev) +{ + return test_bit(QUEUE_FLAG_STABLE_WRITES, + &bdev_get_queue(bdev)->queue_flags); +} + static inline bool bdev_write_cache(struct block_device *bdev) { return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); -- cgit v1.2.3 From 2aba0d19f4d8c8929b4b3b94a9cfde2aa20e6ee2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:46 +0200 Subject: block: add a bdev_max_zone_append_sectors helper Add a helper to check the max supported sectors for zone append based on the block_device instead of having to poke into the block layer internal request_queue. Signed-off-by: Christoph Hellwig Acked-by: Damien Le Moal Reviewed-by: Martin K. Petersen Reviewed-by: Johannes Thumshirn Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-16-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a433798c3343..f8c50b77543e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1188,6 +1188,12 @@ static inline unsigned int queue_max_zone_append_sectors(const struct request_qu return min(l->max_zone_append_sectors, l->max_sectors); } +static inline unsigned int +bdev_max_zone_append_sectors(struct block_device *bdev) +{ + return queue_max_zone_append_sectors(bdev_get_queue(bdev)); +} + static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; -- cgit v1.2.3 From 640f2a23911b8388989547f89d055afbb910b88e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:48 +0200 Subject: block: use bdev_alignment_offset in disk_alignment_offset_show This does the same as the open coded variant except for an extra branch, and allows to remove queue_alignment_offset entirely. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220415045258.199825-18-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f8c50b77543e..d5346e72e364 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1251,14 +1251,6 @@ bdev_zone_write_granularity(struct block_device *bdev) return queue_zone_write_granularity(bdev_get_queue(bdev)); } -static inline int queue_alignment_offset(const struct request_queue *q) -{ - if (q->limits.misaligned) - return -1; - - return q->limits.alignment_offset; -} - static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); -- cgit v1.2.3 From 89098b075cb74a80083bc4ed6b71d0ee18b6898f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:49 +0200 Subject: block: move bdev_alignment_offset and queue_limit_alignment_offset out of line No need to inline these fairly larger helpers. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220415045258.199825-19-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 21 +-------------------- 1 file changed, 1 insertion(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d5346e72e364..0a1795ac2627 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1251,26 +1251,7 @@ bdev_zone_write_granularity(struct block_device *bdev) return queue_zone_write_granularity(bdev_get_queue(bdev)); } -static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) -{ - unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) - << SECTOR_SHIFT; - - return (granularity + lim->alignment_offset - alignment) % granularity; -} - -static inline int bdev_alignment_offset(struct block_device *bdev) -{ - struct request_queue *q = bdev_get_queue(bdev); - - if (q->limits.misaligned) - return -1; - if (bdev_is_partition(bdev)) - return queue_limit_alignment_offset(&q->limits, - bdev->bd_start_sect); - return q->limits.alignment_offset; -} +int bdev_alignment_offset(struct block_device *bdev); static inline int queue_discard_alignment(const struct request_queue *q) { -- cgit v1.2.3 From 4e1462ffe8998749884d61f91be251a7a8719677 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:50 +0200 Subject: block: remove queue_discard_alignment Just use bdev_alignment_offset in disk_discard_alignment_show instead. That helpers is the same except for an always false branch that doesn't matter in this slow path. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220415045258.199825-20-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0a1795ac2627..5a9b7aeda010 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1253,14 +1253,6 @@ bdev_zone_write_granularity(struct block_device *bdev) int bdev_alignment_offset(struct block_device *bdev); -static inline int queue_discard_alignment(const struct request_queue *q) -{ - if (q->limits.discard_misaligned) - return -1; - - return q->limits.discard_alignment; -} - static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) { unsigned int alignment, granularity, offset; -- cgit v1.2.3 From 5c4b4a5c6f11c869a57c6bd977143430bc9dc43d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:52 +0200 Subject: block: move {bdev,queue_limit}_discard_alignment out of line No need to inline these fairly larger helpers. Also fix the return value to be unsigned, just like the field in struct queue_limits. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220415045258.199825-22-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 34 +--------------------------------- 1 file changed, 1 insertion(+), 33 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5a9b7aeda010..34b1cfd06742 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1252,39 +1252,7 @@ bdev_zone_write_granularity(struct block_device *bdev) } int bdev_alignment_offset(struct block_device *bdev); - -static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) -{ - unsigned int alignment, granularity, offset; - - if (!lim->max_discard_sectors) - return 0; - - /* Why are these in bytes, not sectors? */ - alignment = lim->discard_alignment >> SECTOR_SHIFT; - granularity = lim->discard_granularity >> SECTOR_SHIFT; - if (!granularity) - return 0; - - /* Offset of the partition start in 'granularity' sectors */ - offset = sector_div(sector, granularity); - - /* And why do we do this modulus *again* in blkdev_issue_discard()? */ - offset = (granularity + alignment - offset) % granularity; - - /* Turn it back into bytes, gaah */ - return offset << SECTOR_SHIFT; -} - -static inline int bdev_discard_alignment(struct block_device *bdev) -{ - struct request_queue *q = bdev_get_queue(bdev); - - if (bdev_is_partition(bdev)) - return queue_limit_discard_alignment(&q->limits, - bdev->bd_start_sect); - return q->limits.discard_alignment; -} +unsigned int bdev_discard_alignment(struct block_device *bdev); static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { -- cgit v1.2.3 From cf0fbf894bb543f472f682c486be48298eccf199 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:54 +0200 Subject: block: add a bdev_max_discard_sectors helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a helper to query the number of sectors support per each discard bio based on the block device and use this helper to stop various places from poking into the request_queue to see if discard is supported and if so how much. This mirrors what is done e.g. for write zeroes as well. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: Christoph Böhmwalder [drbd] Acked-by: Coly Li [bcache] Acked-by: David Sterba [btrfs] Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-24-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 34b1cfd06742..ce16247d3afa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1254,6 +1254,11 @@ bdev_zone_write_granularity(struct block_device *bdev) int bdev_alignment_offset(struct block_device *bdev); unsigned int bdev_discard_alignment(struct block_device *bdev); +static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_discard_sectors; +} + static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 70200574cc229f6ba038259e8142af2aa09e6976 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:55 +0200 Subject: block: remove QUEUE_FLAG_DISCARD MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Just use a non-zero max_discard_sectors as an indicator for discard support, similar to what is done for write zeroes. The only places where needs special attention is the RAID5 driver, which must clear discard support for security reasons by default, even if the default stacking rules would allow for it. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: Christoph Böhmwalder [drbd] Acked-by: Jan Höppner [s390] Acked-by: Coly Li [bcache] Acked-by: David Sterba [btrfs] Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-25-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ce16247d3afa..767ab22e1052 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -540,7 +540,6 @@ struct request_queue { #define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ -#define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ @@ -582,7 +581,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) #define blk_queue_secure_erase(q) \ -- cgit v1.2.3 From 7b47ef52d0a2025fd1408a8a0990933b8e1e510f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:56 +0200 Subject: block: add a bdev_discard_granularity helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Abstract away implementation details from file systems by providing a block_device based helper to retrieve the discard granularity. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: Christoph Böhmwalder [drbd] Acked-by: Ryusuke Konishi Acked-by: David Sterba [btrfs] Link: https://lore.kernel.org/r/20220415045258.199825-26-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 767ab22e1052..f1cf557ea20e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1257,6 +1257,11 @@ static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) return bdev_get_queue(bdev)->limits.max_discard_sectors; } +static inline unsigned int bdev_discard_granularity(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.discard_granularity; +} + static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 44abff2c0b970ae3d310b97617525dc01f248d7c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:57 +0200 Subject: block: decouple REQ_OP_SECURE_ERASE from REQ_OP_DISCARD MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Secure erase is a very different operation from discard in that it is a data integrity operation vs hint. Fully split the limits and helper infrastructure to make the separation more clear. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: Christoph Böhmwalder [drbd] Acked-by: Ryusuke Konishi [nifs2] Acked-by: Jaegeuk Kim [f2fs] Acked-by: Coly Li [bcache] Acked-by: David Sterba [btrfs] Acked-by: Chao Yu Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-27-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f1cf557ea20e..c9b5925af5a3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -248,6 +248,7 @@ struct queue_limits { unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; + unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; @@ -542,7 +543,6 @@ struct request_queue { #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ -#define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ @@ -583,8 +583,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) -#define blk_queue_secure_erase(q) \ - (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) @@ -947,6 +945,8 @@ extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_discard_segments(struct request_queue *, unsigned short); +void blk_queue_max_secure_erase_sectors(struct request_queue *q, + unsigned int max_sectors); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); @@ -1087,13 +1087,12 @@ static inline long nr_blockdev_pages(void) extern void blk_io_schedule(void); -#define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ - -extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); -extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int flags, - struct bio **biop); +int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask); +int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, struct bio **biop); +int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ @@ -1112,7 +1111,7 @@ static inline int sb_issue_discard(struct super_block *sb, sector_t block, SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), - gfp_mask, flags); + gfp_mask); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) @@ -1262,6 +1261,12 @@ static inline unsigned int bdev_discard_granularity(struct block_device *bdev) return bdev_get_queue(bdev)->limits.discard_granularity; } +static inline unsigned int +bdev_max_secure_erase_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_secure_erase_sectors; +} + static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From a2daa27c0c6137481226aee5b3136e453c642929 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Feb 2022 11:44:42 +0100 Subject: swiotlb: simplify swiotlb_max_segment Remove the bogus Xen override that was usually larger than the actual size and just calculate the value on demand. Note that swiotlb_max_segment still doesn't make sense as an interface and should eventually be removed. Signed-off-by: Christoph Hellwig Reviewed-by: Anshuman Khandual Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index f6c3638255d5..9fb3a568f0c5 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -164,7 +164,6 @@ static inline void swiotlb_adjust_size(unsigned long size) #endif /* CONFIG_SWIOTLB */ extern void swiotlb_print_info(void); -extern void swiotlb_set_max_segment(unsigned int); #ifdef CONFIG_DMA_RESTRICTED_POOL struct page *swiotlb_alloc(struct device *dev, size_t size); -- cgit v1.2.3 From 0d5ffd9a256d8995764f9d4a35a8c3917839d169 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Feb 2022 11:07:28 +0100 Subject: swiotlb: rename swiotlb_late_init_with_default_size swiotlb_late_init_with_default_size is an overly verbose name that doesn't even catch what the function is doing, given that the size is not just a default but the actual requested size. Rename it to swiotlb_init_late. Signed-off-by: Christoph Hellwig Reviewed-by: Anshuman Khandual Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 9fb3a568f0c5..b48b26bfa0ed 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -40,7 +40,7 @@ extern void swiotlb_init(int verbose); int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); -extern int swiotlb_late_init_with_default_size(size_t default_size); +int swiotlb_init_late(size_t size); extern void __init swiotlb_update_mem_attributes(void); phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, -- cgit v1.2.3 From 78013eaadf696d2105982abb4018fbae394ca08f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Feb 2022 14:11:44 +0100 Subject: x86: remove the IOMMU table infrastructure The IOMMU table tries to separate the different IOMMUs into different backends, but actually requires various cross calls. Rewrite the code to do the generic swiotlb/swiotlb-xen setup directly in pci-dma.c and then just call into the IOMMU drivers. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/dmar.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 45e903d84733..cbd714a198a0 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -121,7 +121,7 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment, struct dmar_dev_scope *devices, int count); /* Intel IOMMU detection */ -extern int detect_intel_iommu(void); +void detect_intel_iommu(void); extern int enable_drhd_fault_handling(void); extern int dmar_device_add(acpi_handle handle); extern int dmar_device_remove(acpi_handle handle); @@ -197,6 +197,10 @@ static inline bool dmar_platform_optin(void) return false; } +static inline void detect_intel_iommu(void) +{ +} + #endif /* CONFIG_DMAR_TABLE */ struct irte { -- cgit v1.2.3 From c6af2aa9ffc9763826607bc2664ef3ea4475ed18 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Mar 2022 17:27:33 +0200 Subject: swiotlb: make the swiotlb_init interface more useful Pass a boolean flag to indicate if swiotlb needs to be enabled based on the addressing needs, and replace the verbose argument with a set of flags, including one to force enable bounce buffering. Note that this patch removes the possibility to force xen-swiotlb use with the swiotlb=force parameter on the command line on x86 (arm and arm64 never supported that), but this interface will be restored shortly. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 15 +++++++-------- include/trace/events/swiotlb.h | 29 ++++++++++------------------- 2 files changed, 17 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index b48b26bfa0ed..ae0407173e84 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -13,11 +13,8 @@ struct device; struct page; struct scatterlist; -enum swiotlb_force { - SWIOTLB_NORMAL, /* Default - depending on HW DMA mask etc. */ - SWIOTLB_FORCE, /* swiotlb=force */ - SWIOTLB_NO_FORCE, /* swiotlb=noforce */ -}; +#define SWIOTLB_VERBOSE (1 << 0) /* verbose initialization */ +#define SWIOTLB_FORCE (1 << 1) /* force bounce buffering */ /* * Maximum allowable number of contiguous slabs to map, @@ -36,8 +33,7 @@ enum swiotlb_force { /* default to 64MB */ #define IO_TLB_DEFAULT_SIZE (64UL<<20) -extern void swiotlb_init(int verbose); -int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); +int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); int swiotlb_init_late(size_t size); @@ -126,13 +122,16 @@ static inline bool is_swiotlb_force_bounce(struct device *dev) return mem && mem->force_bounce; } +void swiotlb_init(bool addressing_limited, unsigned int flags); void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); bool is_swiotlb_active(struct device *dev); void __init swiotlb_adjust_size(unsigned long size); #else -#define swiotlb_force SWIOTLB_NO_FORCE +static inline void swiotlb_init(bool addressing_limited, unsigned int flags) +{ +} static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { return false; diff --git a/include/trace/events/swiotlb.h b/include/trace/events/swiotlb.h index 705be43b71ab..da05c9ebd224 100644 --- a/include/trace/events/swiotlb.h +++ b/include/trace/events/swiotlb.h @@ -8,20 +8,15 @@ #include TRACE_EVENT(swiotlb_bounced, - - TP_PROTO(struct device *dev, - dma_addr_t dev_addr, - size_t size, - enum swiotlb_force swiotlb_force), - - TP_ARGS(dev, dev_addr, size, swiotlb_force), + TP_PROTO(struct device *dev, dma_addr_t dev_addr, size_t size), + TP_ARGS(dev, dev_addr, size), TP_STRUCT__entry( - __string( dev_name, dev_name(dev) ) - __field( u64, dma_mask ) - __field( dma_addr_t, dev_addr ) - __field( size_t, size ) - __field( enum swiotlb_force, swiotlb_force ) + __string(dev_name, dev_name(dev)) + __field(u64, dma_mask) + __field(dma_addr_t, dev_addr) + __field(size_t, size) + __field(bool, force) ), TP_fast_assign( @@ -29,19 +24,15 @@ TRACE_EVENT(swiotlb_bounced, __entry->dma_mask = (dev->dma_mask ? *dev->dma_mask : 0); __entry->dev_addr = dev_addr; __entry->size = size; - __entry->swiotlb_force = swiotlb_force; + __entry->force = is_swiotlb_force_bounce(dev); ), - TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx " - "size=%zu %s", + TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx size=%zu %s", __get_str(dev_name), __entry->dma_mask, (unsigned long long)__entry->dev_addr, __entry->size, - __print_symbolic(__entry->swiotlb_force, - { SWIOTLB_NORMAL, "NORMAL" }, - { SWIOTLB_FORCE, "FORCE" }, - { SWIOTLB_NO_FORCE, "NO_FORCE" })) + __entry->force ? "FORCE" : "NORMAL") ); #endif /* _TRACE_SWIOTLB_H */ -- cgit v1.2.3 From 8ba2ed1be90fc210126f68186564707478552c95 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 28 Feb 2022 13:36:57 +0200 Subject: swiotlb: add a SWIOTLB_ANY flag to lift the low memory restriction Power SVM wants to allocate a swiotlb buffer that is not restricted to low memory for the trusted hypervisor scheme. Consolidate the support for this into the swiotlb_init interface by adding a new flag. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index ae0407173e84..eabdd8998702 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -15,6 +15,7 @@ struct scatterlist; #define SWIOTLB_VERBOSE (1 << 0) /* verbose initialization */ #define SWIOTLB_FORCE (1 << 1) /* force bounce buffering */ +#define SWIOTLB_ANY (1 << 2) /* allow any memory for the buffer */ /* * Maximum allowable number of contiguous slabs to map, -- cgit v1.2.3 From 742519538e6b07250c8085bbff4bd358bc03bf16 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Feb 2022 11:12:59 +0100 Subject: swiotlb: pass a gfp_mask argument to swiotlb_init_late Let the caller chose a zone to allocate from. This will be used later on by the xen-swiotlb initialization on arm. Signed-off-by: Christoph Hellwig Reviewed-by: Anshuman Khandual Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index eabdd8998702..ee655f2e4d28 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -37,7 +37,7 @@ struct scatterlist; int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); -int swiotlb_init_late(size_t size); +int swiotlb_init_late(size_t size, gfp_t gfp_mask); extern void __init swiotlb_update_mem_attributes(void); phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, -- cgit v1.2.3 From 7374153d294eb51de5a81ac38ff1c4fef8927bec Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Mar 2022 08:02:57 +0100 Subject: swiotlb: provide swiotlb_init variants that remap the buffer To shared more code between swiotlb and xen-swiotlb, offer a swiotlb_init_remap interface and add a remap callback to swiotlb_init_late that will allow Xen to remap the buffer without duplicating much of the logic. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index ee655f2e4d28..7b50c82f84ce 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -36,8 +36,11 @@ struct scatterlist; int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags); unsigned long swiotlb_size_or_default(void); +void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, + int (*remap)(void *tlb, unsigned long nslabs)); +int swiotlb_init_late(size_t size, gfp_t gfp_mask, + int (*remap)(void *tlb, unsigned long nslabs)); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); -int swiotlb_init_late(size_t size, gfp_t gfp_mask); extern void __init swiotlb_update_mem_attributes(void); phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, -- cgit v1.2.3 From 3f70356edf5611c28a68d8d5a9c2b442c9eb81e6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Mar 2022 07:58:45 +0100 Subject: swiotlb: merge swiotlb-xen initialization into swiotlb Reuse the generic swiotlb initialization for xen-swiotlb. For ARM/ARM64 this works trivially, while for x86 xen_swiotlb_fixup needs to be passed as the remap argument to swiotlb_init_remap/swiotlb_init_late. Note that the lower bound of the swiotlb size is changed to the smaller IO_TLB_MIN_SLABS based value with this patch, but that is fine as the 2MB value used in Xen before was just an optimization and is not the hard lower bound. Signed-off-by: Christoph Hellwig Reviewed-by: Stefano Stabellini Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/xen/arm/page.h | 1 - include/xen/swiotlb-xen.h | 8 ++++++-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h index ac1b65470563..7e199c6656b9 100644 --- a/include/xen/arm/page.h +++ b/include/xen/arm/page.h @@ -115,6 +115,5 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) bool xen_arch_need_swiotlb(struct device *dev, phys_addr_t phys, dma_addr_t dev_addr); -unsigned long xen_get_swiotlb_free_pages(unsigned int order); #endif /* _ASM_ARM_XEN_PAGE_H */ diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h index b3e647f86e3e..590ceb923f0c 100644 --- a/include/xen/swiotlb-xen.h +++ b/include/xen/swiotlb-xen.h @@ -10,8 +10,12 @@ void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle, void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir); -int xen_swiotlb_init(void); -void __init xen_swiotlb_init_early(void); +#ifdef CONFIG_SWIOTLB_XEN +int xen_swiotlb_fixup(void *buf, unsigned long nslabs); +#else +#define xen_swiotlb_fixup NULL +#endif + extern const struct dma_map_ops xen_swiotlb_dma_ops; #endif /* __LINUX_SWIOTLB_XEN_H */ -- cgit v1.2.3 From 6424e31b1c050a25aea033206d5f626f3523448c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 15 Mar 2022 07:41:04 +0100 Subject: swiotlb: remove swiotlb_init_with_tbl and swiotlb_init_late_with_tbl No users left. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 7b50c82f84ce..7ed35dd3de6e 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -34,13 +34,11 @@ struct scatterlist; /* default to 64MB */ #define IO_TLB_DEFAULT_SIZE (64UL<<20) -int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags); unsigned long swiotlb_size_or_default(void); void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, int (*remap)(void *tlb, unsigned long nslabs)); int swiotlb_init_late(size_t size, gfp_t gfp_mask, int (*remap)(void *tlb, unsigned long nslabs)); -extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); extern void __init swiotlb_update_mem_attributes(void); phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, -- cgit v1.2.3 From 964320cb45eecdcd0bd322896593bf805d8b3711 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:13 +0200 Subject: media: dvb-usb-ids.h: sort entries The entries there are alphabetically sorted, but some are at the wrong place. Re-sort them. While here, replace spaces by tabs where needed. Link: https://lore.kernel.org/linux-media/0208dbba189b754b999759f06c2584242c879f4d.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 591 ++++++++++++++++++++++---------------------- 1 file changed, 297 insertions(+), 294 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index b0a535d6893a..dcf5772c84a0 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -11,80 +11,74 @@ #define _DVB_USB_IDS_H_ /* Vendor IDs */ -#define USB_VID_ADSTECH 0x06e1 -#define USB_VID_AFATECH 0x15a4 + +#define USB_VID_774 0x7a69 +#define USB_VID_ADSTECH 0x06e1 +#define USB_VID_AFATECH 0x15a4 #define USB_VID_ALCOR_MICRO 0x058f #define USB_VID_ALINK 0x05e3 #define USB_VID_AMT 0x1c73 #define USB_VID_ANCHOR 0x0547 -#define USB_VID_ANSONIC 0x10b9 +#define USB_VID_ANSONIC 0x10b9 #define USB_VID_ANUBIS_ELECTRONIC 0x10fd #define USB_VID_ASUS 0x0b05 #define USB_VID_AVERMEDIA 0x07ca +#define USB_VID_AZUREWAVE 0x13d3 #define USB_VID_COMPRO 0x185b #define USB_VID_COMPRO_UNK 0x145f #define USB_VID_CONEXANT 0x0572 -#define USB_VID_CYPRESS 0x04b4 -#define USB_VID_DEXATEK 0x1d19 +#define USB_VID_CYPRESS 0x04b4 +#define USB_VID_DEXATEK 0x1d19 #define USB_VID_DIBCOM 0x10b8 #define USB_VID_DPOSH 0x1498 #define USB_VID_DVICO 0x0fe9 #define USB_VID_E3C 0x18b4 #define USB_VID_ELGATO 0x0fd9 #define USB_VID_EMPIA 0xeb1a +#define USB_VID_EVOLUTEPC 0x1e59 #define USB_VID_GENPIX 0x09c0 +#define USB_VID_GIGABYTE 0x1044 #define USB_VID_GRANDTEC 0x5032 #define USB_VID_GTEK 0x1f4d -#define USB_VID_HANFTEK 0x15f4 +#define USB_VID_HAMA 0x147f +#define USB_VID_HANFTEK 0x15f4 #define USB_VID_HAUPPAUGE 0x2040 +#define USB_VID_HUMAX_COEX 0x10b9 #define USB_VID_HYPER_PALTEK 0x1025 #define USB_VID_INTEL 0x8086 -#define USB_VID_ITETECH 0x048d +#define USB_VID_ITETECH 0x048d #define USB_VID_KWORLD 0xeb2a #define USB_VID_KWORLD_2 0x1b80 #define USB_VID_KYE 0x0458 -#define USB_VID_LEADTEK 0x0413 +#define USB_VID_LEADTEK 0x0413 #define USB_VID_LITEON 0x04ca #define USB_VID_MEDION 0x1660 +#define USB_VID_MICROSOFT 0x045e #define USB_VID_MIGLIA 0x18f3 #define USB_VID_MSI 0x0db0 #define USB_VID_MSI_2 0x1462 #define USB_VID_OPERA1 0x695c -#define USB_VID_PINNACLE 0x2304 #define USB_VID_PCTV 0x2013 +#define USB_VID_PINNACLE 0x2304 #define USB_VID_PIXELVIEW 0x1554 -#define USB_VID_REALTEK 0x0bda +#define USB_VID_REALTEK 0x0bda +#define USB_VID_SONY 0x1415 +#define USB_VID_TECHNISAT 0x14f7 #define USB_VID_TECHNOTREND 0x0b48 +#define USB_VID_TELESTAR 0x10b9 #define USB_VID_TERRATEC 0x0ccd #define USB_VID_TERRATEC_2 0x153b -#define USB_VID_TELESTAR 0x10b9 -#define USB_VID_VISIONPLUS 0x13d3 -#define USB_VID_SONY 0x1415 -#define USB_PID_TEVII_S421 0xd421 -#define USB_PID_TEVII_S480_1 0xd481 -#define USB_PID_TEVII_S480_2 0xd482 -#define USB_PID_TEVII_S630 0xd630 -#define USB_PID_TEVII_S632 0xd632 -#define USB_PID_TEVII_S650 0xd650 -#define USB_PID_TEVII_S660 0xd660 -#define USB_PID_TEVII_S662 0xd662 -#define USB_VID_TWINHAN 0x1822 +#define USB_VID_TWINHAN 0x1822 #define USB_VID_ULTIMA_ELECTRONIC 0x05d8 -#define USB_VID_UNIWILL 0x1584 +#define USB_VID_UNIWILL 0x1584 +#define USB_VID_VISIONPLUS 0x13d3 #define USB_VID_WIDEVIEW 0x14aa -#define USB_VID_GIGABYTE 0x1044 -#define USB_VID_YUAN 0x1164 #define USB_VID_XTENSIONS 0x1ae7 +#define USB_VID_YUAN 0x1164 #define USB_VID_ZYDAS 0x0ace -#define USB_VID_HUMAX_COEX 0x10b9 -#define USB_VID_774 0x7a69 -#define USB_VID_EVOLUTEPC 0x1e59 -#define USB_VID_AZUREWAVE 0x13d3 -#define USB_VID_TECHNISAT 0x14f7 -#define USB_VID_HAMA 0x147f -#define USB_VID_MICROSOFT 0x045e /* Product IDs */ + #define USB_PID_ADSTECH_USB2_COLD 0xa333 #define USB_PID_ADSTECH_USB2_WARM 0xa334 #define USB_PID_AFATECH_AF9005 0x9020 @@ -95,341 +89,350 @@ #define USB_PID_AFATECH_AF9035_1002 0x1002 #define USB_PID_AFATECH_AF9035_1003 0x1003 #define USB_PID_AFATECH_AF9035_9035 0x9035 -#define USB_PID_TREKSTOR_DVBT 0x901b -#define USB_PID_TREKSTOR_TERRES_2_0 0xC803 #define USB_PID_ALINK_DTU 0xf170 #define USB_PID_ANSONIC_DVBT_USB 0x6000 #define USB_PID_ANYSEE 0x861f -#define USB_PID_AZUREWAVE_AD_TU700 0x3237 -#define USB_PID_AZUREWAVE_6007 0x0ccd -#define USB_PID_AVERMEDIA_DVBT_USB_COLD 0x0001 -#define USB_PID_AVERMEDIA_DVBT_USB_WARM 0x0002 +#define USB_PID_ARTEC_T14BR 0x810f +#define USB_PID_ARTEC_T14_COLD 0x810b +#define USB_PID_ARTEC_T14_WARM 0x810c +#define USB_PID_ASUS_U3000 0x171f +#define USB_PID_ASUS_U3000H 0x1736 +#define USB_PID_ASUS_U3100 0x173f +#define USB_PID_ASUS_U3100MINI_PLUS 0x1779 +#define USB_PID_AVERMEDIA_1867 0x1867 +#define USB_PID_AVERMEDIA_A309 0xa309 +#define USB_PID_AVERMEDIA_A310 0xa310 +#define USB_PID_AVERMEDIA_A805 0xa805 +#define USB_PID_AVERMEDIA_A815M 0x815a +#define USB_PID_AVERMEDIA_A835 0xa835 +#define USB_PID_AVERMEDIA_A835B_1835 0x1835 +#define USB_PID_AVERMEDIA_A835B_2835 0x2835 +#define USB_PID_AVERMEDIA_A835B_3835 0x3835 +#define USB_PID_AVERMEDIA_A835B_4835 0x4835 +#define USB_PID_AVERMEDIA_A850 0x850a +#define USB_PID_AVERMEDIA_A850T 0x850b +#define USB_PID_AVERMEDIA_A867 0xa867 +#define USB_PID_AVERMEDIA_B835 0xb835 #define USB_PID_AVERMEDIA_DVBT_USB2_COLD 0xa800 #define USB_PID_AVERMEDIA_DVBT_USB2_WARM 0xa801 +#define USB_PID_AVERMEDIA_DVBT_USB_COLD 0x0001 +#define USB_PID_AVERMEDIA_DVBT_USB_WARM 0x0002 +#define USB_PID_AVERMEDIA_EXPRESS 0xb568 +#define USB_PID_AVERMEDIA_H335 0x0335 +#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R 0x0039 +#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_ATSC 0x1039 +#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_DVBT 0x2039 +#define USB_PID_AVERMEDIA_MCE_USB_M038 0x1228 +#define USB_PID_AVERMEDIA_TD110 0xa110 +#define USB_PID_AVERMEDIA_TD310 0x1871 +#define USB_PID_AVERMEDIA_TWINSTAR 0x0825 +#define USB_PID_AVERMEDIA_VOLAR 0xa807 +#define USB_PID_AVERMEDIA_VOLAR_2 0xb808 +#define USB_PID_AVERMEDIA_VOLAR_A868R 0xa868 +#define USB_PID_AVERMEDIA_VOLAR_X 0xa815 +#define USB_PID_AVERMEDIA_VOLAR_X_2 0x8150 +#define USB_PID_AZUREWAVE_6007 0x0ccd +#define USB_PID_AZUREWAVE_AD_TU700 0x3237 +#define USB_PID_AZUREWAVE_AZ6027 0x3275 #define USB_PID_COMPRO_DVBU2000_COLD 0xd000 -#define USB_PID_COMPRO_DVBU2000_WARM 0xd001 #define USB_PID_COMPRO_DVBU2000_UNK_COLD 0x010c #define USB_PID_COMPRO_DVBU2000_UNK_WARM 0x010d +#define USB_PID_COMPRO_DVBU2000_WARM 0xd001 #define USB_PID_COMPRO_VIDEOMATE_U500 0x1e78 #define USB_PID_COMPRO_VIDEOMATE_U500_PC 0x1e80 #define USB_PID_CONCEPTRONIC_CTVDIGRCU 0xe397 #define USB_PID_CONEXANT_D680_DMB 0x86d6 -#define USB_PID_CREATIX_CTX1921 0x1921 +#define USB_PID_CPYTO_REDI_PC50A 0xa803 +#define USB_PID_CREATIX_CTX1921 0x1921 +#define USB_PID_CTVDIGDUAL_V2 0xe410 #define USB_PID_DELOCK_USB2_DVBT 0xb803 +#define USB_PID_DIBCOM_ANCHOR_2135_COLD 0x2131 #define USB_PID_DIBCOM_HOOK_DEFAULT 0x0064 #define USB_PID_DIBCOM_HOOK_DEFAULT_REENUM 0x0065 #define USB_PID_DIBCOM_MOD3000_COLD 0x0bb8 #define USB_PID_DIBCOM_MOD3000_WARM 0x0bb9 #define USB_PID_DIBCOM_MOD3001_COLD 0x0bc6 #define USB_PID_DIBCOM_MOD3001_WARM 0x0bc7 -#define USB_PID_DIBCOM_STK7700P 0x1e14 +#define USB_PID_DIBCOM_NIM7090 0x1bb2 +#define USB_PID_DIBCOM_NIM8096MD 0x1fa8 +#define USB_PID_DIBCOM_NIM9090M 0x2383 +#define USB_PID_DIBCOM_NIM9090MD 0x2384 +#define USB_PID_DIBCOM_STK7070P 0x1ebc +#define USB_PID_DIBCOM_STK7070PD 0x1ebe +#define USB_PID_DIBCOM_STK7700D 0x1ef0 +#define USB_PID_DIBCOM_STK7700P 0x1e14 #define USB_PID_DIBCOM_STK7700P_PC 0x1e78 -#define USB_PID_DIBCOM_STK7700D 0x1ef0 #define USB_PID_DIBCOM_STK7700_U7000 0x7001 -#define USB_PID_DIBCOM_STK7070P 0x1ebc -#define USB_PID_DIBCOM_STK7070PD 0x1ebe -#define USB_PID_DIBCOM_STK807XP 0x1f90 +#define USB_PID_DIBCOM_STK7770P 0x1e80 +#define USB_PID_DIBCOM_STK807XP 0x1f90 #define USB_PID_DIBCOM_STK807XPVR 0x1f98 -#define USB_PID_DIBCOM_STK8096GP 0x1fa0 -#define USB_PID_DIBCOM_STK8096PVR 0x1faa -#define USB_PID_DIBCOM_NIM8096MD 0x1fa8 -#define USB_PID_DIBCOM_TFE8096P 0x1f9C -#define USB_PID_DIBCOM_ANCHOR_2135_COLD 0x2131 -#define USB_PID_DIBCOM_STK7770P 0x1e80 -#define USB_PID_DIBCOM_NIM7090 0x1bb2 +#define USB_PID_DIBCOM_STK8096GP 0x1fa0 +#define USB_PID_DIBCOM_STK8096PVR 0x1faa #define USB_PID_DIBCOM_TFE7090PVR 0x1bb4 -#define USB_PID_DIBCOM_TFE7790P 0x1e6e -#define USB_PID_DIBCOM_NIM9090M 0x2383 -#define USB_PID_DIBCOM_NIM9090MD 0x2384 +#define USB_PID_DIBCOM_TFE7790P 0x1e6e +#define USB_PID_DIBCOM_TFE8096P 0x1f9C +#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_COLD 0xdb54 +#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_WARM 0xdb55 +#define USB_PID_DIGIVOX_MINI_SL_COLD 0xe360 +#define USB_PID_DIGIVOX_MINI_SL_WARM 0xe361 +#define USB_PID_DNTV_TINYUSB2_COLD 0x3223 +#define USB_PID_DNTV_TINYUSB2_WARM 0x3224 #define USB_PID_DPOSH_M9206_COLD 0x9206 #define USB_PID_DPOSH_M9206_WARM 0xa090 +#define USB_PID_DTT200U_COLD 0x0201 +#define USB_PID_DTT200U_WARM 0x0301 +#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD 0x5000 +#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_WARM 0x5001 +#define USB_PID_DVICO_BLUEBIRD_DUAL_1_COLD 0xdb50 +#define USB_PID_DVICO_BLUEBIRD_DUAL_1_WARM 0xdb51 +#define USB_PID_DVICO_BLUEBIRD_DUAL_2_COLD 0xdb58 +#define USB_PID_DVICO_BLUEBIRD_DUAL_2_WARM 0xdb59 +#define USB_PID_DVICO_BLUEBIRD_DUAL_4 0xdb78 +#define USB_PID_DVICO_BLUEBIRD_DUAL_4_REV_2 0xdb98 +#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2 0xdb70 +#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2_NFW_WARM 0xdb71 +#define USB_PID_DVICO_BLUEBIRD_LG064F_COLD 0xd500 +#define USB_PID_DVICO_BLUEBIRD_LG064F_WARM 0xd501 +#define USB_PID_DVICO_BLUEBIRD_LGDT 0xd820 +#define USB_PID_DVICO_BLUEBIRD_LGZ201_COLD 0xdb00 +#define USB_PID_DVICO_BLUEBIRD_LGZ201_WARM 0xdb01 +#define USB_PID_DVICO_BLUEBIRD_TH7579_COLD 0xdb10 +#define USB_PID_DVICO_BLUEBIRD_TH7579_WARM 0xdb11 +#define USB_PID_DW2102 0x2102 +#define USB_PID_DW2104 0x2104 +#define USB_PID_DW3101 0x3101 #define USB_PID_E3C_EC168 0x1689 #define USB_PID_E3C_EC168_2 0xfffa #define USB_PID_E3C_EC168_3 0xfffb #define USB_PID_E3C_EC168_4 0x1001 #define USB_PID_E3C_EC168_5 0x1002 +#define USB_PID_ELGATO_EYETV_DIVERSITY 0x0011 +#define USB_PID_ELGATO_EYETV_DTT 0x0021 +#define USB_PID_ELGATO_EYETV_DTT_2 0x003f +#define USB_PID_ELGATO_EYETV_DTT_Dlx 0x0020 +#define USB_PID_ELGATO_EYETV_SAT 0x002a +#define USB_PID_ELGATO_EYETV_SAT_V2 0x0025 +#define USB_PID_ELGATO_EYETV_SAT_V3 0x0036 +#define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 #define USB_PID_FREECOM_DVBT 0x0160 #define USB_PID_FREECOM_DVBT_2 0x0161 -#define USB_PID_UNIWILL_STK7700P 0x6003 +#define USB_PID_FRIIO_WHITE 0x0001 #define USB_PID_GENIUS_TVGO_DVB_T03 0x4012 +#define USB_PID_GENPIX_8PSK_REV_1_COLD 0x0200 +#define USB_PID_GENPIX_8PSK_REV_1_WARM 0x0201 +#define USB_PID_GENPIX_8PSK_REV_2 0x0202 +#define USB_PID_GENPIX_SKYWALKER_1 0x0203 +#define USB_PID_GENPIX_SKYWALKER_2 0x0206 +#define USB_PID_GENPIX_SKYWALKER_CW3K 0x0204 +#define USB_PID_GIGABYTE_U7000 0x7001 +#define USB_PID_GIGABYTE_U8000 0x7002 +#define USB_PID_GOTVIEW_SAT_HD 0x5456 +#define USB_PID_GRANDTEC_DVBT_USB2_COLD 0x0bc6 +#define USB_PID_GRANDTEC_DVBT_USB2_WARM 0x0bc7 #define USB_PID_GRANDTEC_DVBT_USB_COLD 0x0fa0 #define USB_PID_GRANDTEC_DVBT_USB_WARM 0x0fa1 -#define USB_PID_GOTVIEW_SAT_HD 0x5456 +#define USB_PID_HAMA_DVBT_HYBRID 0x2758 +#define USB_PID_HANFTEK_UMT_010_COLD 0x0001 +#define USB_PID_HANFTEK_UMT_010_WARM 0x0015 +#define USB_PID_HAUPPAUGE_MYTV_T 0x7080 +#define USB_PID_HAUPPAUGE_NOVA_TD_STICK 0x9580 +#define USB_PID_HAUPPAUGE_NOVA_TD_STICK_52009 0x5200 +#define USB_PID_HAUPPAUGE_NOVA_T_500 0x9941 +#define USB_PID_HAUPPAUGE_NOVA_T_500_2 0x9950 +#define USB_PID_HAUPPAUGE_NOVA_T_500_3 0x8400 +#define USB_PID_HAUPPAUGE_NOVA_T_STICK 0x7050 +#define USB_PID_HAUPPAUGE_NOVA_T_STICK_2 0x7060 +#define USB_PID_HAUPPAUGE_NOVA_T_STICK_3 0x7070 +#define USB_PID_HAUPPAUGE_TIGER_ATSC 0xb200 +#define USB_PID_HAUPPAUGE_TIGER_ATSC_B210 0xb210 #define USB_PID_INTEL_CE9500 0x9500 #define USB_PID_ITETECH_IT9135 0x9135 #define USB_PID_ITETECH_IT9135_9005 0x9005 #define USB_PID_ITETECH_IT9135_9006 0x9006 #define USB_PID_ITETECH_IT9303 0x9306 -#define USB_PID_KWORLD_399U 0xe399 -#define USB_PID_KWORLD_399U_2 0xe400 #define USB_PID_KWORLD_395U 0xe396 #define USB_PID_KWORLD_395U_2 0xe39b #define USB_PID_KWORLD_395U_3 0xe395 #define USB_PID_KWORLD_395U_4 0xe39a +#define USB_PID_KWORLD_399U 0xe399 +#define USB_PID_KWORLD_399U_2 0xe400 #define USB_PID_KWORLD_MC810 0xc810 -#define USB_PID_KWORLD_PC160_2T 0xc160 +#define USB_PID_KWORLD_PC160_2T 0xc160 #define USB_PID_KWORLD_PC160_T 0xc161 #define USB_PID_KWORLD_UB383_T 0xe383 #define USB_PID_KWORLD_UB499_2T_T09 0xe409 #define USB_PID_KWORLD_VSTREAM_COLD 0x17de #define USB_PID_KWORLD_VSTREAM_WARM 0x17df +#define USB_PID_KYE_DVB_T_COLD 0x701e +#define USB_PID_KYE_DVB_T_WARM 0x701f +#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_COLD 0x0514 +#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 +#define USB_PID_LITEON_DVB_T_COLD 0xf000 +#define USB_PID_LITEON_DVB_T_WARM 0xf001 +#define USB_PID_MEDION_MD95700 0x0932 +#define USB_PID_MSI_DIGIVOX_DUO 0x8801 +#define USB_PID_MSI_DIGI_VOX_MINI_II 0x1513 +#define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 +#define USB_PID_MSI_MEGASKY580 0x5580 +#define USB_PID_MSI_MEGASKY580_55801 0x5581 +#define USB_PID_MYGICA_D689 0xd811 +#define USB_PID_MYGICA_T230 0xc688 +#define USB_PID_MYGICA_T230A 0x689a +#define USB_PID_MYGICA_T230C 0xc689 +#define USB_PID_MYGICA_T230C2 0xc68a +#define USB_PID_MYGICA_T230C2_LITE 0xc69a +#define USB_PID_MYGICA_T230C_LITE 0xc699 +#define USB_PID_NEBULA_DIGITV 0x0201 +#define USB_PID_NOXON_DAB_STICK 0x00b3 +#define USB_PID_NOXON_DAB_STICK_REV2 0x00e0 +#define USB_PID_NOXON_DAB_STICK_REV3 0x00b4 +#define USB_PID_OPERA1_COLD 0x2830 +#define USB_PID_OPERA1_WARM 0x3829 +#define USB_PID_PCTV_2002E 0x025c +#define USB_PID_PCTV_2002E_SE 0x025d +#define USB_PID_PCTV_200E 0x020e +#define USB_PID_PCTV_400E 0x020f +#define USB_PID_PCTV_450E 0x0222 +#define USB_PID_PCTV_452E 0x021f +#define USB_PID_PCTV_78E 0x025a +#define USB_PID_PCTV_79E 0x0262 +#define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e +#define USB_PID_PINNACLE_PCTV2000E 0x022c +#define USB_PID_PINNACLE_PCTV282E 0x0248 +#define USB_PID_PINNACLE_PCTV310E 0x3211 +#define USB_PID_PINNACLE_PCTV340E 0x023d +#define USB_PID_PINNACLE_PCTV340E_SE 0x023e +#define USB_PID_PINNACLE_PCTV71E 0x022b +#define USB_PID_PINNACLE_PCTV72E 0x0236 +#define USB_PID_PINNACLE_PCTV73A 0x0243 +#define USB_PID_PINNACLE_PCTV73E 0x0237 +#define USB_PID_PINNACLE_PCTV73ESE 0x0245 +#define USB_PID_PINNACLE_PCTV74E 0x0246 +#define USB_PID_PINNACLE_PCTV801E 0x023a +#define USB_PID_PINNACLE_PCTV801E_SE 0x023b +#define USB_PID_PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T 0x0229 +#define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 +#define USB_PID_PIXELVIEW_SBTVD 0x5010 #define USB_PID_PROF_1100 0xb012 +#define USB_PID_PROLECTRIX_DV107669 0xd803 +#define USB_PID_REALTEK_RTL2831U 0x2831 +#define USB_PID_REALTEK_RTL2832U 0x2832 +#define USB_PID_SIGMATEK_DVB_110 0x6610 +#define USB_PID_SONY_PLAYTV 0x0003 +#define USB_PID_SVEON_STV20 0xe39d +#define USB_PID_SVEON_STV20_RTL2832U 0xd39d +#define USB_PID_SVEON_STV21 0xd3b0 +#define USB_PID_SVEON_STV22 0xe401 +#define USB_PID_SVEON_STV22_IT9137 0xe411 +#define USB_PID_SVEON_STV27 0xd3af +#define USB_PID_TECHNISAT_AIRSTAR_TELESTICK_2 0x0004 +#define USB_PID_TECHNISAT_USB2_CABLESTAR_HDCI 0x0003 +#define USB_PID_TECHNISAT_USB2_DVB_S2 0x0500 +#define USB_PID_TECHNISAT_USB2_HDCI_V1 0x0001 +#define USB_PID_TECHNISAT_USB2_HDCI_V2 0x0002 +#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI 0x3012 +#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI_2 0x3015 +#define USB_PID_TECHNOTREND_CONNECT_CT3650 0x300d +#define USB_PID_TECHNOTREND_CONNECT_S2400 0x3006 +#define USB_PID_TECHNOTREND_CONNECT_S2400_8KEEPROM 0x3009 +#define USB_PID_TECHNOTREND_CONNECT_S2_3600 0x3007 +#define USB_PID_TECHNOTREND_CONNECT_S2_3650_CI 0x300a +#define USB_PID_TECHNOTREND_CONNECT_S2_4600 0x3011 +#define USB_PID_TECHNOTREND_CONNECT_S2_4650_CI 0x3017 +#define USB_PID_TECHNOTREND_TVSTICK_CT2_4400 0x3014 +#define USB_PID_TELESTAR_STARSTICK_2 0x8000 +#define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY 0x005a +#define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY_2 0x0081 +#define USB_PID_TERRATEC_CINERGY_HT_EXPRESS 0x0060 +#define USB_PID_TERRATEC_CINERGY_HT_USB_XE 0x0058 #define USB_PID_TERRATEC_CINERGY_S 0x0064 -#define USB_PID_TERRATEC_CINERGY_T_USB_XE 0x0055 -#define USB_PID_TERRATEC_CINERGY_T_USB_XE_REV2 0x0069 +#define USB_PID_TERRATEC_CINERGY_S2_1 0x1181 +#define USB_PID_TERRATEC_CINERGY_S2_2 0x1182 +#define USB_PID_TERRATEC_CINERGY_S2_R1 0x00a8 +#define USB_PID_TERRATEC_CINERGY_S2_R2 0x00b0 +#define USB_PID_TERRATEC_CINERGY_S2_R3 0x0102 +#define USB_PID_TERRATEC_CINERGY_S2_R4 0x0105 +#define USB_PID_TERRATEC_CINERGY_TC2_STICK 0x10b2 +#define USB_PID_TERRATEC_CINERGY_T_EXPRESS 0x0062 #define USB_PID_TERRATEC_CINERGY_T_STICK 0x0093 -#define USB_PID_TERRATEC_CINERGY_T_STICK_RC 0x0097 -#define USB_PID_TERRATEC_CINERGY_T_STICK_DUAL_RC 0x0099 #define USB_PID_TERRATEC_CINERGY_T_STICK_BLACK_REV1 0x00a9 -#define USB_PID_TERRATEC_CINERGY_TC2_STICK 0x10b2 -#define USB_PID_TWINHAN_VP7041_COLD 0x3201 -#define USB_PID_TWINHAN_VP7041_WARM 0x3202 +#define USB_PID_TERRATEC_CINERGY_T_STICK_DUAL_RC 0x0099 +#define USB_PID_TERRATEC_CINERGY_T_STICK_RC 0x0097 +#define USB_PID_TERRATEC_CINERGY_T_USB_XE 0x0055 +#define USB_PID_TERRATEC_CINERGY_T_USB_XE_REV2 0x0069 +#define USB_PID_TERRATEC_CINERGY_T_XXS 0x0078 +#define USB_PID_TERRATEC_CINERGY_T_XXS_2 0x00ab +#define USB_PID_TERRATEC_DVBS2CI_V1 0x10a4 +#define USB_PID_TERRATEC_DVBS2CI_V2 0x10ac +#define USB_PID_TERRATEC_H7 0x10b4 +#define USB_PID_TERRATEC_H7_2 0x10a3 +#define USB_PID_TERRATEC_H7_3 0x10a5 +#define USB_PID_TERRATEC_T1 0x10ae +#define USB_PID_TERRATEC_T3 0x10a0 +#define USB_PID_TERRATEC_T5 0x10a1 +#define USB_PID_TEVII_S421 0xd421 +#define USB_PID_TEVII_S480_1 0xd481 +#define USB_PID_TEVII_S480_2 0xd482 +#define USB_PID_TEVII_S630 0xd630 +#define USB_PID_TEVII_S632 0xd632 +#define USB_PID_TEVII_S650 0xd650 +#define USB_PID_TEVII_S660 0xd660 +#define USB_PID_TEVII_S662 0xd662 +#define USB_PID_TINYTWIN 0x3226 +#define USB_PID_TINYTWIN_2 0xe402 +#define USB_PID_TINYTWIN_3 0x9016 +#define USB_PID_TREKSTOR_DVBT 0x901b +#define USB_PID_TREKSTOR_TERRES_2_0 0xC803 +#define USB_PID_TURBOX_DTT_2000 0xd3a4 +#define USB_PID_TVWAY_PLUS 0x0002 #define USB_PID_TWINHAN_VP7020_COLD 0x3203 #define USB_PID_TWINHAN_VP7020_WARM 0x3204 -#define USB_PID_TWINHAN_VP7045_COLD 0x3205 -#define USB_PID_TWINHAN_VP7045_WARM 0x3206 #define USB_PID_TWINHAN_VP7021_COLD 0x3207 #define USB_PID_TWINHAN_VP7021_WARM 0x3208 +#define USB_PID_TWINHAN_VP7041_COLD 0x3201 +#define USB_PID_TWINHAN_VP7041_WARM 0x3202 +#define USB_PID_TWINHAN_VP7045_COLD 0x3205 +#define USB_PID_TWINHAN_VP7045_WARM 0x3206 #define USB_PID_TWINHAN_VP7049 0x3219 -#define USB_PID_TINYTWIN 0x3226 -#define USB_PID_TINYTWIN_2 0xe402 -#define USB_PID_TINYTWIN_3 0x9016 -#define USB_PID_DNTV_TINYUSB2_COLD 0x3223 -#define USB_PID_DNTV_TINYUSB2_WARM 0x3224 -#define USB_PID_ULTIMA_TVBOX_COLD 0x8105 -#define USB_PID_ULTIMA_TVBOX_WARM 0x8106 #define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 #define USB_PID_ULTIMA_TVBOX_AN2235_WARM 0x8108 #define USB_PID_ULTIMA_TVBOX_ANCHOR_COLD 0x2235 +#define USB_PID_ULTIMA_TVBOX_COLD 0x8105 #define USB_PID_ULTIMA_TVBOX_USB2_COLD 0x8109 -#define USB_PID_ULTIMA_TVBOX_USB2_WARM 0x810a -#define USB_PID_ARTEC_T14_COLD 0x810b -#define USB_PID_ARTEC_T14_WARM 0x810c -#define USB_PID_ARTEC_T14BR 0x810f #define USB_PID_ULTIMA_TVBOX_USB2_FX_COLD 0x8613 #define USB_PID_ULTIMA_TVBOX_USB2_FX_WARM 0x1002 +#define USB_PID_ULTIMA_TVBOX_USB2_WARM 0x810a +#define USB_PID_ULTIMA_TVBOX_WARM 0x8106 +#define USB_PID_UNIWILL_STK7700P 0x6003 #define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e #define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f -#define USB_PID_HANFTEK_UMT_010_COLD 0x0001 -#define USB_PID_HANFTEK_UMT_010_WARM 0x0015 -#define USB_PID_DTT200U_COLD 0x0201 -#define USB_PID_DTT200U_WARM 0x0301 -#define USB_PID_WT220U_ZAP250_COLD 0x0220 +#define USB_PID_WINFAST_DTV2000DS 0x6a04 +#define USB_PID_WINFAST_DTV2000DS_PLUS 0x6f12 +#define USB_PID_WINFAST_DTV_DONGLE_COLD 0x6025 +#define USB_PID_WINFAST_DTV_DONGLE_GOLD 0x6029 +#define USB_PID_WINFAST_DTV_DONGLE_H 0x60f6 +#define USB_PID_WINFAST_DTV_DONGLE_MINID 0x6f0f +#define USB_PID_WINFAST_DTV_DONGLE_STK7700P 0x6f00 +#define USB_PID_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 +#define USB_PID_WINFAST_DTV_DONGLE_WARM 0x6026 +#define USB_PID_WINTV_NOVA_T_USB2_COLD 0x9300 +#define USB_PID_WINTV_NOVA_T_USB2_WARM 0x9301 +#define USB_PID_WINTV_SOLOHD 0x0264 +#define USB_PID_WINTV_SOLOHD_2 0x8268 #define USB_PID_WT220U_COLD 0x0222 -#define USB_PID_WT220U_WARM 0x0221 #define USB_PID_WT220U_FC_COLD 0x0225 #define USB_PID_WT220U_FC_WARM 0x0226 +#define USB_PID_WT220U_WARM 0x0221 +#define USB_PID_WT220U_ZAP250_COLD 0x0220 #define USB_PID_WT220U_ZL0353_COLD 0x022a #define USB_PID_WT220U_ZL0353_WARM 0x022b -#define USB_PID_WINTV_NOVA_T_USB2_COLD 0x9300 -#define USB_PID_WINTV_NOVA_T_USB2_WARM 0x9301 -#define USB_PID_HAUPPAUGE_NOVA_T_500 0x9941 -#define USB_PID_HAUPPAUGE_NOVA_T_500_2 0x9950 -#define USB_PID_HAUPPAUGE_NOVA_T_500_3 0x8400 -#define USB_PID_HAUPPAUGE_NOVA_T_STICK 0x7050 -#define USB_PID_HAUPPAUGE_NOVA_T_STICK_2 0x7060 -#define USB_PID_HAUPPAUGE_NOVA_T_STICK_3 0x7070 -#define USB_PID_HAUPPAUGE_MYTV_T 0x7080 -#define USB_PID_HAUPPAUGE_NOVA_TD_STICK 0x9580 -#define USB_PID_HAUPPAUGE_NOVA_TD_STICK_52009 0x5200 -#define USB_PID_HAUPPAUGE_TIGER_ATSC 0xb200 -#define USB_PID_HAUPPAUGE_TIGER_ATSC_B210 0xb210 -#define USB_PID_AVERMEDIA_EXPRESS 0xb568 -#define USB_PID_AVERMEDIA_VOLAR 0xa807 -#define USB_PID_AVERMEDIA_VOLAR_2 0xb808 -#define USB_PID_AVERMEDIA_VOLAR_A868R 0xa868 -#define USB_PID_AVERMEDIA_MCE_USB_M038 0x1228 -#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R 0x0039 -#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_ATSC 0x1039 -#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_DVBT 0x2039 -#define USB_PID_AVERMEDIA_VOLAR_X 0xa815 -#define USB_PID_AVERMEDIA_VOLAR_X_2 0x8150 -#define USB_PID_AVERMEDIA_A309 0xa309 -#define USB_PID_AVERMEDIA_A310 0xa310 -#define USB_PID_AVERMEDIA_A850 0x850a -#define USB_PID_AVERMEDIA_A850T 0x850b -#define USB_PID_AVERMEDIA_A805 0xa805 -#define USB_PID_AVERMEDIA_A815M 0x815a -#define USB_PID_AVERMEDIA_A835 0xa835 -#define USB_PID_AVERMEDIA_B835 0xb835 -#define USB_PID_AVERMEDIA_A835B_1835 0x1835 -#define USB_PID_AVERMEDIA_A835B_2835 0x2835 -#define USB_PID_AVERMEDIA_A835B_3835 0x3835 -#define USB_PID_AVERMEDIA_A835B_4835 0x4835 -#define USB_PID_AVERMEDIA_1867 0x1867 -#define USB_PID_AVERMEDIA_A867 0xa867 -#define USB_PID_AVERMEDIA_H335 0x0335 -#define USB_PID_AVERMEDIA_TD110 0xa110 -#define USB_PID_AVERMEDIA_TD310 0x1871 -#define USB_PID_AVERMEDIA_TWINSTAR 0x0825 -#define USB_PID_TECHNOTREND_CONNECT_S2400 0x3006 -#define USB_PID_TECHNOTREND_CONNECT_S2400_8KEEPROM 0x3009 -#define USB_PID_TECHNOTREND_CONNECT_CT3650 0x300d -#define USB_PID_TECHNOTREND_CONNECT_S2_4600 0x3011 -#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI 0x3012 -#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI_2 0x3015 -#define USB_PID_TECHNOTREND_TVSTICK_CT2_4400 0x3014 -#define USB_PID_TECHNOTREND_CONNECT_S2_4650_CI 0x3017 -#define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY 0x005a -#define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY_2 0x0081 -#define USB_PID_TERRATEC_CINERGY_HT_USB_XE 0x0058 -#define USB_PID_TERRATEC_CINERGY_HT_EXPRESS 0x0060 -#define USB_PID_TERRATEC_CINERGY_T_EXPRESS 0x0062 -#define USB_PID_TERRATEC_CINERGY_T_XXS 0x0078 -#define USB_PID_TERRATEC_CINERGY_T_XXS_2 0x00ab -#define USB_PID_TERRATEC_CINERGY_S2_R1 0x00a8 -#define USB_PID_TERRATEC_CINERGY_S2_R2 0x00b0 -#define USB_PID_TERRATEC_CINERGY_S2_R3 0x0102 -#define USB_PID_TERRATEC_CINERGY_S2_R4 0x0105 -#define USB_PID_TERRATEC_CINERGY_S2_1 0x1181 -#define USB_PID_TERRATEC_CINERGY_S2_2 0x1182 -#define USB_PID_TERRATEC_H7 0x10b4 -#define USB_PID_TERRATEC_H7_2 0x10a3 -#define USB_PID_TERRATEC_H7_3 0x10a5 -#define USB_PID_TERRATEC_T1 0x10ae -#define USB_PID_TERRATEC_T3 0x10a0 -#define USB_PID_TERRATEC_T5 0x10a1 -#define USB_PID_NOXON_DAB_STICK 0x00b3 -#define USB_PID_NOXON_DAB_STICK_REV2 0x00e0 -#define USB_PID_NOXON_DAB_STICK_REV3 0x00b4 -#define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e -#define USB_PID_PINNACLE_PCTV2000E 0x022c -#define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 -#define USB_PID_PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T 0x0229 -#define USB_PID_PINNACLE_PCTV71E 0x022b -#define USB_PID_PINNACLE_PCTV72E 0x0236 -#define USB_PID_PINNACLE_PCTV73E 0x0237 -#define USB_PID_PINNACLE_PCTV310E 0x3211 -#define USB_PID_PINNACLE_PCTV801E 0x023a -#define USB_PID_PINNACLE_PCTV801E_SE 0x023b -#define USB_PID_PINNACLE_PCTV340E 0x023d -#define USB_PID_PINNACLE_PCTV340E_SE 0x023e -#define USB_PID_PINNACLE_PCTV73A 0x0243 -#define USB_PID_PINNACLE_PCTV73ESE 0x0245 -#define USB_PID_PINNACLE_PCTV74E 0x0246 -#define USB_PID_PINNACLE_PCTV282E 0x0248 -#define USB_PID_PIXELVIEW_SBTVD 0x5010 -#define USB_PID_PCTV_200E 0x020e -#define USB_PID_PCTV_400E 0x020f -#define USB_PID_PCTV_450E 0x0222 -#define USB_PID_PCTV_452E 0x021f -#define USB_PID_PCTV_78E 0x025a -#define USB_PID_PCTV_79E 0x0262 -#define USB_PID_REALTEK_RTL2831U 0x2831 -#define USB_PID_REALTEK_RTL2832U 0x2832 -#define USB_PID_TECHNOTREND_CONNECT_S2_3600 0x3007 -#define USB_PID_TECHNOTREND_CONNECT_S2_3650_CI 0x300a -#define USB_PID_NEBULA_DIGITV 0x0201 -#define USB_PID_DVICO_BLUEBIRD_LGDT 0xd820 -#define USB_PID_DVICO_BLUEBIRD_LG064F_COLD 0xd500 -#define USB_PID_DVICO_BLUEBIRD_LG064F_WARM 0xd501 -#define USB_PID_DVICO_BLUEBIRD_LGZ201_COLD 0xdb00 -#define USB_PID_DVICO_BLUEBIRD_LGZ201_WARM 0xdb01 -#define USB_PID_DVICO_BLUEBIRD_TH7579_COLD 0xdb10 -#define USB_PID_DVICO_BLUEBIRD_TH7579_WARM 0xdb11 -#define USB_PID_DVICO_BLUEBIRD_DUAL_1_COLD 0xdb50 -#define USB_PID_DVICO_BLUEBIRD_DUAL_1_WARM 0xdb51 -#define USB_PID_DVICO_BLUEBIRD_DUAL_2_COLD 0xdb58 -#define USB_PID_DVICO_BLUEBIRD_DUAL_2_WARM 0xdb59 -#define USB_PID_DVICO_BLUEBIRD_DUAL_4 0xdb78 -#define USB_PID_DVICO_BLUEBIRD_DUAL_4_REV_2 0xdb98 -#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2 0xdb70 -#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2_NFW_WARM 0xdb71 -#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_COLD 0xdb54 -#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_WARM 0xdb55 -#define USB_PID_MEDION_MD95700 0x0932 -#define USB_PID_MSI_MEGASKY580 0x5580 -#define USB_PID_MSI_MEGASKY580_55801 0x5581 -#define USB_PID_KYE_DVB_T_COLD 0x701e -#define USB_PID_KYE_DVB_T_WARM 0x701f -#define USB_PID_LITEON_DVB_T_COLD 0xf000 -#define USB_PID_LITEON_DVB_T_WARM 0xf001 -#define USB_PID_DIGIVOX_MINI_SL_COLD 0xe360 -#define USB_PID_DIGIVOX_MINI_SL_WARM 0xe361 -#define USB_PID_GRANDTEC_DVBT_USB2_COLD 0x0bc6 -#define USB_PID_GRANDTEC_DVBT_USB2_WARM 0x0bc7 -#define USB_PID_WINFAST_DTV2000DS 0x6a04 -#define USB_PID_WINFAST_DTV2000DS_PLUS 0x6f12 -#define USB_PID_WINFAST_DTV_DONGLE_COLD 0x6025 -#define USB_PID_WINFAST_DTV_DONGLE_WARM 0x6026 -#define USB_PID_WINFAST_DTV_DONGLE_STK7700P 0x6f00 -#define USB_PID_WINFAST_DTV_DONGLE_H 0x60f6 -#define USB_PID_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 -#define USB_PID_WINFAST_DTV_DONGLE_GOLD 0x6029 -#define USB_PID_WINFAST_DTV_DONGLE_MINID 0x6f0f -#define USB_PID_GENPIX_8PSK_REV_1_COLD 0x0200 -#define USB_PID_GENPIX_8PSK_REV_1_WARM 0x0201 -#define USB_PID_GENPIX_8PSK_REV_2 0x0202 -#define USB_PID_GENPIX_SKYWALKER_1 0x0203 -#define USB_PID_GENPIX_SKYWALKER_CW3K 0x0204 -#define USB_PID_GENPIX_SKYWALKER_2 0x0206 -#define USB_PID_SIGMATEK_DVB_110 0x6610 -#define USB_PID_MSI_DIGI_VOX_MINI_II 0x1513 -#define USB_PID_MSI_DIGIVOX_DUO 0x8801 -#define USB_PID_OPERA1_COLD 0x2830 -#define USB_PID_OPERA1_WARM 0x3829 -#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_COLD 0x0514 -#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 -#define USB_PID_GIGABYTE_U7000 0x7001 -#define USB_PID_GIGABYTE_U8000 0x7002 -#define USB_PID_ASUS_U3000 0x171f -#define USB_PID_ASUS_U3000H 0x1736 -#define USB_PID_ASUS_U3100 0x173f -#define USB_PID_ASUS_U3100MINI_PLUS 0x1779 +#define USB_PID_XBOX_ONE_TUNER 0x02d5 +#define USB_PID_XTENSIONS_XD_380 0x0381 #define USB_PID_YUAN_EC372S 0x1edc -#define USB_PID_YUAN_STK7700PH 0x1f08 -#define USB_PID_YUAN_PD378S 0x2edc #define USB_PID_YUAN_MC770 0x0871 +#define USB_PID_YUAN_PD378S 0x2edc #define USB_PID_YUAN_STK7700D 0x1efc -#define USB_PID_YUAN_STK7700D_2 0x1e8c -#define USB_PID_DW2102 0x2102 -#define USB_PID_DW2104 0x2104 -#define USB_PID_DW3101 0x3101 -#define USB_PID_XTENSIONS_XD_380 0x0381 -#define USB_PID_TELESTAR_STARSTICK_2 0x8000 -#define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 -#define USB_PID_SONY_PLAYTV 0x0003 -#define USB_PID_MYGICA_D689 0xd811 -#define USB_PID_MYGICA_T230 0xc688 -#define USB_PID_MYGICA_T230C 0xc689 -#define USB_PID_MYGICA_T230C2 0xc68a -#define USB_PID_MYGICA_T230C_LITE 0xc699 -#define USB_PID_MYGICA_T230C2_LITE 0xc69a -#define USB_PID_MYGICA_T230A 0x689a -#define USB_PID_ELGATO_EYETV_DIVERSITY 0x0011 -#define USB_PID_ELGATO_EYETV_DTT 0x0021 -#define USB_PID_ELGATO_EYETV_DTT_2 0x003f -#define USB_PID_ELGATO_EYETV_DTT_Dlx 0x0020 -#define USB_PID_ELGATO_EYETV_SAT 0x002a -#define USB_PID_ELGATO_EYETV_SAT_V2 0x0025 -#define USB_PID_ELGATO_EYETV_SAT_V3 0x0036 -#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD 0x5000 -#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_WARM 0x5001 -#define USB_PID_FRIIO_WHITE 0x0001 -#define USB_PID_TVWAY_PLUS 0x0002 -#define USB_PID_SVEON_STV20 0xe39d -#define USB_PID_SVEON_STV20_RTL2832U 0xd39d -#define USB_PID_SVEON_STV21 0xd3b0 -#define USB_PID_SVEON_STV22 0xe401 -#define USB_PID_SVEON_STV22_IT9137 0xe411 -#define USB_PID_AZUREWAVE_AZ6027 0x3275 -#define USB_PID_TERRATEC_DVBS2CI_V1 0x10a4 -#define USB_PID_TERRATEC_DVBS2CI_V2 0x10ac -#define USB_PID_TECHNISAT_USB2_HDCI_V1 0x0001 -#define USB_PID_TECHNISAT_USB2_HDCI_V2 0x0002 -#define USB_PID_TECHNISAT_USB2_CABLESTAR_HDCI 0x0003 -#define USB_PID_TECHNISAT_AIRSTAR_TELESTICK_2 0x0004 -#define USB_PID_TECHNISAT_USB2_DVB_S2 0x0500 -#define USB_PID_CPYTO_REDI_PC50A 0xa803 -#define USB_PID_CTVDIGDUAL_V2 0xe410 -#define USB_PID_PCTV_2002E 0x025c -#define USB_PID_PCTV_2002E_SE 0x025d -#define USB_PID_SVEON_STV27 0xd3af -#define USB_PID_TURBOX_DTT_2000 0xd3a4 -#define USB_PID_WINTV_SOLOHD 0x0264 -#define USB_PID_WINTV_SOLOHD_2 0x8268 -#define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 -#define USB_PID_HAMA_DVBT_HYBRID 0x2758 -#define USB_PID_XBOX_ONE_TUNER 0x02d5 -#define USB_PID_PROLECTRIX_DV107669 0xd803 +#define USB_PID_YUAN_STK7700D_2 0x1e8c +#define USB_PID_YUAN_STK7700PH 0x1f08 + #endif -- cgit v1.2.3 From 2f8bc51dd0c5b9376259ae03e2a145e5261e06a9 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:14 +0200 Subject: media: dvb-usb: move USB IDs to dvb-usb-ids.h Almost all drivers based on dvb-usb place their USB IDs at dvb-usb-ids.h. In order to make it more standard, place the remaining ones also there. Link: https://lore.kernel.org/linux-media/7b32d5383169d23082758a7b69edef2f099202f3.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index dcf5772c84a0..9577cae8c73b 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -17,6 +17,7 @@ #define USB_VID_AFATECH 0x15a4 #define USB_VID_ALCOR_MICRO 0x058f #define USB_VID_ALINK 0x05e3 +#define USB_VID_AME 0x06be #define USB_VID_AMT 0x1c73 #define USB_VID_ANCHOR 0x0547 #define USB_VID_ANSONIC 0x10b9 @@ -38,6 +39,7 @@ #define USB_VID_EVOLUTEPC 0x1e59 #define USB_VID_GENPIX 0x09c0 #define USB_VID_GIGABYTE 0x1044 +#define USB_VID_GOTVIEW 0x1fe1 #define USB_VID_GRANDTEC 0x5032 #define USB_VID_GTEK 0x1f4d #define USB_VID_HAMA 0x147f @@ -61,6 +63,8 @@ #define USB_VID_PCTV 0x2013 #define USB_VID_PINNACLE 0x2304 #define USB_VID_PIXELVIEW 0x1554 +#define USB_VID_PROF_1 0x3011 +#define USB_VID_PROF_2 0x3034 #define USB_VID_REALTEK 0x0bda #define USB_VID_SONY 0x1415 #define USB_VID_TECHNISAT 0x14f7 @@ -68,6 +72,7 @@ #define USB_VID_TELESTAR 0x10b9 #define USB_VID_TERRATEC 0x0ccd #define USB_VID_TERRATEC_2 0x153b +#define USB_VID_TEVII 0x9022 #define USB_VID_TWINHAN 0x1822 #define USB_VID_ULTIMA_ELECTRONIC 0x05d8 #define USB_VID_UNIWILL 0x1584 @@ -90,6 +95,7 @@ #define USB_PID_AFATECH_AF9035_1003 0x1003 #define USB_PID_AFATECH_AF9035_9035 0x9035 #define USB_PID_ALINK_DTU 0xf170 +#define USB_PID_AME_DTV5100 0xa232 #define USB_PID_ANSONIC_DVBT_USB 0x6000 #define USB_PID_ANYSEE 0x861f #define USB_PID_ARTEC_T14BR 0x810f @@ -198,6 +204,7 @@ #define USB_PID_DVICO_BLUEBIRD_LGZ201_WARM 0xdb01 #define USB_PID_DVICO_BLUEBIRD_TH7579_COLD 0xdb10 #define USB_PID_DVICO_BLUEBIRD_TH7579_WARM 0xdb11 +#define USB_PID_DW2101 0x2101 #define USB_PID_DW2102 0x2102 #define USB_PID_DW2104 0x2104 #define USB_PID_DW3101 0x3101 @@ -217,6 +224,9 @@ #define USB_PID_FREECOM_DVBT 0x0160 #define USB_PID_FREECOM_DVBT_2 0x0161 #define USB_PID_FRIIO_WHITE 0x0001 +#define USB_PID_GENIATECH_SU3000 0x3000 +#define USB_PID_GENIATECH_T220 0xd220 +#define USB_PID_GENIATECH_X3M_SPC1400HD 0x3100 #define USB_PID_GENIUS_TVGO_DVB_T03 0x4012 #define USB_PID_GENPIX_8PSK_REV_1_COLD 0x0200 #define USB_PID_GENPIX_8PSK_REV_1_WARM 0x0201 @@ -234,6 +244,7 @@ #define USB_PID_HAMA_DVBT_HYBRID 0x2758 #define USB_PID_HANFTEK_UMT_010_COLD 0x0001 #define USB_PID_HANFTEK_UMT_010_WARM 0x0015 +#define USB_PID_HAUPPAUGE_MAX_S2 0xd900 #define USB_PID_HAUPPAUGE_MYTV_T 0x7080 #define USB_PID_HAUPPAUGE_NOVA_TD_STICK 0x9580 #define USB_PID_HAUPPAUGE_NOVA_TD_STICK_52009 0x5200 @@ -314,6 +325,7 @@ #define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 #define USB_PID_PIXELVIEW_SBTVD 0x5010 #define USB_PID_PROF_1100 0xb012 +#define USB_PID_PROF_7500 0x7500 #define USB_PID_PROLECTRIX_DV107669 0xd803 #define USB_PID_REALTEK_RTL2831U 0x2831 #define USB_PID_REALTEK_RTL2832U 0x2832 @@ -348,10 +360,12 @@ #define USB_PID_TERRATEC_CINERGY_S 0x0064 #define USB_PID_TERRATEC_CINERGY_S2_1 0x1181 #define USB_PID_TERRATEC_CINERGY_S2_2 0x1182 +#define USB_PID_TERRATEC_CINERGY_S2_BOX 0x0105 #define USB_PID_TERRATEC_CINERGY_S2_R1 0x00a8 #define USB_PID_TERRATEC_CINERGY_S2_R2 0x00b0 #define USB_PID_TERRATEC_CINERGY_S2_R3 0x0102 #define USB_PID_TERRATEC_CINERGY_S2_R4 0x0105 +#define USB_PID_TERRATEC_CINERGY_T2 0x0038 #define USB_PID_TERRATEC_CINERGY_TC2_STICK 0x10b2 #define USB_PID_TERRATEC_CINERGY_T_EXPRESS 0x0062 #define USB_PID_TERRATEC_CINERGY_T_STICK 0x0093 @@ -383,6 +397,8 @@ #define USB_PID_TINYTWIN_3 0x9016 #define USB_PID_TREKSTOR_DVBT 0x901b #define USB_PID_TREKSTOR_TERRES_2_0 0xC803 +#define USB_PID_TTEVII_S482_1 0xd483 +#define USB_PID_TTEVII_S482_2 0xd484 #define USB_PID_TURBOX_DTT_2000 0xd3a4 #define USB_PID_TVWAY_PLUS 0x0002 #define USB_PID_TWINHAN_VP7020_COLD 0x3203 -- cgit v1.2.3 From 82a4a3ba3380bafc33f58c9b8057bb6577a7f113 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:16 +0200 Subject: media: dvb-usb: Add helper macros for using USB VID/PID In order to use designated initializers and to avoid avoid big lines at the USB ID tables, define some helper macros. Link: https://lore.kernel.org/linux-media/f82e376dea2e9b922f51a03d1e7730b03e49cc7d.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 9577cae8c73b..5ae55c20912e 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -10,6 +10,14 @@ #ifndef _DVB_USB_IDS_H_ #define _DVB_USB_IDS_H_ +#include + +#define DVB_USB_DEV(pid, vid) \ + [vid] = { USB_DEVICE(USB_VID_ ## pid, USB_PID_ ## vid) } + +#define DVB_USB_DEV_VER(pid, vid, lo, hi) \ + [vid] = { USB_DEVICE_VER(USB_VID_ ## pid, USB_PID_ ## vid, lo, hi) } + /* Vendor IDs */ #define USB_VID_774 0x7a69 -- cgit v1.2.3 From b18869ba190dce7ac9802143253fa0a0a639d059 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:22 +0200 Subject: media: digitv: use the newer dvb-usb macros for USB device In order to make the drivers under dvb-usb more homogeneous, use the new macro. Link: https://lore.kernel.org/linux-media/68de8820a361e61c25bf7402acac71b3770ff906.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 5ae55c20912e..c3bea2bf9dda 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -104,6 +104,7 @@ #define USB_PID_AFATECH_AF9035_9035 0x9035 #define USB_PID_ALINK_DTU 0xf170 #define USB_PID_AME_DTV5100 0xa232 +#define USB_PID_ANCHOR_NEBULA_DIGITV 0x0201 #define USB_PID_ANSONIC_DVBT_USB 0x6000 #define USB_PID_ANYSEE 0x861f #define USB_PID_ARTEC_T14BR 0x810f @@ -301,7 +302,6 @@ #define USB_PID_MYGICA_T230C2 0xc68a #define USB_PID_MYGICA_T230C2_LITE 0xc69a #define USB_PID_MYGICA_T230C_LITE 0xc699 -#define USB_PID_NEBULA_DIGITV 0x0201 #define USB_PID_NOXON_DAB_STICK 0x00b3 #define USB_PID_NOXON_DAB_STICK_REV2 0x00e0 #define USB_PID_NOXON_DAB_STICK_REV3 0x00b4 -- cgit v1.2.3 From 86fd1a41fc58108833358e3a5e238c548c98edd2 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:23 +0200 Subject: media: dvb-usb: dtt200u: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/9fa3d1add4c58e1320dcc18578fda2d0106becda.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index c3bea2bf9dda..66a5b2045552 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -194,8 +194,6 @@ #define USB_PID_DNTV_TINYUSB2_WARM 0x3224 #define USB_PID_DPOSH_M9206_COLD 0x9206 #define USB_PID_DPOSH_M9206_WARM 0xa090 -#define USB_PID_DTT200U_COLD 0x0201 -#define USB_PID_DTT200U_WARM 0x0301 #define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD 0x5000 #define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_WARM 0x5001 #define USB_PID_DVICO_BLUEBIRD_DUAL_1_COLD 0xdb50 @@ -290,6 +288,7 @@ #define USB_PID_LITEON_DVB_T_COLD 0xf000 #define USB_PID_LITEON_DVB_T_WARM 0xf001 #define USB_PID_MEDION_MD95700 0x0932 +#define USB_PID_MIGLIA_WT220U_ZAP250_COLD 0x0220 #define USB_PID_MSI_DIGIVOX_DUO 0x8801 #define USB_PID_MSI_DIGI_VOX_MINI_II 0x1513 #define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 @@ -430,6 +429,15 @@ #define USB_PID_UNIWILL_STK7700P 0x6003 #define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e #define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f +#define USB_PID_WIDEVIEW_DTT200U_COLD 0x0201 +#define USB_PID_WIDEVIEW_DTT200U_WARM 0x0301 +#define USB_PID_WIDEVIEW_WT220U_COLD 0x0222 +#define USB_PID_WIDEVIEW_WT220U_FC_COLD 0x0225 +#define USB_PID_WIDEVIEW_WT220U_FC_WARM 0x0226 +#define USB_PID_WIDEVIEW_WT220U_WARM 0x0221 +#define USB_PID_WIDEVIEW_WT220U_ZAP250_COLD 0x0220 +#define USB_PID_WIDEVIEW_WT220U_ZL0353_COLD 0x022a +#define USB_PID_WIDEVIEW_WT220U_ZL0353_WARM 0x022b #define USB_PID_WINFAST_DTV2000DS 0x6a04 #define USB_PID_WINFAST_DTV2000DS_PLUS 0x6f12 #define USB_PID_WINFAST_DTV_DONGLE_COLD 0x6025 @@ -443,13 +451,6 @@ #define USB_PID_WINTV_NOVA_T_USB2_WARM 0x9301 #define USB_PID_WINTV_SOLOHD 0x0264 #define USB_PID_WINTV_SOLOHD_2 0x8268 -#define USB_PID_WT220U_COLD 0x0222 -#define USB_PID_WT220U_FC_COLD 0x0225 -#define USB_PID_WT220U_FC_WARM 0x0226 -#define USB_PID_WT220U_WARM 0x0221 -#define USB_PID_WT220U_ZAP250_COLD 0x0220 -#define USB_PID_WT220U_ZL0353_COLD 0x022a -#define USB_PID_WT220U_ZL0353_WARM 0x022b #define USB_PID_XBOX_ONE_TUNER 0x02d5 #define USB_PID_XTENSIONS_XD_380 0x0381 #define USB_PID_YUAN_EC372S 0x1edc -- cgit v1.2.3 From 2fa2002f533e0ed847922cdf9479ea0875f4e49f Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:25 +0200 Subject: media: dw2102: use the newer dvb-usb macros for USB device In order to make the drivers under dvb-usb more homogeneous, use the new macro, and rename some PIDs. Link: https://lore.kernel.org/linux-media/828998ef3f0843bab4e84780e42f8f0802f57be7.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 66a5b2045552..e41902d06ccc 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -160,6 +160,10 @@ #define USB_PID_CPYTO_REDI_PC50A 0xa803 #define USB_PID_CREATIX_CTX1921 0x1921 #define USB_PID_CTVDIGDUAL_V2 0xe410 +#define USB_PID_CYPRESS_DW2101 0x2101 +#define USB_PID_CYPRESS_DW2102 0x2102 +#define USB_PID_CYPRESS_DW2104 0x2104 +#define USB_PID_CYPRESS_DW3101 0x3101 #define USB_PID_DELOCK_USB2_DVBT 0xb803 #define USB_PID_DIBCOM_ANCHOR_2135_COLD 0x2131 #define USB_PID_DIBCOM_HOOK_DEFAULT 0x0064 @@ -211,10 +215,6 @@ #define USB_PID_DVICO_BLUEBIRD_LGZ201_WARM 0xdb01 #define USB_PID_DVICO_BLUEBIRD_TH7579_COLD 0xdb10 #define USB_PID_DVICO_BLUEBIRD_TH7579_WARM 0xdb11 -#define USB_PID_DW2101 0x2101 -#define USB_PID_DW2102 0x2102 -#define USB_PID_DW2104 0x2104 -#define USB_PID_DW3101 0x3101 #define USB_PID_E3C_EC168 0x1689 #define USB_PID_E3C_EC168_2 0xfffa #define USB_PID_E3C_EC168_3 0xfffb @@ -394,6 +394,8 @@ #define USB_PID_TEVII_S421 0xd421 #define USB_PID_TEVII_S480_1 0xd481 #define USB_PID_TEVII_S480_2 0xd482 +#define USB_PID_TEVII_S482_1 0xd483 +#define USB_PID_TEVII_S482_2 0xd484 #define USB_PID_TEVII_S630 0xd630 #define USB_PID_TEVII_S632 0xd632 #define USB_PID_TEVII_S650 0xd650 @@ -404,8 +406,6 @@ #define USB_PID_TINYTWIN_3 0x9016 #define USB_PID_TREKSTOR_DVBT 0x901b #define USB_PID_TREKSTOR_TERRES_2_0 0xC803 -#define USB_PID_TTEVII_S482_1 0xd483 -#define USB_PID_TTEVII_S482_2 0xd484 #define USB_PID_TURBOX_DTT_2000 0xd3a4 #define USB_PID_TVWAY_PLUS 0x0002 #define USB_PID_TWINHAN_VP7020_COLD 0x3203 -- cgit v1.2.3 From 3473fd1711527c24b3d37d6b13cfd341e2d5a3c7 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:27 +0200 Subject: media: dvb-usb: m920x: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/c6f6bab97c39561add54f69a75980f4d453f7c17.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index e41902d06ccc..10d73c108149 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -106,6 +106,9 @@ #define USB_PID_AME_DTV5100 0xa232 #define USB_PID_ANCHOR_NEBULA_DIGITV 0x0201 #define USB_PID_ANSONIC_DVBT_USB 0x6000 +#define USB_PID_ANUBIS_LIFEVIEW_TV_WALKER_TWIN_COLD 0x0514 +#define USB_PID_ANUBIS_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 +#define USB_PID_ANUBIS_MSI_DIGI_VOX_MINI_II 0x1513 #define USB_PID_ANYSEE 0x861f #define USB_PID_ARTEC_T14BR 0x810f #define USB_PID_ARTEC_T14_COLD 0x810b @@ -149,6 +152,7 @@ #define USB_PID_AZUREWAVE_6007 0x0ccd #define USB_PID_AZUREWAVE_AD_TU700 0x3237 #define USB_PID_AZUREWAVE_AZ6027 0x3275 +#define USB_PID_AZUREWAVE_TWINHAN_VP7049 0x3219 #define USB_PID_COMPRO_DVBU2000_COLD 0xd000 #define USB_PID_COMPRO_DVBU2000_UNK_COLD 0x010c #define USB_PID_COMPRO_DVBU2000_UNK_WARM 0x010d @@ -283,14 +287,11 @@ #define USB_PID_KWORLD_VSTREAM_WARM 0x17df #define USB_PID_KYE_DVB_T_COLD 0x701e #define USB_PID_KYE_DVB_T_WARM 0x701f -#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_COLD 0x0514 -#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 #define USB_PID_LITEON_DVB_T_COLD 0xf000 #define USB_PID_LITEON_DVB_T_WARM 0xf001 #define USB_PID_MEDION_MD95700 0x0932 #define USB_PID_MIGLIA_WT220U_ZAP250_COLD 0x0220 #define USB_PID_MSI_DIGIVOX_DUO 0x8801 -#define USB_PID_MSI_DIGI_VOX_MINI_II 0x1513 #define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 #define USB_PID_MSI_MEGASKY580 0x5580 #define USB_PID_MSI_MEGASKY580_55801 0x5581 @@ -317,7 +318,6 @@ #define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e #define USB_PID_PINNACLE_PCTV2000E 0x022c #define USB_PID_PINNACLE_PCTV282E 0x0248 -#define USB_PID_PINNACLE_PCTV310E 0x3211 #define USB_PID_PINNACLE_PCTV340E 0x023d #define USB_PID_PINNACLE_PCTV340E_SE 0x023e #define USB_PID_PINNACLE_PCTV71E 0x022b @@ -416,7 +416,6 @@ #define USB_PID_TWINHAN_VP7041_WARM 0x3202 #define USB_PID_TWINHAN_VP7045_COLD 0x3205 #define USB_PID_TWINHAN_VP7045_WARM 0x3206 -#define USB_PID_TWINHAN_VP7049 0x3219 #define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 #define USB_PID_ULTIMA_TVBOX_AN2235_WARM 0x8108 #define USB_PID_ULTIMA_TVBOX_ANCHOR_COLD 0x2235 @@ -429,6 +428,7 @@ #define USB_PID_UNIWILL_STK7700P 0x6003 #define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e #define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f +#define USB_PID_VISIONPLUS_PINNACLE_PCTV310E 0x3211 #define USB_PID_WIDEVIEW_DTT200U_COLD 0x0201 #define USB_PID_WIDEVIEW_DTT200U_WARM 0x0301 #define USB_PID_WIDEVIEW_WT220U_COLD 0x0222 -- cgit v1.2.3 From cb794c2b7ae5b769fd46a3cce9508f7e04bf172b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:28 +0200 Subject: media: dvb-usb: nova-t-usb2: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/58f1a356b7b75bbefef3aa07cd99896c446df32f.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 10d73c108149..cc1df632d08b 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -267,6 +267,8 @@ #define USB_PID_HAUPPAUGE_NOVA_T_STICK_3 0x7070 #define USB_PID_HAUPPAUGE_TIGER_ATSC 0xb200 #define USB_PID_HAUPPAUGE_TIGER_ATSC_B210 0xb210 +#define USB_PID_HAUPPAUGE_WINTV_NOVA_T_USB2_COLD 0x9300 +#define USB_PID_HAUPPAUGE_WINTV_NOVA_T_USB2_WARM 0x9301 #define USB_PID_INTEL_CE9500 0x9500 #define USB_PID_ITETECH_IT9135 0x9135 #define USB_PID_ITETECH_IT9135_9005 0x9005 @@ -447,8 +449,6 @@ #define USB_PID_WINFAST_DTV_DONGLE_STK7700P 0x6f00 #define USB_PID_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 #define USB_PID_WINFAST_DTV_DONGLE_WARM 0x6026 -#define USB_PID_WINTV_NOVA_T_USB2_COLD 0x9300 -#define USB_PID_WINTV_NOVA_T_USB2_WARM 0x9301 #define USB_PID_WINTV_SOLOHD 0x0264 #define USB_PID_WINTV_SOLOHD_2 0x8268 #define USB_PID_XBOX_ONE_TUNER 0x02d5 -- cgit v1.2.3 From 22127ac8eb8d919d7366b370c1451f3b61ebc1de Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:29 +0200 Subject: media: dvb-usb: opera1: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/08861d80b6706ac1ed04a68959ebb78f27cb028d.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index cc1df632d08b..6aa15988b577 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -168,6 +168,7 @@ #define USB_PID_CYPRESS_DW2102 0x2102 #define USB_PID_CYPRESS_DW2104 0x2104 #define USB_PID_CYPRESS_DW3101 0x3101 +#define USB_PID_CYPRESS_OPERA1_COLD 0x2830 #define USB_PID_DELOCK_USB2_DVBT 0xb803 #define USB_PID_DIBCOM_ANCHOR_2135_COLD 0x2131 #define USB_PID_DIBCOM_HOOK_DEFAULT 0x0064 @@ -307,7 +308,6 @@ #define USB_PID_NOXON_DAB_STICK 0x00b3 #define USB_PID_NOXON_DAB_STICK_REV2 0x00e0 #define USB_PID_NOXON_DAB_STICK_REV3 0x00b4 -#define USB_PID_OPERA1_COLD 0x2830 #define USB_PID_OPERA1_WARM 0x3829 #define USB_PID_PCTV_2002E 0x025c #define USB_PID_PCTV_2002E_SE 0x025d -- cgit v1.2.3 From 710801c7ba81993d635a458cd9a0fc02f921c439 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:30 +0200 Subject: media: dvb-usb: pctv452e: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/283a8c6bdf9778f832b4f6acc104c06688281668.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 6aa15988b577..ed6e37f23cbc 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -314,7 +314,6 @@ #define USB_PID_PCTV_200E 0x020e #define USB_PID_PCTV_400E 0x020f #define USB_PID_PCTV_450E 0x0222 -#define USB_PID_PCTV_452E 0x021f #define USB_PID_PCTV_78E 0x025a #define USB_PID_PCTV_79E 0x0262 #define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e @@ -330,6 +329,7 @@ #define USB_PID_PINNACLE_PCTV74E 0x0246 #define USB_PID_PINNACLE_PCTV801E 0x023a #define USB_PID_PINNACLE_PCTV801E_SE 0x023b +#define USB_PID_PINNACLE_PCTV_452E 0x021f #define USB_PID_PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T 0x0229 #define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 #define USB_PID_PIXELVIEW_SBTVD 0x5010 -- cgit v1.2.3 From 5c1a56c9f0658d9b2d4be333fd896cd1b6cbaa82 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:32 +0200 Subject: media: dvb-usb: ttusb2: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/b447d9fd3832da5eff6267e8fe742c431f1133f2.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index ed6e37f23cbc..0fad68bfe6f9 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -312,8 +312,6 @@ #define USB_PID_PCTV_2002E 0x025c #define USB_PID_PCTV_2002E_SE 0x025d #define USB_PID_PCTV_200E 0x020e -#define USB_PID_PCTV_400E 0x020f -#define USB_PID_PCTV_450E 0x0222 #define USB_PID_PCTV_78E 0x025a #define USB_PID_PCTV_79E 0x0262 #define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e @@ -329,6 +327,8 @@ #define USB_PID_PINNACLE_PCTV74E 0x0246 #define USB_PID_PINNACLE_PCTV801E 0x023a #define USB_PID_PINNACLE_PCTV801E_SE 0x023b +#define USB_PID_PINNACLE_PCTV_400E 0x020f +#define USB_PID_PINNACLE_PCTV_450E 0x0222 #define USB_PID_PINNACLE_PCTV_452E 0x021f #define USB_PID_PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T 0x0229 #define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 -- cgit v1.2.3 From 9c06331ca07f0e7288c949e7969ab108aa1c9807 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:34 +0200 Subject: media: dvb-usb: vp702x: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/13bf6aab3909fae5da4c9a24c114b15e76abd146.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 0fad68bfe6f9..e022e38b6f95 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -410,9 +410,6 @@ #define USB_PID_TREKSTOR_TERRES_2_0 0xC803 #define USB_PID_TURBOX_DTT_2000 0xd3a4 #define USB_PID_TVWAY_PLUS 0x0002 -#define USB_PID_TWINHAN_VP7020_COLD 0x3203 -#define USB_PID_TWINHAN_VP7020_WARM 0x3204 -#define USB_PID_TWINHAN_VP7021_COLD 0x3207 #define USB_PID_TWINHAN_VP7021_WARM 0x3208 #define USB_PID_TWINHAN_VP7041_COLD 0x3201 #define USB_PID_TWINHAN_VP7041_WARM 0x3202 @@ -431,6 +428,9 @@ #define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e #define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f #define USB_PID_VISIONPLUS_PINNACLE_PCTV310E 0x3211 +#define USB_PID_VISIONPLUS_VP7020_COLD 0x3203 +#define USB_PID_VISIONPLUS_VP7020_WARM 0x3204 +#define USB_PID_VISIONPLUS_VP7021_COLD 0x3207 #define USB_PID_WIDEVIEW_DTT200U_COLD 0x0201 #define USB_PID_WIDEVIEW_DTT200U_WARM 0x0301 #define USB_PID_WIDEVIEW_WT220U_COLD 0x0222 -- cgit v1.2.3 From 5710a24b34576a8873ee836953575fdb234b37e2 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:35 +0200 Subject: media: dvb-usb: vp7045: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/0241bf842bf592dfa01b0ef4916afda396194f98.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index e022e38b6f95..9f53b3ce3e58 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -199,8 +199,6 @@ #define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_WARM 0xdb55 #define USB_PID_DIGIVOX_MINI_SL_COLD 0xe360 #define USB_PID_DIGIVOX_MINI_SL_WARM 0xe361 -#define USB_PID_DNTV_TINYUSB2_COLD 0x3223 -#define USB_PID_DNTV_TINYUSB2_WARM 0x3224 #define USB_PID_DPOSH_M9206_COLD 0x9206 #define USB_PID_DPOSH_M9206_WARM 0xa090 #define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD 0x5000 @@ -413,8 +411,6 @@ #define USB_PID_TWINHAN_VP7021_WARM 0x3208 #define USB_PID_TWINHAN_VP7041_COLD 0x3201 #define USB_PID_TWINHAN_VP7041_WARM 0x3202 -#define USB_PID_TWINHAN_VP7045_COLD 0x3205 -#define USB_PID_TWINHAN_VP7045_WARM 0x3206 #define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 #define USB_PID_ULTIMA_TVBOX_AN2235_WARM 0x8108 #define USB_PID_ULTIMA_TVBOX_ANCHOR_COLD 0x2235 @@ -428,9 +424,13 @@ #define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e #define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f #define USB_PID_VISIONPLUS_PINNACLE_PCTV310E 0x3211 +#define USB_PID_VISIONPLUS_TINYUSB2_COLD 0x3223 +#define USB_PID_VISIONPLUS_TINYUSB2_WARM 0x3224 #define USB_PID_VISIONPLUS_VP7020_COLD 0x3203 #define USB_PID_VISIONPLUS_VP7020_WARM 0x3204 #define USB_PID_VISIONPLUS_VP7021_COLD 0x3207 +#define USB_PID_VISIONPLUS_VP7045_COLD 0x3205 +#define USB_PID_VISIONPLUS_VP7045_WARM 0x3206 #define USB_PID_WIDEVIEW_DTT200U_COLD 0x0201 #define USB_PID_WIDEVIEW_DTT200U_WARM 0x0301 #define USB_PID_WIDEVIEW_WT220U_COLD 0x0222 -- cgit v1.2.3 From d763479abd67fc67a13aabe0ce19b4d775fbdcee Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:36 +0200 Subject: media: dvb-usb: dibusb-mb: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/a300c26ad4e9bb913e86eeaf0ec7d72b9e7d5d3e.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 9f53b3ce3e58..e4796464b0d7 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -133,8 +133,6 @@ #define USB_PID_AVERMEDIA_B835 0xb835 #define USB_PID_AVERMEDIA_DVBT_USB2_COLD 0xa800 #define USB_PID_AVERMEDIA_DVBT_USB2_WARM 0xa801 -#define USB_PID_AVERMEDIA_DVBT_USB_COLD 0x0001 -#define USB_PID_AVERMEDIA_DVBT_USB_WARM 0x0002 #define USB_PID_AVERMEDIA_EXPRESS 0xb568 #define USB_PID_AVERMEDIA_H335 0x0335 #define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R 0x0039 @@ -230,6 +228,8 @@ #define USB_PID_ELGATO_EYETV_SAT 0x002a #define USB_PID_ELGATO_EYETV_SAT_V2 0x0025 #define USB_PID_ELGATO_EYETV_SAT_V3 0x0036 +#define USB_PID_EMPIA_VSTREAM_COLD 0x17de +#define USB_PID_EMPIA_VSTREAM_WARM 0x17df #define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 #define USB_PID_FREECOM_DVBT 0x0160 #define USB_PID_FREECOM_DVBT_2 0x0161 @@ -251,6 +251,8 @@ #define USB_PID_GRANDTEC_DVBT_USB2_WARM 0x0bc7 #define USB_PID_GRANDTEC_DVBT_USB_COLD 0x0fa0 #define USB_PID_GRANDTEC_DVBT_USB_WARM 0x0fa1 +#define USB_PID_GRANDTEC_MOD3000_COLD 0x0bb8 +#define USB_PID_GRANDTEC_MOD3000_WARM 0x0bb9 #define USB_PID_HAMA_DVBT_HYBRID 0x2758 #define USB_PID_HANFTEK_UMT_010_COLD 0x0001 #define USB_PID_HANFTEK_UMT_010_WARM 0x0015 @@ -285,7 +287,6 @@ #define USB_PID_KWORLD_UB383_T 0xe383 #define USB_PID_KWORLD_UB499_2T_T09 0xe409 #define USB_PID_KWORLD_VSTREAM_COLD 0x17de -#define USB_PID_KWORLD_VSTREAM_WARM 0x17df #define USB_PID_KYE_DVB_T_COLD 0x701e #define USB_PID_KYE_DVB_T_WARM 0x701f #define USB_PID_LITEON_DVB_T_COLD 0xf000 @@ -429,10 +430,14 @@ #define USB_PID_VISIONPLUS_VP7020_COLD 0x3203 #define USB_PID_VISIONPLUS_VP7020_WARM 0x3204 #define USB_PID_VISIONPLUS_VP7021_COLD 0x3207 +#define USB_PID_VISIONPLUS_VP7041_COLD 0x3201 +#define USB_PID_VISIONPLUS_VP7041_WARM 0x3202 #define USB_PID_VISIONPLUS_VP7045_COLD 0x3205 #define USB_PID_VISIONPLUS_VP7045_WARM 0x3206 #define USB_PID_WIDEVIEW_DTT200U_COLD 0x0201 #define USB_PID_WIDEVIEW_DTT200U_WARM 0x0301 +#define USB_PID_WIDEVIEW_DVBT_USB_COLD 0x0001 +#define USB_PID_WIDEVIEW_DVBT_USB_WARM 0x0002 #define USB_PID_WIDEVIEW_WT220U_COLD 0x0222 #define USB_PID_WIDEVIEW_WT220U_FC_COLD 0x0225 #define USB_PID_WIDEVIEW_WT220U_FC_WARM 0x0226 -- cgit v1.2.3 From 281b21c56ed325ad5a23bf2dce45a8d7f751a577 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:37 +0200 Subject: media: dvb-usb: dibusb-mc: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/f1d4fa4960b709152ae693800c830e19a4bc1f48.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index e4796464b0d7..4dba939760ed 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -111,8 +111,6 @@ #define USB_PID_ANUBIS_MSI_DIGI_VOX_MINI_II 0x1513 #define USB_PID_ANYSEE 0x861f #define USB_PID_ARTEC_T14BR 0x810f -#define USB_PID_ARTEC_T14_COLD 0x810b -#define USB_PID_ARTEC_T14_WARM 0x810c #define USB_PID_ASUS_U3000 0x171f #define USB_PID_ASUS_U3000H 0x1736 #define USB_PID_ASUS_U3100 0x173f @@ -195,12 +193,8 @@ #define USB_PID_DIBCOM_TFE8096P 0x1f9C #define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_COLD 0xdb54 #define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_WARM 0xdb55 -#define USB_PID_DIGIVOX_MINI_SL_COLD 0xe360 -#define USB_PID_DIGIVOX_MINI_SL_WARM 0xe361 #define USB_PID_DPOSH_M9206_COLD 0x9206 #define USB_PID_DPOSH_M9206_WARM 0xa090 -#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD 0x5000 -#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_WARM 0x5001 #define USB_PID_DVICO_BLUEBIRD_DUAL_1_COLD 0xdb50 #define USB_PID_DVICO_BLUEBIRD_DUAL_1_WARM 0xdb51 #define USB_PID_DVICO_BLUEBIRD_DUAL_2_COLD 0xdb58 @@ -228,6 +222,8 @@ #define USB_PID_ELGATO_EYETV_SAT 0x002a #define USB_PID_ELGATO_EYETV_SAT_V2 0x0025 #define USB_PID_ELGATO_EYETV_SAT_V3 0x0036 +#define USB_PID_EMPIA_DIGIVOX_MINI_SL_COLD 0xe360 +#define USB_PID_EMPIA_DIGIVOX_MINI_SL_WARM 0xe361 #define USB_PID_EMPIA_VSTREAM_COLD 0x17de #define USB_PID_EMPIA_VSTREAM_WARM 0x17df #define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 @@ -270,6 +266,8 @@ #define USB_PID_HAUPPAUGE_TIGER_ATSC_B210 0xb210 #define USB_PID_HAUPPAUGE_WINTV_NOVA_T_USB2_COLD 0x9300 #define USB_PID_HAUPPAUGE_WINTV_NOVA_T_USB2_WARM 0x9301 +#define USB_PID_HUMAX_DVB_T_STICK_HIGH_SPEED_COLD 0x5000 +#define USB_PID_HUMAX_DVB_T_STICK_HIGH_SPEED_WARM 0x5001 #define USB_PID_INTEL_CE9500 0x9500 #define USB_PID_ITETECH_IT9135 0x9135 #define USB_PID_ITETECH_IT9135_9005 0x9005 @@ -289,6 +287,8 @@ #define USB_PID_KWORLD_VSTREAM_COLD 0x17de #define USB_PID_KYE_DVB_T_COLD 0x701e #define USB_PID_KYE_DVB_T_WARM 0x701f +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_COLD 0x6025 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_WARM 0x6026 #define USB_PID_LITEON_DVB_T_COLD 0xf000 #define USB_PID_LITEON_DVB_T_WARM 0xf001 #define USB_PID_MEDION_MD95700 0x0932 @@ -412,6 +412,8 @@ #define USB_PID_TWINHAN_VP7021_WARM 0x3208 #define USB_PID_TWINHAN_VP7041_COLD 0x3201 #define USB_PID_TWINHAN_VP7041_WARM 0x3202 +#define USB_PID_ULTIMA_ARTEC_T14_COLD 0x810b +#define USB_PID_ULTIMA_ARTEC_T14_WARM 0x810c #define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 #define USB_PID_ULTIMA_TVBOX_AN2235_WARM 0x8108 #define USB_PID_ULTIMA_TVBOX_ANCHOR_COLD 0x2235 @@ -447,13 +449,11 @@ #define USB_PID_WIDEVIEW_WT220U_ZL0353_WARM 0x022b #define USB_PID_WINFAST_DTV2000DS 0x6a04 #define USB_PID_WINFAST_DTV2000DS_PLUS 0x6f12 -#define USB_PID_WINFAST_DTV_DONGLE_COLD 0x6025 #define USB_PID_WINFAST_DTV_DONGLE_GOLD 0x6029 #define USB_PID_WINFAST_DTV_DONGLE_H 0x60f6 #define USB_PID_WINFAST_DTV_DONGLE_MINID 0x6f0f #define USB_PID_WINFAST_DTV_DONGLE_STK7700P 0x6f00 #define USB_PID_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 -#define USB_PID_WINFAST_DTV_DONGLE_WARM 0x6026 #define USB_PID_WINTV_SOLOHD 0x0264 #define USB_PID_WINTV_SOLOHD_2 0x8268 #define USB_PID_XBOX_ONE_TUNER 0x02d5 -- cgit v1.2.3 From 3d59142ad94cf60b94b3dc94c19fdafa23aec8b1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:38 +0200 Subject: media: dvb-usb: dib0700_devices: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/028699ec71158dbc49d710a4259eb8cdb7f673cb.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 4dba939760ed..1b7d10f3d4aa 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -110,7 +110,6 @@ #define USB_PID_ANUBIS_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 #define USB_PID_ANUBIS_MSI_DIGI_VOX_MINI_II 0x1513 #define USB_PID_ANYSEE 0x861f -#define USB_PID_ARTEC_T14BR 0x810f #define USB_PID_ASUS_U3000 0x171f #define USB_PID_ASUS_U3000H 0x1736 #define USB_PID_ASUS_U3100 0x173f @@ -158,7 +157,6 @@ #define USB_PID_CONCEPTRONIC_CTVDIGRCU 0xe397 #define USB_PID_CONEXANT_D680_DMB 0x86d6 #define USB_PID_CPYTO_REDI_PC50A 0xa803 -#define USB_PID_CREATIX_CTX1921 0x1921 #define USB_PID_CTVDIGDUAL_V2 0xe410 #define USB_PID_CYPRESS_DW2101 0x2101 #define USB_PID_CYPRESS_DW2102 0x2102 @@ -226,6 +224,7 @@ #define USB_PID_EMPIA_DIGIVOX_MINI_SL_WARM 0xe361 #define USB_PID_EMPIA_VSTREAM_COLD 0x17de #define USB_PID_EMPIA_VSTREAM_WARM 0x17df +#define USB_PID_EVOLUTEPC_TVWAY_PLUS 0x0002 #define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 #define USB_PID_FREECOM_DVBT 0x0160 #define USB_PID_FREECOM_DVBT_2 0x0161 @@ -288,10 +287,15 @@ #define USB_PID_KYE_DVB_T_COLD 0x701e #define USB_PID_KYE_DVB_T_WARM 0x701f #define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_COLD 0x6025 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_H 0x60f6 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_STK7700P 0x6f00 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 #define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_WARM 0x6026 #define USB_PID_LITEON_DVB_T_COLD 0xf000 #define USB_PID_LITEON_DVB_T_WARM 0xf001 +#define USB_PID_MEDION_CREATIX_CTX1921 0x1921 #define USB_PID_MEDION_MD95700 0x0932 +#define USB_PID_MICROSOFT_XBOX_ONE_TUNER 0x02d5 #define USB_PID_MIGLIA_WT220U_ZAP250_COLD 0x0220 #define USB_PID_MSI_DIGIVOX_DUO 0x8801 #define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 @@ -313,6 +317,9 @@ #define USB_PID_PCTV_200E 0x020e #define USB_PID_PCTV_78E 0x025a #define USB_PID_PCTV_79E 0x0262 +#define USB_PID_PCTV_DIBCOM_STK8096PVR 0x1faa +#define USB_PID_PCTV_PINNACLE_PCTV282E 0x0248 +#define USB_PID_PCTV_PINNACLE_PCTV73ESE 0x0245 #define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e #define USB_PID_PINNACLE_PCTV2000E 0x022c #define USB_PID_PINNACLE_PCTV282E 0x0248 @@ -408,10 +415,10 @@ #define USB_PID_TREKSTOR_DVBT 0x901b #define USB_PID_TREKSTOR_TERRES_2_0 0xC803 #define USB_PID_TURBOX_DTT_2000 0xd3a4 -#define USB_PID_TVWAY_PLUS 0x0002 #define USB_PID_TWINHAN_VP7021_WARM 0x3208 #define USB_PID_TWINHAN_VP7041_COLD 0x3201 #define USB_PID_TWINHAN_VP7041_WARM 0x3202 +#define USB_PID_ULTIMA_ARTEC_T14BR 0x810f #define USB_PID_ULTIMA_ARTEC_T14_COLD 0x810b #define USB_PID_ULTIMA_ARTEC_T14_WARM 0x810c #define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 @@ -450,13 +457,9 @@ #define USB_PID_WINFAST_DTV2000DS 0x6a04 #define USB_PID_WINFAST_DTV2000DS_PLUS 0x6f12 #define USB_PID_WINFAST_DTV_DONGLE_GOLD 0x6029 -#define USB_PID_WINFAST_DTV_DONGLE_H 0x60f6 #define USB_PID_WINFAST_DTV_DONGLE_MINID 0x6f0f -#define USB_PID_WINFAST_DTV_DONGLE_STK7700P 0x6f00 -#define USB_PID_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 #define USB_PID_WINTV_SOLOHD 0x0264 #define USB_PID_WINTV_SOLOHD_2 0x8268 -#define USB_PID_XBOX_ONE_TUNER 0x02d5 #define USB_PID_XTENSIONS_XD_380 0x0381 #define USB_PID_YUAN_EC372S 0x1edc #define USB_PID_YUAN_MC770 0x0871 -- cgit v1.2.3 From f47a6113f4e87db7ca066635822e1b3ca3ed9514 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Wed, 16 Feb 2022 16:03:03 +0800 Subject: platform/chrome: cros_ec: remove unused variable `was_wake_device` Reviewed-by: Prashant Malani Signed-off-by: Tzung-Bi Shih --- include/linux/platform_data/cros_ec_proto.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index df3c78c92ca2..c65971ec90ea 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -76,8 +76,6 @@ struct cros_ec_command { * struct cros_ec_device - Information about a ChromeOS EC device. * @phys_name: Name of physical comms layer (e.g. 'i2c-4'). * @dev: Device pointer for physical comms device - * @was_wake_device: True if this device was set to wake the system from - * sleep at the last suspend. * @cros_class: The class structure for this device. * @cmd_readmem: Direct read of the EC memory-mapped region, if supported. * @offset: Is within EC_LPC_ADDR_MEMMAP region. @@ -137,7 +135,6 @@ struct cros_ec_device { /* These are used by other drivers that want to talk to the EC */ const char *phys_name; struct device *dev; - bool was_wake_device; struct class *cros_class; int (*cmd_readmem)(struct cros_ec_device *ec, unsigned int offset, unsigned int bytes, void *dest); -- cgit v1.2.3 From 39772efd98adecbd5b8c6096d465d2fcbafbde6a Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 13 Mar 2022 13:39:49 +0100 Subject: clk: imx8mp: Add DISP2 pixel clock Add pixel clock for second LCDIFv3 interface. Both LCDIFv3 interfaces use the same set of parent clock, so deduplicate imx8mp_media_disp1_pix_sels into common imx8mp_media_disp_pix_sels and use it for both. Signed-off-by: Marek Vasut Cc: Abel Vesa Cc: Fabio Estevam Cc: NXP Linux Team Cc: Peng Fan Cc: Shawn Guo Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20220313123949.207284-1-marex@denx.de Signed-off-by: Abel Vesa --- include/dt-bindings/clock/imx8mp-clock.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/imx8mp-clock.h b/include/dt-bindings/clock/imx8mp-clock.h index 235c7a00d379..e05d21bf7813 100644 --- a/include/dt-bindings/clock/imx8mp-clock.h +++ b/include/dt-bindings/clock/imx8mp-clock.h @@ -318,7 +318,9 @@ #define IMX8MP_CLK_HSIO_AXI 311 #define IMX8MP_CLK_MEDIA_ISP 312 -#define IMX8MP_CLK_END 313 +#define IMX8MP_CLK_MEDIA_DISP2_PIX 313 + +#define IMX8MP_CLK_END 314 #define IMX8MP_CLK_AUDIOMIX_SAI1_IPG 0 #define IMX8MP_CLK_AUDIOMIX_SAI1_MCLK1 1 -- cgit v1.2.3 From c246f9b5fd617fe487f8b6f18851703f468501d6 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 18 Apr 2022 09:42:25 +0300 Subject: devlink: add support to create line card and expose to user Extend the devlink API so the driver is going to be able to create and destroy linecard instances. There can be multiple line cards per devlink device. Expose this new type of object over devlink netlink API to the userspace, with notifications. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 4 ++++ include/uapi/linux/devlink.h | 7 +++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index a30180c0988a..7aabdfb3bc6a 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -22,6 +22,7 @@ #include struct devlink; +struct devlink_linecard; struct devlink_port_phys_attrs { u32 port_number; /* Same value as "split group". @@ -1536,6 +1537,9 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, int devlink_rate_leaf_create(struct devlink_port *port, void *priv); void devlink_rate_leaf_destroy(struct devlink_port *devlink_port); void devlink_rate_nodes_destroy(struct devlink *devlink); +struct devlink_linecard *devlink_linecard_create(struct devlink *devlink, + unsigned int linecard_index); +void devlink_linecard_destroy(struct devlink_linecard *linecard); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index b897b80770f6..59c33ed2d3e7 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -131,6 +131,11 @@ enum devlink_command { DEVLINK_CMD_RATE_NEW, DEVLINK_CMD_RATE_DEL, + DEVLINK_CMD_LINECARD_GET, /* can dump */ + DEVLINK_CMD_LINECARD_SET, + DEVLINK_CMD_LINECARD_NEW, + DEVLINK_CMD_LINECARD_DEL, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -553,6 +558,8 @@ enum devlink_attr { DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, /* u32 */ + DEVLINK_ATTR_LINECARD_INDEX, /* u32 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From fcdc8ce23a309c26a67fc613a741d9b21a248311 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 18 Apr 2022 09:42:26 +0300 Subject: devlink: implement line card provisioning In order to be able to configure all needed stuff on a port/netdevice of a line card without the line card being present, introduce line card provisioning. Basically by setting a type, provisioning process will start and driver is supposed to create a placeholder for instances (ports/netdevices) for a line card type. Allow the user to query the supported line card types over line card get command. Then implement two netlink command SET to allow user to set/unset the card type. On the driver API side, add provision/unprovision ops and supported types array to be advertised. Upon provision op call, the driver should take care of creating the instances for the particular line card type. Introduce provision_set/clear() functions to be called by the driver once the provisioning/unprovisioning is done on its side. These helpers are not to be called directly due to the async nature of provisioning. Example: $ devlink port # No ports are listed $ devlink lc pci/0000:01:00.0: lc 1 state unprovisioned supported_types: 16x100G lc 2 state unprovisioned supported_types: 16x100G lc 3 state unprovisioned supported_types: 16x100G lc 4 state unprovisioned supported_types: 16x100G lc 5 state unprovisioned supported_types: 16x100G lc 6 state unprovisioned supported_types: 16x100G lc 7 state unprovisioned supported_types: 16x100G lc 8 state unprovisioned supported_types: 16x100G $ devlink lc set pci/0000:01:00.0 lc 8 type 16x100G $ devlink lc show pci/0000:01:00.0 lc 8 pci/0000:01:00.0: lc 8 state active type 16x100G supported_types: 16x100G $ devlink port pci/0000:01:00.0/0: type notset flavour cpu port 0 splittable false pci/0000:01:00.0/53: type eth netdev enp1s0nl8p1 flavour physical lc 8 port 1 splittable true lanes 4 pci/0000:01:00.0/54: type eth netdev enp1s0nl8p2 flavour physical lc 8 port 2 splittable true lanes 4 pci/0000:01:00.0/55: type eth netdev enp1s0nl8p3 flavour physical lc 8 port 3 splittable true lanes 4 pci/0000:01:00.0/56: type eth netdev enp1s0nl8p4 flavour physical lc 8 port 4 splittable true lanes 4 pci/0000:01:00.0/57: type eth netdev enp1s0nl8p5 flavour physical lc 8 port 5 splittable true lanes 4 pci/0000:01:00.0/58: type eth netdev enp1s0nl8p6 flavour physical lc 8 port 6 splittable true lanes 4 pci/0000:01:00.0/59: type eth netdev enp1s0nl8p7 flavour physical lc 8 port 7 splittable true lanes 4 pci/0000:01:00.0/60: type eth netdev enp1s0nl8p8 flavour physical lc 8 port 8 splittable true lanes 4 pci/0000:01:00.0/61: type eth netdev enp1s0nl8p9 flavour physical lc 8 port 9 splittable true lanes 4 pci/0000:01:00.0/62: type eth netdev enp1s0nl8p10 flavour physical lc 8 port 10 splittable true lanes 4 pci/0000:01:00.0/63: type eth netdev enp1s0nl8p11 flavour physical lc 8 port 11 splittable true lanes 4 pci/0000:01:00.0/64: type eth netdev enp1s0nl8p12 flavour physical lc 8 port 12 splittable true lanes 4 pci/0000:01:00.0/125: type eth netdev enp1s0nl8p13 flavour physical lc 8 port 13 splittable true lanes 4 pci/0000:01:00.0/126: type eth netdev enp1s0nl8p14 flavour physical lc 8 port 14 splittable true lanes 4 pci/0000:01:00.0/127: type eth netdev enp1s0nl8p15 flavour physical lc 8 port 15 splittable true lanes 4 pci/0000:01:00.0/128: type eth netdev enp1s0nl8p16 flavour physical lc 8 port 16 splittable true lanes 4 $ devlink lc set pci/0000:01:00.0 lc 8 notype Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 43 +++++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/devlink.h | 15 +++++++++++++++ 2 files changed, 56 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 7aabdfb3bc6a..3e49d4ff498c 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -149,6 +149,40 @@ struct devlink_port_new_attrs { sfnum_valid:1; }; +/** + * struct devlink_linecard_ops - Linecard operations + * @provision: callback to provision the linecard slot with certain + * type of linecard. As a result of this operation, + * driver is expected to eventually (could be after + * the function call returns) call one of: + * devlink_linecard_provision_set() + * devlink_linecard_provision_fail() + * @unprovision: callback to unprovision the linecard slot. As a result + * of this operation, driver is expected to eventually + * (could be after the function call returns) call + * devlink_linecard_provision_clear() + * devlink_linecard_provision_fail() + * @same_provision: callback to ask the driver if linecard is already + * provisioned in the same way user asks this linecard to be + * provisioned. + * @types_count: callback to get number of supported types + * @types_get: callback to get next type in list + */ +struct devlink_linecard_ops { + int (*provision)(struct devlink_linecard *linecard, void *priv, + const char *type, const void *type_priv, + struct netlink_ext_ack *extack); + int (*unprovision)(struct devlink_linecard *linecard, void *priv, + struct netlink_ext_ack *extack); + bool (*same_provision)(struct devlink_linecard *linecard, void *priv, + const char *type, const void *type_priv); + unsigned int (*types_count)(struct devlink_linecard *linecard, + void *priv); + void (*types_get)(struct devlink_linecard *linecard, + void *priv, unsigned int index, const char **type, + const void **type_priv); +}; + struct devlink_sb_pool_info { enum devlink_sb_pool_type pool_type; u32 size; @@ -1537,9 +1571,14 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, int devlink_rate_leaf_create(struct devlink_port *port, void *priv); void devlink_rate_leaf_destroy(struct devlink_port *devlink_port); void devlink_rate_nodes_destroy(struct devlink *devlink); -struct devlink_linecard *devlink_linecard_create(struct devlink *devlink, - unsigned int linecard_index); +struct devlink_linecard * +devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, + const struct devlink_linecard_ops *ops, void *priv); void devlink_linecard_destroy(struct devlink_linecard *linecard); +void devlink_linecard_provision_set(struct devlink_linecard *linecard, + const char *type); +void devlink_linecard_provision_clear(struct devlink_linecard *linecard); +void devlink_linecard_provision_fail(struct devlink_linecard *linecard); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 59c33ed2d3e7..de91e4a0d476 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -343,6 +343,18 @@ enum devlink_reload_limit { #define DEVLINK_RELOAD_LIMITS_VALID_MASK (_BITUL(__DEVLINK_RELOAD_LIMIT_MAX) - 1) +enum devlink_linecard_state { + DEVLINK_LINECARD_STATE_UNSPEC, + DEVLINK_LINECARD_STATE_UNPROVISIONED, + DEVLINK_LINECARD_STATE_UNPROVISIONING, + DEVLINK_LINECARD_STATE_PROVISIONING, + DEVLINK_LINECARD_STATE_PROVISIONING_FAILED, + DEVLINK_LINECARD_STATE_PROVISIONED, + + __DEVLINK_LINECARD_STATE_MAX, + DEVLINK_LINECARD_STATE_MAX = __DEVLINK_LINECARD_STATE_MAX - 1 +}; + enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, @@ -559,6 +571,9 @@ enum devlink_attr { DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, /* u32 */ DEVLINK_ATTR_LINECARD_INDEX, /* u32 */ + DEVLINK_ATTR_LINECARD_STATE, /* u8 */ + DEVLINK_ATTR_LINECARD_TYPE, /* string */ + DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES, /* nested */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From fc9f50d5b366cd9f35bdee22fe3f8d77833cb1d8 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 18 Apr 2022 09:42:27 +0300 Subject: devlink: implement line card active state Allow driver to mark a line card as active. Expose this state to the userspace over devlink netlink interface with proper notifications. 'active' state means that line card was plugged in after being provisioned. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 2 ++ include/uapi/linux/devlink.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 3e49d4ff498c..d8061a11fee6 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1579,6 +1579,8 @@ void devlink_linecard_provision_set(struct devlink_linecard *linecard, const char *type); void devlink_linecard_provision_clear(struct devlink_linecard *linecard); void devlink_linecard_provision_fail(struct devlink_linecard *linecard); +void devlink_linecard_activate(struct devlink_linecard *linecard); +void devlink_linecard_deactivate(struct devlink_linecard *linecard); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index de91e4a0d476..b3d40a5d72ff 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -350,6 +350,7 @@ enum devlink_linecard_state { DEVLINK_LINECARD_STATE_PROVISIONING, DEVLINK_LINECARD_STATE_PROVISIONING_FAILED, DEVLINK_LINECARD_STATE_PROVISIONED, + DEVLINK_LINECARD_STATE_ACTIVE, __DEVLINK_LINECARD_STATE_MAX, DEVLINK_LINECARD_STATE_MAX = __DEVLINK_LINECARD_STATE_MAX - 1 -- cgit v1.2.3 From b837585985386e05478cb17868d23a6fa87c4f8d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 18 Apr 2022 09:42:28 +0300 Subject: devlink: add port to line card relationship set In order to properly inform user about relationship between port and line card, introduce a driver API to set line card for a port. Use this information to extend port devlink netlink message by line card index and also include the line card index into phys_port_name and by that into a netdevice name. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index d8061a11fee6..2a2a2a0c93f7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -136,6 +136,7 @@ struct devlink_port { struct mutex reporters_lock; /* Protects reporter_list */ struct devlink_rate *devlink_rate; + struct devlink_linecard *linecard; }; struct devlink_port_new_attrs { @@ -1571,6 +1572,8 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, int devlink_rate_leaf_create(struct devlink_port *port, void *priv); void devlink_rate_leaf_destroy(struct devlink_port *devlink_port); void devlink_rate_nodes_destroy(struct devlink *devlink); +void devlink_port_linecard_set(struct devlink_port *devlink_port, + struct devlink_linecard *linecard); struct devlink_linecard * devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, const struct devlink_linecard_ops *ops, void *priv); -- cgit v1.2.3 From 5f0614a55ecebdf55f1a17db0b5f6b787ed009f1 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 17 Apr 2022 22:27:13 -0400 Subject: block: change exported IO accounting interface from gendisk to bdev Export IO accounting interfaces in terms of block_device now that gendisk has become more internal to block core. Rename __part_{start,end}_io_acct's first argument from part to bdev. Rename __part_{start,end}_io_acct to bdev_{start,end}_io_acct and export them. Remove disk_{start,end}_io_acct and update caller (zram) to use bdev_{start,end}_io_acct. DM can now be updated to use bdev_{start,end}_io_acct. Signed-off-by: Ming Lei Signed-off-by: Mike Snitzer Link: https://lore.kernel.org/r/20220418022733.56168-2-snitzer@kernel.org Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c9b5925af5a3..34724b15813b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1463,9 +1463,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, - unsigned int op); -void disk_end_io_acct(struct gendisk *disk, unsigned int op, +unsigned long bdev_start_io_acct(struct block_device *bdev, + unsigned int sectors, unsigned int op, + unsigned long start_time); +void bdev_end_io_acct(struct block_device *bdev, unsigned int op, unsigned long start_time); void bio_start_io_acct_time(struct bio *bio, unsigned long start_time); -- cgit v1.2.3 From dbdc1be32591af023db2812706f01e6cd2f42bfc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Mar 2022 07:29:06 +0200 Subject: block: add a disk_openers helper Add a helper that returns the openers for a given gendisk to avoid having drivers poke into disk->part0 to get at this information in a somewhat cumbersome way. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20220330052917.2566582-5-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c9b5925af5a3..436645bde13f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -176,6 +176,21 @@ static inline bool disk_live(struct gendisk *disk) return !inode_unhashed(disk->part0->bd_inode); } +/** + * disk_openers - returns how many openers are there for a disk + * @disk: disk to check + * + * This returns the number of openers for a disk. Note that this value is only + * stable if disk->open_mutex is held. + * + * Note: Due to a quirk in the block layer open code, each open partition is + * only counted once even if there are multiple openers. + */ +static inline unsigned int disk_openers(struct gendisk *disk) +{ + return disk->part0->bd_openers; +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. -- cgit v1.2.3 From 9acf381f3e8f715175c29f4b6d722f6b6797d139 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Mar 2022 07:29:07 +0200 Subject: block: turn bdev->bd_openers into an atomic_t All manipulation of bd_openers is under disk->open_mutex and will remain so for the foreseeable future. But at least one place reads it without the lock (blkdev_get) and there are more to be added. So make sure the compiler does not do turn the increments and decrements into non-atomic sequences by using an atomic_t. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20220330052917.2566582-6-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- include/linux/blkdev.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4968cb17b13b..c62274466e72 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -44,7 +44,7 @@ struct block_device { unsigned long bd_stamp; bool bd_read_only; /* read-only policy */ dev_t bd_dev; - int bd_openers; + atomic_t bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; void * bd_claiming; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 436645bde13f..afad3d1d0dac 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -188,7 +188,7 @@ static inline bool disk_live(struct gendisk *disk) */ static inline unsigned int disk_openers(struct gendisk *disk) { - return disk->part0->bd_openers; + return atomic_read(&disk->part0->bd_openers); } /* -- cgit v1.2.3 From 57b888ca2541785de2fcb90575b378921919b6c0 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 18 Mar 2022 09:54:22 -0700 Subject: platform/chrome: Re-introduce cros_ec_cmd_xfer and use it for ioctls Commit 413dda8f2c6f ("platform/chrome: cros_ec_chardev: Use cros_ec_cmd_xfer_status helper") inadvertendly changed the userspace ABI. Previously, cros_ec ioctls would only report errors if the EC communication failed, and otherwise return success and the result of the EC communication. An EC command execution failure was reported in the EC response field. The above mentioned commit changed this behavior, and the ioctl itself would fail. This breaks userspace commands trying to analyze the EC command execution error since the actual EC command response is no longer reported to userspace. Fix the problem by re-introducing the cros_ec_cmd_xfer() helper, and use it to handle ioctl messages. Fixes: 413dda8f2c6f ("platform/chrome: cros_ec_chardev: Use cros_ec_cmd_xfer_status helper") Cc: Daisuke Nojiri Cc: Rob Barnes Cc: Rajat Jain Cc: Brian Norris Cc: Parth Malkan Reviewed-by: Daisuke Nojiri Reviewed-by: Brian Norris Signed-off-by: Guenter Roeck Signed-off-by: Tzung-Bi Shih --- include/linux/platform_data/cros_ec_proto.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index c65971ec90ea..138fd912c808 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -213,6 +213,9 @@ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); +int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, + struct cros_ec_command *msg); + int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -- cgit v1.2.3 From 2f1e85b1aee459b7d0fd981839042c6a38ffaf0c Mon Sep 17 00:00:00 2001 From: Tonghao Zhang Date: Sat, 16 Apr 2022 00:40:45 +0800 Subject: net: sched: use queue_mapping to pick tx queue This patch fixes issue: * If we install tc filters with act_skbedit in clsact hook. It doesn't work, because netdev_core_pick_tx() overwrites queue_mapping. $ tc filter ... action skbedit queue_mapping 1 And this patch is useful: * We can use FQ + EDT to implement efficient policies. Tx queues are picked by xps, ndo_select_queue of netdev driver, or skb hash in netdev_core_pick_tx(). In fact, the netdev driver, and skb hash are _not_ under control. xps uses the CPUs map to select Tx queues, but we can't figure out which task_struct of pod/containter running on this cpu in most case. We can use clsact filters to classify one pod/container traffic to one Tx queue. Why ? In containter networking environment, there are two kinds of pod/ containter/net-namespace. One kind (e.g. P1, P2), the high throughput is key in these applications. But avoid running out of network resource, the outbound traffic of these pods is limited, using or sharing one dedicated Tx queues assigned HTB/TBF/FQ Qdisc. Other kind of pods (e.g. Pn), the low latency of data access is key. And the traffic is not limited. Pods use or share other dedicated Tx queues assigned FIFO Qdisc. This choice provides two benefits. First, contention on the HTB/FQ Qdisc lock is significantly reduced since fewer CPUs contend for the same queue. More importantly, Qdisc contention can be eliminated completely if each CPU has its own FIFO Qdisc for the second kind of pods. There must be a mechanism in place to support classifying traffic based on pods/container to different Tx queues. Note that clsact is outside of Qdisc while Qdisc can run a classifier to select a sub-queue under the lock. In general recording the decision in the skb seems a little heavy handed. This patch introduces a per-CPU variable, suggested by Eric. The xmit.skip_txqueue flag is firstly cleared in __dev_queue_xmit(). - Tx Qdisc may install that skbedit actions, then xmit.skip_txqueue flag is set in qdisc->enqueue() though tx queue has been selected in netdev_tx_queue_mapping() or netdev_core_pick_tx(). That flag is cleared firstly in __dev_queue_xmit(), is useful: - Avoid picking Tx queue with netdev_tx_queue_mapping() in next netdev in such case: eth0 macvlan - eth0.3 vlan - eth0 ixgbe-phy: For example, eth0, macvlan in pod, which root Qdisc install skbedit queue_mapping, send packets to eth0.3, vlan in host. In __dev_queue_xmit() of eth0.3, clear the flag, does not select tx queue according to skb->queue_mapping because there is no filters in clsact or tx Qdisc of this netdev. Same action taked in eth0, ixgbe in Host. - Avoid picking Tx queue for next packet. If we set xmit.skip_txqueue in tx Qdisc (qdisc->enqueue()), the proper way to clear it is clearing it in __dev_queue_xmit when processing next packets. For performance reasons, use the static key. If user does not config the NET_EGRESS, the patch will not be compiled. +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | q1 | qn v v v HTB/FQ HTB/FQ ... FIFO Cc: Jamal Hadi Salim Cc: Cong Wang Cc: Jiri Pirko Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Jonathan Lemon Cc: Eric Dumazet Cc: Alexander Lobakin Cc: Paolo Abeni Cc: Talal Ahmad Cc: Kevin Hao Cc: Ilias Apalodimas Cc: Kees Cook Cc: Kumar Kartikeya Dwivedi Cc: Antoine Tenart Cc: Wei Wang Cc: Arnd Bergmann Suggested-by: Eric Dumazet Signed-off-by: Tonghao Zhang Acked-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 3 +++ include/linux/rtnetlink.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a602f29365b0..7dccbfd1bf56 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3061,6 +3061,9 @@ struct softnet_data { struct { u16 recursion; u8 more; +#ifdef CONFIG_NET_EGRESS + u8 skip_txqueue; +#endif } xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 7f970b16da3a..ae2c6a3cec5d 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -100,6 +100,7 @@ void net_dec_ingress_queue(void); #ifdef CONFIG_NET_EGRESS void net_inc_egress_queue(void); void net_dec_egress_queue(void); +void netdev_xmit_skip_txqueue(bool skip); #endif void rtnetlink_init(void); -- cgit v1.2.3 From 38a6f0865796e26fc38fff4858f681d9ae76fa0f Mon Sep 17 00:00:00 2001 From: Tonghao Zhang Date: Sat, 16 Apr 2022 00:40:46 +0800 Subject: net: sched: support hash selecting tx queue This patch allows users to pick queue_mapping, range from A to B. Then we can load balance packets from A to B tx queue. The range is an unsigned 16bit value in decimal format. $ tc filter ... action skbedit queue_mapping skbhash A B "skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit") is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | qn | qm v v v HTB/FQ FIFO ... FIFO For example: If P1 sends out packets to different Pods on other host, and we want distribute flows from qn - qm. Then we can use skb->hash as hash. setup commands: $ NETDEV=eth0 $ ip netns add n1 $ ip link add ipv1 link $NETDEV type ipvlan mode l2 $ ip link set ipv1 netns n1 $ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up $ tc qdisc add dev $NETDEV clsact $ tc filter add dev $NETDEV egress protocol ip prio 1 \ flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6 $ tc qdisc add dev $NETDEV handle 1: root mq $ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb $ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit $ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit $ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1 $ tc qdisc add dev $NETDEV parent 1:3 pfifo $ tc qdisc add dev $NETDEV parent 1:4 pfifo $ tc qdisc add dev $NETDEV parent 1:5 pfifo $ tc qdisc add dev $NETDEV parent 1:6 pfifo $ tc qdisc add dev $NETDEV parent 1:7 pfifo $ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10 pick txqueue from 2 - 6: $ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes tx_queue_0_bytes: 42 tx_queue_1_bytes: 0 tx_queue_2_bytes: 11442586444 tx_queue_3_bytes: 7383615334 tx_queue_4_bytes: 3981365579 tx_queue_5_bytes: 3983235051 tx_queue_6_bytes: 6706236461 tx_queue_7_bytes: 42 tx_queue_8_bytes: 0 tx_queue_9_bytes: 0 txqueues 2 - 6 are mapped to classid 1:3 - 1:7 $ tc -s class show dev $NETDEV ... class mq 1:3 root leaf 8002: Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:4 root leaf 8003: Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:5 root leaf 8004: Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:6 root leaf 8005: Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:7 root leaf 8006: Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... Cc: Jamal Hadi Salim Cc: Cong Wang Cc: Jiri Pirko Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Jonathan Lemon Cc: Eric Dumazet Cc: Alexander Lobakin Cc: Paolo Abeni Cc: Talal Ahmad Cc: Kevin Hao Cc: Ilias Apalodimas Cc: Kees Cook Cc: Kumar Kartikeya Dwivedi Cc: Antoine Tenart Cc: Wei Wang Cc: Arnd Bergmann Signed-off-by: Tonghao Zhang Reviewed-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni --- include/net/tc_act/tc_skbedit.h | 1 + include/uapi/linux/tc_act/tc_skbedit.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index cab8229b9bed..dc1079f28e13 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -17,6 +17,7 @@ struct tcf_skbedit_params { u32 mark; u32 mask; u16 queue_mapping; + u16 mapping_mod; u16 ptype; struct rcu_head rcu; }; diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h index 800e93377218..6cb6101208d0 100644 --- a/include/uapi/linux/tc_act/tc_skbedit.h +++ b/include/uapi/linux/tc_act/tc_skbedit.h @@ -29,6 +29,7 @@ #define SKBEDIT_F_PTYPE 0x8 #define SKBEDIT_F_MASK 0x10 #define SKBEDIT_F_INHERITDSFIELD 0x20 +#define SKBEDIT_F_TXQ_SKBHASH 0x40 struct tc_skbedit { tc_gen; @@ -45,6 +46,7 @@ enum { TCA_SKBEDIT_PTYPE, TCA_SKBEDIT_MASK, TCA_SKBEDIT_FLAGS, + TCA_SKBEDIT_QUEUE_MAPPING_MAX, __TCA_SKBEDIT_MAX }; #define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1) -- cgit v1.2.3 From 15527fee767f592d894d954d78cf8af3685cda6d Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 14 Apr 2022 13:48:03 -0500 Subject: ASoC: SOF: add definitions for different IPC types MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add enum type to allow for different types of IPCs. The IPCv4 is intended for Intel only as a convergence path with firmware used in Windows. Follow-up patches will introduce different abstractions with .ops and different search paths for firmware and topology files. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Link: https://lore.kernel.org/r/20220414184817.362215-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index 7cdfc954df12..2658a38be5bd 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -47,6 +47,13 @@ enum sof_dsp_power_states { SOF_DSP_PM_D3, }; +/* Definitions for multiple IPCs */ +enum sof_ipc_type { + SOF_IPC, + SOF_INTEL_IPC4, + SOF_IPC_TYPE_COUNT +}; + /* * SOF Platform data. */ @@ -83,6 +90,8 @@ struct snd_sof_pdata { const struct snd_soc_acpi_mach *machine; void *hw_pdata; + + enum sof_ipc_type ipc_type; }; /* -- cgit v1.2.3 From a375791512254c154fd0d3e4091c78f4b92a5c66 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 14 Apr 2022 13:48:04 -0500 Subject: ASoC: SOF: add path indirection to each IPC type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the addition of the IPCv4, we need the ability to select different paths for firmware and topologies. First add an indirection. Follow-up patches will add mechanisms to select a default IPC or override it. No functionality change in this patch. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Link: https://lore.kernel.org/r/20220414184817.362215-3-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index 2658a38be5bd..69066fe064da 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -125,8 +125,8 @@ struct sof_dev_desc { const char *nocodec_tplg_filename; /* defaults paths for firmware and topology files */ - const char *default_fw_path; - const char *default_tplg_path; + const char *default_fw_path[SOF_IPC_TYPE_COUNT]; + const char *default_tplg_path[SOF_IPC_TYPE_COUNT]; /* default firmware name */ const char *default_fw_filename; -- cgit v1.2.3 From 0cf8ff05e5d2b94b3ccf8a1fbfc633ecb0be56b0 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 14 Apr 2022 13:48:05 -0500 Subject: ASoC: SOF: add default IPC capability and file paths MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds a default IPC type for each platform, along with file paths to be used for each IPC type. To make reviews simpler, we only modify platform descriptors in this table, the information will be used in the next patch. The Intel IPCv4 is only supported on Intel platforms after APL, and not by default. In follow-up patches, support for SKL and KBL will be added, and in those two cases the IPCv4 will be the default (and only supported mode). Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Link: https://lore.kernel.org/r/20220414184817.362215-4-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index 69066fe064da..a65af85a4074 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -124,6 +124,10 @@ struct sof_dev_desc { /* defaults for no codec mode */ const char *nocodec_tplg_filename; + /* information on supported IPCs */ + unsigned int ipc_supported_mask; + enum sof_ipc_type ipc_default; + /* defaults paths for firmware and topology files */ const char *default_fw_path[SOF_IPC_TYPE_COUNT]; const char *default_tplg_path[SOF_IPC_TYPE_COUNT]; -- cgit v1.2.3 From a97abb3cae31b4e2420da96b95e54756333f2cc3 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 14 Apr 2022 13:48:06 -0500 Subject: ASoC: SOF: add IPC-dependent file names MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To avoid misleading file names, use different names for INTEL_IPC4 firmware files. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Reviewed-by: Chao Song Link: https://lore.kernel.org/r/20220414184817.362215-5-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index a65af85a4074..96997650be65 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -133,7 +133,7 @@ struct sof_dev_desc { const char *default_tplg_path[SOF_IPC_TYPE_COUNT]; /* default firmware name */ - const char *default_fw_filename; + const char *default_fw_filename[SOF_IPC_TYPE_COUNT]; const struct snd_sof_dsp_ops *ops; }; -- cgit v1.2.3 From 856601e5a7ebe69b1c07adef7be80f9a03884329 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 14 Apr 2022 13:48:10 -0500 Subject: ASoC: SOF: remove const qualifier for 'struct snd_sof_dsp_ops' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that we start having multiple platforms with minor variants, the use of the const qualifier for 'dsp_ops' is starting to be sub-optimal: the structures are copied across platforms, with only a couple of members that differ. This patch removes the const qualifier without any functionality changes, and adds an optional initialization callback. In follow-up patches, the dsp_ops will revisited for Intel HDaudio platforms, with the differences added programmatically over a common baseline. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Reviewed-by: Péter Ujfalusi Reviewed-by: Kai Vehmanen Reviewed-by: Rander Wang Reviewed-by: Bard Liao Link: https://lore.kernel.org/r/20220414184817.362215-9-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index 96997650be65..1a82a0db5e7f 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -16,6 +16,7 @@ #include struct snd_sof_dsp_ops; +struct snd_sof_dev; /** * enum sof_fw_state - DSP firmware state definitions @@ -135,7 +136,8 @@ struct sof_dev_desc { /* default firmware name */ const char *default_fw_filename[SOF_IPC_TYPE_COUNT]; - const struct snd_sof_dsp_ops *ops; + struct snd_sof_dsp_ops *ops; + int (*ops_init)(struct snd_sof_dev *sdev); }; int sof_dai_get_mclk(struct snd_soc_pcm_runtime *rtd); -- cgit v1.2.3 From 99a15348d5842b3c1f95220dc9b119ee0fe0d81b Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Thu, 31 Mar 2022 15:52:33 +0200 Subject: ASoC: Intel: avs: Declare vendor tokens MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Expose all vendor tokens that help shape AVS topology. Parsing helpers introduced in follow up patches make use of these to know which block they are currently dealing with and to verify their correctness. Signed-off-by: Amadeusz Sławiński Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220331135246.993089-2-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/uapi/sound/intel/avs/tokens.h | 126 ++++++++++++++++++++++++++++++++++ 1 file changed, 126 insertions(+) create mode 100644 include/uapi/sound/intel/avs/tokens.h (limited to 'include') diff --git a/include/uapi/sound/intel/avs/tokens.h b/include/uapi/sound/intel/avs/tokens.h new file mode 100644 index 000000000000..754f02b2f444 --- /dev/null +++ b/include/uapi/sound/intel/avs/tokens.h @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright(c) 2021 Intel Corporation. All rights reserved. + * + * Authors: Cezary Rojewski + * Amadeusz Slawinski + */ + +#ifndef __UAPI_SOUND_INTEL_AVS_TOKENS_H +#define __UAPI_SOUND_INTEL_AVS_TOKENS_H + +enum avs_tplg_token { + /* struct avs_tplg */ + AVS_TKN_MANIFEST_NAME_STRING = 1, + AVS_TKN_MANIFEST_VERSION_U32 = 2, + AVS_TKN_MANIFEST_NUM_LIBRARIES_U32 = 3, + AVS_TKN_MANIFEST_NUM_AFMTS_U32 = 4, + AVS_TKN_MANIFEST_NUM_MODCFGS_BASE_U32 = 5, + AVS_TKN_MANIFEST_NUM_MODCFGS_EXT_U32 = 6, + AVS_TKN_MANIFEST_NUM_PPLCFGS_U32 = 7, + AVS_TKN_MANIFEST_NUM_BINDINGS_U32 = 8, + + /* struct avs_tplg_library */ + AVS_TKN_LIBRARY_ID_U32 = 101, + AVS_TKN_LIBRARY_NAME_STRING = 102, + + /* struct avs_audio_format */ + AVS_TKN_AFMT_ID_U32 = 201, + AVS_TKN_AFMT_SAMPLE_RATE_U32 = 202, + AVS_TKN_AFMT_BIT_DEPTH_U32 = 203, + AVS_TKN_AFMT_CHANNEL_MAP_U32 = 204, + AVS_TKN_AFMT_CHANNEL_CFG_U32 = 205, + AVS_TKN_AFMT_INTERLEAVING_U32 = 206, + AVS_TKN_AFMT_NUM_CHANNELS_U32 = 207, + AVS_TKN_AFMT_VALID_BIT_DEPTH_U32 = 208, + AVS_TKN_AFMT_SAMPLE_TYPE_U32 = 209, + + /* struct avs_tplg_modcfg_base */ + AVS_TKN_MODCFG_BASE_ID_U32 = 301, + AVS_TKN_MODCFG_BASE_CPC_U32 = 302, + AVS_TKN_MODCFG_BASE_IBS_U32 = 303, + AVS_TKN_MODCFG_BASE_OBS_U32 = 304, + AVS_TKN_MODCFG_BASE_PAGES_U32 = 305, + + /* struct avs_tplg_modcfg_ext */ + AVS_TKN_MODCFG_EXT_ID_U32 = 401, + AVS_TKN_MODCFG_EXT_TYPE_UUID = 402, + AVS_TKN_MODCFG_CPR_OUT_AFMT_ID_U32 = 403, + AVS_TKN_MODCFG_CPR_FEATURE_MASK_U32 = 404, + AVS_TKN_MODCFG_CPR_DMA_TYPE_U32 = 405, + AVS_TKN_MODCFG_CPR_DMABUFF_SIZE_U32 = 406, + AVS_TKN_MODCFG_CPR_VINDEX_U8 = 407, + AVS_TKN_MODCFG_CPR_BLOB_FMT_ID_U32 = 408, + AVS_TKN_MODCFG_MICSEL_OUT_AFMT_ID_U32 = 409, + AVS_TKN_MODCFG_INTELWOV_CPC_LP_MODE_U32 = 410, + AVS_TKN_MODCFG_SRC_OUT_FREQ_U32 = 411, + AVS_TKN_MODCFG_MUX_REF_AFMT_ID_U32 = 412, + AVS_TKN_MODCFG_MUX_OUT_AFMT_ID_U32 = 413, + AVS_TKN_MODCFG_AEC_REF_AFMT_ID_U32 = 414, + AVS_TKN_MODCFG_AEC_OUT_AFMT_ID_U32 = 415, + AVS_TKN_MODCFG_AEC_CPC_LP_MODE_U32 = 416, + AVS_TKN_MODCFG_ASRC_OUT_FREQ_U32 = 417, + AVS_TKN_MODCFG_ASRC_MODE_U8 = 418, + AVS_TKN_MODCFG_ASRC_DISABLE_JITTER_U8 = 419, + AVS_TKN_MODCFG_UPDOWN_MIX_OUT_CHAN_CFG_U32 = 420, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_SELECT_U32 = 421, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_0_S32 = 422, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_1_S32 = 423, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_2_S32 = 424, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_3_S32 = 425, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_4_S32 = 426, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_5_S32 = 427, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_6_S32 = 428, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_7_S32 = 429, + AVS_TKN_MODCFG_UPDOWN_MIX_CHAN_MAP_U32 = 430, + AVS_TKN_MODCFG_EXT_NUM_INPUT_PINS_U16 = 431, + AVS_TKN_MODCFG_EXT_NUM_OUTPUT_PINS_U16 = 432, + + /* struct avs_tplg_pplcfg */ + AVS_TKN_PPLCFG_ID_U32 = 1401, + AVS_TKN_PPLCFG_REQ_SIZE_U16 = 1402, + AVS_TKN_PPLCFG_PRIORITY_U8 = 1403, + AVS_TKN_PPLCFG_LOW_POWER_BOOL = 1404, + AVS_TKN_PPLCFG_ATTRIBUTES_U16 = 1405, + AVS_TKN_PPLCFG_TRIGGER_U32 = 1406, + + /* struct avs_tplg_binding */ + AVS_TKN_BINDING_ID_U32 = 1501, + AVS_TKN_BINDING_TARGET_TPLG_NAME_STRING = 1502, + AVS_TKN_BINDING_TARGET_PATH_TMPL_ID_U32 = 1503, + AVS_TKN_BINDING_TARGET_PPL_ID_U32 = 1504, + AVS_TKN_BINDING_TARGET_MOD_ID_U32 = 1505, + AVS_TKN_BINDING_TARGET_MOD_PIN_U8 = 1506, + AVS_TKN_BINDING_MOD_ID_U32 = 1507, + AVS_TKN_BINDING_MOD_PIN_U8 = 1508, + AVS_TKN_BINDING_IS_SINK_U8 = 1509, + + /* struct avs_tplg_pipeline */ + AVS_TKN_PPL_ID_U32 = 1601, + AVS_TKN_PPL_PPLCFG_ID_U32 = 1602, + AVS_TKN_PPL_NUM_BINDING_IDS_U32 = 1603, + AVS_TKN_PPL_BINDING_ID_U32 = 1604, + + /* struct avs_tplg_module */ + AVS_TKN_MOD_ID_U32 = 1701, + AVS_TKN_MOD_MODCFG_BASE_ID_U32 = 1702, + AVS_TKN_MOD_IN_AFMT_ID_U32 = 1703, + AVS_TKN_MOD_CORE_ID_U8 = 1704, + AVS_TKN_MOD_PROC_DOMAIN_U8 = 1705, + AVS_TKN_MOD_MODCFG_EXT_ID_U32 = 1706, + + /* struct avs_tplg_path_template */ + AVS_TKN_PATH_TMPL_ID_U32 = 1801, + + /* struct avs_tplg_path */ + AVS_TKN_PATH_ID_U32 = 1901, + AVS_TKN_PATH_FE_FMT_ID_U32 = 1902, + AVS_TKN_PATH_BE_FMT_ID_U32 = 1903, + + /* struct avs_tplg_pin_format */ + AVS_TKN_PIN_FMT_INDEX_U32 = 2201, + AVS_TKN_PIN_FMT_IOBS_U32 = 2202, + AVS_TKN_PIN_FMT_AFMT_ID_U32 = 2203, +}; + +#endif -- cgit v1.2.3 From c6547c2ed0e1487c91983faccad841611ab6a783 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Thu, 14 Apr 2022 18:22:37 +0200 Subject: dmaengine: imx: Move header to include/dma/ The i.MX DMA drivers are device tree only, nothing in include/linux/platform_data/dma-imx.h has platform_data in it, so move the file to include/linux/dma/imx-dma.h. Signed-off-by: Sascha Hauer Acked-By: Vinod Koul Link: https://lore.kernel.org/r/20220414162249.3934543-10-s.hauer@pengutronix.de Signed-off-by: Mark Brown --- include/linux/dma/imx-dma.h | 68 +++++++++++++++++++++++++++++++++++ include/linux/platform_data/dma-imx.h | 68 ----------------------------------- 2 files changed, 68 insertions(+), 68 deletions(-) create mode 100644 include/linux/dma/imx-dma.h delete mode 100644 include/linux/platform_data/dma-imx.h (limited to 'include') diff --git a/include/linux/dma/imx-dma.h b/include/linux/dma/imx-dma.h new file mode 100644 index 000000000000..b06cba85a6d4 --- /dev/null +++ b/include/linux/dma/imx-dma.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2004-2009 Freescale Semiconductor, Inc. All Rights Reserved. + */ + +#ifndef __LINUX_DMA_IMX_H +#define __LINUX_DMA_IMX_H + +#include +#include +#include + +/* + * This enumerates peripheral types. Used for SDMA. + */ +enum sdma_peripheral_type { + IMX_DMATYPE_SSI, /* MCU domain SSI */ + IMX_DMATYPE_SSI_SP, /* Shared SSI */ + IMX_DMATYPE_MMC, /* MMC */ + IMX_DMATYPE_SDHC, /* SDHC */ + IMX_DMATYPE_UART, /* MCU domain UART */ + IMX_DMATYPE_UART_SP, /* Shared UART */ + IMX_DMATYPE_FIRI, /* FIRI */ + IMX_DMATYPE_CSPI, /* MCU domain CSPI */ + IMX_DMATYPE_CSPI_SP, /* Shared CSPI */ + IMX_DMATYPE_SIM, /* SIM */ + IMX_DMATYPE_ATA, /* ATA */ + IMX_DMATYPE_CCM, /* CCM */ + IMX_DMATYPE_EXT, /* External peripheral */ + IMX_DMATYPE_MSHC, /* Memory Stick Host Controller */ + IMX_DMATYPE_MSHC_SP, /* Shared Memory Stick Host Controller */ + IMX_DMATYPE_DSP, /* DSP */ + IMX_DMATYPE_MEMORY, /* Memory */ + IMX_DMATYPE_FIFO_MEMORY,/* FIFO type Memory */ + IMX_DMATYPE_SPDIF, /* SPDIF */ + IMX_DMATYPE_IPU_MEMORY, /* IPU Memory */ + IMX_DMATYPE_ASRC, /* ASRC */ + IMX_DMATYPE_ESAI, /* ESAI */ + IMX_DMATYPE_SSI_DUAL, /* SSI Dual FIFO */ + IMX_DMATYPE_ASRC_SP, /* Shared ASRC */ + IMX_DMATYPE_SAI, /* SAI */ +}; + +enum imx_dma_prio { + DMA_PRIO_HIGH = 0, + DMA_PRIO_MEDIUM = 1, + DMA_PRIO_LOW = 2 +}; + +struct imx_dma_data { + int dma_request; /* DMA request line */ + int dma_request2; /* secondary DMA request line */ + enum sdma_peripheral_type peripheral_type; + int priority; +}; + +static inline int imx_dma_is_ipu(struct dma_chan *chan) +{ + return !strcmp(dev_name(chan->device->dev), "ipu-core"); +} + +static inline int imx_dma_is_general_purpose(struct dma_chan *chan) +{ + return !strcmp(chan->device->dev->driver->name, "imx-sdma") || + !strcmp(chan->device->dev->driver->name, "imx-dma"); +} + +#endif /* __LINUX_DMA_IMX_H */ diff --git a/include/linux/platform_data/dma-imx.h b/include/linux/platform_data/dma-imx.h deleted file mode 100644 index 281adbb26e6b..000000000000 --- a/include/linux/platform_data/dma-imx.h +++ /dev/null @@ -1,68 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2004-2009 Freescale Semiconductor, Inc. All Rights Reserved. - */ - -#ifndef __ASM_ARCH_MXC_DMA_H__ -#define __ASM_ARCH_MXC_DMA_H__ - -#include -#include -#include - -/* - * This enumerates peripheral types. Used for SDMA. - */ -enum sdma_peripheral_type { - IMX_DMATYPE_SSI, /* MCU domain SSI */ - IMX_DMATYPE_SSI_SP, /* Shared SSI */ - IMX_DMATYPE_MMC, /* MMC */ - IMX_DMATYPE_SDHC, /* SDHC */ - IMX_DMATYPE_UART, /* MCU domain UART */ - IMX_DMATYPE_UART_SP, /* Shared UART */ - IMX_DMATYPE_FIRI, /* FIRI */ - IMX_DMATYPE_CSPI, /* MCU domain CSPI */ - IMX_DMATYPE_CSPI_SP, /* Shared CSPI */ - IMX_DMATYPE_SIM, /* SIM */ - IMX_DMATYPE_ATA, /* ATA */ - IMX_DMATYPE_CCM, /* CCM */ - IMX_DMATYPE_EXT, /* External peripheral */ - IMX_DMATYPE_MSHC, /* Memory Stick Host Controller */ - IMX_DMATYPE_MSHC_SP, /* Shared Memory Stick Host Controller */ - IMX_DMATYPE_DSP, /* DSP */ - IMX_DMATYPE_MEMORY, /* Memory */ - IMX_DMATYPE_FIFO_MEMORY,/* FIFO type Memory */ - IMX_DMATYPE_SPDIF, /* SPDIF */ - IMX_DMATYPE_IPU_MEMORY, /* IPU Memory */ - IMX_DMATYPE_ASRC, /* ASRC */ - IMX_DMATYPE_ESAI, /* ESAI */ - IMX_DMATYPE_SSI_DUAL, /* SSI Dual FIFO */ - IMX_DMATYPE_ASRC_SP, /* Shared ASRC */ - IMX_DMATYPE_SAI, /* SAI */ -}; - -enum imx_dma_prio { - DMA_PRIO_HIGH = 0, - DMA_PRIO_MEDIUM = 1, - DMA_PRIO_LOW = 2 -}; - -struct imx_dma_data { - int dma_request; /* DMA request line */ - int dma_request2; /* secondary DMA request line */ - enum sdma_peripheral_type peripheral_type; - int priority; -}; - -static inline int imx_dma_is_ipu(struct dma_chan *chan) -{ - return !strcmp(dev_name(chan->device->dev), "ipu-core"); -} - -static inline int imx_dma_is_general_purpose(struct dma_chan *chan) -{ - return !strcmp(chan->device->dev->driver->name, "imx-sdma") || - !strcmp(chan->device->dev->driver->name, "imx-dma"); -} - -#endif -- cgit v1.2.3 From 824a0a02cd74776461aaa30d792b1ed9111c9aa5 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Thu, 14 Apr 2022 18:22:39 +0200 Subject: dmaengine: imx-sdma: Add multi fifo support The i.MX SDMA engine can read from / write to multiple successive hardware FIFO registers, referred to as "Multi FIFO support". This is needed for the micfil driver and certain configurations of the SAI driver. This patch adds support for this feature. The number of FIFOs to read from / write to must be communicated from the client driver to the SDMA engine. For this the struct dma_slave_config::peripheral_config field is used. Signed-off-by: Sascha Hauer Acked-By: Vinod Koul Link: https://lore.kernel.org/r/20220414162249.3934543-12-s.hauer@pengutronix.de Signed-off-by: Mark Brown --- include/linux/dma/imx-dma.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/dma/imx-dma.h b/include/linux/dma/imx-dma.h index b06cba85a6d4..8887762360d4 100644 --- a/include/linux/dma/imx-dma.h +++ b/include/linux/dma/imx-dma.h @@ -39,6 +39,7 @@ enum sdma_peripheral_type { IMX_DMATYPE_SSI_DUAL, /* SSI Dual FIFO */ IMX_DMATYPE_ASRC_SP, /* Shared ASRC */ IMX_DMATYPE_SAI, /* SAI */ + IMX_DMATYPE_MULTI_SAI, /* MULTI FIFOs For Audio */ }; enum imx_dma_prio { @@ -65,4 +66,23 @@ static inline int imx_dma_is_general_purpose(struct dma_chan *chan) !strcmp(chan->device->dev->driver->name, "imx-dma"); } +/** + * struct sdma_peripheral_config - SDMA config for audio + * @n_fifos_src: Number of FIFOs for recording + * @n_fifos_dst: Number of FIFOs for playback + * @sw_done: Use software done. Needed for PDM (micfil) + * + * Some i.MX Audio devices (SAI, micfil) have multiple successive FIFO + * registers. For multichannel recording/playback the SAI/micfil have + * one FIFO register per channel and the SDMA engine has to read/write + * the next channel from/to the next register and wrap around to the + * first register when all channels are handled. The number of active + * channels must be communicated to the SDMA engine using this struct. + */ +struct sdma_peripheral_config { + int n_fifos_src; + int n_fifos_dst; + bool sw_done; +}; + #endif /* __LINUX_DMA_IMX_H */ -- cgit v1.2.3 From b617be33502d2bfefffef71924c7a7ba50264ff6 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Mon, 11 Apr 2022 21:45:27 +0300 Subject: spi: add SPI_RX_CPHA_FLIP mode bit Some SPI devices latch MOSI bits on one clock phase, but produce valid MISO bits on the other phase. Add SPI_RX_CPHA_FLIP mode to instruct the controller driver to flip CPHA for Rx (MISO) only transfers. Signed-off-by: Baruch Siach Link: https://lore.kernel.org/r/a715ca92713ca02071f33dcca9960a66a03c949a.1649702729.git.baruch@tkos.co.il Signed-off-by: Mark Brown --- include/uapi/linux/spi/spi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/spi/spi.h b/include/uapi/linux/spi/spi.h index 236a85f08ded..9d5f58059703 100644 --- a/include/uapi/linux/spi/spi.h +++ b/include/uapi/linux/spi/spi.h @@ -27,6 +27,7 @@ #define SPI_TX_OCTAL _BITUL(13) /* transmit with 8 wires */ #define SPI_RX_OCTAL _BITUL(14) /* receive with 8 wires */ #define SPI_3WIRE_HIZ _BITUL(15) /* high impedance turnaround */ +#define SPI_RX_CPHA_FLIP _BITUL(16) /* flip CPHA on Rx only xfer */ /* * All the bits defined above should be covered by SPI_MODE_USER_MASK. @@ -36,6 +37,6 @@ * These bits must not overlap. A static assert check should make sure of that. * If adding extra bits, make sure to increase the bit index below as well. */ -#define SPI_MODE_USER_MASK (_BITUL(16) - 1) +#define SPI_MODE_USER_MASK (_BITUL(17) - 1) #endif /* _UAPI_SPI_H */ -- cgit v1.2.3 From 6c846d026d490b2383d395bc8e7b06336219667b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 19 Apr 2022 15:18:37 +0100 Subject: gpio: Don't fiddle with irqchips marked as immutable In order to move away from gpiolib messing with the internals of unsuspecting irqchips, add a flag by which irqchips advertise that they are not to be messed with, and do solemnly swear that they correctly call into the gpiolib helpers when required. Also nudge the users into converting their drivers to the new model. Reviewed-by: Andy Shevchenko Reviewed-by: Bartosz Golaszewski Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220419141846.598305-2-maz@kernel.org --- include/linux/irq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index f92788ccdba2..505308253d23 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -569,6 +569,7 @@ struct irq_chip { * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup + * IRQCHIP_IMMUTABLE: Don't ever change anything in this chip */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -582,6 +583,7 @@ enum { IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), + IRQCHIP_IMMUTABLE = (1 << 11), }; #include -- cgit v1.2.3 From 704f08753b6dcd0e08c1953af0b2c7f3fac87111 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 19 Apr 2022 15:18:38 +0100 Subject: gpio: Expose the gpiochip_irq_re[ql]res helpers The GPIO subsystem has a couple of internal helpers to manage resources on behalf of the irqchip. Expose them so that GPIO drivers can use them directly. Reviewed-by: Andy Shevchenko Reviewed-by: Bartosz Golaszewski Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220419141846.598305-3-maz@kernel.org --- include/linux/gpio/driver.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..066bcfdf878d 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -579,6 +579,10 @@ void gpiochip_relres_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_disable_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset); +/* irq_data versions of the above */ +int gpiochip_irq_reqres(struct irq_data *data); +void gpiochip_irq_relres(struct irq_data *data); + /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset); bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset); -- cgit v1.2.3 From 36b78aae4bfee749bbde73be570796bfd0f56bec Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 19 Apr 2022 15:18:39 +0100 Subject: gpio: Add helpers to ease the transition towards immutable irq_chip Add a couple of new helpers to make it slightly simpler to convert drivers to immutable irq_chip structures: - GPIOCHIP_IRQ_RESOURCE_HELPERS populates the irq_chip structure with the resource management callbacks - gpio_irq_chip_set_chip() populates the gpio_irq_chip.chip structure, avoiding the proliferation of ugly casts Reviewed-by: Andy Shevchenko Reviewed-by: Bartosz Golaszewski Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220419141846.598305-4-maz@kernel.org --- include/linux/gpio/driver.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 066bcfdf878d..832990099097 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -583,6 +583,18 @@ void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset); int gpiochip_irq_reqres(struct irq_data *data); void gpiochip_irq_relres(struct irq_data *data); +/* Paste this in your irq_chip structure */ +#define GPIOCHIP_IRQ_RESOURCE_HELPERS \ + .irq_request_resources = gpiochip_irq_reqres, \ + .irq_release_resources = gpiochip_irq_relres + +static inline void gpio_irq_chip_set_chip(struct gpio_irq_chip *girq, + const struct irq_chip *chip) +{ + /* Yes, dropping const is ugly, but it isn't like we have a choice */ + girq->chip = (struct irq_chip *)chip; +} + /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset); bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset); -- cgit v1.2.3 From 08d3df8c81537089fc8f21006b56f2f6fb23c6f8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 1 Sep 2019 22:26:10 +0200 Subject: ARM: pxa: split up mach/hardware.h The mach/hardware.h is included in lots of places, and it provides three different things on pxa: - the cpu_is_pxa* macros - an indirect inclusion of mach/addr-map.h - the __REG() and io_pv2() helper macros Split it up into separate and mach/pxa-regs.h headers, then change all the files that use mach/hardware.h to include the exact set of those three headers that they actually need, allowing for further more targeted cleanup. linux/soc/pxa/cpu.h can remain permanently exported and is now in a global location along with similar headers. pxa-regs.h and addr-map.h are only used in a very small number of drivers now and can be moved to arch/arm/mach-pxa/ directly when those drivers are to pass the necessary data as resources. Cc: Michael Turquette Cc: Stephen Boyd Acked-by: Viresh Kumar Acked-by: Dmitry Torokhov Cc: Jacek Anaszewski Cc: Pavel Machek Acked-by: Ulf Hansson Cc: Dominik Brodowski Acked-by: Alexandre Belloni Cc: Greg Kroah-Hartman Cc: Guenter Roeck Acked-by: Mark Brown Cc: linux-clk@vger.kernel.org Cc: linux-pm@vger.kernel.org Cc: linux-input@vger.kernel.org Cc: linux-leds@vger.kernel.org Cc: linux-mmc@vger.kernel.org Cc: linux-mtd@lists.infradead.org Cc: linux-rtc@vger.kernel.org Cc: linux-usb@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Cc: linux-watchdog@vger.kernel.org Cc: alsa-devel@alsa-project.org Signed-off-by: Arnd Bergmann --- include/linux/soc/pxa/cpu.h | 252 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 252 insertions(+) create mode 100644 include/linux/soc/pxa/cpu.h (limited to 'include') diff --git a/include/linux/soc/pxa/cpu.h b/include/linux/soc/pxa/cpu.h new file mode 100644 index 000000000000..5782450ee45c --- /dev/null +++ b/include/linux/soc/pxa/cpu.h @@ -0,0 +1,252 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Author: Nicolas Pitre + * Created: Jun 15, 2001 + * Copyright: MontaVista Software Inc. + */ + +#ifndef __SOC_PXA_CPU_H +#define __SOC_PXA_CPU_H + +#ifdef CONFIG_ARM +#include +#endif + +/* + * CPU Stepping CPU_ID JTAG_ID + * + * PXA210 B0 0x69052922 0x2926C013 + * PXA210 B1 0x69052923 0x3926C013 + * PXA210 B2 0x69052924 0x4926C013 + * PXA210 C0 0x69052D25 0x5926C013 + * + * PXA250 A0 0x69052100 0x09264013 + * PXA250 A1 0x69052101 0x19264013 + * PXA250 B0 0x69052902 0x29264013 + * PXA250 B1 0x69052903 0x39264013 + * PXA250 B2 0x69052904 0x49264013 + * PXA250 C0 0x69052D05 0x59264013 + * + * PXA255 A0 0x69052D06 0x69264013 + * + * PXA26x A0 0x69052903 0x39264013 + * PXA26x B0 0x69052D05 0x59264013 + * + * PXA27x A0 0x69054110 0x09265013 + * PXA27x A1 0x69054111 0x19265013 + * PXA27x B0 0x69054112 0x29265013 + * PXA27x B1 0x69054113 0x39265013 + * PXA27x C0 0x69054114 0x49265013 + * PXA27x C5 0x69054117 0x79265013 + * + * PXA30x A0 0x69056880 0x0E648013 + * PXA30x A1 0x69056881 0x1E648013 + * PXA31x A0 0x69056890 0x0E649013 + * PXA31x A1 0x69056891 0x1E649013 + * PXA31x A2 0x69056892 0x2E649013 + * PXA32x B1 0x69056825 0x5E642013 + * PXA32x B2 0x69056826 0x6E642013 + * + * PXA930 B0 0x69056835 0x5E643013 + * PXA930 B1 0x69056837 0x7E643013 + * PXA930 B2 0x69056838 0x8E643013 + * + * PXA935 A0 0x56056931 0x1E653013 + * PXA935 B0 0x56056936 0x6E653013 + * PXA935 B1 0x56056938 0x8E653013 + */ +#ifdef CONFIG_PXA25x +#define __cpu_is_pxa210(id) \ + ({ \ + unsigned int _id = (id) & 0xf3f0; \ + _id == 0x2120; \ + }) + +#define __cpu_is_pxa250(id) \ + ({ \ + unsigned int _id = (id) & 0xf3ff; \ + _id <= 0x2105; \ + }) + +#define __cpu_is_pxa255(id) \ + ({ \ + unsigned int _id = (id) & 0xffff; \ + _id == 0x2d06; \ + }) + +#define __cpu_is_pxa25x(id) \ + ({ \ + unsigned int _id = (id) & 0xf300; \ + _id == 0x2100; \ + }) +#else +#define __cpu_is_pxa210(id) (0) +#define __cpu_is_pxa250(id) (0) +#define __cpu_is_pxa255(id) (0) +#define __cpu_is_pxa25x(id) (0) +#endif + +#ifdef CONFIG_PXA27x +#define __cpu_is_pxa27x(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x411; \ + }) +#else +#define __cpu_is_pxa27x(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA300 +#define __cpu_is_pxa300(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x688; \ + }) +#else +#define __cpu_is_pxa300(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA310 +#define __cpu_is_pxa310(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x689; \ + }) +#else +#define __cpu_is_pxa310(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA320 +#define __cpu_is_pxa320(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x603 || _id == 0x682; \ + }) +#else +#define __cpu_is_pxa320(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA930 +#define __cpu_is_pxa930(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x683; \ + }) +#else +#define __cpu_is_pxa930(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA935 +#define __cpu_is_pxa935(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x693; \ + }) +#else +#define __cpu_is_pxa935(id) (0) +#endif + +#define cpu_is_pxa210() \ + ({ \ + __cpu_is_pxa210(read_cpuid_id()); \ + }) + +#define cpu_is_pxa250() \ + ({ \ + __cpu_is_pxa250(read_cpuid_id()); \ + }) + +#define cpu_is_pxa255() \ + ({ \ + __cpu_is_pxa255(read_cpuid_id()); \ + }) + +#define cpu_is_pxa25x() \ + ({ \ + __cpu_is_pxa25x(read_cpuid_id()); \ + }) + +#define cpu_is_pxa27x() \ + ({ \ + __cpu_is_pxa27x(read_cpuid_id()); \ + }) + +#define cpu_is_pxa300() \ + ({ \ + __cpu_is_pxa300(read_cpuid_id()); \ + }) + +#define cpu_is_pxa310() \ + ({ \ + __cpu_is_pxa310(read_cpuid_id()); \ + }) + +#define cpu_is_pxa320() \ + ({ \ + __cpu_is_pxa320(read_cpuid_id()); \ + }) + +#define cpu_is_pxa930() \ + ({ \ + __cpu_is_pxa930(read_cpuid_id()); \ + }) + +#define cpu_is_pxa935() \ + ({ \ + __cpu_is_pxa935(read_cpuid_id()); \ + }) + + + +/* + * CPUID Core Generation Bit + * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x + */ +#if defined(CONFIG_PXA25x) || defined(CONFIG_PXA27x) +#define __cpu_is_pxa2xx(id) \ + ({ \ + unsigned int _id = (id) >> 13 & 0x7; \ + _id <= 0x2; \ + }) +#else +#define __cpu_is_pxa2xx(id) (0) +#endif + +#ifdef CONFIG_PXA3xx +#define __cpu_is_pxa3xx(id) \ + ({ \ + __cpu_is_pxa300(id) \ + || __cpu_is_pxa310(id) \ + || __cpu_is_pxa320(id) \ + || __cpu_is_pxa93x(id); \ + }) +#else +#define __cpu_is_pxa3xx(id) (0) +#endif + +#if defined(CONFIG_CPU_PXA930) || defined(CONFIG_CPU_PXA935) +#define __cpu_is_pxa93x(id) \ + ({ \ + __cpu_is_pxa930(id) \ + || __cpu_is_pxa935(id); \ + }) +#else +#define __cpu_is_pxa93x(id) (0) +#endif + +#define cpu_is_pxa2xx() \ + ({ \ + __cpu_is_pxa2xx(read_cpuid_id()); \ + }) + +#define cpu_is_pxa3xx() \ + ({ \ + __cpu_is_pxa3xx(read_cpuid_id()); \ + }) + +#define cpu_is_pxa93x() \ + ({ \ + __cpu_is_pxa93x(read_cpuid_id()); \ + }) + +#endif -- cgit v1.2.3 From 22f0866513c2e531ae65a9d5dfc82f24497ef3b3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 2 Sep 2019 00:02:08 +0200 Subject: ARM: pxa: move mach/sound.h to linux/platform_data/ This is a basically a platform_data file, so move it out of the mach/* header directory. Cc: Marek Vasut Cc: Tomas Cech Cc: Sergey Lapin Acked-by: Mark Brown Acked-by: Robert Jarzmik Cc: alsa-devel@alsa-project.org Signed-off-by: Arnd Bergmann --- include/linux/platform_data/asoc-pxa.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/linux/platform_data/asoc-pxa.h (limited to 'include') diff --git a/include/linux/platform_data/asoc-pxa.h b/include/linux/platform_data/asoc-pxa.h new file mode 100644 index 000000000000..327454cd8246 --- /dev/null +++ b/include/linux/platform_data/asoc-pxa.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SOC_PXA_AUDIO_H__ +#define __SOC_PXA_AUDIO_H__ + +#include +#include +#include + +/* + * @reset_gpio: AC97 reset gpio (normally gpio113 or gpio95) + * a -1 value means no gpio will be used for reset + * @codec_pdata: AC97 codec platform_data + + * reset_gpio should only be specified for pxa27x CPUs where a silicon + * bug prevents correct operation of the reset line. If not specified, + * the default behaviour on these CPUs is to consider gpio 113 as the + * AC97 reset line, which is the default on most boards. + */ +typedef struct { + int (*startup)(struct snd_pcm_substream *, void *); + void (*shutdown)(struct snd_pcm_substream *, void *); + void (*suspend)(void *); + void (*resume)(void *); + void *priv; + int reset_gpio; + void *codec_pdata[AC97_BUS_MAX_DEVICES]; +} pxa2xx_audio_ops_t; + +extern void pxa_set_ac97_info(pxa2xx_audio_ops_t *ops); + +#endif -- cgit v1.2.3 From ee84cbd5df2beaf14e8af0955f1ab15ad3f81504 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 2 Sep 2019 00:15:44 +0200 Subject: ARM: pxa: move regs-lcd.h into driver Only the pxafb driver uses this header, so move it into the same directory. The SMART_* macros are required by some platform data definitions and can go into the linux/platform_data/video-pxafb.h header. Acked-by: Bartlomiej Zolnierkiewicz Acked-by: Robert Jarzmik Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Signed-off-by: Arnd Bergmann --- include/linux/platform_data/video-pxafb.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/video-pxafb.h b/include/linux/platform_data/video-pxafb.h index b3d574778326..6333bac166a5 100644 --- a/include/linux/platform_data/video-pxafb.h +++ b/include/linux/platform_data/video-pxafb.h @@ -8,7 +8,6 @@ */ #include -#include /* * Supported LCD connections @@ -153,6 +152,27 @@ struct pxafb_mach_info { void pxa_set_fb_info(struct device *, struct pxafb_mach_info *); unsigned long pxafb_get_hsync_time(struct device *dev); +/* smartpanel related */ +#define SMART_CMD_A0 (0x1 << 8) +#define SMART_CMD_READ_STATUS_REG (0x0 << 9) +#define SMART_CMD_READ_FRAME_BUFFER ((0x0 << 9) | SMART_CMD_A0) +#define SMART_CMD_WRITE_COMMAND (0x1 << 9) +#define SMART_CMD_WRITE_DATA ((0x1 << 9) | SMART_CMD_A0) +#define SMART_CMD_WRITE_FRAME ((0x2 << 9) | SMART_CMD_A0) +#define SMART_CMD_WAIT_FOR_VSYNC (0x3 << 9) +#define SMART_CMD_NOOP (0x4 << 9) +#define SMART_CMD_INTERRUPT (0x5 << 9) + +#define SMART_CMD(x) (SMART_CMD_WRITE_COMMAND | ((x) & 0xff)) +#define SMART_DAT(x) (SMART_CMD_WRITE_DATA | ((x) & 0xff)) + +/* SMART_DELAY() is introduced for software controlled delay primitive which + * can be inserted between command sequences, unused command 0x6 is used here + * and delay ranges from 0ms ~ 255ms + */ +#define SMART_CMD_DELAY (0x6 << 9) +#define SMART_DELAY(ms) (SMART_CMD_DELAY | ((ms) & 0xff)) + #ifdef CONFIG_FB_PXA_SMARTPANEL extern int pxafb_smart_queue(struct fb_info *info, uint16_t *cmds, int); extern int pxafb_smart_flush(struct fb_info *info); -- cgit v1.2.3 From eb38c2053b67977844404cbbdee341dbf3a02d36 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 14 Mar 2022 23:09:10 +0100 Subject: can: rx-offload: rename can_rx_offload_queue_sorted() -> can_rx_offload_queue_timestamp() This patch renames the function can_rx_offload_queue_sorted() to can_rx_offload_queue_timestamp(). This better describes what the function does, it adds a newly RX'ed skb to the sorted queue by its timestamp. Link: https://lore.kernel.org/all/20220417194327.2699059-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/rx-offload.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index c11477620403..c205c51d79c9 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -42,8 +42,8 @@ int can_rx_offload_add_manual(struct net_device *dev, int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 reg); int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); -int can_rx_offload_queue_sorted(struct can_rx_offload *offload, - struct sk_buff *skb, u32 timestamp); +int can_rx_offload_queue_timestamp(struct can_rx_offload *offload, + struct sk_buff *skb, u32 timestamp); unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, unsigned int idx, u32 timestamp, unsigned int *frame_len_ptr); -- cgit v1.2.3 From 9995c1d096c8ab1b5f1edc4141257719f6a53524 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 6 Apr 2022 14:00:55 -0500 Subject: ASoC: soc-pcm: improve BE transition for PAUSE_RELEASE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 3aa1e96a2b95 ("ASoC: soc-pcm: fix BE handling of PAUSE_RELEASE") did not modify the existing logic and kept the same logic for the following transition play FE1 -> BE state is START pause FE1 -> BE state is PAUSED play FE2 -> BE state is START stop FE2 -> BE state is STOP <<< !! release FE1 -> BE state is START stop FE1 -> BE state is STOP At the time it was identified by reviewers that a better solution might consist in play FE1 -> BE state is START pause FE1 -> BE state is PAUSED play FE2 -> BE state is START stop FE2 -> BE state is PAUSE <<< !! release FE1 -> BE state is START stop FE1 -> BE state is STOP This patch suggest a transition to PAUSE when all the 'active' streams are paused. This would allow for a more consistent resource management for platforms where PAUSE and STOP are handled differently. To track the special case of an FE going from PAUSE_PUSH to STOP, we add a state variable for each FE context. This 'fe_pause' boolean is set on PAUSE_PUSH and cleared on either PAUSE_RELEASE and STOP triggers. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Reviewed-by: Ranjani Sridharan Reviewed-by: Péter Ujfalusi Reviewed-by: Bard Liao Link: https://lore.kernel.org/r/20220406190056.233481-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/soc-dpcm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h index 75b92d883976..5b689c663290 100644 --- a/include/sound/soc-dpcm.h +++ b/include/sound/soc-dpcm.h @@ -103,6 +103,8 @@ struct snd_soc_dpcm_runtime { int trigger_pending; /* trigger cmd + 1 if pending, 0 if not */ int be_start; /* refcount protected by BE stream pcm lock */ + int be_pause; /* refcount protected by BE stream pcm lock */ + bool fe_pause; /* used to track STOP after PAUSE */ }; #define for_each_dpcm_fe(be, stream, _dpcm) \ -- cgit v1.2.3 From 055eb95533273bc334794dbc598400d10800528f Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 14 Apr 2022 09:12:33 -0700 Subject: bpf: Move rcu lock management out of BPF_PROG_RUN routines Commit 7d08c2c91171 ("bpf: Refactor BPF_PROG_RUN_ARRAY family of macros into functions") switched a bunch of BPF_PROG_RUN macros to inline routines. This changed the semantic a bit. Due to arguments expansion of macros, it used to be: rcu_read_lock(); array = rcu_dereference(cgrp->bpf.effective[atype]); ... Now, with with inline routines, we have: array_rcu = rcu_dereference(cgrp->bpf.effective[atype]); /* array_rcu can be kfree'd here */ rcu_read_lock(); array = rcu_dereference(array_rcu); I'm assuming in practice rcu subsystem isn't fast enough to trigger this but let's use rcu API properly. Also, rename to lower caps to not confuse with macros. Additionally, drop and expand BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY. See [1] for more context. [1] https://lore.kernel.org/bpf/CAKH8qBs60fOinFdxiiQikK_q0EcVxGvNTQoWvHLEUGbgcj1UYg@mail.gmail.com/T/#u v2 - keep rcu locks inside by passing cgroup_bpf Fixes: 7d08c2c91171 ("bpf: Refactor BPF_PROG_RUN_ARRAY family of macros into functions") Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20220414161233.170780-1-sdf@google.com --- include/linux/bpf.h | 115 ++++------------------------------------------------ 1 file changed, 7 insertions(+), 108 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdb5298735ce..7bf441563ffc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1221,7 +1221,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, /* an array of programs to be executed under rcu_lock. * * Typical usage: - * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, bpf_prog_run); + * ret = bpf_prog_run_array(rcu_dereference(&bpf_prog_array), ctx, bpf_prog_run); * * the structure returned by bpf_prog_array_alloc() should be populated * with program pointers and the last pointer must be NULL. @@ -1315,83 +1315,22 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); -static __always_inline int -BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog, - int retval, u32 *ret_flags) -{ - const struct bpf_prog_array_item *item; - const struct bpf_prog *prog; - const struct bpf_prog_array *array; - struct bpf_run_ctx *old_run_ctx; - struct bpf_cg_run_ctx run_ctx; - u32 func_ret; - - run_ctx.retval = retval; - migrate_disable(); - rcu_read_lock(); - array = rcu_dereference(array_rcu); - item = &array->items[0]; - old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); - while ((prog = READ_ONCE(item->prog))) { - run_ctx.prog_item = item; - func_ret = run_prog(prog, ctx); - if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval)) - run_ctx.retval = -EPERM; - *(ret_flags) |= (func_ret >> 1); - item++; - } - bpf_reset_run_ctx(old_run_ctx); - rcu_read_unlock(); - migrate_enable(); - return run_ctx.retval; -} - -static __always_inline int -BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog, - int retval) -{ - const struct bpf_prog_array_item *item; - const struct bpf_prog *prog; - const struct bpf_prog_array *array; - struct bpf_run_ctx *old_run_ctx; - struct bpf_cg_run_ctx run_ctx; - - run_ctx.retval = retval; - migrate_disable(); - rcu_read_lock(); - array = rcu_dereference(array_rcu); - item = &array->items[0]; - old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); - while ((prog = READ_ONCE(item->prog))) { - run_ctx.prog_item = item; - if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval)) - run_ctx.retval = -EPERM; - item++; - } - bpf_reset_run_ctx(old_run_ctx); - rcu_read_unlock(); - migrate_enable(); - return run_ctx.retval; -} - static __always_inline u32 -BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu, +bpf_prog_run_array(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; - const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; - migrate_disable(); - rcu_read_lock(); - array = rcu_dereference(array_rcu); + RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held"); + if (unlikely(!array)) - goto out; + return ret; + + migrate_disable(); old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { @@ -1400,50 +1339,10 @@ BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu, item++; } bpf_reset_run_ctx(old_run_ctx); -out: - rcu_read_unlock(); migrate_enable(); return ret; } -/* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs - * so BPF programs can request cwr for TCP packets. - * - * Current cgroup skb programs can only return 0 or 1 (0 to drop the - * packet. This macro changes the behavior so the low order bit - * indicates whether the packet should be dropped (0) or not (1) - * and the next bit is a congestion notification bit. This could be - * used by TCP to call tcp_enter_cwr() - * - * Hence, new allowed return values of CGROUP EGRESS BPF programs are: - * 0: drop packet - * 1: keep packet - * 2: drop packet and cn - * 3: keep packet and cn - * - * This macro then converts it to one of the NET_XMIT or an error - * code that is then interpreted as drop packet (and no cn): - * 0: NET_XMIT_SUCCESS skb should be transmitted - * 1: NET_XMIT_DROP skb should be dropped and cn - * 2: NET_XMIT_CN skb should be transmitted and cn - * 3: -err skb should be dropped - */ -#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ - ({ \ - u32 _flags = 0; \ - bool _cn; \ - u32 _ret; \ - _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \ - _cn = _flags & BPF_RET_SET_CN; \ - if (_ret && !IS_ERR_VALUE((long)_ret)) \ - _ret = -EFAULT; \ - if (!_ret) \ - _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ - else \ - _ret = (_cn ? NET_XMIT_DROP : _ret); \ - _ret; \ - }) - #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; -- cgit v1.2.3 From 368cfcbaa3bf7a8c482f596a131dea4befeba10a Mon Sep 17 00:00:00 2001 From: Michael Srba Date: Mon, 11 Apr 2022 09:21:52 +0200 Subject: dt-bindings: clock: gcc-msm8998: Add definitions of SSC-related clocks Add definitions of four clocks which need to be manipulated in order to initialize the AHB bus which exposes the SCC block in the global address space. Signed-off-by: Michael Srba Acked-by: Rob Herring Reviewed-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220411072156.24451-2-michael.srba@seznam.cz --- include/dt-bindings/clock/qcom,gcc-msm8998.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-msm8998.h b/include/dt-bindings/clock/qcom,gcc-msm8998.h index 72c99e486d86..1badb4f9c58f 100644 --- a/include/dt-bindings/clock/qcom,gcc-msm8998.h +++ b/include/dt-bindings/clock/qcom,gcc-msm8998.h @@ -186,6 +186,10 @@ #define UFS_UNIPRO_CORE_CLK_SRC 177 #define GCC_MMSS_GPLL0_CLK 178 #define HMSS_GPLL0_CLK_SRC 179 +#define GCC_IM_SLEEP 180 +#define AGGRE2_SNOC_NORTH_AXI 181 +#define SSC_XO 182 +#define SSC_CNOC_AHBS_CLK 183 #define PCIE_0_GDSC 0 #define UFS_GDSC 1 -- cgit v1.2.3 From b83deaa741558babf4b8d51d34f6637ccfff1b26 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 28 May 2020 22:57:40 +0200 Subject: ARM: pxa: move pcmcia board data into mach-pxa The drivers/pcmcia/pxa2xx_*.c are essentially part of the board files, but for historic reasons located in drivers/pcmcia. Move them into the same place as the actual board file to avoid lots of machine header inclusions. Cc: Marek Vasut Cc: Dominik Brodowski Cc: Jonathan Cameron Signed-off-by: Arnd Bergmann --- include/linux/platform_data/pcmcia-pxa2xx_viper.h | 12 --- include/pcmcia/soc_common.h | 125 ++++++++++++++++++++++ 2 files changed, 125 insertions(+), 12 deletions(-) delete mode 100644 include/linux/platform_data/pcmcia-pxa2xx_viper.h create mode 100644 include/pcmcia/soc_common.h (limited to 'include') diff --git a/include/linux/platform_data/pcmcia-pxa2xx_viper.h b/include/linux/platform_data/pcmcia-pxa2xx_viper.h deleted file mode 100644 index a23b58aff9e1..000000000000 --- a/include/linux/platform_data/pcmcia-pxa2xx_viper.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ARCOM_PCMCIA_H -#define __ARCOM_PCMCIA_H - -struct arcom_pcmcia_pdata { - int cd_gpio; - int rdy_gpio; - int pwr_gpio; - void (*reset)(int state); -}; - -#endif diff --git a/include/pcmcia/soc_common.h b/include/pcmcia/soc_common.h new file mode 100644 index 000000000000..26f1473a06c5 --- /dev/null +++ b/include/pcmcia/soc_common.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include + +struct module; +struct cpufreq_freqs; + +struct soc_pcmcia_regulator { + struct regulator *reg; + bool on; +}; + +struct pcmcia_state { + unsigned detect: 1, + ready: 1, + bvd1: 1, + bvd2: 1, + wrprot: 1, + vs_3v: 1, + vs_Xv: 1; +}; + +/* + * This structure encapsulates per-socket state which we might need to + * use when responding to a Card Services query of some kind. + */ +struct soc_pcmcia_socket { + struct pcmcia_socket socket; + + /* + * Info from low level handler + */ + unsigned int nr; + struct clk *clk; + + /* + * Core PCMCIA state + */ + const struct pcmcia_low_level *ops; + + unsigned int status; + socket_state_t cs_state; + + unsigned short spd_io[MAX_IO_WIN]; + unsigned short spd_mem[MAX_WIN]; + unsigned short spd_attr[MAX_WIN]; + + struct resource res_skt; + struct resource res_io; + struct resource res_mem; + struct resource res_attr; + void __iomem *virt_io; + + struct { + int gpio; + struct gpio_desc *desc; + unsigned int irq; + const char *name; + } stat[6]; +#define SOC_STAT_CD 0 /* Card detect */ +#define SOC_STAT_BVD1 1 /* BATDEAD / IOSTSCHG */ +#define SOC_STAT_BVD2 2 /* BATWARN / IOSPKR */ +#define SOC_STAT_RDY 3 /* Ready / Interrupt */ +#define SOC_STAT_VS1 4 /* Voltage sense 1 */ +#define SOC_STAT_VS2 5 /* Voltage sense 2 */ + + struct gpio_desc *gpio_reset; + struct gpio_desc *gpio_bus_enable; + struct soc_pcmcia_regulator vcc; + struct soc_pcmcia_regulator vpp; + + unsigned int irq_state; + +#ifdef CONFIG_CPU_FREQ + struct notifier_block cpufreq_nb; +#endif + struct timer_list poll_timer; + struct list_head node; + void *driver_data; +}; + + +struct pcmcia_low_level { + struct module *owner; + + /* first socket in system */ + int first; + /* nr of sockets */ + int nr; + + int (*hw_init)(struct soc_pcmcia_socket *); + void (*hw_shutdown)(struct soc_pcmcia_socket *); + + void (*socket_state)(struct soc_pcmcia_socket *, struct pcmcia_state *); + int (*configure_socket)(struct soc_pcmcia_socket *, const socket_state_t *); + + /* + * Enable card status IRQs on (re-)initialisation. This can + * be called at initialisation, power management event, or + * pcmcia event. + */ + void (*socket_init)(struct soc_pcmcia_socket *); + + /* + * Disable card status IRQs and PCMCIA bus on suspend. + */ + void (*socket_suspend)(struct soc_pcmcia_socket *); + + /* + * Hardware specific timing routines. + * If provided, the get_timing routine overrides the SOC default. + */ + unsigned int (*get_timing)(struct soc_pcmcia_socket *, unsigned int, unsigned int); + int (*set_timing)(struct soc_pcmcia_socket *); + int (*show_timing)(struct soc_pcmcia_socket *, char *); + +#ifdef CONFIG_CPU_FREQ + /* + * CPUFREQ support. + */ + int (*frequency_change)(struct soc_pcmcia_socket *, unsigned long, struct cpufreq_freqs *); +#endif +}; + + + -- cgit v1.2.3 From 72c3c8d6e5275b19fd2d32ec787e8135a421c7ec Mon Sep 17 00:00:00 2001 From: Matt Atwood Date: Mon, 18 Apr 2022 11:51:57 +0530 Subject: drm/i915/rpl-p: Add PCI IDs Adding initial PCI ids for RPL-P. RPL-P behaves identically to ADL-P from i915's point of view. Changes since V1 : - SUBPLATFORM ADL_N and RPL_P clash as both are ADLP based - Matthew R Bspec: 55376 Signed-off-by: Matt Atwood Signed-off-by: Madhumitha Tolakanahalli Pradeep Signed-off-by: Tejas Upadhyay [mattrope: Corrected comment formatting to match coding style] Signed-off-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20220418062157.2974665-1-tejaskumarx.surendrakumar.upadhyay@intel.com --- include/drm/i915_pciids.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index 0800dc8b98b3..a7b5eea7ffaa 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -683,4 +683,13 @@ INTEL_VGA_DEVICE(0xA78A, info), \ INTEL_VGA_DEVICE(0xA78B, info) +/* RPL-P */ +#define INTEL_RPLP_IDS(info) \ + INTEL_VGA_DEVICE(0xA720, info), \ + INTEL_VGA_DEVICE(0xA721, info), \ + INTEL_VGA_DEVICE(0xA7A0, info), \ + INTEL_VGA_DEVICE(0xA7A1, info), \ + INTEL_VGA_DEVICE(0xA7A8, info), \ + INTEL_VGA_DEVICE(0xA7A9, info) + #endif /* _I915_PCIIDS_H */ -- cgit v1.2.3 From dcf456c9a095a6e71f53d6f6f004133ee851ee70 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Mon, 18 Apr 2022 15:51:58 +0000 Subject: bpf: Fix usage of trace RCU in local storage. bpf_{sk,task,inode}_storage_free() do not need to use call_rcu_tasks_trace as no BPF program should be accessing the owner as it's being destroyed. The only other reader at this point is bpf_local_storage_map_free() which uses normal RCU. The only path that needs trace RCU are: * bpf_local_storage_{delete,update} helpers * map_{delete,update}_elem() syscalls Fixes: 0fe4b381a59e ("bpf: Allow bpf_local_storage to be used by sleepable programs") Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20220418155158.2865678-1-kpsingh@kernel.org --- include/linux/bpf_local_storage.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 493e63258497..7ea18d4da84b 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -143,9 +143,9 @@ void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, - bool uncharge_omem); + bool uncharge_omem, bool use_trace_rcu); -void bpf_selem_unlink(struct bpf_local_storage_elem *selem); +void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu); void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem); -- cgit v1.2.3 From 3abfaefb9a6dda5e0bfa6160f55abfd0e32d8b0a Mon Sep 17 00:00:00 2001 From: Liu Ying Date: Tue, 19 Apr 2022 09:08:49 +0800 Subject: phy: Add LVDS configuration options This patch allows LVDS PHYs to be configured through the generic functions and through a custom structure added to the generic union. The parameters added here are based on common LVDS PHY implementation practices. The set of parameters should cover all potential users. Cc: Kishon Vijay Abraham I Cc: Vinod Koul Cc: NXP Linux Team Signed-off-by: Liu Ying Link: https://lore.kernel.org/r/20220419010852.452169-3-victor.liu@nxp.com Signed-off-by: Vinod Koul --- include/linux/phy/phy-lvds.h | 32 ++++++++++++++++++++++++++++++++ include/linux/phy/phy.h | 4 ++++ 2 files changed, 36 insertions(+) create mode 100644 include/linux/phy/phy-lvds.h (limited to 'include') diff --git a/include/linux/phy/phy-lvds.h b/include/linux/phy/phy-lvds.h new file mode 100644 index 000000000000..09931d080a6d --- /dev/null +++ b/include/linux/phy/phy-lvds.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2020,2022 NXP + */ + +#ifndef __PHY_LVDS_H_ +#define __PHY_LVDS_H_ + +/** + * struct phy_configure_opts_lvds - LVDS configuration set + * @bits_per_lane_and_dclk_cycle: Number of bits per lane per differential + * clock cycle. + * @differential_clk_rate: Clock rate, in Hertz, of the LVDS + * differential clock. + * @lanes: Number of active, consecutive, + * data lanes, starting from lane 0, + * used for the transmissions. + * @is_slave: Boolean, true if the phy is a slave + * which works together with a master + * phy to support dual link transmission, + * otherwise a regular phy or a master phy. + * + * This structure is used to represent the configuration state of a LVDS phy. + */ +struct phy_configure_opts_lvds { + unsigned int bits_per_lane_and_dclk_cycle; + unsigned long differential_clk_rate; + unsigned int lanes; + bool is_slave; +}; + +#endif /* __PHY_LVDS_H_ */ diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index f3286f4cd306..b1413757fcc3 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -17,6 +17,7 @@ #include #include +#include #include struct phy; @@ -57,10 +58,13 @@ enum phy_media { * the MIPI_DPHY phy mode. * @dp: Configuration set applicable for phys supporting * the DisplayPort protocol. + * @lvds: Configuration set applicable for phys supporting + * the LVDS phy mode. */ union phy_configure_opts { struct phy_configure_opts_mipi_dphy mipi_dphy; struct phy_configure_opts_dp dp; + struct phy_configure_opts_lvds lvds; }; /** -- cgit v1.2.3 From 34951fcf26c59e78ae430fba1fce7c08b1871249 Mon Sep 17 00:00:00 2001 From: Boris Sukholitko Date: Tue, 19 Apr 2022 11:14:32 +0300 Subject: flow_dissector: Add number of vlan tags dissector Our customers in the fiber telecom world have network configurations where they would like to control their traffic according to the number of tags appearing in the packet. For example, TR247 GPON conformance test suite specification mostly talks about untagged, single, double tagged packets and gives lax guidelines on the vlan protocol vs. number of vlan tags. This is different from the common IT networks where 802.1Q and 802.1ad protocols are usually describe single and double tagged packet. GPON configurations that we work with have arbitrary mix the above protocols and number of vlan tags in the packet. The goal is to make the following TC commands possible: tc filter add dev eth1 ingress flower \ num_of_vlans 1 vlan_prio 5 action drop From our logs, we have redirect rules such that: tc filter add dev $GPON ingress flower num_of_vlans $N \ action mirred egress redirect dev $DEV where N can range from 0 to 3 and $DEV is the function of $N. Also there are rules setting skb mark based on the number of vlans: tc filter add dev $GPON ingress flower num_of_vlans $N vlan_prio \ $P action skbedit mark $M This new dissector allows extracting the number of vlan tags existing in the packet. Signed-off-by: Boris Sukholitko Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 9f65f1bfbd24..a4c6057c7097 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -253,6 +253,14 @@ struct flow_dissector_key_hash { u32 hash; }; +/** + * struct flow_dissector_key_num_of_vlans: + * @num_of_vlans: num_of_vlans value + */ +struct flow_dissector_key_num_of_vlans { + u8 num_of_vlans; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -282,6 +290,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */ FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */ FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */ + FLOW_DISSECTOR_KEY_NUM_OF_VLANS, /* struct flow_dissector_key_num_of_vlans */ FLOW_DISSECTOR_KEY_MAX, }; -- cgit v1.2.3 From b4000312822615ba2222e368188029e9b725dbf4 Mon Sep 17 00:00:00 2001 From: Boris Sukholitko Date: Tue, 19 Apr 2022 11:14:33 +0300 Subject: net/sched: flower: Add number of vlan tags filter These are bookkeeping parts of the new num_of_vlans filter. Defines, dump, load and set are being done here. Signed-off-by: Boris Sukholitko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 404f97fb239c..9a2ee1e39fad 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -587,6 +587,8 @@ enum { TCA_FLOWER_KEY_HASH, /* u32 */ TCA_FLOWER_KEY_HASH_MASK, /* u32 */ + TCA_FLOWER_KEY_NUM_OF_VLANS, /* u8 */ + __TCA_FLOWER_MAX, }; -- cgit v1.2.3 From fc44ff0ae9f2aa20b64c4e63ab4614156df80240 Mon Sep 17 00:00:00 2001 From: Ben Walker Date: Tue, 1 Mar 2022 11:25:48 -0700 Subject: dmaengine: Document dmaengine_prep_dma_memset Document this function to make clear the expected behavior of the 'value' parameter. It was intended to match the behavior of POSIX memset as laid out here: https://lore.kernel.org/dmaengine/YejrA5ZWZ3lTRO%2F1@matsya/ Signed-off-by: Ben Walker Link: https://lore.kernel.org/r/20220301182551.883474-2-benjamin.walker@intel.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 6db9e03afd0b..b46b88e6aa0d 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1030,6 +1030,14 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma( return chan->device->device_prep_interleaved_dma(chan, xt, flags); } +/** + * dmaengine_prep_dma_memset() - Prepare a DMA memset descriptor. + * @chan: The channel to be used for this descriptor + * @dest: Address of buffer to be set + * @value: Treated as a single byte value that fills the destination buffer + * @len: The total size of dest + * @flags: DMA engine flags + */ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memset( struct dma_chan *chan, dma_addr_t dest, int value, size_t len, unsigned long flags) -- cgit v1.2.3 From 5252c1c5a08e583ab1363f809002cd8a59272b35 Mon Sep 17 00:00:00 2001 From: Chun-Kuang Hu Date: Sat, 16 Apr 2022 17:54:28 +0800 Subject: soc: mediatek: cmdq: Use mailbox rx_callback instead of cmdq_task_cb rx_callback is a standard mailbox callback mechanism and could cover the function of proprietary cmdq_task_cb, so use the standard one instead of the proprietary one. Client has changed to use the standard callback machanism and sync dma buffer in client driver, so remove the proprietary callback in cmdq helper. Signed-off-by: Chun-Kuang Hu Reviewed-by: jason-jh.lin Tested-by: jason-jh.lin Link: https://lore.kernel.org/r/1650102868-26219-1-git-send-email-chunkuang.hu@kernel.org Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-cmdq.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index ac6b5f3cba95..2b498f4f3946 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -268,8 +268,6 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt); * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ * packet and call back at the end of done packet * @pkt: the CMDQ packet - * @cb: called at the end of done packet - * @data: this data will pass back to cb * * Return: 0 for success; else the error code is returned * @@ -277,7 +275,6 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt); * at the end of done packet. Note that this is an ASYNC function. When the * function returned, it may or may not be finished. */ -int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb, - void *data); +int cmdq_pkt_flush_async(struct cmdq_pkt *pkt); #endif /* __MTK_CMDQ_H__ */ -- cgit v1.2.3 From b57de4ffd7c6d1247fdaef8437450ab7c1dd4ed0 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 19 Apr 2022 19:27:48 +0100 Subject: KVM: arm64: Simplify kvm_cpu_has_pending_timer() kvm_cpu_has_pending_timer() ends up checking all the possible timers for a wake-up cause. However, we already check for pending interrupts whenever we try to wake-up a vcpu, including the timer interrupts. Obviously, doing the same work twice is once too many. Reduce this helper to almost nothing, but keep it around, as we are going to make use of it soon. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220419182755.601427-4-maz@kernel.org --- include/kvm/arm_arch_timer.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 51c19381108c..cd6d8f260eab 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -76,8 +76,6 @@ int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); -bool kvm_timer_is_pending(struct kvm_vcpu *vcpu); - u64 kvm_phys_timer_read(void); void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From 7a107b2c6b813c3c587d1e76cb405dc637dd2b36 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Wed, 20 Apr 2022 11:19:01 +0300 Subject: Revert "serial: 8250: Handle UART without interrupt on TEMT using em485" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This partially reverts commit f6f586102add. The code added by that commit containted math overflow for 32-bit archs. In addition, the approach used in it is unnecessarily complicated requiring a dedicated timer just for notemt. A simpler approach for providing UART_CAP_NOTEMT already exists (patches 1-2): https://lore.kernel.org/linux-serial/20220411083321.9131-3-ilpo.jarvinen@linux.intel.com/T/#u Thus, simply revert the UART_CAP_NOTEMT change for now. There were two driver changes within the patch series adding UART_CAP_NOTEMT taking advantage of the newly added flag. This does not revert the driver changes and therefore also UART_CAP_NOTEMT define has to remain. UART_CAP_NOTEMT remains no-op until support is again added. Fixes: f6f586102add ("serial: 8250: Handle UART without interrupt on TEMT using em485") Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/5f874142-fb1f-bff7-f33-fac823e65e2e@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index de135852107c..ff84a3ed10ea 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -79,9 +79,7 @@ struct uart_8250_ops { struct uart_8250_em485 { struct hrtimer start_tx_timer; /* "rs485 start tx" timer */ struct hrtimer stop_tx_timer; /* "rs485 stop tx" timer */ - struct hrtimer no_temt_timer; /* "rs485 no TEMT interrupt" timer */ struct hrtimer *active_timer; /* pointer to active timer */ - unsigned long no_temt_delay; /* Delay for no_temt_timer */ struct uart_8250_port *port; /* for hrtimer callbacks */ unsigned int tx_stopped:1; /* tx is currently stopped */ }; -- cgit v1.2.3 From 92ece28072f18f30099770c5d4b8e300ea6820fa Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Sat, 16 Apr 2022 18:58:00 +0800 Subject: net: Change skb_ensure_writable()'s write_len param to unsigned int type Both pskb_may_pull() and skb_clone_writable()'s length parameters are of type unsigned int already. Therefore, change this function's write_len param to unsigned int type. Signed-off-by: Liu Jian Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20220416105801.88708-3-liujian56@huawei.com --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2394441fa3dd..b37c829d08e1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3885,7 +3885,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); -int skb_ensure_writable(struct sk_buff *skb, int write_len); +int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); -- cgit v1.2.3 From f4c5c7f9d2e5ab005d57826b740b694b042a737c Mon Sep 17 00:00:00 2001 From: Felix Matouschek Date: Mon, 18 Apr 2022 15:28:03 +0200 Subject: mtd: spinand: Add support for XTX XT26G0xA Add support for XTX Technology XT26G01AXXXXX, XTX26G02AXXXXX and XTX26G04AXXXXX SPI NAND. These are 3V, 1G/2G/4Gbit serial SLC NAND flash devices with on-die ECC (8bit strength per 512bytes). Tested on Teltonika RUTX10 flashed with OpenWrt. Links: - http://www.xtxtech.com/download/?AId=225 - https://datasheet.lcsc.com/szlcsc/2005251034_XTX-XT26G01AWSEGA_C558841.pdf Signed-off-by: Felix Matouschek Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20220418132803.664103-1-felix@matouschek.org --- include/linux/mtd/spinand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 3aa28240a77f..5584d3bb6556 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -266,6 +266,7 @@ extern const struct spinand_manufacturer micron_spinand_manufacturer; extern const struct spinand_manufacturer paragon_spinand_manufacturer; extern const struct spinand_manufacturer toshiba_spinand_manufacturer; extern const struct spinand_manufacturer winbond_spinand_manufacturer; +extern const struct spinand_manufacturer xtx_spinand_manufacturer; /** * struct spinand_op_variants - SPI NAND operation variants -- cgit v1.2.3 From 0b0002315adfea3d9eb102665a4441727d4d2621 Mon Sep 17 00:00:00 2001 From: Weili Qian Date: Sat, 16 Apr 2022 18:45:56 +0800 Subject: crypto: hisilicon/qm - remove unused function declaration The 'hisi_qm_get_hw_version' function is unused, so remove the function declaration. Signed-off-by: Weili Qian Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index e5522eaf88fd..5177858aeea9 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -453,7 +453,6 @@ int hisi_qp_send(struct hisi_qp *qp, const void *msg); int hisi_qm_get_free_qp_num(struct hisi_qm *qm); int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number); void hisi_qm_debug_init(struct hisi_qm *qm); -enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev); void hisi_qm_debug_regs_clear(struct hisi_qm *qm); int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen); -- cgit v1.2.3 From fb06eb9727d67eac16e6b6aff35362476389cb88 Mon Sep 17 00:00:00 2001 From: Weili Qian Date: Sat, 16 Apr 2022 18:45:57 +0800 Subject: crypto: hisilicon/qm - set function with static These functions 'hisi_qm_create_qp' and 'hisi_qm_set_vft' are not used outside qm.c, so they are marked as static. Signed-off-by: Weili Qian Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 5177858aeea9..e99b286b50bc 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -445,13 +445,11 @@ int hisi_qm_init(struct hisi_qm *qm); void hisi_qm_uninit(struct hisi_qm *qm); int hisi_qm_start(struct hisi_qm *qm); int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); -struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type); int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); int hisi_qm_stop_qp(struct hisi_qp *qp); void hisi_qm_release_qp(struct hisi_qp *qp); int hisi_qp_send(struct hisi_qp *qp, const void *msg); int hisi_qm_get_free_qp_num(struct hisi_qm *qm); -int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number); void hisi_qm_debug_init(struct hisi_qm *qm); void hisi_qm_debug_regs_clear(struct hisi_qm *qm); int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); -- cgit v1.2.3 From 7982996c5b0812cbf7846deff0e2f5dcbf290129 Mon Sep 17 00:00:00 2001 From: Weili Qian Date: Sat, 16 Apr 2022 18:45:58 +0800 Subject: crypto: hisilicon/qm - replace hisi_qm_release_qp() with hisi_qm_free_qps() hisi_qm_free_qps() can release multiple queues in one call, and it is already exported. So, replace hisi_qm_release_qp() with hisi_qm_free_qps() in zip_crypto.c, and do not export hisi_qm_release_qp() outside qm.c. Signed-off-by: Weili Qian Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index e99b286b50bc..d2ccb11071c5 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -447,7 +447,6 @@ int hisi_qm_start(struct hisi_qm *qm); int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); int hisi_qm_stop_qp(struct hisi_qp *qp); -void hisi_qm_release_qp(struct hisi_qp *qp); int hisi_qp_send(struct hisi_qp *qp, const void *msg); int hisi_qm_get_free_qp_num(struct hisi_qm *qm); void hisi_qm_debug_init(struct hisi_qm *qm); -- cgit v1.2.3 From b0c42232fce499ba96fbf2c5ebd2368efeb6597e Mon Sep 17 00:00:00 2001 From: Weili Qian Date: Sat, 16 Apr 2022 18:45:59 +0800 Subject: crypto: hisilicon/qm - remove hisi_qm_get_free_qp_num() hisi_qm_get_free_qp_num() is to get the free queue number on the function. It is a simple function and is only called by hisi_qm_get_available_instances(). This patch modifies to get the free queue directly in hisi_qm_get_available_instances(), and remove hisi_qm_get_free_qp_num(). Signed-off-by: Weili Qian Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index d2ccb11071c5..6cabafffd0dd 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -448,7 +448,6 @@ int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); int hisi_qm_stop_qp(struct hisi_qp *qp); int hisi_qp_send(struct hisi_qp *qp, const void *msg); -int hisi_qm_get_free_qp_num(struct hisi_qm *qm); void hisi_qm_debug_init(struct hisi_qm *qm); void hisi_qm_debug_regs_clear(struct hisi_qm *qm); int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); -- cgit v1.2.3 From 6c7f98b334a32df5cac8abac8983ac4ce17cab57 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 16:13:59 +0200 Subject: vfio/mdev: Remove vfio_mdev.c Now that all mdev drivers directly create their own mdev_device driver and directly register with the vfio core's vfio_device_ops this is all dead code. Delete vfio_mdev.c and the mdev_parent_ops members that are connected to it. Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Zhi Wang Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-31-hch@lst.de Reviewed-by: Kirti Wankhede Reviewed-by: Zhi Wang --- include/linux/mdev.h | 48 +----------------------------------------------- 1 file changed, 1 insertion(+), 47 deletions(-) (limited to 'include') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 15d03f6532d0..192aed656116 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -40,40 +40,7 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype); * @mdev_attr_groups: Attributes of the mediated device. * @supported_type_groups: Attributes to define supported types. It is mandatory * to provide supported types. - * @create: Called to allocate basic resources in parent device's - * driver for a particular mediated device. It is - * mandatory to provide create ops. - * @mdev: mdev_device structure on of mediated device - * that is being created - * Returns integer: success (0) or error (< 0) - * @remove: Called to free resources in parent device's driver for - * a mediated device. It is mandatory to provide 'remove' - * ops. - * @mdev: mdev_device device structure which is being - * destroyed - * Returns integer: success (0) or error (< 0) - * @read: Read emulation callback - * @mdev: mediated device structure - * @buf: read buffer - * @count: number of bytes to read - * @ppos: address. - * Retuns number on bytes read on success or error. - * @write: Write emulation callback - * @mdev: mediated device structure - * @buf: write buffer - * @count: number of bytes to be written - * @ppos: address. - * Retuns number on bytes written on success or error. - * @ioctl: IOCTL callback - * @mdev: mediated device structure - * @cmd: ioctl command - * @arg: arguments to ioctl - * @mmap: mmap callback - * @mdev: mediated device structure - * @vma: vma structure - * @request: request callback to release device - * @mdev: mediated device structure - * @count: request sequence number + * * Parent device that support mediated device should be registered with mdev * module with mdev_parent_ops structure. **/ @@ -83,19 +50,6 @@ struct mdev_parent_ops { const struct attribute_group **dev_attr_groups; const struct attribute_group **mdev_attr_groups; struct attribute_group **supported_type_groups; - - int (*create)(struct mdev_device *mdev); - int (*remove)(struct mdev_device *mdev); - int (*open_device)(struct mdev_device *mdev); - void (*close_device)(struct mdev_device *mdev); - ssize_t (*read)(struct mdev_device *mdev, char __user *buf, - size_t count, loff_t *ppos); - ssize_t (*write)(struct mdev_device *mdev, const char __user *buf, - size_t count, loff_t *ppos); - long (*ioctl)(struct mdev_device *mdev, unsigned int cmd, - unsigned long arg); - int (*mmap)(struct mdev_device *mdev, struct vm_area_struct *vma); - void (*request)(struct mdev_device *mdev, unsigned int count); }; /* interface for exporting mdev supported type attributes */ -- cgit v1.2.3 From e6486939d8ea22569af942a1888aa3824f59cc5e Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 16:14:00 +0200 Subject: vfio/mdev: Remove mdev_parent_ops dev_attr_groups This is only used by one sample to print a fixed string that is pointless. In general, having a device driver attach sysfs attributes to the parent is horrific. This should never happen, and always leads to some kind of liftime bug as it become very difficult for the sysfs attribute to go back to any data owned by the device driver. Remove the general mechanism to create this abuse. Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Zhi Wang Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-32-hch@lst.de Reviewed-by: Kirti Wankhede Reviewed-by: Zhi Wang --- include/linux/mdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 192aed656116..69df1fa2cb6f 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -36,7 +36,6 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype); * * @owner: The module owner. * @device_driver: Which device driver to probe() on newly created devices - * @dev_attr_groups: Attributes of the parent device. * @mdev_attr_groups: Attributes of the mediated device. * @supported_type_groups: Attributes to define supported types. It is mandatory * to provide supported types. @@ -47,7 +46,6 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype); struct mdev_parent_ops { struct module *owner; struct mdev_driver *device_driver; - const struct attribute_group **dev_attr_groups; const struct attribute_group **mdev_attr_groups; struct attribute_group **supported_type_groups; }; -- cgit v1.2.3 From 6b42f491e17ce13f5ff7f2d1f49c73a0f4c47b20 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 16:14:01 +0200 Subject: vfio/mdev: Remove mdev_parent_ops The last useful member in this struct is the supported_type_groups, move it to the mdev_driver and delete mdev_parent_ops. Replace it with mdev_driver as an argument to mdev_register_device() Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Zhi Wang Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-33-hch@lst.de Reviewed-by: Kirti Wankhede Reviewed-by: Zhi Wang --- include/linux/mdev.h | 25 ++++--------------------- 1 file changed, 4 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 69df1fa2cb6f..1f6f57a3c316 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -30,26 +30,6 @@ unsigned int mdev_get_type_group_id(struct mdev_device *mdev); unsigned int mtype_get_type_group_id(struct mdev_type *mtype); struct device *mtype_get_parent_dev(struct mdev_type *mtype); -/** - * struct mdev_parent_ops - Structure to be registered for each parent device to - * register the device to mdev module. - * - * @owner: The module owner. - * @device_driver: Which device driver to probe() on newly created devices - * @mdev_attr_groups: Attributes of the mediated device. - * @supported_type_groups: Attributes to define supported types. It is mandatory - * to provide supported types. - * - * Parent device that support mediated device should be registered with mdev - * module with mdev_parent_ops structure. - **/ -struct mdev_parent_ops { - struct module *owner; - struct mdev_driver *device_driver; - const struct attribute_group **mdev_attr_groups; - struct attribute_group **supported_type_groups; -}; - /* interface for exporting mdev supported type attributes */ struct mdev_type_attribute { struct attribute attr; @@ -74,12 +54,15 @@ struct mdev_type_attribute mdev_type_attr_##_name = \ * struct mdev_driver - Mediated device driver * @probe: called when new device created * @remove: called when device removed + * @supported_type_groups: Attributes to define supported types. It is mandatory + * to provide supported types. * @driver: device driver structure * **/ struct mdev_driver { int (*probe)(struct mdev_device *dev); void (*remove)(struct mdev_device *dev); + struct attribute_group **supported_type_groups; struct device_driver driver; }; @@ -98,7 +81,7 @@ static inline const guid_t *mdev_uuid(struct mdev_device *mdev) extern struct bus_type mdev_bus_type; -int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops); +int mdev_register_device(struct device *dev, struct mdev_driver *mdev_driver); void mdev_unregister_device(struct device *dev); int mdev_register_driver(struct mdev_driver *drv); -- cgit v1.2.3 From 2917f53113be3b7a0f374e02cebe6d6b749366b5 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 16:14:03 +0200 Subject: vfio/mdev: Remove mdev drvdata This is no longer used, remove it. All usages were moved over to either use container_of() from a vfio_device or to use dev_drvdata() directly on the mdev. Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Zhi Wang Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-35-hch@lst.de Reviewed-by: Kirti Wankhede Reviewed-by: Zhi Wang --- include/linux/mdev.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 1f6f57a3c316..bb539794f54a 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -15,7 +15,6 @@ struct mdev_type; struct mdev_device { struct device dev; guid_t uuid; - void *driver_data; struct list_head next; struct mdev_type *type; bool active; @@ -66,14 +65,6 @@ struct mdev_driver { struct device_driver driver; }; -static inline void *mdev_get_drvdata(struct mdev_device *mdev) -{ - return mdev->driver_data; -} -static inline void mdev_set_drvdata(struct mdev_device *mdev, void *data) -{ - mdev->driver_data = data; -} static inline const guid_t *mdev_uuid(struct mdev_device *mdev) { return &mdev->uuid; -- cgit v1.2.3 From 042c48848b7d8dab4f095bce2872c02f711bf5d0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 5 Aug 2019 23:15:37 +0200 Subject: ARM: omap1: move lcd_dma code into omapfb driver The omapfb driver is split into platform specific code for omap1, and driver code that is also specific to omap1. Moving both parts into the driver directory simplifies the structure and avoids the dependency on certain omap machine header files. As mach/lcd_dma.h can not be included from include/linux/omap-dma.h any more now, move the omap_lcd_dma_running() declaration into the omap-dma header, which matches where it is defined. Acked-by: Bartlomiej Zolnierkiewicz Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/omap-dma.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 5c5c93ad6b50..441f5f0919c6 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -328,8 +328,8 @@ extern dma_addr_t omap_get_dma_dst_pos(int lch); extern int omap_get_dma_active_status(int lch); extern int omap_dma_running(void); -#if defined(CONFIG_ARCH_OMAP1) && IS_ENABLED(CONFIG_FB_OMAP) -#include +#if IS_ENABLED(CONFIG_FB_OMAP) +extern int omap_lcd_dma_running(void); #else static inline int omap_lcd_dma_running(void) { -- cgit v1.2.3 From 0768fb6709343679e55f7135e2ed2c432e4500d8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Aug 2019 21:42:31 +0200 Subject: ARM: omap1: declare a dummy omap_set_dma_priority omapfb calls directly into the omap_set_dma_priority() function in the DMA driver. This prevents compile-testing omapfb on other architectures. Add an inline function next to the other ones for non-omap configurations. Acked-by: Bartlomiej Zolnierkiewicz Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/omap-dma.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 441f5f0919c6..5e228428fda1 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -338,6 +338,9 @@ static inline int omap_lcd_dma_running(void) #endif #else /* CONFIG_ARCH_OMAP */ +static inline void omap_set_dma_priority(int lch, int dst_port, int priority) +{ +} static inline struct omap_system_dma_plat_info *omap_get_plat_info(void) { -- cgit v1.2.3 From e8e77e97507bf3ec5419b8067d242b538cf75cba Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 6 Aug 2019 14:34:31 +0200 Subject: ARM: omap1: move mach/usb.h to include/linux/soc The register definitions in this header are used in at least four different places, with little hope of completely cleaning that up. Split up the file into a portion that becomes a linux-wide header under include/linux/soc/ti/, and the parts that are actually only needed by board files. Acked-by: Felipe Balbi Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/soc/ti/omap1-usb.h | 116 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 include/linux/soc/ti/omap1-usb.h (limited to 'include') diff --git a/include/linux/soc/ti/omap1-usb.h b/include/linux/soc/ti/omap1-usb.h new file mode 100644 index 000000000000..67488698601a --- /dev/null +++ b/include/linux/soc/ti/omap1-usb.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SOC_TI_OMAP1_USB +#define __SOC_TI_OMAP1_USB +/* + * Constants in this file are used all over the place, in platform + * code, as well as the udc, phy and ohci drivers. + * This is not a great design, but unlikely to get fixed after + * such a long time. Don't do this elsewhere. + */ + +#define OMAP1_OTG_BASE 0xfffb0400 +#define OMAP1_UDC_BASE 0xfffb4000 + +#define OMAP2_UDC_BASE 0x4805e200 +#define OMAP2_OTG_BASE 0x4805e300 +#define OTG_BASE OMAP1_OTG_BASE +#define UDC_BASE OMAP1_UDC_BASE + +/* + * OTG and transceiver registers, for OMAPs starting with ARM926 + */ +#define OTG_REV (OTG_BASE + 0x00) +#define OTG_SYSCON_1 (OTG_BASE + 0x04) +# define USB2_TRX_MODE(w) (((w)>>24)&0x07) +# define USB1_TRX_MODE(w) (((w)>>20)&0x07) +# define USB0_TRX_MODE(w) (((w)>>16)&0x07) +# define OTG_IDLE_EN (1 << 15) +# define HST_IDLE_EN (1 << 14) +# define DEV_IDLE_EN (1 << 13) +# define OTG_RESET_DONE (1 << 2) +# define OTG_SOFT_RESET (1 << 1) +#define OTG_SYSCON_2 (OTG_BASE + 0x08) +# define OTG_EN (1 << 31) +# define USBX_SYNCHRO (1 << 30) +# define OTG_MST16 (1 << 29) +# define SRP_GPDATA (1 << 28) +# define SRP_GPDVBUS (1 << 27) +# define SRP_GPUVBUS(w) (((w)>>24)&0x07) +# define A_WAIT_VRISE(w) (((w)>>20)&0x07) +# define B_ASE_BRST(w) (((w)>>16)&0x07) +# define SRP_DPW (1 << 14) +# define SRP_DATA (1 << 13) +# define SRP_VBUS (1 << 12) +# define OTG_PADEN (1 << 10) +# define HMC_PADEN (1 << 9) +# define UHOST_EN (1 << 8) +# define HMC_TLLSPEED (1 << 7) +# define HMC_TLLATTACH (1 << 6) +# define OTG_HMC(w) (((w)>>0)&0x3f) +#define OTG_CTRL (OTG_BASE + 0x0c) +# define OTG_USB2_EN (1 << 29) +# define OTG_USB2_DP (1 << 28) +# define OTG_USB2_DM (1 << 27) +# define OTG_USB1_EN (1 << 26) +# define OTG_USB1_DP (1 << 25) +# define OTG_USB1_DM (1 << 24) +# define OTG_USB0_EN (1 << 23) +# define OTG_USB0_DP (1 << 22) +# define OTG_USB0_DM (1 << 21) +# define OTG_ASESSVLD (1 << 20) +# define OTG_BSESSEND (1 << 19) +# define OTG_BSESSVLD (1 << 18) +# define OTG_VBUSVLD (1 << 17) +# define OTG_ID (1 << 16) +# define OTG_DRIVER_SEL (1 << 15) +# define OTG_A_SETB_HNPEN (1 << 12) +# define OTG_A_BUSREQ (1 << 11) +# define OTG_B_HNPEN (1 << 9) +# define OTG_B_BUSREQ (1 << 8) +# define OTG_BUSDROP (1 << 7) +# define OTG_PULLDOWN (1 << 5) +# define OTG_PULLUP (1 << 4) +# define OTG_DRV_VBUS (1 << 3) +# define OTG_PD_VBUS (1 << 2) +# define OTG_PU_VBUS (1 << 1) +# define OTG_PU_ID (1 << 0) +#define OTG_IRQ_EN (OTG_BASE + 0x10) /* 16-bit */ +# define DRIVER_SWITCH (1 << 15) +# define A_VBUS_ERR (1 << 13) +# define A_REQ_TMROUT (1 << 12) +# define A_SRP_DETECT (1 << 11) +# define B_HNP_FAIL (1 << 10) +# define B_SRP_TMROUT (1 << 9) +# define B_SRP_DONE (1 << 8) +# define B_SRP_STARTED (1 << 7) +# define OPRT_CHG (1 << 0) +#define OTG_IRQ_SRC (OTG_BASE + 0x14) /* 16-bit */ + // same bits as in IRQ_EN +#define OTG_OUTCTRL (OTG_BASE + 0x18) /* 16-bit */ +# define OTGVPD (1 << 14) +# define OTGVPU (1 << 13) +# define OTGPUID (1 << 12) +# define USB2VDR (1 << 10) +# define USB2PDEN (1 << 9) +# define USB2PUEN (1 << 8) +# define USB1VDR (1 << 6) +# define USB1PDEN (1 << 5) +# define USB1PUEN (1 << 4) +# define USB0VDR (1 << 2) +# define USB0PDEN (1 << 1) +# define USB0PUEN (1 << 0) +#define OTG_TEST (OTG_BASE + 0x20) /* 16-bit */ +#define OTG_VENDOR_CODE (OTG_BASE + 0xfc) /* 16-bit */ + +/*-------------------------------------------------------------------------*/ + +/* OMAP1 */ +#define USB_TRANSCEIVER_CTRL (0xfffe1000 + 0x0064) +# define CONF_USB2_UNI_R (1 << 8) +# define CONF_USB1_UNI_R (1 << 7) +# define CONF_USB_PORT0_R(x) (((x)>>4)&0x7) +# define CONF_USB0_ISOLATE_R (1 << 3) +# define CONF_USB_PWRDN_DM_R (1 << 2) +# define CONF_USB_PWRDN_DP_R (1 << 1) + +#endif -- cgit v1.2.3 From 1e9ca7c811f76b16c7822ad009b6b0c352227a15 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 6 Aug 2019 15:24:58 +0200 Subject: ARM: omap1: move some headers to include/linux/soc There are three remaining header files that are used by omap1 specific device drivers: - mach/soc.h provides cpu_is_omapXXX abstractions - mach/hardware.h provides omap_read/omap_write functions and physical addresses - mach/mux.h provides an omap specific pinctrl abstraction This is generally not how we do platform abstractions today, and it would be good to completely get rid of these in favor of passing information through platform devices and the pinctrl subsystem. However, given that nobody is working on that, just move it one step forward by splitting out the header files that are used by drivers today from the machine headers that are only used internally. Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/soc/ti/omap1-io.h | 143 ++++++++++++++++++ include/linux/soc/ti/omap1-mux.h | 311 +++++++++++++++++++++++++++++++++++++++ include/linux/soc/ti/omap1-soc.h | 198 +++++++++++++++++++++++++ 3 files changed, 652 insertions(+) create mode 100644 include/linux/soc/ti/omap1-io.h create mode 100644 include/linux/soc/ti/omap1-mux.h create mode 100644 include/linux/soc/ti/omap1-soc.h (limited to 'include') diff --git a/include/linux/soc/ti/omap1-io.h b/include/linux/soc/ti/omap1-io.h new file mode 100644 index 000000000000..9332c92690f4 --- /dev/null +++ b/include/linux/soc/ti/omap1-io.h @@ -0,0 +1,143 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_ARCH_OMAP_IO_H +#define __ASM_ARCH_OMAP_IO_H + +#ifndef __ASSEMBLER__ +#include + +#if defined(CONFIG_ARCH_OMAP) && defined(CONFIG_ARCH_OMAP1) +/* + * NOTE: Please use ioremap + __raw_read/write where possible instead of these + */ +extern u8 omap_readb(u32 pa); +extern u16 omap_readw(u32 pa); +extern u32 omap_readl(u32 pa); +extern void omap_writeb(u8 v, u32 pa); +extern void omap_writew(u16 v, u32 pa); +extern void omap_writel(u32 v, u32 pa); +#elif defined(CONFIG_COMPILE_TEST) +static inline u8 omap_readb(u32 pa) { return 0; } +static inline u16 omap_readw(u32 pa) { return 0; } +static inline u32 omap_readl(u32 pa) { return 0; } +static inline void omap_writeb(u8 v, u32 pa) { } +static inline void omap_writew(u16 v, u32 pa) { } +static inline void omap_writel(u32 v, u32 pa) { } +#endif +#endif + +/* + * ---------------------------------------------------------------------------- + * System control registers + * ---------------------------------------------------------------------------- + */ +#define MOD_CONF_CTRL_0 0xfffe1080 +#define MOD_CONF_CTRL_1 0xfffe1110 + +/* + * --------------------------------------------------------------------------- + * UPLD + * --------------------------------------------------------------------------- + */ +#define ULPD_REG_BASE (0xfffe0800) +#define ULPD_IT_STATUS (ULPD_REG_BASE + 0x14) +#define ULPD_SETUP_ANALOG_CELL_3 (ULPD_REG_BASE + 0x24) +#define ULPD_CLOCK_CTRL (ULPD_REG_BASE + 0x30) +# define DIS_USB_PVCI_CLK (1 << 5) /* no USB/FAC synch */ +# define USB_MCLK_EN (1 << 4) /* enable W4_USB_CLKO */ +#define ULPD_SOFT_REQ (ULPD_REG_BASE + 0x34) +# define SOFT_UDC_REQ (1 << 4) +# define SOFT_USB_CLK_REQ (1 << 3) +# define SOFT_DPLL_REQ (1 << 0) +#define ULPD_DPLL_CTRL (ULPD_REG_BASE + 0x3c) +#define ULPD_STATUS_REQ (ULPD_REG_BASE + 0x40) +#define ULPD_APLL_CTRL (ULPD_REG_BASE + 0x4c) +#define ULPD_POWER_CTRL (ULPD_REG_BASE + 0x50) +#define ULPD_SOFT_DISABLE_REQ_REG (ULPD_REG_BASE + 0x68) +# define DIS_MMC2_DPLL_REQ (1 << 11) +# define DIS_MMC1_DPLL_REQ (1 << 10) +# define DIS_UART3_DPLL_REQ (1 << 9) +# define DIS_UART2_DPLL_REQ (1 << 8) +# define DIS_UART1_DPLL_REQ (1 << 7) +# define DIS_USB_HOST_DPLL_REQ (1 << 6) +#define ULPD_SDW_CLK_DIV_CTRL_SEL (ULPD_REG_BASE + 0x74) +#define ULPD_CAM_CLK_CTRL (ULPD_REG_BASE + 0x7c) + +/* + * ---------------------------------------------------------------------------- + * Clocks + * ---------------------------------------------------------------------------- + */ +#define CLKGEN_REG_BASE (0xfffece00) +#define ARM_CKCTL (CLKGEN_REG_BASE + 0x0) +#define ARM_IDLECT1 (CLKGEN_REG_BASE + 0x4) +#define ARM_IDLECT2 (CLKGEN_REG_BASE + 0x8) +#define ARM_EWUPCT (CLKGEN_REG_BASE + 0xC) +#define ARM_RSTCT1 (CLKGEN_REG_BASE + 0x10) +#define ARM_RSTCT2 (CLKGEN_REG_BASE + 0x14) +#define ARM_SYSST (CLKGEN_REG_BASE + 0x18) +#define ARM_IDLECT3 (CLKGEN_REG_BASE + 0x24) + +#define CK_RATEF 1 +#define CK_IDLEF 2 +#define CK_ENABLEF 4 +#define CK_SELECTF 8 +#define SETARM_IDLE_SHIFT + +/* DPLL control registers */ +#define DPLL_CTL (0xfffecf00) + +/* DSP clock control. Must use __raw_readw() and __raw_writew() with these */ +#define DSP_CONFIG_REG_BASE IOMEM(0xe1008000) +#define DSP_CKCTL (DSP_CONFIG_REG_BASE + 0x0) +#define DSP_IDLECT1 (DSP_CONFIG_REG_BASE + 0x4) +#define DSP_IDLECT2 (DSP_CONFIG_REG_BASE + 0x8) +#define DSP_RSTCT2 (DSP_CONFIG_REG_BASE + 0x14) + +/* + * ---------------------------------------------------------------------------- + * Pulse-Width Light + * ---------------------------------------------------------------------------- + */ +#define OMAP_PWL_BASE 0xfffb5800 +#define OMAP_PWL_ENABLE (OMAP_PWL_BASE + 0x00) +#define OMAP_PWL_CLK_ENABLE (OMAP_PWL_BASE + 0x04) + +/* + * ---------------------------------------------------------------------------- + * Pin multiplexing registers + * ---------------------------------------------------------------------------- + */ +#define FUNC_MUX_CTRL_0 0xfffe1000 +#define FUNC_MUX_CTRL_1 0xfffe1004 +#define FUNC_MUX_CTRL_2 0xfffe1008 +#define COMP_MODE_CTRL_0 0xfffe100c +#define FUNC_MUX_CTRL_3 0xfffe1010 +#define FUNC_MUX_CTRL_4 0xfffe1014 +#define FUNC_MUX_CTRL_5 0xfffe1018 +#define FUNC_MUX_CTRL_6 0xfffe101C +#define FUNC_MUX_CTRL_7 0xfffe1020 +#define FUNC_MUX_CTRL_8 0xfffe1024 +#define FUNC_MUX_CTRL_9 0xfffe1028 +#define FUNC_MUX_CTRL_A 0xfffe102C +#define FUNC_MUX_CTRL_B 0xfffe1030 +#define FUNC_MUX_CTRL_C 0xfffe1034 +#define FUNC_MUX_CTRL_D 0xfffe1038 +#define PULL_DWN_CTRL_0 0xfffe1040 +#define PULL_DWN_CTRL_1 0xfffe1044 +#define PULL_DWN_CTRL_2 0xfffe1048 +#define PULL_DWN_CTRL_3 0xfffe104c +#define PULL_DWN_CTRL_4 0xfffe10ac + +/* OMAP-1610 specific multiplexing registers */ +#define FUNC_MUX_CTRL_E 0xfffe1090 +#define FUNC_MUX_CTRL_F 0xfffe1094 +#define FUNC_MUX_CTRL_10 0xfffe1098 +#define FUNC_MUX_CTRL_11 0xfffe109c +#define FUNC_MUX_CTRL_12 0xfffe10a0 +#define PU_PD_SEL_0 0xfffe10b4 +#define PU_PD_SEL_1 0xfffe10b8 +#define PU_PD_SEL_2 0xfffe10bc +#define PU_PD_SEL_3 0xfffe10c0 +#define PU_PD_SEL_4 0xfffe10c4 + +#endif diff --git a/include/linux/soc/ti/omap1-mux.h b/include/linux/soc/ti/omap1-mux.h new file mode 100644 index 000000000000..59c239b5569c --- /dev/null +++ b/include/linux/soc/ti/omap1-mux.h @@ -0,0 +1,311 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef __SOC_TI_OMAP1_MUX_H +#define __SOC_TI_OMAP1_MUX_H +/* + * This should not really be a global header, it reflects the + * traditional way that omap1 does pin muxing without the + * pinctrl subsystem. + */ + +enum omap7xx_index { + /* OMAP 730 keyboard */ + E2_7XX_KBR0, + J7_7XX_KBR1, + E1_7XX_KBR2, + F3_7XX_KBR3, + D2_7XX_KBR4, + C2_7XX_KBC0, + D3_7XX_KBC1, + E4_7XX_KBC2, + F4_7XX_KBC3, + E3_7XX_KBC4, + + /* USB */ + AA17_7XX_USB_DM, + W16_7XX_USB_PU_EN, + W17_7XX_USB_VBUSI, + W18_7XX_USB_DMCK_OUT, + W19_7XX_USB_DCRST, + + /* MMC */ + MMC_7XX_CMD, + MMC_7XX_CLK, + MMC_7XX_DAT0, + + /* I2C */ + I2C_7XX_SCL, + I2C_7XX_SDA, + + /* SPI */ + SPI_7XX_1, + SPI_7XX_2, + SPI_7XX_3, + SPI_7XX_4, + SPI_7XX_5, + SPI_7XX_6, + + /* UART */ + UART_7XX_1, + UART_7XX_2, +}; + +enum omap1xxx_index { + /* UART1 (BT_UART_GATING)*/ + UART1_TX = 0, + UART1_RTS, + + /* UART2 (COM_UART_GATING)*/ + UART2_TX, + UART2_RX, + UART2_CTS, + UART2_RTS, + + /* UART3 (GIGA_UART_GATING) */ + UART3_TX, + UART3_RX, + UART3_CTS, + UART3_RTS, + UART3_CLKREQ, + UART3_BCLK, /* 12MHz clock out */ + Y15_1610_UART3_RTS, + + /* PWT & PWL */ + PWT, + PWL, + + /* USB master generic */ + R18_USB_VBUS, + R18_1510_USB_GPIO0, + W4_USB_PUEN, + W4_USB_CLKO, + W4_USB_HIGHZ, + W4_GPIO58, + + /* USB1 master */ + USB1_SUSP, + USB1_SEO, + W13_1610_USB1_SE0, + USB1_TXEN, + USB1_TXD, + USB1_VP, + USB1_VM, + USB1_RCV, + USB1_SPEED, + R13_1610_USB1_SPEED, + R13_1710_USB1_SE0, + + /* USB2 master */ + USB2_SUSP, + USB2_VP, + USB2_TXEN, + USB2_VM, + USB2_RCV, + USB2_SEO, + USB2_TXD, + + /* OMAP-1510 GPIO */ + R18_1510_GPIO0, + R19_1510_GPIO1, + M14_1510_GPIO2, + + /* OMAP1610 GPIO */ + P18_1610_GPIO3, + Y15_1610_GPIO17, + + /* OMAP-1710 GPIO */ + R18_1710_GPIO0, + V2_1710_GPIO10, + N21_1710_GPIO14, + W15_1710_GPIO40, + + /* MPUIO */ + MPUIO2, + N15_1610_MPUIO2, + MPUIO4, + MPUIO5, + T20_1610_MPUIO5, + W11_1610_MPUIO6, + V10_1610_MPUIO7, + W11_1610_MPUIO9, + V10_1610_MPUIO10, + W10_1610_MPUIO11, + E20_1610_MPUIO13, + U20_1610_MPUIO14, + E19_1610_MPUIO15, + + /* MCBSP2 */ + MCBSP2_CLKR, + MCBSP2_CLKX, + MCBSP2_DR, + MCBSP2_DX, + MCBSP2_FSR, + MCBSP2_FSX, + + /* MCBSP3 */ + MCBSP3_CLKX, + + /* Misc ballouts */ + BALLOUT_V8_ARMIO3, + N20_HDQ, + + /* OMAP-1610 MMC2 */ + W8_1610_MMC2_DAT0, + V8_1610_MMC2_DAT1, + W15_1610_MMC2_DAT2, + R10_1610_MMC2_DAT3, + Y10_1610_MMC2_CLK, + Y8_1610_MMC2_CMD, + V9_1610_MMC2_CMDDIR, + V5_1610_MMC2_DATDIR0, + W19_1610_MMC2_DATDIR1, + R18_1610_MMC2_CLKIN, + + /* OMAP-1610 External Trace Interface */ + M19_1610_ETM_PSTAT0, + L15_1610_ETM_PSTAT1, + L18_1610_ETM_PSTAT2, + L19_1610_ETM_D0, + J19_1610_ETM_D6, + J18_1610_ETM_D7, + + /* OMAP16XX GPIO */ + P20_1610_GPIO4, + V9_1610_GPIO7, + W8_1610_GPIO9, + N20_1610_GPIO11, + N19_1610_GPIO13, + P10_1610_GPIO22, + V5_1610_GPIO24, + AA20_1610_GPIO_41, + W19_1610_GPIO48, + M7_1610_GPIO62, + V14_16XX_GPIO37, + R9_16XX_GPIO18, + L14_16XX_GPIO49, + + /* OMAP-1610 uWire */ + V19_1610_UWIRE_SCLK, + U18_1610_UWIRE_SDI, + W21_1610_UWIRE_SDO, + N14_1610_UWIRE_CS0, + P15_1610_UWIRE_CS3, + N15_1610_UWIRE_CS1, + + /* OMAP-1610 SPI */ + U19_1610_SPIF_SCK, + U18_1610_SPIF_DIN, + P20_1610_SPIF_DIN, + W21_1610_SPIF_DOUT, + R18_1610_SPIF_DOUT, + N14_1610_SPIF_CS0, + N15_1610_SPIF_CS1, + T19_1610_SPIF_CS2, + P15_1610_SPIF_CS3, + + /* OMAP-1610 Flash */ + L3_1610_FLASH_CS2B_OE, + M8_1610_FLASH_CS2B_WE, + + /* First MMC */ + MMC_CMD, + MMC_DAT1, + MMC_DAT2, + MMC_DAT0, + MMC_CLK, + MMC_DAT3, + + /* OMAP-1710 MMC CMDDIR and DATDIR0 */ + M15_1710_MMC_CLKI, + P19_1710_MMC_CMDDIR, + P20_1710_MMC_DATDIR0, + + /* OMAP-1610 USB0 alternate pin configuration */ + W9_USB0_TXEN, + AA9_USB0_VP, + Y5_USB0_RCV, + R9_USB0_VM, + V6_USB0_TXD, + W5_USB0_SE0, + V9_USB0_SPEED, + V9_USB0_SUSP, + + /* USB2 */ + W9_USB2_TXEN, + AA9_USB2_VP, + Y5_USB2_RCV, + R9_USB2_VM, + V6_USB2_TXD, + W5_USB2_SE0, + + /* 16XX UART */ + R13_1610_UART1_TX, + V14_16XX_UART1_RX, + R14_1610_UART1_CTS, + AA15_1610_UART1_RTS, + R9_16XX_UART2_RX, + L14_16XX_UART3_RX, + + /* I2C OMAP-1610 */ + I2C_SCL, + I2C_SDA, + + /* Keypad */ + F18_1610_KBC0, + D20_1610_KBC1, + D19_1610_KBC2, + E18_1610_KBC3, + C21_1610_KBC4, + G18_1610_KBR0, + F19_1610_KBR1, + H14_1610_KBR2, + E20_1610_KBR3, + E19_1610_KBR4, + N19_1610_KBR5, + + /* Power management */ + T20_1610_LOW_PWR, + + /* MCLK Settings */ + V5_1710_MCLK_ON, + V5_1710_MCLK_OFF, + R10_1610_MCLK_ON, + R10_1610_MCLK_OFF, + + /* CompactFlash controller */ + P11_1610_CF_CD2, + R11_1610_CF_IOIS16, + V10_1610_CF_IREQ, + W10_1610_CF_RESET, + W11_1610_CF_CD1, + + /* parallel camera */ + J15_1610_CAM_LCLK, + J18_1610_CAM_D7, + J19_1610_CAM_D6, + J14_1610_CAM_D5, + K18_1610_CAM_D4, + K19_1610_CAM_D3, + K15_1610_CAM_D2, + K14_1610_CAM_D1, + L19_1610_CAM_D0, + L18_1610_CAM_VS, + L15_1610_CAM_HS, + M19_1610_CAM_RSTZ, + Y15_1610_CAM_OUTCLK, + + /* serial camera */ + H19_1610_CAM_EXCLK, + Y12_1610_CCP_CLKP, + W13_1610_CCP_CLKM, + W14_1610_CCP_DATAP, + Y14_1610_CCP_DATAM, + +}; + +#ifdef CONFIG_OMAP_MUX +extern int omap_cfg_reg(unsigned long reg_cfg); +#else +static inline int omap_cfg_reg(unsigned long reg_cfg) { return 0; } +#endif + +#endif diff --git a/include/linux/soc/ti/omap1-soc.h b/include/linux/soc/ti/omap1-soc.h new file mode 100644 index 000000000000..81008d400bb6 --- /dev/null +++ b/include/linux/soc/ti/omap1-soc.h @@ -0,0 +1,198 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * OMAP cpu type detection + * + * Copyright (C) 2004, 2008 Nokia Corporation + * + * Copyright (C) 2009-11 Texas Instruments. + * + * Written by Tony Lindgren + * + * Added OMAP4/5 specific defines - Santosh Shilimkar + */ + +#ifndef __ASM_ARCH_OMAP_CPU_H +#define __ASM_ARCH_OMAP_CPU_H + +/* + * Test if multicore OMAP support is needed + */ +#undef MULTI_OMAP1 +#undef OMAP_NAME + +#ifdef CONFIG_ARCH_OMAP730 +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap730 +# endif +#endif +#ifdef CONFIG_ARCH_OMAP850 +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap850 +# endif +#endif +#ifdef CONFIG_ARCH_OMAP15XX +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap1510 +# endif +#endif +#ifdef CONFIG_ARCH_OMAP16XX +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap16xx +# endif +#endif + +/* + * omap_rev bits: + * CPU id bits (0730, 1510, 1710, 2422...) [31:16] + * CPU revision (See _REV_ defined in cpu.h) [15:08] + * CPU class bits (15xx, 16xx, 24xx, 34xx...) [07:00] + */ +unsigned int omap_rev(void); + +/* + * Get the CPU revision for OMAP devices + */ +#define GET_OMAP_REVISION() ((omap_rev() >> 8) & 0xff) + +/* + * Macros to group OMAP into cpu classes. + * These can be used in most places. + * cpu_is_omap7xx(): True for OMAP730, OMAP850 + * cpu_is_omap15xx(): True for OMAP1510, OMAP5910 and OMAP310 + * cpu_is_omap16xx(): True for OMAP1610, OMAP5912 and OMAP1710 + */ +#define GET_OMAP_CLASS (omap_rev() & 0xff) + +#define IS_OMAP_CLASS(class, id) \ +static inline int is_omap ##class (void) \ +{ \ + return (GET_OMAP_CLASS == (id)) ? 1 : 0; \ +} + +#define GET_OMAP_SUBCLASS ((omap_rev() >> 20) & 0x0fff) + +#define IS_OMAP_SUBCLASS(subclass, id) \ +static inline int is_omap ##subclass (void) \ +{ \ + return (GET_OMAP_SUBCLASS == (id)) ? 1 : 0; \ +} + +IS_OMAP_CLASS(7xx, 0x07) +IS_OMAP_CLASS(15xx, 0x15) +IS_OMAP_CLASS(16xx, 0x16) + +#define cpu_is_omap7xx() 0 +#define cpu_is_omap15xx() 0 +#define cpu_is_omap16xx() 0 + +#if defined(MULTI_OMAP1) +# if defined(CONFIG_ARCH_OMAP730) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() is_omap7xx() +# endif +# if defined(CONFIG_ARCH_OMAP850) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() is_omap7xx() +# endif +# if defined(CONFIG_ARCH_OMAP15XX) +# undef cpu_is_omap15xx +# define cpu_is_omap15xx() is_omap15xx() +# endif +# if defined(CONFIG_ARCH_OMAP16XX) +# undef cpu_is_omap16xx +# define cpu_is_omap16xx() is_omap16xx() +# endif +#else +# if defined(CONFIG_ARCH_OMAP730) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() 1 +# endif +# if defined(CONFIG_ARCH_OMAP850) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() 1 +# endif +# if defined(CONFIG_ARCH_OMAP15XX) +# undef cpu_is_omap15xx +# define cpu_is_omap15xx() 1 +# endif +# if defined(CONFIG_ARCH_OMAP16XX) +# undef cpu_is_omap16xx +# define cpu_is_omap16xx() 1 +# endif +#endif + +/* + * Macros to detect individual cpu types. + * These are only rarely needed. + * cpu_is_omap310(): True for OMAP310 + * cpu_is_omap1510(): True for OMAP1510 + * cpu_is_omap1610(): True for OMAP1610 + * cpu_is_omap1611(): True for OMAP1611 + * cpu_is_omap5912(): True for OMAP5912 + * cpu_is_omap1621(): True for OMAP1621 + * cpu_is_omap1710(): True for OMAP1710 + */ +#define GET_OMAP_TYPE ((omap_rev() >> 16) & 0xffff) + +#define IS_OMAP_TYPE(type, id) \ +static inline int is_omap ##type (void) \ +{ \ + return (GET_OMAP_TYPE == (id)) ? 1 : 0; \ +} + +IS_OMAP_TYPE(310, 0x0310) +IS_OMAP_TYPE(1510, 0x1510) +IS_OMAP_TYPE(1610, 0x1610) +IS_OMAP_TYPE(1611, 0x1611) +IS_OMAP_TYPE(5912, 0x1611) +IS_OMAP_TYPE(1621, 0x1621) +IS_OMAP_TYPE(1710, 0x1710) + +#define cpu_is_omap310() 0 +#define cpu_is_omap1510() 0 +#define cpu_is_omap1610() 0 +#define cpu_is_omap5912() 0 +#define cpu_is_omap1611() 0 +#define cpu_is_omap1621() 0 +#define cpu_is_omap1710() 0 + +#define cpu_class_is_omap1() 1 + +/* + * Whether we have MULTI_OMAP1 or not, we still need to distinguish + * between 310 vs. 1510 and 1611B/5912 vs. 1710. + */ + +#if defined(CONFIG_ARCH_OMAP15XX) +# undef cpu_is_omap310 +# undef cpu_is_omap1510 +# define cpu_is_omap310() is_omap310() +# define cpu_is_omap1510() is_omap1510() +#endif + +#if defined(CONFIG_ARCH_OMAP16XX) +# undef cpu_is_omap1610 +# undef cpu_is_omap1611 +# undef cpu_is_omap5912 +# undef cpu_is_omap1621 +# undef cpu_is_omap1710 +# define cpu_is_omap1610() is_omap1610() +# define cpu_is_omap1611() is_omap1611() +# define cpu_is_omap5912() is_omap5912() +# define cpu_is_omap1621() is_omap1621() +# define cpu_is_omap1710() is_omap1710() +#endif + +#endif -- cgit v1.2.3 From 9fe15316563cbd46601c770a7214ccc5e1925bfb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 6 Aug 2019 15:13:18 +0200 Subject: ARM: omap1: innovator: move ohci phy power handling to board file The innovator board needs a special case for its phy control. Move the corresponding code into the board file and out of the common code by adding another callback. Acked-by: Felipe Balbi Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/platform_data/usb-omap1.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/usb-omap1.h b/include/linux/platform_data/usb-omap1.h index 878e572a78bf..e7b8dc92a269 100644 --- a/include/linux/platform_data/usb-omap1.h +++ b/include/linux/platform_data/usb-omap1.h @@ -50,6 +50,8 @@ struct omap_usb_config { int (*ocpi_enable)(void); void (*lb_reset)(void); + + int (*transceiver_power)(int on); }; #endif /* __LINUX_USB_OMAP1_H */ -- cgit v1.2.3 From 17ea03b75e5665c9ce4945aa5afd097f3c845cdf Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 27 Nov 2020 15:46:47 +0100 Subject: ARM: omap: dma: make usb support optional Most of the plat-omap/dma.c code is specific to the USB driver. Hide that code when it is not in use, to make it clearer which parts are actually still required. Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/omap-dma.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 5e228428fda1..07fa58ae9902 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -299,8 +299,9 @@ extern void omap_set_dma_priority(int lch, int dst_port, int priority); extern int omap_request_dma(int dev_id, const char *dev_name, void (*callback)(int lch, u16 ch_status, void *data), void *data, int *dma_ch); -extern void omap_disable_dma_irq(int ch, u16 irq_bits); extern void omap_free_dma(int ch); +#if IS_ENABLED(CONFIG_USB_OMAP) +extern void omap_disable_dma_irq(int ch, u16 irq_bits); extern void omap_start_dma(int lch); extern void omap_stop_dma(int lch); extern void omap_set_dma_transfer_params(int lch, int data_type, @@ -326,6 +327,8 @@ extern void omap_set_dma_dest_burst_mode(int lch, extern dma_addr_t omap_get_dma_src_pos(int lch); extern dma_addr_t omap_get_dma_dst_pos(int lch); extern int omap_get_dma_active_status(int lch); +#endif + extern int omap_dma_running(void); #if IS_ENABLED(CONFIG_FB_OMAP) -- cgit v1.2.3 From 3550bba25d5587a701e6edf20e20984d2ee72c78 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sat, 9 Apr 2022 11:51:28 +0200 Subject: gpiolib: of: Introduce hook for missing gpio-ranges Since commit 2ab73c6d8323 ("gpio: Support GPIO controllers without pin-ranges") the device tree nodes of GPIO controller need the gpio-ranges property to handle gpio-hogs. Unfortunately it's impossible to guarantee that every new kernel is shipped with an updated device tree binary. In order to provide backward compatibility with those older DTB, we need a callback within of_gpiochip_add_pin_range() so the relevant platform driver can handle this case. Fixes: 2ab73c6d8323 ("gpio: Support GPIO controllers without pin-ranges") Signed-off-by: Stefan Wahren Reviewed-by: Florian Fainelli Tested-by: Florian Fainelli Acked-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20220409095129.45786-2-stefan.wahren@i2se.com Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..c2041bd01f90 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -492,6 +492,18 @@ struct gpio_chip { */ int (*of_xlate)(struct gpio_chip *gc, const struct of_phandle_args *gpiospec, u32 *flags); + + /** + * @of_gpio_ranges_fallback: + * + * Optional hook for the case that no gpio-ranges property is defined + * within the device tree node "np" (usually DT before introduction + * of gpio-ranges). So this callback is helpful to provide the + * necessary backward compatibility for the pin ranges. + */ + int (*of_gpio_ranges_fallback)(struct gpio_chip *gc, + struct device_node *np); + #endif /* CONFIG_OF_GPIO */ }; -- cgit v1.2.3 From 988f11e046401f8561c4afefa506a50f0203de40 Mon Sep 17 00:00:00 2001 From: liaohua Date: Thu, 7 Apr 2022 15:29:48 +0800 Subject: latencytop: move sysctl to its own file This moves latencytop sysctl to kernel/latencytop.c Signed-off-by: liaohua Signed-off-by: Luis Chamberlain --- include/linux/latencytop.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h index abe3d95f795b..84f1053cf2a8 100644 --- a/include/linux/latencytop.h +++ b/include/linux/latencytop.h @@ -38,9 +38,6 @@ account_scheduler_latency(struct task_struct *task, int usecs, int inter) void clear_tsk_latency_tracing(struct task_struct *p); -int sysctl_latencytop(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); - #else static inline void -- cgit v1.2.3 From 651877176c0846616add00f50b719ea6d59dff8d Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Sat, 4 Sep 2021 10:06:03 -0700 Subject: drm/fourcc: Add QCOM tiled modifiers These are mainly used internally in mesa, although I believe the display should be able to scan out the TILED3 format. Currently we define this modifier internally in mesa for use with modifier based allocation. But we can get rid of that hack if we define the modfiers properly. Signed-off-by: Rob Clark Link: https://lore.kernel.org/r/20210904170603.1739137-1-robdclark@gmail.com Signed-off-by: Rob Clark --- include/uapi/drm/drm_fourcc.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index fc0c1454d275..4bdf8dded9e7 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -609,6 +609,28 @@ extern "C" { */ #define DRM_FORMAT_MOD_QCOM_COMPRESSED fourcc_mod_code(QCOM, 1) +/* + * Qualcomm Tiled Format + * + * Similar to DRM_FORMAT_MOD_QCOM_COMPRESSED but not compressed. + * Implementation may be platform and base-format specific. + * + * Each macrotile consists of m x n (mostly 4 x 4) tiles. + * Pixel data pitch/stride is aligned with macrotile width. + * Pixel data height is aligned with macrotile height. + * Entire pixel data buffer is aligned with 4k(bytes). + */ +#define DRM_FORMAT_MOD_QCOM_TILED3 fourcc_mod_code(QCOM, 3) + +/* + * Qualcomm Alternate Tiled Format + * + * Alternate tiled format typically only used within GMEM. + * Implementation may be platform and base-format specific. + */ +#define DRM_FORMAT_MOD_QCOM_TILED2 fourcc_mod_code(QCOM, 2) + + /* Vivante framebuffer modifiers */ /* -- cgit v1.2.3 From 4bfba71640f8578b3daadb551d6bce12a2d436d8 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 17 Mar 2022 09:51:38 -0700 Subject: drm/msm: Add support for pointer params The 64b value field is already suffient to hold a pointer instead of immediate, but we also need a length field. Signed-off-by: Rob Clark Link: https://lore.kernel.org/r/20220317165144.222101-2-robdclark@gmail.com Signed-off-by: Rob Clark --- include/uapi/drm/msm_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 07efc8033492..0aa1a8cb4e0d 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -95,6 +95,8 @@ struct drm_msm_param { __u32 pipe; /* in, MSM_PIPE_x */ __u32 param; /* in, MSM_PARAM_x */ __u64 value; /* out (get_param) or in (set_param) */ + __u32 len; /* zero for non-pointer params */ + __u32 pad; /* must be zero */ }; /* -- cgit v1.2.3 From d4726d7700688835f4784d3b94de6fff2cbe16c2 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 17 Mar 2022 09:51:40 -0700 Subject: drm/msm: Add a way to override processes comm/cmdline In the cause of using the GPU via virtgpu, the host side process is really a sort of proxy, and not terribly interesting from the PoV of crash/fault logging. Add a way to override these per process so that we can see the guest process's name. v2: Handle kmalloc failure, add comment to explain kstrdup returns NULL if passed NULL [Dan Carpenter] Signed-off-by: Rob Clark Link: https://lore.kernel.org/r/20220317165144.222101-4-robdclark@gmail.com Signed-off-by: Rob Clark --- include/uapi/drm/msm_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 0aa1a8cb4e0d..794ad1948497 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -82,6 +82,8 @@ struct drm_msm_timespec { #define MSM_PARAM_FAULTS 0x09 /* RO */ #define MSM_PARAM_SUSPENDS 0x0a /* RO */ #define MSM_PARAM_SYSPROF 0x0b /* WO: 1 preserves perfcntrs, 2 also disables suspend */ +#define MSM_PARAM_COMM 0x0c /* WO: override for task->comm */ +#define MSM_PARAM_CMDLINE 0x0d /* WO: override for task cmdline */ /* For backwards compat. The original support for preemption was based on * a single ring per priority level so # of priority levels equals the # -- cgit v1.2.3 From a636a0ff11483a4c158acc31ee7ca083d98a0d13 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 11 Apr 2022 14:58:39 -0700 Subject: drm/msm: Add a way for userspace to allocate GPU iova The motivation at this point is mainly native userspace mesa driver in a VM guest. The one remaining synchronous "hotpath" is buffer allocation, because guest needs to wait to know the bo's iova before it can start emitting cmdstream/state that references the new bo. By allocating the iova in the guest userspace, we no longer need to wait for a response from the host, but can just rely on the allocation request being processed before the cmdstream submission. Allocation failures (OoM, etc) would just be treated as context-lost (ie. GL_GUILTY_CONTEXT_RESET) or subsequent allocations (or readpix, etc) can raise GL_OUT_OF_MEMORY. v2: Fix inuse check v3: Change mismatched iova case to -EBUSY Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov Reviewed-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20220411215849.297838-11-robdclark@gmail.com Signed-off-by: Rob Clark --- include/uapi/drm/msm_drm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 794ad1948497..3c7b097c4e3d 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -84,6 +84,8 @@ struct drm_msm_timespec { #define MSM_PARAM_SYSPROF 0x0b /* WO: 1 preserves perfcntrs, 2 also disables suspend */ #define MSM_PARAM_COMM 0x0c /* WO: override for task->comm */ #define MSM_PARAM_CMDLINE 0x0d /* WO: override for task cmdline */ +#define MSM_PARAM_VA_START 0x0e /* RO: start of valid GPU iova range */ +#define MSM_PARAM_VA_SIZE 0x0f /* RO: size of valid GPU iova range (bytes) */ /* For backwards compat. The original support for preemption was based on * a single ring per priority level so # of priority levels equals the # @@ -135,6 +137,7 @@ struct drm_msm_gem_new { #define MSM_INFO_GET_IOVA 0x01 /* get iova, returned by value */ #define MSM_INFO_SET_NAME 0x02 /* set the debug name (by pointer) */ #define MSM_INFO_GET_NAME 0x03 /* get debug name, returned by pointer */ +#define MSM_INFO_SET_IOVA 0x04 /* set the iova, passed by value */ struct drm_msm_gem_info { __u32 handle; /* in */ -- cgit v1.2.3 From ea3364db9068e37bd8e12b9a99c7c92385593ed7 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 8 Apr 2022 14:48:34 -0700 Subject: dt-bindings: interconnect: qcom: Add sc8280xp binding The Qualcomm SC8280XP platform has the usual set of busses, add a binding for these interconnect providers and port definitions to allow interconnect paths to be expressed in the sc8280xp DeviceTree. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220408214835.624494-1-bjorn.andersson@linaro.org Signed-off-by: Georgi Djakov --- include/dt-bindings/interconnect/qcom,sc8280xp.h | 232 +++++++++++++++++++++++ 1 file changed, 232 insertions(+) create mode 100644 include/dt-bindings/interconnect/qcom,sc8280xp.h (limited to 'include') diff --git a/include/dt-bindings/interconnect/qcom,sc8280xp.h b/include/dt-bindings/interconnect/qcom,sc8280xp.h new file mode 100644 index 000000000000..a3e5fda7c127 --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,sc8280xp.h @@ -0,0 +1,232 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2022, Linaro Ltd. + */ + +#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SC8280XP_H +#define __DT_BINDINGS_INTERCONNECT_QCOM_SC8280XP_H + +/* aggre1_noc */ +#define MASTER_QSPI_0 0 +#define MASTER_QUP_1 1 +#define MASTER_QUP_2 2 +#define MASTER_A1NOC_CFG 3 +#define MASTER_IPA 4 +#define MASTER_EMAC_1 5 +#define MASTER_SDCC_4 6 +#define MASTER_UFS_MEM 7 +#define MASTER_USB3_0 8 +#define MASTER_USB3_1 9 +#define MASTER_USB3_MP 10 +#define MASTER_USB4_0 11 +#define MASTER_USB4_1 12 +#define SLAVE_A1NOC_SNOC 13 +#define SLAVE_USB_NOC_SNOC 14 +#define SLAVE_SERVICE_A1NOC 15 + +/* aggre2_noc */ +#define MASTER_QDSS_BAM 0 +#define MASTER_QUP_0 1 +#define MASTER_A2NOC_CFG 2 +#define MASTER_CRYPTO 3 +#define MASTER_SENSORS_PROC 4 +#define MASTER_SP 5 +#define MASTER_EMAC 6 +#define MASTER_PCIE_0 7 +#define MASTER_PCIE_1 8 +#define MASTER_PCIE_2A 9 +#define MASTER_PCIE_2B 10 +#define MASTER_PCIE_3A 11 +#define MASTER_PCIE_3B 12 +#define MASTER_PCIE_4 13 +#define MASTER_QDSS_ETR 14 +#define MASTER_SDCC_2 15 +#define MASTER_UFS_CARD 16 +#define SLAVE_A2NOC_SNOC 17 +#define SLAVE_ANOC_PCIE_GEM_NOC 18 +#define SLAVE_SERVICE_A2NOC 19 + +/* clk_virt */ +#define MASTER_IPA_CORE 0 +#define MASTER_QUP_CORE_0 1 +#define MASTER_QUP_CORE_1 2 +#define MASTER_QUP_CORE_2 3 +#define SLAVE_IPA_CORE 4 +#define SLAVE_QUP_CORE_0 5 +#define SLAVE_QUP_CORE_1 6 +#define SLAVE_QUP_CORE_2 7 + +/* config_noc */ +#define MASTER_GEM_NOC_CNOC 0 +#define MASTER_GEM_NOC_PCIE_SNOC 1 +#define SLAVE_AHB2PHY_0 2 +#define SLAVE_AHB2PHY_1 3 +#define SLAVE_AHB2PHY_2 4 +#define SLAVE_AOSS 5 +#define SLAVE_APPSS 6 +#define SLAVE_CAMERA_CFG 7 +#define SLAVE_CLK_CTL 8 +#define SLAVE_CDSP_CFG 9 +#define SLAVE_CDSP1_CFG 10 +#define SLAVE_RBCPR_CX_CFG 11 +#define SLAVE_RBCPR_MMCX_CFG 12 +#define SLAVE_RBCPR_MX_CFG 13 +#define SLAVE_CPR_NSPCX 14 +#define SLAVE_CRYPTO_0_CFG 15 +#define SLAVE_CX_RDPM 16 +#define SLAVE_DCC_CFG 17 +#define SLAVE_DISPLAY_CFG 18 +#define SLAVE_DISPLAY1_CFG 19 +#define SLAVE_EMAC_CFG 20 +#define SLAVE_EMAC1_CFG 21 +#define SLAVE_GFX3D_CFG 22 +#define SLAVE_HWKM 23 +#define SLAVE_IMEM_CFG 24 +#define SLAVE_IPA_CFG 25 +#define SLAVE_IPC_ROUTER_CFG 26 +#define SLAVE_LPASS 27 +#define SLAVE_MX_RDPM 28 +#define SLAVE_MXC_RDPM 29 +#define SLAVE_PCIE_0_CFG 30 +#define SLAVE_PCIE_1_CFG 31 +#define SLAVE_PCIE_2A_CFG 32 +#define SLAVE_PCIE_2B_CFG 33 +#define SLAVE_PCIE_3A_CFG 34 +#define SLAVE_PCIE_3B_CFG 35 +#define SLAVE_PCIE_4_CFG 36 +#define SLAVE_PCIE_RSC_CFG 37 +#define SLAVE_PDM 38 +#define SLAVE_PIMEM_CFG 39 +#define SLAVE_PKA_WRAPPER_CFG 40 +#define SLAVE_PMU_WRAPPER_CFG 41 +#define SLAVE_QDSS_CFG 42 +#define SLAVE_QSPI_0 43 +#define SLAVE_QUP_0 44 +#define SLAVE_QUP_1 45 +#define SLAVE_QUP_2 46 +#define SLAVE_SDCC_2 47 +#define SLAVE_SDCC_4 48 +#define SLAVE_SECURITY 49 +#define SLAVE_SMMUV3_CFG 50 +#define SLAVE_SMSS_CFG 51 +#define SLAVE_SPSS_CFG 52 +#define SLAVE_TCSR 53 +#define SLAVE_TLMM 54 +#define SLAVE_UFS_CARD_CFG 55 +#define SLAVE_UFS_MEM_CFG 56 +#define SLAVE_USB3_0 57 +#define SLAVE_USB3_1 58 +#define SLAVE_USB3_MP 59 +#define SLAVE_USB4_0 60 +#define SLAVE_USB4_1 61 +#define SLAVE_VENUS_CFG 62 +#define SLAVE_VSENSE_CTRL_CFG 63 +#define SLAVE_VSENSE_CTRL_R_CFG 64 +#define SLAVE_A1NOC_CFG 65 +#define SLAVE_A2NOC_CFG 66 +#define SLAVE_ANOC_PCIE_BRIDGE_CFG 67 +#define SLAVE_DDRSS_CFG 68 +#define SLAVE_CNOC_MNOC_CFG 69 +#define SLAVE_SNOC_CFG 70 +#define SLAVE_SNOC_SF_BRIDGE_CFG 71 +#define SLAVE_IMEM 72 +#define SLAVE_PIMEM 73 +#define SLAVE_SERVICE_CNOC 74 +#define SLAVE_PCIE_0 75 +#define SLAVE_PCIE_1 76 +#define SLAVE_PCIE_2A 77 +#define SLAVE_PCIE_2B 78 +#define SLAVE_PCIE_3A 79 +#define SLAVE_PCIE_3B 80 +#define SLAVE_PCIE_4 81 +#define SLAVE_QDSS_STM 82 +#define SLAVE_SMSS 83 +#define SLAVE_TCU 84 + +/* dc_noc */ +#define MASTER_CNOC_DC_NOC 0 +#define SLAVE_LLCC_CFG 1 +#define SLAVE_GEM_NOC_CFG 2 + +/* gem_noc */ +#define MASTER_GPU_TCU 0 +#define MASTER_PCIE_TCU 1 +#define MASTER_SYS_TCU 2 +#define MASTER_APPSS_PROC 3 +#define MASTER_COMPUTE_NOC 4 +#define MASTER_COMPUTE_NOC_1 5 +#define MASTER_GEM_NOC_CFG 6 +#define MASTER_GFX3D 7 +#define MASTER_MNOC_HF_MEM_NOC 8 +#define MASTER_MNOC_SF_MEM_NOC 9 +#define MASTER_ANOC_PCIE_GEM_NOC 10 +#define MASTER_SNOC_GC_MEM_NOC 11 +#define MASTER_SNOC_SF_MEM_NOC 12 +#define SLAVE_GEM_NOC_CNOC 13 +#define SLAVE_LLCC 14 +#define SLAVE_GEM_NOC_PCIE_CNOC 15 +#define SLAVE_SERVICE_GEM_NOC_1 16 +#define SLAVE_SERVICE_GEM_NOC_2 17 +#define SLAVE_SERVICE_GEM_NOC 18 + +/* lpass_ag_noc */ +#define MASTER_CNOC_LPASS_AG_NOC 0 +#define MASTER_LPASS_PROC 1 +#define SLAVE_LPASS_CORE_CFG 2 +#define SLAVE_LPASS_LPI_CFG 3 +#define SLAVE_LPASS_MPU_CFG 4 +#define SLAVE_LPASS_TOP_CFG 5 +#define SLAVE_LPASS_SNOC 6 +#define SLAVE_SERVICES_LPASS_AML_NOC 7 +#define SLAVE_SERVICE_LPASS_AG_NOC 8 + +/* mc_virt */ +#define MASTER_LLCC 0 +#define SLAVE_EBI1 1 + +/*mmss_noc */ +#define MASTER_CAMNOC_HF 0 +#define MASTER_MDP0 1 +#define MASTER_MDP1 2 +#define MASTER_MDP_CORE1_0 3 +#define MASTER_MDP_CORE1_1 4 +#define MASTER_CNOC_MNOC_CFG 5 +#define MASTER_ROTATOR 6 +#define MASTER_ROTATOR_1 7 +#define MASTER_VIDEO_P0 8 +#define MASTER_VIDEO_P1 9 +#define MASTER_VIDEO_PROC 10 +#define MASTER_CAMNOC_ICP 11 +#define MASTER_CAMNOC_SF 12 +#define SLAVE_MNOC_HF_MEM_NOC 13 +#define SLAVE_MNOC_SF_MEM_NOC 14 +#define SLAVE_SERVICE_MNOC 15 + +/* nspa_noc */ +#define MASTER_CDSP_NOC_CFG 0 +#define MASTER_CDSP_PROC 1 +#define SLAVE_CDSP_MEM_NOC 2 +#define SLAVE_NSP_XFR 3 +#define SLAVE_SERVICE_NSP_NOC 4 + +/* nspb_noc */ +#define MASTER_CDSPB_NOC_CFG 0 +#define MASTER_CDSP_PROC_B 1 +#define SLAVE_CDSPB_MEM_NOC 2 +#define SLAVE_NSPB_XFR 3 +#define SLAVE_SERVICE_NSPB_NOC 4 + +/* system_noc */ +#define MASTER_A1NOC_SNOC 0 +#define MASTER_A2NOC_SNOC 1 +#define MASTER_USB_NOC_SNOC 2 +#define MASTER_LPASS_ANOC 3 +#define MASTER_SNOC_CFG 4 +#define MASTER_PIMEM 5 +#define MASTER_GIC 6 +#define SLAVE_SNOC_GEM_NOC_GC 7 +#define SLAVE_SNOC_GEM_NOC_SF 8 +#define SLAVE_SERVICE_SNOC 9 + +#endif -- cgit v1.2.3 From 52ef8efcb75e8a8aab88e74c1376c2785d9a5452 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 2 Apr 2022 00:28:23 +0200 Subject: dma: omap: hide legacy interface The legacy interface for omap-dma is only used on OMAP1, and the same is true for the non-DT case. Make both of these conditional on CONFIG_ARCH_OMAP1 being set to simplify the dependency. The non-OMAP stub functions in include/linux/omap-dma.h are note needed any more either now, because they are only called on OMAP1. Acked-by: Tony Lindgren Acked-By: Vinod Koul Signed-off-by: Arnd Bergmann --- include/linux/omap-dma.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 07fa58ae9902..254b4e10511b 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -292,7 +292,6 @@ struct omap_system_dma_plat_info { #define dma_omap15xx() __dma_omap15xx(d) #define dma_omap16xx() __dma_omap16xx(d) -#if defined(CONFIG_ARCH_OMAP) extern struct omap_system_dma_plat_info *omap_get_plat_info(void); extern void omap_set_dma_priority(int lch, int dst_port, int priority); @@ -340,25 +339,4 @@ static inline int omap_lcd_dma_running(void) } #endif -#else /* CONFIG_ARCH_OMAP */ -static inline void omap_set_dma_priority(int lch, int dst_port, int priority) -{ -} - -static inline struct omap_system_dma_plat_info *omap_get_plat_info(void) -{ - return NULL; -} - -static inline int omap_request_dma(int dev_id, const char *dev_name, - void (*callback)(int lch, u16 ch_status, void *data), - void *data, int *dma_ch) -{ - return -ENODEV; -} - -static inline void omap_free_dma(int ch) { } - -#endif /* CONFIG_ARCH_OMAP */ - #endif /* __LINUX_OMAP_DMA_H */ -- cgit v1.2.3 From 615dce5bf7369334f8c4f19f7f8f2a5634b4f911 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 12 Sep 2019 10:11:24 +0200 Subject: ARM: omap1: fix build with no SoC selected In a multiplatform randconfig kernel, one can have CONFIG_ARCH_OMAP1 enabled, but none of the specific SoCs. This leads to some build issues as the code is not meant to deal with this configuration at the moment: arch/arm/mach-omap1/io.c:86:20: error: unused function 'omap1_map_common_io' [-Werror,-Wunused-function] arch/arm/mach-omap1/pm.h:113:2: error: "Power management for this processor not implemented yet" [-Werror,-W#warnings] Use the same trick as on OMAP2 and guard the actual compilation of platform code with another Makefile ifdef check based on an option that depends on having at least one SoC enabled. The io.c file still needs to get compiled to allow building device drivers with a dependency on CONFIG_ARCH_OMAP1. Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/soc/ti/omap1-io.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/soc/ti/omap1-io.h b/include/linux/soc/ti/omap1-io.h index 9332c92690f4..f7f12728d4a6 100644 --- a/include/linux/soc/ti/omap1-io.h +++ b/include/linux/soc/ti/omap1-io.h @@ -5,7 +5,7 @@ #ifndef __ASSEMBLER__ #include -#if defined(CONFIG_ARCH_OMAP) && defined(CONFIG_ARCH_OMAP1) +#ifdef CONFIG_ARCH_OMAP1_ANY /* * NOTE: Please use ioremap + __raw_read/write where possible instead of these */ @@ -15,7 +15,7 @@ extern u32 omap_readl(u32 pa); extern void omap_writeb(u8 v, u32 pa); extern void omap_writew(u16 v, u32 pa); extern void omap_writel(u32 v, u32 pa); -#elif defined(CONFIG_COMPILE_TEST) +#else static inline u8 omap_readb(u32 pa) { return 0; } static inline u16 omap_readw(u32 pa) { return 0; } static inline u32 omap_readl(u32 pa) { return 0; } -- cgit v1.2.3 From 78ed93d72ded679e3caf0758357209887bda885f Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 4 Apr 2022 13:12:04 +0200 Subject: signal: Deliver SIGTRAP on perf event asynchronously if blocked With SIGTRAP on perf events, we have encountered termination of processes due to user space attempting to block delivery of SIGTRAP. Consider this case: ... sigset_t s; sigemptyset(&s); sigaddset(&s, SIGTRAP | ); sigprocmask(SIG_BLOCK, &s, ...); ... When the perf event triggers, while SIGTRAP is blocked, force_sig_perf() will force the signal, but revert back to the default handler, thus terminating the task. This makes sense for error conditions, but not so much for explicitly requested monitoring. However, the expectation is still that signals generated by perf events are synchronous, which will no longer be the case if the signal is blocked and delivered later. To give user space the ability to clearly distinguish synchronous from asynchronous signals, introduce siginfo_t::si_perf_flags and TRAP_PERF_FLAG_ASYNC (opted for flags in case more binary information is required in future). The resolution to the problem is then to (a) no longer force the signal (avoiding the terminations), but (b) tell user space via si_perf_flags if the signal was synchronous or not, so that such signals can be handled differently (e.g. let user space decide to ignore or consider the data imprecise). The alternative of making the kernel ignore SIGTRAP on perf events if the signal is blocked may work for some usecases, but likely causes issues in others that then have to revert back to interception of sigprocmask() (which we want to avoid). [ A concrete example: when using breakpoint perf events to track data-flow, in a region of code where signals are blocked, data-flow can no longer be tracked accurately. When a relevant asynchronous signal is received after unblocking the signal, the data-flow tracking logic needs to know its state is imprecise. ] Fixes: 97ba62b27867 ("perf: Add support for SIGTRAP on perf events") Reported-by: Dmitry Vyukov Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Acked-by: Geert Uytterhoeven Tested-by: Dmitry Vyukov Link: https://lore.kernel.org/r/20220404111204.935357-1-elver@google.com --- include/linux/compat.h | 1 + include/linux/sched/signal.h | 2 +- include/uapi/asm-generic/siginfo.h | 7 +++++++ 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index 1c758b0e0359..01fddf72a81f 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -235,6 +235,7 @@ typedef struct compat_siginfo { struct { compat_ulong_t _data; u32 _type; + u32 _flags; } _perf; }; } _sigfault; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..bab7cc56b13a 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -320,7 +320,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); -int force_sig_perf(void __user *addr, u32 type, u64 sig_data); +int send_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 3ba180f550d7..ffbe4cec9f32 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -99,6 +99,7 @@ union __sifields { struct { unsigned long _data; __u32 _type; + __u32 _flags; } _perf; }; } _sigfault; @@ -164,6 +165,7 @@ typedef struct siginfo { #define si_pkey _sifields._sigfault._addr_pkey._pkey #define si_perf_data _sifields._sigfault._perf._data #define si_perf_type _sifields._sigfault._perf._type +#define si_perf_flags _sifields._sigfault._perf._flags #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd #define si_call_addr _sifields._sigsys._call_addr @@ -270,6 +272,11 @@ typedef struct siginfo { * that are of the form: ((PTRACE_EVENT_XXX << 8) | SIGTRAP) */ +/* + * Flags for si_perf_flags if SIGTRAP si_code is TRAP_PERF. + */ +#define TRAP_PERF_FLAG_ASYNC (1u << 0) + /* * SIGCHLD si_codes */ -- cgit v1.2.3 From 03f16cd020eb8bb2eb837e2090086f296a9fa91d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Apr 2022 09:50:36 -0700 Subject: objtool: Add CONFIG_OBJTOOL Now that stack validation is an optional feature of objtool, add CONFIG_OBJTOOL and replace most usages of CONFIG_STACK_VALIDATION with it. CONFIG_STACK_VALIDATION can now be considered to be frame-pointer specific. CONFIG_UNWINDER_ORC is already inherently valid for live patching, so no need to "validate" it. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Miroslav Benes Link: https://lkml.kernel.org/r/939bf3d85604b2a126412bf11af6e3bd3b872bcb.1650300597.git.jpoimboe@redhat.com --- include/linux/compiler.h | 6 +++--- include/linux/instrumentation.h | 6 +++--- include/linux/objtool.h | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 219aa5ddbc73..01ce94b58b42 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -109,7 +109,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* Unreachable code */ -#ifdef CONFIG_STACK_VALIDATION +#ifdef CONFIG_OBJTOOL /* * These macros help objtool understand GCC code flow for unreachable code. * The __COUNTER__ based labels are a hack to make each instance of the macros @@ -128,10 +128,10 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(".rodata..c_jump_table") -#else +#else /* !CONFIG_OBJTOOL */ #define annotate_unreachable() #define __annotate_jump_table -#endif +#endif /* CONFIG_OBJTOOL */ #ifndef unreachable # define unreachable() do { \ diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index 24359b4a9605..9111a3704072 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -2,7 +2,7 @@ #ifndef __LINUX_INSTRUMENTATION_H #define __LINUX_INSTRUMENTATION_H -#if defined(CONFIG_DEBUG_ENTRY) && defined(CONFIG_STACK_VALIDATION) +#ifdef CONFIG_VMLINUX_VALIDATION #include @@ -53,9 +53,9 @@ ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) -#else +#else /* !CONFIG_VMLINUX_VALIDATION */ # define instrumentation_begin() do { } while(0) # define instrumentation_end() do { } while(0) -#endif +#endif /* CONFIG_VMLINUX_VALIDATION */ #endif /* __LINUX_INSTRUMENTATION_H */ diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 586d35720f13..977d90ba642d 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -38,7 +38,7 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 -#ifdef CONFIG_STACK_VALIDATION +#ifdef CONFIG_OBJTOOL #ifndef __ASSEMBLY__ @@ -157,7 +157,7 @@ struct unwind_hint { #endif /* __ASSEMBLY__ */ -#else /* !CONFIG_STACK_VALIDATION */ +#else /* !CONFIG_OBJTOOL */ #ifndef __ASSEMBLY__ @@ -179,6 +179,6 @@ struct unwind_hint { .endm #endif -#endif /* CONFIG_STACK_VALIDATION */ +#endif /* CONFIG_OBJTOOL */ #endif /* _LINUX_OBJTOOL_H */ -- cgit v1.2.3 From 0f620cefd7753175b6258fed85f76c2014ec3799 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Apr 2022 09:50:41 -0700 Subject: objtool: Rename "VMLINUX_VALIDATION" -> "NOINSTR_VALIDATION" CONFIG_VMLINUX_VALIDATION is just the validation of the "noinstr" rules. That name is a misnomer, because now objtool actually does vmlinux validation for other reasons. Rename CONFIG_VMLINUX_VALIDATION to CONFIG_NOINSTR_VALIDATION. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Miroslav Benes Link: https://lkml.kernel.org/r/173f07e2d6d1afc0874aed975a61783207c6a531.1650300597.git.jpoimboe@redhat.com --- include/linux/instrumentation.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index 9111a3704072..bc7babe91b2e 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -2,7 +2,7 @@ #ifndef __LINUX_INSTRUMENTATION_H #define __LINUX_INSTRUMENTATION_H -#ifdef CONFIG_VMLINUX_VALIDATION +#ifdef CONFIG_NOINSTR_VALIDATION #include @@ -53,9 +53,9 @@ ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) -#else /* !CONFIG_VMLINUX_VALIDATION */ +#else /* !CONFIG_NOINSTR_VALIDATION */ # define instrumentation_begin() do { } while(0) # define instrumentation_end() do { } while(0) -#endif /* CONFIG_VMLINUX_VALIDATION */ +#endif /* CONFIG_NOINSTR_VALIDATION */ #endif /* __LINUX_INSTRUMENTATION_H */ -- cgit v1.2.3 From 89e9c7280075f6733b22dd0740daeddeb1256ebf Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 20 Apr 2022 10:58:50 +0900 Subject: ipv6: Remove __ipv6_only_sock(). Since commit 9fe516ba3fb2 ("inet: move ipv6only in sock_common"), ipv6_only_sock() and __ipv6_only_sock() are the same macro. Let's remove the one. Signed-off-by: Kuniyuki Iwashima Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 918bfea4ef5f..ec5ca392eaa3 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -340,8 +340,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) return (struct raw6_sock *)sk; } -#define __ipv6_only_sock(sk) (sk->sk_ipv6only) -#define ipv6_only_sock(sk) (__ipv6_only_sock(sk)) +#define ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ inet6_sk(sk)->rxopt.bits.rxinfo) @@ -358,7 +357,6 @@ static inline int inet_v6_ipv6only(const struct sock *sk) return ipv6_only_sock(sk); } #else -#define __ipv6_only_sock(sk) 0 #define ipv6_only_sock(sk) 0 #define ipv6_sk_rxinfo(sk) 0 -- cgit v1.2.3 From 67e1e2f4854bb2c0dd2b8440cf090016a0e1a091 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Thu, 21 Apr 2022 01:21:33 +0200 Subject: ipv4: Avoid using RTO_ONLINK with ip_route_connect(). Now that ip_rt_fix_tos() doesn't reset ->flowi4_scope unconditionally, we don't have to rely on the RTO_ONLINK bit to properly set the scope of a flowi4 structure. We can just set ->flowi4_scope explicitly and avoid using RTO_ONLINK in ->flowi4_tos. This patch converts callers of ip_route_connect(). Instead of setting the tos parameter with RT_CONN_FLAGS(sk), as all callers do, we can: 1- Drop the tos parameter from ip_route_connect(): its value was entirely based on sk, which is also passed as parameter. 2- Set ->flowi4_scope depending on the SOCK_LOCALROUTE socket option instead of always initialising it with RT_SCOPE_UNIVERSE (let's define ip_sock_rt_scope() for this purpose). 3- Avoid overloading ->flowi4_tos with RTO_ONLINK: since the scope is now properly initialised, we don't need to tell ip_rt_fix_tos() to adjust ->flowi4_scope for us. So let's define ip_sock_rt_tos(), which is the same as RT_CONN_FLAGS() but without the RTO_ONLINK bit overload. Note: In the original ip_route_connect() code, __ip_route_output_key() might clear the RTO_ONLINK bit of fl4->flowi4_tos (because of ip_rt_fix_tos()). Therefore flowi4_update_output() had to reuse the original tos variable. Now that we don't set RTO_ONLINK any more, this is not a problem and we can use fl4->flowi4_tos in flowi4_update_output(). Signed-off-by: Guillaume Nault Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/route.h | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index 25404fc2b483..991a3985712d 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -43,6 +43,19 @@ #define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE)) #define RT_CONN_FLAGS_TOS(sk,tos) (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE)) +static inline __u8 ip_sock_rt_scope(const struct sock *sk) +{ + if (sock_flag(sk, SOCK_LOCALROUTE)) + return RT_SCOPE_LINK; + + return RT_SCOPE_UNIVERSE; +} + +static inline __u8 ip_sock_rt_tos(const struct sock *sk) +{ + return RT_TOS(inet_sk(sk)->tos); +} + struct ip_tunnel_info; struct fib_nh; struct fib_info; @@ -289,39 +302,38 @@ static inline char rt_tos2priority(u8 tos) * ip_route_newports() calls. */ -static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 src, - u32 tos, int oif, u8 protocol, +static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, + __be32 src, int oif, u8 protocol, __be16 sport, __be16 dport, - struct sock *sk) + const struct sock *sk) { __u8 flow_flags = 0; if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; - flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, - protocol, flow_flags, dst, src, dport, sport, - sk->sk_uid); + flowi4_init_output(fl4, oif, sk->sk_mark, ip_sock_rt_tos(sk), + ip_sock_rt_scope(sk), protocol, flow_flags, dst, + src, dport, sport, sk->sk_uid); } -static inline struct rtable *ip_route_connect(struct flowi4 *fl4, - __be32 dst, __be32 src, u32 tos, - int oif, u8 protocol, +static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst, + __be32 src, int oif, u8 protocol, __be16 sport, __be16 dport, struct sock *sk) { struct net *net = sock_net(sk); struct rtable *rt; - ip_route_connect_init(fl4, dst, src, tos, oif, protocol, - sport, dport, sk); + ip_route_connect_init(fl4, dst, src, oif, protocol, sport, dport, sk); if (!dst || !src) { rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) return rt; ip_rt_put(rt); - flowi4_update_output(fl4, oif, tos, fl4->daddr, fl4->saddr); + flowi4_update_output(fl4, oif, fl4->flowi4_tos, fl4->daddr, + fl4->saddr); } security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); -- cgit v1.2.3 From b804923b7ccb9c9629703364e927b48cd02a9254 Mon Sep 17 00:00:00 2001 From: "jason-jh.lin" Date: Tue, 19 Apr 2022 17:41:36 +0800 Subject: soc: mediatek: add mtk-mmsys support for mt8195 vdosys0 1. Add mt8195 mmsys compatible for 2 vdosys. 2. Add io_start into each driver data of mt8195 vdosys. 3. Add get match data function to identify mmsys by io_start. 4. Add mt8195 routing table settings of vdosys0. Signed-off-by: jason-jh.lin Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Rex-BC Chen Reviewed-by: CK Hu Link: https://lore.kernel.org/r/20220419094143.9561-2-jason-jh.lin@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-mmsys.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index 4bba275e235a..cff5c9adbf46 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -17,13 +17,24 @@ enum mtk_ddp_comp_id { DDP_COMPONENT_COLOR0, DDP_COMPONENT_COLOR1, DDP_COMPONENT_DITHER, + DDP_COMPONENT_DITHER1, + DDP_COMPONENT_DP_INTF0, + DDP_COMPONENT_DP_INTF1, DDP_COMPONENT_DPI0, DDP_COMPONENT_DPI1, + DDP_COMPONENT_DSC0, + DDP_COMPONENT_DSC1, DDP_COMPONENT_DSI0, DDP_COMPONENT_DSI1, DDP_COMPONENT_DSI2, DDP_COMPONENT_DSI3, DDP_COMPONENT_GAMMA, + DDP_COMPONENT_MERGE0, + DDP_COMPONENT_MERGE1, + DDP_COMPONENT_MERGE2, + DDP_COMPONENT_MERGE3, + DDP_COMPONENT_MERGE4, + DDP_COMPONENT_MERGE5, DDP_COMPONENT_OD0, DDP_COMPONENT_OD1, DDP_COMPONENT_OVL0, -- cgit v1.2.3 From 4e8988c634a1159e803bfdc0118578ded97e012c Mon Sep 17 00:00:00 2001 From: "jason-jh.lin" Date: Tue, 19 Apr 2022 17:41:41 +0800 Subject: soc: mediatek: add DDP_DOMPONENT_DITHER0 enum for mt8195 vdosys0 The mmsys routing table of mt8195 vdosys0 has 2 DITHER components, so mmsys need to add DDP_COMPONENT_DITHER1 and change all usages of DITHER enum form DDP_COMPONENT_DITHER to DDP_COMPONENT_DITHER0. But its header need to keep DDP_COMPONENT_DITHER enum until drm/mediatek also changed it. Signed-off-by: jason-jh.lin Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Rex-BC Chen Link: https://lore.kernel.org/r/20220419094143.9561-7-jason-jh.lin@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-mmsys.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index cff5c9adbf46..59117d970daf 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -17,6 +17,7 @@ enum mtk_ddp_comp_id { DDP_COMPONENT_COLOR0, DDP_COMPONENT_COLOR1, DDP_COMPONENT_DITHER, + DDP_COMPONENT_DITHER0 = DDP_COMPONENT_DITHER, DDP_COMPONENT_DITHER1, DDP_COMPONENT_DP_INTF0, DDP_COMPONENT_DP_INTF1, -- cgit v1.2.3 From bd40cbb0e3b37a4d2a2d9e2ac40122cdf619b1f3 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 19 Apr 2022 19:29:16 +0200 Subject: PM: domains: Move genpd's time-accounting to ktime_get_mono_fast_ns() To move towards a more consistent behaviour between genpd and the runtime PM core, let's start by converting genpd's time-accounting from ktime_get() into ktime_get_mono_fast_ns(). Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 67017c9390c8..043d48e4420a 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -98,7 +98,7 @@ struct genpd_power_state { u64 usage; u64 rejected; struct fwnode_handle *fwnode; - ktime_t idle_time; + u64 idle_time; void *data; }; @@ -149,8 +149,8 @@ struct generic_pm_domain { unsigned int state_count); unsigned int state_count; /* number of states */ unsigned int state_idx; /* state that genpd will go to when off */ - ktime_t on_time; - ktime_t accounting_time; + u64 on_time; + u64 accounting_time; const struct genpd_lock_ops *lock_ops; union { struct mutex mlock; -- cgit v1.2.3 From 6c2f421174273de8f83cde4286d1c076d43a2d35 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:24 +0200 Subject: driver: platform: Add helper for safer setting of driver_override Several core drivers and buses expect that driver_override is a dynamically allocated memory thus later they can kfree() it. However such assumption is not documented, there were in the past and there are already users setting it to a string literal. This leads to kfree() of static memory during device release (e.g. in error paths or during unbind): kernel BUG at ../mm/slub.c:3960! Internal error: Oops - BUG: 0 [#1] PREEMPT SMP ARM ... (kfree) from [] (platform_device_release+0x88/0xb4) (platform_device_release) from [] (device_release+0x2c/0x90) (device_release) from [] (kobject_put+0xec/0x20c) (kobject_put) from [] (exynos5_clk_probe+0x154/0x18c) (exynos5_clk_probe) from [] (platform_drv_probe+0x6c/0xa4) (platform_drv_probe) from [] (really_probe+0x280/0x414) (really_probe) from [] (driver_probe_device+0x78/0x1c4) (driver_probe_device) from [] (bus_for_each_drv+0x74/0xb8) (bus_for_each_drv) from [] (__device_attach+0xd4/0x16c) (__device_attach) from [] (bus_probe_device+0x88/0x90) (bus_probe_device) from [] (device_add+0x3dc/0x62c) (device_add) from [] (of_platform_device_create_pdata+0x94/0xbc) (of_platform_device_create_pdata) from [] (of_platform_bus_create+0x1a8/0x4fc) (of_platform_bus_create) from [] (of_platform_bus_create+0x20c/0x4fc) (of_platform_bus_create) from [] (of_platform_populate+0x84/0x118) (of_platform_populate) from [] (of_platform_default_populate_init+0xa0/0xb8) (of_platform_default_populate_init) from [] (do_one_initcall+0x8c/0x404) Provide a helper which clearly documents the usage of driver_override. This will allow later to reuse the helper and reduce the amount of duplicated code. Convert the platform driver to use a new helper and make the driver_override field const char (it is not modified by the core). Reviewed-by: Rafael J. Wysocki Acked-by: Rafael J. Wysocki Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-2-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/driver.h | 2 ++ include/linux/platform_device.h | 6 +++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 15e7c5e15d62..700453017e1c 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -151,6 +151,8 @@ extern int __must_check driver_create_file(struct device_driver *driver, extern void driver_remove_file(struct device_driver *driver, const struct driver_attribute *attr); +int driver_set_override(struct device *dev, const char **override, + const char *s, size_t len); extern int __must_check driver_for_each_device(struct device_driver *drv, struct device *start, void *data, diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 7c96f169d274..582d83ed9a91 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -31,7 +31,11 @@ struct platform_device { struct resource *resource; const struct platform_device_id *id_entry; - char *driver_override; /* Driver name to force a match */ + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; /* MFD cell pointer */ struct mfd_cell *mfd_cell; -- cgit v1.2.3 From 6e67955087e72f1a5f64dd8014c27e1d9317fbb4 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:25 +0200 Subject: amba: Use driver_set_override() instead of open-coding Use a helper to set driver_override to reduce the amount of duplicated code. Make the driver_override field const char, because it is not modified by the core and it matches other subsystems. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-3-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/amba/bus.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 6562f543c3e0..93799a72ff82 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -70,7 +70,11 @@ struct amba_device { unsigned int cid; struct amba_cs_uci_id uci; unsigned int irq[AMBA_NR_IRQS]; - char *driver_override; + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; }; struct amba_driver { -- cgit v1.2.3 From 5688f212e98a2469583a067fa5da4312ddc4e357 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:26 +0200 Subject: fsl-mc: Use driver_set_override() instead of open-coding Use a helper to set driver_override to reduce the amount of duplicated code. Make the driver_override field const char, because it is not modified by the core and it matches other subsystems. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-4-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 7b6c42bfb660..7a87ab9eba99 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -170,7 +170,9 @@ struct fsl_mc_obj_desc { * @regions: pointer to array of MMIO region entries * @irqs: pointer to array of pointers to interrupts allocated to this device * @resource: generic resource associated with this MC object device, if any. - * @driver_override: driver name to force a match + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. * * Generic device object for MC object devices that are "attached" to a * MC bus. @@ -204,7 +206,7 @@ struct fsl_mc_device { struct fsl_mc_device_irq **irqs; struct fsl_mc_resource *resource; struct device_link *consumer_link; - char *driver_override; + const char *driver_override; }; #define to_fsl_mc_device(_dev) \ -- cgit v1.2.3 From 01ed100276bdac259f1b418b998904a7486b0b68 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:27 +0200 Subject: hv: Use driver_set_override() instead of open-coding Use a helper to set driver_override to the reduce amount of duplicated code. Make the driver_override field const char, because it is not modified by the core and it matches other subsystems. Reviewed-by: Michael Kelley Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-5-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index fe2e0179ed51..12e2336b23b7 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1257,7 +1257,11 @@ struct hv_device { u16 device_id; struct device device; - char *driver_override; /* Driver name to force a match */ + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; struct vmbus_channel *channel; struct kset *channels_kset; -- cgit v1.2.3 From 23d99baf9d729ca30b2fb6798a7b403a37bfb800 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:28 +0200 Subject: PCI: Use driver_set_override() instead of open-coding Use a helper to set driver_override to the reduce amount of duplicated code. Make the driver_override field const char, because it is not modified by the core and it matches other subsystems. Reviewed-by: Andy Shevchenko Acked-by: Bjorn Helgaas Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-6-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 60adf42460ab..844d38f589cf 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -516,7 +516,11 @@ struct pci_dev { u16 acs_cap; /* ACS Capability offset */ phys_addr_t rom; /* Physical address if not from BAR */ size_t romlen; /* Length if not from BAR */ - char *driver_override; /* Driver name to force a match */ + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; unsigned long priv_flags; /* Private flags for the PCI driver */ -- cgit v1.2.3 From 19368f0f23e80929691dd5b1354832c0e0494419 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:30 +0200 Subject: spi: Use helper for safer setting of driver_override Use a helper to set driver_override to the reduce amount of duplicated code. Reviewed-by: Mark Brown Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-8-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/spi/spi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 5f8c063ddff4..f0177f9b6e13 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -138,6 +138,8 @@ extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); * for driver coldplugging, and in uevents used for hotplugging * @driver_override: If the name of a driver is written to this attribute, then * the device will bind to the named driver and only the named driver. + * Do not set directly, because core frees it; use driver_set_override() to + * set or clear it. * @cs_gpiod: gpio descriptor of the chipselect line (optional, NULL when * not using a GPIO line) * @word_delay: delay to be inserted between consecutive -- cgit v1.2.3 From 240bf4e665741241983580812a2be1b033f120ee Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:31 +0200 Subject: vdpa: Use helper for safer setting of driver_override Use a helper to set driver_override to the reduce amount of duplicated code. Acked-by: Michael S. Tsirkin Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-9-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/vdpa.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 8943a209202e..c0a5083632ab 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -64,7 +64,9 @@ struct vdpa_mgmt_dev; * struct vdpa_device - representation of a vDPA device * @dev: underlying device * @dma_dev: the actual device that is performing DMA - * @driver_override: driver name to force a match + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. * @config: the configuration ops for this device. * @cf_mutex: Protects get and set access to configuration layout. * @index: device index -- cgit v1.2.3 From 42cd402b8fd4672b692400fe5f9eecd55d2794ac Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:35 +0200 Subject: rpmsg: Fix kfree() of static memory on setting driver_override The driver_override field from platform driver should not be initialized from static memory (string literal) because the core later kfree() it, for example when driver_override is set via sysfs. Use dedicated helper to set driver_override properly. Fixes: 950a7388f02b ("rpmsg: Turn name service into a stand alone driver") Fixes: c0cdc19f84a4 ("rpmsg: Driver for user space endpoint interface") Reviewed-by: Bjorn Andersson Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-13-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/rpmsg.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index 02fa9116cd60..20c8cd1cde21 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -41,7 +41,9 @@ struct rpmsg_channel_info { * rpmsg_device - device that belong to the rpmsg bus * @dev: the device struct * @id: device id (used to match between rpmsg drivers and devices) - * @driver_override: driver name to force a match + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. * @src: local address * @dst: destination address * @ept: the rpmsg endpoint of this channel @@ -51,7 +53,7 @@ struct rpmsg_channel_info { struct rpmsg_device { struct device dev; struct rpmsg_device_id id; - char *driver_override; + const char *driver_override; u32 src; u32 dst; struct rpmsg_endpoint *ept; -- cgit v1.2.3 From f918cfc08c1755b9e54cd6effc923fa809045cf4 Mon Sep 17 00:00:00 2001 From: Ronak Jain Date: Wed, 6 Apr 2022 03:55:23 -0700 Subject: firmware: xilinx: add support for IOCTL and QUERY ID feature check Add support to check if IOCTL ID or QUERY ID is supported in firmware or not. Signed-off-by: Ronak Jain Link: https://lore.kernel.org/r/1649242526-17493-2-git-send-email-ronak.jain@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 14f00a7672d1..1ec73d5352c3 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -29,6 +29,11 @@ /* SMC SIP service Call Function Identifier Prefix */ #define PM_SIP_SVC 0xC2000000 + +/* PM API versions */ +#define PM_API_VERSION_2 2 + +/* ATF only commands */ #define PM_GET_TRUSTZONE_VERSION 0xa03 #define PM_SET_SUSPEND_MODE 0xa02 #define GET_CALLBACK_DATA 0xa01 @@ -460,6 +465,7 @@ int zynqmp_pm_load_pdi(const u32 src, const u64 address); int zynqmp_pm_register_notifier(const u32 node, const u32 event, const u32 wake, const u32 enable); int zynqmp_pm_feature(const u32 api_id); +int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id); int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value); int zynqmp_pm_get_feature_config(enum pm_feature_config_id id, u32 *payload); #else @@ -678,6 +684,11 @@ static inline int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id) return -ENODEV; } +static inline int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id) +{ + return -ENODEV; +} + static inline int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id) { return -ENODEV; -- cgit v1.2.3 From 10fa1b2cdc899ab471000968af56215bf3c90d8e Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 22 Apr 2022 17:13:48 +0200 Subject: ACPI: bus: Avoid non-ACPI device objects in walks over children When walking the children of an ACPI device, take extra care to avoid using to_acpi_device() on the ones that are not ACPI devices, because that may lead to out-of-bounds access and memory corruption. While at it, make the function passed to acpi_dev_for_each_child() take a struct acpi_device pointer argument (instead of a struct device one), so it is more straightforward to use. Fixes: b7dd6298db81 ("ACPI: PM: Introduce acpi_dev_power_up_children_with_adr()") Reported-by: kernel test robot BugLink: https://lore.kernel.org/lkml/20220420064725.GB16310@xsang-OptiPlex-9020/ Signed-off-by: Rafael J. Wysocki Reviewed-by: Mika Westerberg --- include/acpi/acpi_bus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index b44aaffedb91..772590e2eddb 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -482,7 +482,7 @@ extern struct bus_type acpi_bus_type; int acpi_bus_for_each_dev(int (*fn)(struct device *, void *), void *data); int acpi_dev_for_each_child(struct acpi_device *adev, - int (*fn)(struct device *, void *), void *data); + int (*fn)(struct acpi_device *, void *), void *data); /* * Events -- cgit v1.2.3 From bc1ce713a0843ba14a1e00d5275ad42a8873a5ce Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 3 Mar 2022 17:35:43 -0500 Subject: pwm: Add support for Xilinx AXI Timer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds PWM support for Xilinx LogiCORE IP AXI soft timers commonly found on Xilinx FPGAs. At the moment clock control is very basic: we just enable the clock during probe and pin the frequency. In the future, someone could add support for disabling the clock when not in use. Some common code has been specially demarcated. While currently only used by the PWM driver, it is anticipated that it may be split off in the future to be used by the timer driver as well. This driver was written with reference to Xilinx DS764 for v1.03.a [1]. [1] https://www.xilinx.com/support/documentation/ip_documentation/axi_timer/v1_03_a/axi_timer_ds764.pdf Signed-off-by: Sean Anderson Acked-by: Michal Simek Reviewed-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- include/clocksource/timer-xilinx.h | 73 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) create mode 100644 include/clocksource/timer-xilinx.h (limited to 'include') diff --git a/include/clocksource/timer-xilinx.h b/include/clocksource/timer-xilinx.h new file mode 100644 index 000000000000..c0f56fe6d22a --- /dev/null +++ b/include/clocksource/timer-xilinx.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2021 Sean Anderson + */ + +#ifndef XILINX_TIMER_H +#define XILINX_TIMER_H + +#include + +#define TCSR0 0x00 +#define TLR0 0x04 +#define TCR0 0x08 +#define TCSR1 0x10 +#define TLR1 0x14 +#define TCR1 0x18 + +#define TCSR_MDT BIT(0) +#define TCSR_UDT BIT(1) +#define TCSR_GENT BIT(2) +#define TCSR_CAPT BIT(3) +#define TCSR_ARHT BIT(4) +#define TCSR_LOAD BIT(5) +#define TCSR_ENIT BIT(6) +#define TCSR_ENT BIT(7) +#define TCSR_TINT BIT(8) +#define TCSR_PWMA BIT(9) +#define TCSR_ENALL BIT(10) +#define TCSR_CASC BIT(11) + +struct clk; +struct device_node; +struct regmap; + +/** + * struct xilinx_timer_priv - Private data for Xilinx AXI timer drivers + * @map: Regmap of the device, possibly with an offset + * @clk: Parent clock + * @max: Maximum value of the counters + */ +struct xilinx_timer_priv { + struct regmap *map; + struct clk *clk; + u32 max; +}; + +/** + * xilinx_timer_tlr_cycles() - Calculate the TLR for a period specified + * in clock cycles + * @priv: The timer's private data + * @tcsr: The value of the TCSR register for this counter + * @cycles: The number of cycles in this period + * + * Callers of this function MUST ensure that @cycles is representable as + * a TLR. + * + * Return: The calculated value for TLR + */ +u32 xilinx_timer_tlr_cycles(struct xilinx_timer_priv *priv, u32 tcsr, + u64 cycles); + +/** + * xilinx_timer_get_period() - Get the current period of a counter + * @priv: The timer's private data + * @tlr: The value of TLR for this counter + * @tcsr: The value of TCSR for this counter + * + * Return: The period, in ns + */ +unsigned int xilinx_timer_get_period(struct xilinx_timer_priv *priv, + u32 tlr, u32 tcsr); + +#endif /* XILINX_TIMER_H */ -- cgit v1.2.3 From 9e4ab6c89109472082616f8d2f6ada7deaffe161 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 19 Apr 2022 12:22:19 +0100 Subject: arm64/sme: Implement vector length configuration prctl()s As for SVE provide a prctl() interface which allows processes to configure their SME vector length. Signed-off-by: Mark Brown Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20220419112247.711548-12-broonie@kernel.org Signed-off-by: Catalin Marinas --- include/uapi/linux/prctl.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index e998764f0262..a5e06dcbba13 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -272,6 +272,15 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 +/* arm64 Scalable Matrix Extension controls */ +/* Flag values must be in sync with SVE versions */ +#define PR_SME_SET_VL 63 /* set task vector length */ +# define PR_SME_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SME_GET_VL 64 /* get task vector length */ +/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */ +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 -- cgit v1.2.3 From e12310a0d30f260b26297bc8d7c95769489af038 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 19 Apr 2022 12:22:28 +0100 Subject: arm64/sme: Implement ptrace support for streaming mode SVE registers The streaming mode SVE registers are represented using the same data structures as for SVE but since the vector lengths supported and in use may not be the same as SVE we represent them with a new type NT_ARM_SSVE. Unfortunately we only have a single 16 bit reserved field available in the header so there is no space to fit the current and maximum vector length for both standard and streaming SVE mode without redefining the structure in a way the creates a complicatd and fragile ABI. Since FFR is not present in streaming mode it is read and written as zero. Setting NT_ARM_SSVE registers will put the task into streaming mode, similarly setting NT_ARM_SVE registers will exit it. Reads that do not correspond to the current mode of the task will return the header with no register data. For compatibility reasons on write setting no flag for the register type will be interpreted as setting SVE registers, though users can provide no register data as an alternative mechanism for doing so. Signed-off-by: Mark Brown Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20220419112247.711548-21-broonie@kernel.org Signed-off-by: Catalin Marinas --- include/uapi/linux/elf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..a8dc688e1826 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -431,6 +431,7 @@ typedef struct elf64_shdr { #define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ +#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ -- cgit v1.2.3 From 776b4a1cf36411e96972455ca72906b722b80ea1 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 19 Apr 2022 12:22:29 +0100 Subject: arm64/sme: Add ptrace support for ZA The ZA array can be read and written with the NT_ARM_ZA. Similarly to our interface for the SVE vector registers the regset consists of a header with information on the current vector length followed by an optional register data payload, represented as for signals as a series of horizontal vectors from 0 to VL/8 in the endianness independent format used for vectors. On get if ZA is enabled then register data will be provided, otherwise it will be omitted. On set if register data is provided then ZA is enabled and initialized using the provided data, otherwise it is disabled. Signed-off-by: Mark Brown Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20220419112247.711548-22-broonie@kernel.org Signed-off-by: Catalin Marinas --- include/uapi/linux/elf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index a8dc688e1826..97808f958903 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -432,6 +432,7 @@ typedef struct elf64_shdr { #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ #define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ +#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ -- cgit v1.2.3 From faebd693c59387b7b765fab64b543855e15a91b4 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:36 +0206 Subject: printk: rename cpulock functions Since the printk cpulock is CPU-reentrant and since it is used in all contexts, its usage must be carefully considered and most likely will require programming locklessly. To avoid mistaking the printk cpulock as a typical lock, rename it to cpu_sync. The main functions then become: printk_cpu_sync_get_irqsave(flags); printk_cpu_sync_put_irqrestore(flags); Add extra notes of caution in the function description to help developers understand the requirements for correct usage. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-2-john.ogness@linutronix.de --- include/linux/printk.h | 54 ++++++++++++++++++++++++++++++-------------------- 1 file changed, 33 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 1522df223c0f..859323a52985 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -277,43 +277,55 @@ static inline void printk_trigger_flush(void) #endif #ifdef CONFIG_SMP -extern int __printk_cpu_trylock(void); -extern void __printk_wait_on_cpu_lock(void); -extern void __printk_cpu_unlock(void); +extern int __printk_cpu_sync_try_get(void); +extern void __printk_cpu_sync_wait(void); +extern void __printk_cpu_sync_put(void); /** - * printk_cpu_lock_irqsave() - Acquire the printk cpu-reentrant spinning - * lock and disable interrupts. + * printk_cpu_sync_get_irqsave() - Acquire the printk cpu-reentrant spinning + * lock and disable interrupts. * @flags: Stack-allocated storage for saving local interrupt state, - * to be passed to printk_cpu_unlock_irqrestore(). + * to be passed to printk_cpu_sync_put_irqrestore(). * * If the lock is owned by another CPU, spin until it becomes available. * Interrupts are restored while spinning. + * + * CAUTION: This function must be used carefully. It does not behave like a + * typical lock. Here are important things to watch out for... + * + * * This function is reentrant on the same CPU. Therefore the calling + * code must not assume exclusive access to data if code accessing the + * data can run reentrant or within NMI context on the same CPU. + * + * * If there exists usage of this function from NMI context, it becomes + * unsafe to perform any type of locking or spinning to wait for other + * CPUs after calling this function from any context. This includes + * using spinlocks or any other busy-waiting synchronization methods. */ -#define printk_cpu_lock_irqsave(flags) \ - for (;;) { \ - local_irq_save(flags); \ - if (__printk_cpu_trylock()) \ - break; \ - local_irq_restore(flags); \ - __printk_wait_on_cpu_lock(); \ +#define printk_cpu_sync_get_irqsave(flags) \ + for (;;) { \ + local_irq_save(flags); \ + if (__printk_cpu_sync_try_get()) \ + break; \ + local_irq_restore(flags); \ + __printk_cpu_sync_wait(); \ } /** - * printk_cpu_unlock_irqrestore() - Release the printk cpu-reentrant spinning - * lock and restore interrupts. - * @flags: Caller's saved interrupt state, from printk_cpu_lock_irqsave(). + * printk_cpu_sync_put_irqrestore() - Release the printk cpu-reentrant spinning + * lock and restore interrupts. + * @flags: Caller's saved interrupt state, from printk_cpu_sync_get_irqsave(). */ -#define printk_cpu_unlock_irqrestore(flags) \ +#define printk_cpu_sync_put_irqrestore(flags) \ do { \ - __printk_cpu_unlock(); \ + __printk_cpu_sync_put(); \ local_irq_restore(flags); \ - } while (0) \ + } while (0) #else -#define printk_cpu_lock_irqsave(flags) ((void)flags) -#define printk_cpu_unlock_irqrestore(flags) ((void)flags) +#define printk_cpu_sync_get_irqsave(flags) ((void)flags) +#define printk_cpu_sync_put_irqrestore(flags) ((void)flags) #endif /* CONFIG_SMP */ -- cgit v1.2.3 From f5343321b71ac0a1112adeab0ff90b239bad3a83 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:37 +0206 Subject: printk: cpu sync always disable interrupts The CPU sync functions are a NOP for !CONFIG_SMP. But for !CONFIG_SMP they still need to disable interrupts in order to preserve context within the CPU sync sections. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Reviewed-by: Sergey Senozhatsky Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-3-john.ogness@linutronix.de --- include/linux/printk.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 859323a52985..b70a42f94031 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -281,9 +281,16 @@ extern int __printk_cpu_sync_try_get(void); extern void __printk_cpu_sync_wait(void); extern void __printk_cpu_sync_put(void); +#else + +#define __printk_cpu_sync_try_get() true +#define __printk_cpu_sync_wait() +#define __printk_cpu_sync_put() +#endif /* CONFIG_SMP */ + /** - * printk_cpu_sync_get_irqsave() - Acquire the printk cpu-reentrant spinning - * lock and disable interrupts. + * printk_cpu_sync_get_irqsave() - Disable interrupts and acquire the printk + * cpu-reentrant spinning lock. * @flags: Stack-allocated storage for saving local interrupt state, * to be passed to printk_cpu_sync_put_irqrestore(). * @@ -322,13 +329,6 @@ extern void __printk_cpu_sync_put(void); local_irq_restore(flags); \ } while (0) -#else - -#define printk_cpu_sync_get_irqsave(flags) ((void)flags) -#define printk_cpu_sync_put_irqrestore(flags) ((void)flags) - -#endif /* CONFIG_SMP */ - extern int kptr_restrict; /** -- cgit v1.2.3 From a699449bb13b70b8bd10dc03ad7327ea3993221e Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:44 +0206 Subject: printk: refactor and rework printing logic Refactor/rework printing logic in order to prepare for moving to threaded console printing. - Move @console_seq into struct console so that the current "position" of each console can be tracked individually. - Move @console_dropped into struct console so that the current drop count of each console can be tracked individually. - Modify printing logic so that each console independently loads, prepares, and prints its next record. - Remove exclusive_console logic. Since console positions are handled independently, replaying past records occurs naturally. - Update the comments explaining why preemption is disabled while printing from printk() context. With these changes, there is a change in behavior: the console replaying the log (formerly exclusive console) will no longer block other consoles. New messages appear on the other consoles while the newly added console is still replaying. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-10-john.ogness@linutronix.de --- include/linux/console.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/console.h b/include/linux/console.h index 7cd758a4f44e..8c1686e2c233 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -151,6 +151,8 @@ struct console { int cflag; uint ispeed; uint ospeed; + u64 seq; + unsigned long dropped; void *data; struct console *next; }; -- cgit v1.2.3 From 3b604ca81202eea2a917eb6491e90f610fba0ec7 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:46 +0206 Subject: printk: add pr_flush() Provide a might-sleep function to allow waiting for console printers to catch up to the latest logged message. Use pr_flush() whenever it is desirable to get buffered messages printed before continuing: suspend_console(), resume_console(), console_stop(), console_start(), console_unblank(). Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-12-john.ogness@linutronix.de --- include/linux/printk.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index b70a42f94031..091fba7283e1 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -170,6 +170,8 @@ extern void __printk_safe_exit(void); #define printk_deferred_enter __printk_safe_enter #define printk_deferred_exit __printk_safe_exit +extern bool pr_flush(int timeout_ms, bool reset_on_progress); + /* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use @@ -220,6 +222,11 @@ static inline void printk_deferred_exit(void) { } +static inline bool pr_flush(int timeout_ms, bool reset_on_progress) +{ + return true; +} + static inline int printk_ratelimit(void) { return 0; -- cgit v1.2.3 From 2bb2b7b57f81255c13f4395ea911d6bdc70c9fe2 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:47 +0206 Subject: printk: add functions to prefer direct printing Once kthread printing is available, console printing will no longer occur in the context of the printk caller. However, there are some special contexts where it is desirable for the printk caller to directly print out kernel messages. Using pr_flush() to wait for threaded printers is only possible if the caller is in a sleepable context and the kthreads are active. That is not always the case. Introduce printk_prefer_direct_enter() and printk_prefer_direct_exit() functions to explicitly (and globally) activate/deactivate preferred direct console printing. The term "direct console printing" refers to printing to all enabled consoles from the context of the printk caller. The term "prefer" is used because this type of printing is only best effort. If the console is currently locked or other printers are already actively printing, the printk caller will need to rely on the other contexts to handle the printing. This preferred direct printing is how all printing has been handled until now (unless it was explicitly deferred). When kthread printing is introduced, there may be some unanticipated problems due to kthreads being unable to flush important messages. In order to minimize such risks, preferred direct printing is activated for the primary important messages when the system experiences general types of major errors. These are: - emergency reboot/shutdown - cpu and rcu stalls - hard and soft lockups - hung tasks - warn - sysrq Note that since kthread printing does not yet exist, no behavior changes result from this commit. This is only implementing the counter and marking the various places where preferred direct printing is active. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Acked-by: Paul E. McKenney # for RCU Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-13-john.ogness@linutronix.de --- include/linux/printk.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 091fba7283e1..cd26aab0ab2a 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -170,6 +170,9 @@ extern void __printk_safe_exit(void); #define printk_deferred_enter __printk_safe_enter #define printk_deferred_exit __printk_safe_exit +extern void printk_prefer_direct_enter(void); +extern void printk_prefer_direct_exit(void); + extern bool pr_flush(int timeout_ms, bool reset_on_progress); /* @@ -222,6 +225,14 @@ static inline void printk_deferred_exit(void) { } +static inline void printk_prefer_direct_enter(void) +{ +} + +static inline void printk_prefer_direct_exit(void) +{ +} + static inline bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; -- cgit v1.2.3 From 09c5ba0aa2fcfdadb17d045c3ee6f86d69270df7 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:48 +0206 Subject: printk: add kthread console printers Create a kthread for each console to perform console printing. During normal operation (@system_state == SYSTEM_RUNNING), the kthread printers are responsible for all printing on their respective consoles. During non-normal operation, console printing is done as it has been: within the context of the printk caller or within irqwork triggered by the printk caller, referred to as direct printing. Since threaded console printers are responsible for all printing during normal operation, this also includes messages generated via deferred printk calls. If direct printing is in effect during a deferred printk call, the queued irqwork will perform the direct printing. To make it clear that this is the only time that the irqwork will perform direct printing, rename the flag PRINTK_PENDING_OUTPUT to PRINTK_PENDING_DIRECT_OUTPUT. Threaded console printers synchronize against each other and against console lockers by taking the console lock for each message that is printed. Note that the kthread printers do not care about direct printing. They will always try to print if new records are available. They can be blocked by direct printing, but will be woken again once direct printing is finished. Console unregistration is a bit tricky because the associated kthread printer cannot be stopped while the console lock is held. A policy is implemented that states: whichever task clears con->thread (under the console lock) is responsible for stopping the kthread. unregister_console() will clear con->thread while the console lock is held and then stop the kthread after releasing the console lock. For consoles that have implemented the exit() callback, the kthread is stopped before exit() is called. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-14-john.ogness@linutronix.de --- include/linux/console.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/console.h b/include/linux/console.h index 8c1686e2c233..9a251e70c090 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -153,6 +153,8 @@ struct console { uint ospeed; u64 seq; unsigned long dropped; + struct task_struct *thread; + void *data; struct console *next; }; -- cgit v1.2.3 From 5e7260712b9a76de19c32f15d667f8f93e573978 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Thu, 21 Apr 2022 14:47:26 +0200 Subject: qed: Remove IP services API. qed_nvmetcp_ip_services.c and its corresponding header file were introduced in commit 806ee7f81a2b ("qed: Add IP services APIs support") but there's still no users for any of the functions they declare. Since these files are effectively unused, let's just drop them. Found by code inspection. Compile-tested only. Signed-off-by: Guillaume Nault Link: https://lore.kernel.org/r/351ac8c847980e22850eb390553f8cc0e1ccd0ce.1650545051.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- include/linux/qed/qed_nvmetcp_ip_services_if.h | 29 -------------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/linux/qed/qed_nvmetcp_ip_services_if.h (limited to 'include') diff --git a/include/linux/qed/qed_nvmetcp_ip_services_if.h b/include/linux/qed/qed_nvmetcp_ip_services_if.h deleted file mode 100644 index 3604aee53796..000000000000 --- a/include/linux/qed/qed_nvmetcp_ip_services_if.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ -/* - * Copyright 2021 Marvell. All rights reserved. - */ - -#ifndef _QED_IP_SERVICES_IF_H -#define _QED_IP_SERVICES_IF_H - -#include -#include -#include -#include - -int qed_route_ipv4(struct sockaddr_storage *local_addr, - struct sockaddr_storage *remote_addr, - struct sockaddr *hardware_address, - struct net_device **ndev); -int qed_route_ipv6(struct sockaddr_storage *local_addr, - struct sockaddr_storage *remote_addr, - struct sockaddr *hardware_address, - struct net_device **ndev); -void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id); -struct pci_dev *qed_validate_ndev(struct net_device *ndev); -void qed_return_tcp_port(struct socket *sock); -int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr, - struct socket **sock, u16 *port); -__be16 qed_get_in_port(struct sockaddr_storage *sa); - -#endif /* _QED_IP_SERVICES_IF_H */ -- cgit v1.2.3 From 9ea4dcf49878bb9546b8fa9319dcbdc9b7ee20f8 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 22 Apr 2022 15:58:11 -0700 Subject: PM: CXL: Disable suspend The CXL specification claims S3 support at a hardware level, but at a system software level there are some missing pieces. Section 9.4 (CXL 2.0) rightly claims that "CXL mem adapters may need aux power to retain memory context across S3", but there is no enumeration mechanism for the OS to determine if a given adapter has that support. Moreover the save state and resume image for the system may inadvertantly end up in a CXL device that needs to be restored before the save state is recoverable. I.e. a circular dependency that is not resolvable without a third party save-area. Arrange for the cxl_mem driver to fail S3 attempts. This still nominaly allows for suspend, but requires unbinding all CXL memory devices before the suspend to ensure the typical DRAM flow is taken. The cxl_mem unbind flow is intended to also tear down all CXL memory regions associated with a given cxl_memdev. It is reasonable to assume that any device participating in a System RAM range published in the EFI memory map is covered by aux power and save-area outside the device itself. So this restriction can be minimized in the future once pre-existing region enumeration support arrives, and perhaps a spec update to clarify if the EFI memory map is sufficent for determining the range of devices managed by platform-firmware for S3 support. Per Rafael, if the CXL configuration prevents suspend then it should fail early before tasks are frozen, and mem_sleep should stop showing 'mem' as an option [1]. Effectively CXL augments the platform suspend ->valid() op since, for example, the ACPI ops are not aware of the CXL / PCI dependencies. Given the split role of platform firmware vs OS provisioned CXL memory it is up to the cxl_mem driver to determine if the CXL configuration has elements that platform firmware may not be prepared to restore. Link: https://lore.kernel.org/r/CAJZ5v0hGVN_=3iU8OLpHY3Ak35T5+JcBM-qs8SbojKrpd0VXsA@mail.gmail.com [1] Cc: "Rafael J. Wysocki" Cc: Pavel Machek Cc: Len Brown Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/165066828317.3907920.5690432272182042556.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/pm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index e65b3ab28377..7911c4c9a7be 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -36,6 +36,15 @@ static inline void pm_vt_switch_unregister(struct device *dev) } #endif /* CONFIG_VT_CONSOLE_SLEEP */ +#ifdef CONFIG_CXL_SUSPEND +bool cxl_mem_active(void); +#else +static inline bool cxl_mem_active(void) +{ + return false; +} +#endif + /* * Device power management */ -- cgit v1.2.3 From 26f89535a5bb17915a2e1062c3999a2ee797c7b0 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Wed, 13 Apr 2022 22:12:46 -0700 Subject: cxl/mbox: Use type __u32 for mailbox payload sizes Payload sizes for mailbox commands are expected to be positive values coming from userspace. The documentation correctly describes these as always unsigned values. The mailbox and send structures that support the mailbox commands however, use __s32 types for the payloads. Replace __s32 with __u32 in the mailbox and send command structures and update usages. Kernel users of the interface already block all negative values and there is no known ability for userspace to have grown a dependency on submitting negative values to the kernel. The known user of the IOCTL, the CXL command line interface (cxl-cli) already enforces positive size values. A Smatch warning of a signedness uncovered this issue. Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Alison Schofield Link: https://lore.kernel.org/r/20220414051246.1244575-1-alison.schofield@intel.com Signed-off-by: Dan Williams --- include/uapi/linux/cxl_mem.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 8d206f27bb6d..c71021a2a9ed 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -68,8 +68,8 @@ static const struct { * struct cxl_command_info - Command information returned from a query. * @id: ID number for the command. * @flags: Flags that specify command behavior. - * @size_in: Expected input size, or -1 if variable length. - * @size_out: Expected output size, or -1 if variable length. + * @size_in: Expected input size, or ~0 if variable length. + * @size_out: Expected output size, or ~0 if variable length. * * Represents a single command that is supported by both the driver and the * hardware. This is returned as part of an array from the query ioctl. The @@ -78,7 +78,7 @@ static const struct { * * - @id = 10 * - @flags = 0 - * - @size_in = -1 + * - @size_in = ~0 * - @size_out = 0 * * See struct cxl_mem_query_commands. @@ -89,8 +89,8 @@ struct cxl_command_info { __u32 flags; #define CXL_MEM_COMMAND_FLAG_MASK GENMASK(0, 0) - __s32 size_in; - __s32 size_out; + __u32 size_in; + __u32 size_out; }; /** @@ -169,13 +169,13 @@ struct cxl_send_command { __u32 retval; struct { - __s32 size; + __u32 size; __u32 rsvd; __u64 payload; } in; struct { - __s32 size; + __u32 size; __u32 rsvd; __u64 payload; } out; -- cgit v1.2.3 From f226041424cf87245d39a1b2dfae304308b36b6b Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Sat, 9 Apr 2022 14:12:15 -0700 Subject: soc: ti: wkup_m3_ipc: Add support for toggling VTT regulator Some boards like the AM335x EVM-SK and AM437x GP EVM provide software control via a GPIO pin to toggle the DDR VTT regulator to reduce power consumption in low power states. The VTT regulator should be disabled after enabling self-refresh on suspend, and should be enabled before disabling self-refresh on resume. This is to allow proper self-refresh entry/exit commands to be transmitted to the memory. The "ti,vtt-gpio-pin" device tree property in the wkup_m3_ipc node specifies which GPIO pin to use. This property is communicated to the Wakeup Cortex M3 co-processor where the actual toggling of the GPIO pin happens in CM3 firmware [1]. Please note that the GPIO pin must be on the GPIO0 module as that module is in the wakeup power domain. [1] https://git.ti.com/cgit/processor-firmware/ti-amx3-cm3-pm-firmware/tree/src/pm_services/ddr.c?h=08.02.00.006#n190 Signed-off-by: Dave Gerlach Signed-off-by: Keerthy [dfustini: remove the unnecessary "ti,needs-vtt-toggle" property] Signed-off-by: Drew Fustini Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20220409211215.2529387-3-dfustini@baylibre.com --- include/linux/wkup_m3_ipc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index 3f496967b538..2bc52c6381d5 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -33,6 +33,7 @@ struct wkup_m3_ipc { int mem_type; unsigned long resume_addr; + int vtt_conf; int state; struct completion sync_complete; -- cgit v1.2.3 From 038010bb30684c0219fa4f93a13149038f28291a Mon Sep 17 00:00:00 2001 From: John Crispin Date: Mon, 14 Mar 2022 09:44:03 +0100 Subject: dt-bindings: Add en7523-scu device tree binding documentation Adds device tree binding documentation for clocks in the EN7523 SOC. Reviewed-by: Rob Herring Signed-off-by: John Crispin Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20220314084409.84394-2-nbd@nbd.name Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/en7523-clk.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/dt-bindings/clock/en7523-clk.h (limited to 'include') diff --git a/include/dt-bindings/clock/en7523-clk.h b/include/dt-bindings/clock/en7523-clk.h new file mode 100644 index 000000000000..717d23a5e5ae --- /dev/null +++ b/include/dt-bindings/clock/en7523-clk.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ + +#ifndef _DT_BINDINGS_CLOCK_AIROHA_EN7523_H_ +#define _DT_BINDINGS_CLOCK_AIROHA_EN7523_H_ + +#define EN7523_CLK_GSW 0 +#define EN7523_CLK_EMI 1 +#define EN7523_CLK_BUS 2 +#define EN7523_CLK_SLIC 3 +#define EN7523_CLK_SPI 4 +#define EN7523_CLK_NPU 5 +#define EN7523_CLK_CRYPTO 6 +#define EN7523_CLK_PCIE 7 + +#define EN7523_NUM_CLOCKS 8 + +#endif /* _DT_BINDINGS_CLOCK_AIROHA_EN7523_H_ */ -- cgit v1.2.3 From 0f08c2e7458e25c967d844170f8ad1aac3b57a02 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 17 Mar 2022 12:55:06 +0900 Subject: usb: deprecate the third argument of usb_maxpacket() This is a transitional patch with the ultimate goal of changing the prototype of usb_maxpacket() from: | static inline __u16 | usb_maxpacket(struct usb_device *udev, int pipe, int is_out) into: | static inline u16 usb_maxpacket(struct usb_device *udev, int pipe) The third argument of usb_maxpacket(): is_out gets removed because it can be derived from its second argument: pipe using usb_pipeout(pipe). Furthermore, in the current version, ubs_pipeout(pipe) is called regardless in order to sanitize the is_out parameter. In order to make a smooth change, we first deprecate the is_out parameter by simply ignoring it (using a variadic function) and will remove it later, once all the callers get updated. The body of the function is reworked accordingly and is_out is replaced by usb_pipeout(pipe). The WARN_ON() calls become unnecessary and get removed. Finally, the return type is changed from __u16 to u16 because this is not a UAPI function. Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/r/20220317035514.6378-2-mailhol.vincent@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index 200b7b79acb5..572e136f6314 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1969,21 +1969,17 @@ usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe) return eps[usb_pipeendpoint(pipe)]; } -/*-------------------------------------------------------------------------*/ - -static inline __u16 -usb_maxpacket(struct usb_device *udev, int pipe, int is_out) +static inline u16 usb_maxpacket(struct usb_device *udev, int pipe, + /* int is_out deprecated */ ...) { struct usb_host_endpoint *ep; unsigned epnum = usb_pipeendpoint(pipe); - if (is_out) { - WARN_ON(usb_pipein(pipe)); + if (usb_pipeout(pipe)) ep = udev->ep_out[epnum]; - } else { - WARN_ON(usb_pipeout(pipe)); + else ep = udev->ep_in[epnum]; - } + if (!ep) return 0; @@ -1991,8 +1987,6 @@ usb_maxpacket(struct usb_device *udev, int pipe, int is_out) return usb_endpoint_maxp(&ep->desc); } -/* ----------------------------------------------------------------------- */ - /* translate USB error codes to codes user space understands */ static inline int usb_translate_errors(int error_code) { -- cgit v1.2.3 From 2ddf7617d568fdcbd3cc454bb4849fa6d3398c86 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 17 Mar 2022 12:55:13 +0900 Subject: usb: remove third argument of usb_maxpacket() Now that all users of usb_maxpacket() have been migrated to only use two arguments, remove the third variadic argument which was introduced for the transition. Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/r/20220317035514.6378-9-mailhol.vincent@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index 572e136f6314..8127782aa7a1 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1969,8 +1969,7 @@ usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe) return eps[usb_pipeendpoint(pipe)]; } -static inline u16 usb_maxpacket(struct usb_device *udev, int pipe, - /* int is_out deprecated */ ...) +static inline u16 usb_maxpacket(struct usb_device *udev, int pipe) { struct usb_host_endpoint *ep; unsigned epnum = usb_pipeendpoint(pipe); -- cgit v1.2.3 From bdddc253b0938a0063798881d1f6a971ea1d8943 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 17 Mar 2022 12:55:14 +0900 Subject: usb: rework usb_maxpacket() using usb_pipe_endpoint() Rework the body of usb_maxpacket() and just rely on the usb_pipe_endpoint() helper function to retrieve the host endpoint instead of doing it by hand. Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/r/20220317035514.6378-10-mailhol.vincent@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index 8127782aa7a1..60bee864d897 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1971,13 +1971,7 @@ usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe) static inline u16 usb_maxpacket(struct usb_device *udev, int pipe) { - struct usb_host_endpoint *ep; - unsigned epnum = usb_pipeendpoint(pipe); - - if (usb_pipeout(pipe)) - ep = udev->ep_out[epnum]; - else - ep = udev->ep_in[epnum]; + struct usb_host_endpoint *ep = usb_pipe_endpoint(udev, pipe); if (!ep) return 0; -- cgit v1.2.3 From 1e39e5a32ad7fdd82d6e071aa14ecd511eedc1f7 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 22 Apr 2022 14:55:39 -0700 Subject: mptcp: infinite mapping sending This patch adds the infinite mapping sending logic. Add a new flag send_infinite_map in struct mptcp_subflow_context. Set it true when a single contiguous subflow is in use and the allow_infinite_fallback flag is true in mptcp_pm_mp_fail_received(). In mptcp_sendmsg_frag(), if this flag is true, call the new function mptcp_update_infinite_map() to set the infinite mapping. Add a new flag infinite_map in struct mptcp_ext, set it true in mptcp_update_infinite_map(), and check this flag in a new helper mptcp_check_infinite_map(). In mptcp_update_infinite_map(), set data_len to 0, and clear the send_infinite_map flag, then do fallback. In mptcp_established_options(), use the helper mptcp_check_infinite_map() to let the infinite mapping DSS can be sent out in the fallback mode. Suggested-by: Paolo Abeni Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/net/mptcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 0a3b0fb04a3b..8b1afd6f5cc4 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -35,7 +35,8 @@ struct mptcp_ext { frozen:1, reset_transient:1; u8 reset_reason:4, - csum_reqd:1; + csum_reqd:1, + infinite_map:1; }; #define MPTCP_RM_IDS_MAX 8 -- cgit v1.2.3 From d9fdd02d4265c4c4fd5264b32b46034239192b7e Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 22 Apr 2022 14:55:42 -0700 Subject: mptcp: dump infinite_map field in mptcp_dump_mpext In trace event class mptcp_dump_mpext, dump the newly added infinite_map field of struct mptcp_dump_mpext too. Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/trace/events/mptcp.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index f8e28e686c65..563e48617374 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -84,6 +84,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __field(u8, reset_transient) __field(u8, reset_reason) __field(u8, csum_reqd) + __field(u8, infinite_map) ), TP_fast_assign( @@ -102,9 +103,10 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __entry->reset_transient = mpext->reset_transient; __entry->reset_reason = mpext->reset_reason; __entry->csum_reqd = mpext->csum_reqd; + __entry->infinite_map = mpext->infinite_map; ), - TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u", + TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u infinite_map=%u", __entry->data_ack, __entry->data_seq, __entry->subflow_seq, __entry->data_len, __entry->csum, __entry->use_map, @@ -112,7 +114,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __entry->use_ack, __entry->ack64, __entry->mpc_map, __entry->frozen, __entry->reset_transient, __entry->reset_reason, - __entry->csum_reqd) + __entry->csum_reqd, __entry->infinite_map) ); DEFINE_EVENT(mptcp_dump_mpext, mptcp_sendmsg_frag, -- cgit v1.2.3 From 3813c932ed970dd4f413498ccecb03c73c4f1784 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 3 Mar 2022 13:55:08 +0000 Subject: media: cec: call enable_adap on s_log_addrs Don't enable/disable the adapter if the first fh is opened or the last fh is closed, instead do this when the adapter is configured or unconfigured, and also when we enter Monitor All or Monitor Pin mode for the first time or we exit the Monitor All/Pin mode for the last time. However, if needs_hpd is true, then do this when the physical address is set or cleared: in that case the adapter typically is powered by the HPD, so it really is disabled when the HPD is low. This case (needs_hpd is true) was already handled in this way, so this wasn't changed. The problem with the old behavior was that if the HPD goes low when no fh is open, and a transmit was in progress, then the adapter would be disabled, typically stopping the transmit immediately which leaves a partial message on the bus, which isn't nice and can confuse some adapters. It makes much more sense to disable it only when the adapter is unconfigured and we're not monitoring the bus, since then you really won't be using it anymore. To keep track of this store a CEC activation count and call adap_enable only when it goes from 0 to 1 or back to 0. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 77346f757036..97c5f5bfcbd0 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -185,6 +185,7 @@ struct cec_adap_ops { * Drivers that need this can set this field to true after the * cec_allocate_adapter() call. * @last_initiator: the initiator of the last transmitted message. + * @activate_cnt: number of times that CEC is activated * @monitor_all_cnt: number of filehandles monitoring all msgs * @monitor_pin_cnt: number of filehandles monitoring pin changes * @follower_cnt: number of filehandles in follower mode @@ -236,6 +237,7 @@ struct cec_adapter { bool cec_pin_is_high; bool adap_controls_phys_addr; u8 last_initiator; + u32 activate_cnt; u32 monitor_all_cnt; u32 monitor_pin_cnt; u32 follower_cnt; -- cgit v1.2.3 From 590a8e564c6eff7e77a84e728612f1269e3c0685 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 3 Mar 2022 14:01:44 +0000 Subject: media: cec: abort if the current transmit was canceled If a transmit-in-progress was canceled, then, once the transmit is done, mark it as aborted and refrain from retrying the transmit. To signal this situation the new transmit_in_progress_aborted field is set to true. The old implementation would just set adap->transmitting to NULL and set adap->transmit_in_progress to false, but on the hardware level the transmit was still ongoing. However, the framework would think the transmit was aborted, and if a new transmit was issued, then it could overwrite the HW buffer containing the old transmit with the new transmit, leading to garbled data on the CEC bus. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 97c5f5bfcbd0..31d704f36707 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -163,6 +163,11 @@ struct cec_adap_ops { * @wait_queue: queue of transmits waiting for a reply * @transmitting: CEC messages currently being transmitted * @transmit_in_progress: true if a transmit is in progress + * @transmit_in_progress_aborted: true if a transmit is in progress is to be + * aborted. This happens if the logical address is + * invalidated while the transmit is ongoing. In that + * case the transmit will finish, but will not retransmit + * and be marked as ABORTED. * @kthread_config: kthread used to configure a CEC adapter * @config_completion: used to signal completion of the config kthread * @kthread: main CEC processing thread @@ -218,6 +223,7 @@ struct cec_adapter { struct list_head wait_queue; struct cec_data *transmitting; bool transmit_in_progress; + bool transmit_in_progress_aborted; struct task_struct *kthread_config; struct completion config_completion; -- cgit v1.2.3 From 567f882a401346779d05a90beb8f21865ebdd398 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 9 Mar 2022 10:55:43 +0000 Subject: media: cec.h: add cec_msg_recv_is_rx/tx_result helpers These two helper functions return true if the received message contains the result of a previous non-blocking transmit. Either the tx_status result (cec_msg_recv_is_tx_result) of the transmit, or the rx_status result (cec_msg_recv_is_rx_result) of the reply to the original transmit. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/cec.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index de936f5e446d..1d48da926216 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -142,6 +142,26 @@ static inline void cec_msg_set_reply_to(struct cec_msg *msg, msg->reply = msg->timeout = 0; } +/** + * cec_msg_recv_is_tx_result - return true if this message contains the + * result of an earlier non-blocking transmit + * @msg: the message structure from CEC_RECEIVE + */ +static inline int cec_msg_recv_is_tx_result(const struct cec_msg *msg) +{ + return msg->sequence && msg->tx_status && !msg->rx_status; +} + +/** + * cec_msg_recv_is_rx_result - return true if this message contains the + * reply of an earlier non-blocking transmit + * @msg: the message structure from CEC_RECEIVE + */ +static inline int cec_msg_recv_is_rx_result(const struct cec_msg *msg) +{ + return msg->sequence && !msg->tx_status && msg->rx_status; +} + /* cec_msg flags field */ #define CEC_MSG_FL_REPLY_TO_FOLLOWERS (1 << 0) #define CEC_MSG_FL_RAW (1 << 1) -- cgit v1.2.3 From dad272bd03d541dc7c0ff8331756eccf659f6f02 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 13 Nov 2021 11:05:24 +0000 Subject: media: cec: add xfer_timeout_ms field Allow drivers to change the transmit timeout value, i.e. after how long should a transmit be considered 'lost', i.e. the corresponding cec_transmit_done_ts was never called. Some CEC devices have their own timeout, and so this timeout value must be longer than that hardware timeout value. If it is shorter then the framework would consider the transmit lost, even though it is effectively still in progress at the hardware level. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 31d704f36707..80340c9eb0f2 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -168,6 +168,8 @@ struct cec_adap_ops { * invalidated while the transmit is ongoing. In that * case the transmit will finish, but will not retransmit * and be marked as ABORTED. + * @xfer_timeout_ms: the transfer timeout in ms. + * If 0, then timeout after 2.1 ms. * @kthread_config: kthread used to configure a CEC adapter * @config_completion: used to signal completion of the config kthread * @kthread: main CEC processing thread @@ -224,6 +226,7 @@ struct cec_adapter { struct cec_data *transmitting; bool transmit_in_progress; bool transmit_in_progress_aborted; + unsigned int xfer_timeout_ms; struct task_struct *kthread_config; struct completion config_completion; -- cgit v1.2.3 From f1b57164305d6342b9f77a4f4482cde492b56983 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 3 Feb 2022 12:11:15 +0000 Subject: media: cec: add optional adap_configured callback This new optional callback is called when the adapter is fully configured or fully unconfigured. Some drivers may have to take action when this happens. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 80340c9eb0f2..6f13b0222aa3 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -118,6 +118,7 @@ struct cec_adap_ops { int (*adap_monitor_all_enable)(struct cec_adapter *adap, bool enable); int (*adap_monitor_pin_enable)(struct cec_adapter *adap, bool enable); int (*adap_log_addr)(struct cec_adapter *adap, u8 logical_addr); + void (*adap_configured)(struct cec_adapter *adap, bool configured); int (*adap_transmit)(struct cec_adapter *adap, u8 attempts, u32 signal_free_time, struct cec_msg *msg); void (*adap_status)(struct cec_adapter *adap, struct seq_file *file); -- cgit v1.2.3 From 4e4dab4bb6029dbee63f12a249ddc44b0124ea63 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Wed, 2 Mar 2022 22:03:01 +0000 Subject: media: media.h: Add new media link type To describe in the kernel the connection between devices and their supporting peripherals (for example, a camera sensor and the vcm driving the focusing lens for it), add a new type of media link to introduce the concept of these ancillary links. Add some elements to the uAPI documentation to explain the new link type, their purpose and some aspects of their current implementation. Reviewed-by: Laurent Pinchart Signed-off-by: Daniel Scally Reviewed-by: Jean-Michel Hautbois Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 200fa8462b90..afbae7213d35 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -226,6 +226,7 @@ struct media_pad_desc { #define MEDIA_LNK_FL_LINK_TYPE (0xf << 28) # define MEDIA_LNK_FL_DATA_LINK (0 << 28) # define MEDIA_LNK_FL_INTERFACE_LINK (1 << 28) +# define MEDIA_LNK_FL_ANCILLARY_LINK (2 << 28) struct media_link_desc { struct media_pad_desc source; -- cgit v1.2.3 From 012c87f7696f3191f340d9bd6b4476d8d3bb25ad Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Wed, 2 Mar 2022 22:03:03 +0000 Subject: media: entity: Add support for ancillary links Add functions to create ancillary links, so that they don't need to be manually created by users. Reviewed-by: Laurent Pinchart Signed-off-by: Daniel Scally Reviewed-by: Jean-Michel Hautbois Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/media-entity.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 742918962d46..1d13b8939a11 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -1121,4 +1121,23 @@ void media_remove_intf_links(struct media_interface *intf); (((entity)->ops && (entity)->ops->operation) ? \ (entity)->ops->operation((entity) , ##args) : -ENOIOCTLCMD) +/** + * media_create_ancillary_link() - create an ancillary link between two + * instances of &media_entity + * + * @primary: pointer to the primary &media_entity + * @ancillary: pointer to the ancillary &media_entity + * + * Create an ancillary link between two entities, indicating that they + * represent two connected pieces of hardware that form a single logical unit. + * A typical example is a camera lens controller being linked to the sensor that + * it is supporting. + * + * The function sets both MEDIA_LNK_FL_ENABLED and MEDIA_LNK_FL_IMMUTABLE for + * the new link. + */ +struct media_link * +media_create_ancillary_link(struct media_entity *primary, + struct media_entity *ancillary); + #endif -- cgit v1.2.3 From a8a2bd1001f3b5de1a9cd583467ab4559a7b3b01 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 27 Jan 2022 09:25:48 +0000 Subject: media: mc: Remove redundant documentation Remove redundant kerneldoc documentation in mc-device.c. The functions are already documented in media-device.h, where non-redundant documentation is also moved. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/media-device.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/media/media-device.h b/include/media/media-device.h index 1345e6da688a..7d5b212792a5 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -219,6 +219,12 @@ static inline __must_check int media_entity_enum_init( * So drivers need to first initialize the media device, register any entity * within the media device, create pad to pad links and then finally register * the media device by calling media_device_register() as a final step. + * + * The caller is responsible for initializing the media device before + * registration. The following fields must be set: + * + * - dev must point to the parent device + * - model must be filled with the device model name */ void media_device_init(struct media_device *mdev); -- cgit v1.2.3 From db1fa290a35b1652628ba7b921ac7ad53ce36410 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 9 Mar 2022 09:12:01 +0000 Subject: media: mc: media_device_init() initialises a media_device, not media_entity The documentation for media_device_init() had several references to (struct) media_entity where it should have referred to struct media_device instead. Fix this. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/media-device.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/media-device.h b/include/media/media-device.h index 7d5b212792a5..bc015d2cf541 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -249,28 +249,28 @@ void media_device_cleanup(struct media_device *mdev); * The caller is responsible for initializing the &media_device structure * before registration. The following fields of &media_device must be set: * - * - &media_entity.dev must point to the parent device (usually a &pci_dev, + * - &media_device.dev must point to the parent device (usually a &pci_dev, * &usb_interface or &platform_device instance). * - * - &media_entity.model must be filled with the device model name as a + * - &media_device.model must be filled with the device model name as a * NUL-terminated UTF-8 string. The device/model revision must not be * stored in this field. * * The following fields are optional: * - * - &media_entity.serial is a unique serial number stored as a + * - &media_device.serial is a unique serial number stored as a * NUL-terminated ASCII string. The field is big enough to store a GUID * in text form. If the hardware doesn't provide a unique serial number * this field must be left empty. * - * - &media_entity.bus_info represents the location of the device in the + * - &media_device.bus_info represents the location of the device in the * system as a NUL-terminated ASCII string. For PCI/PCIe devices - * &media_entity.bus_info must be set to "PCI:" (or "PCIe:") followed by + * &media_device.bus_info must be set to "PCI:" (or "PCIe:") followed by * the value of pci_name(). For USB devices,the usb_make_path() function * must be used. This field is used by applications to distinguish between * otherwise identical devices that don't provide a serial number. * - * - &media_entity.hw_revision is the hardware device revision in a + * - &media_device.hw_revision is the hardware device revision in a * driver-specific format. When possible the revision should be formatted * with the KERNEL_VERSION() macro. * -- cgit v1.2.3 From 78a171e58717685ea0eb082a24bc75bd9e20518f Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Sat, 22 Jan 2022 11:25:57 +0000 Subject: media: mc: Provide a helper for setting bus_info field The bus_info or a similar field exists in a lot of structs, yet drivers tend to set the value of that field by themselves in a determinable way. Thus provide a helper for doing this. To be used in subsequent patches. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/media-device.h | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/media/media-device.h b/include/media/media-device.h index bc015d2cf541..f0baee6771ef 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -13,12 +13,13 @@ #include #include +#include +#include #include #include struct ida; -struct device; struct media_device; /** @@ -181,8 +182,7 @@ struct media_device { atomic_t request_id; }; -/* We don't need to include pci.h or usb.h here */ -struct pci_dev; +/* We don't need to include usb.h here */ struct usb_device; #ifdef CONFIG_MEDIA_CONTROLLER @@ -502,4 +502,27 @@ static inline void __media_device_usb_init(struct media_device *mdev, #define media_device_usb_init(mdev, udev, name) \ __media_device_usb_init(mdev, udev, name, KBUILD_MODNAME) +/** + * media_set_bus_info() - Set bus_info field + * + * @bus_info: Variable where to write the bus info (char array) + * @bus_info_size: Length of the bus_info + * @dev: Related struct device + * + * Sets bus information based on &dev. This is currently done for PCI and + * platform devices. dev is required to be non-NULL for this to happen. + * + * This function is not meant to be called from drivers. + */ +static inline void +media_set_bus_info(char *bus_info, size_t bus_info_size, struct device *dev) +{ + if (!dev) + strscpy(bus_info, "no bus info", bus_info_size); + else if (dev_is_platform(dev)) + snprintf(bus_info, bus_info_size, "platform:%s", dev_name(dev)); + else if (dev_is_pci(dev)) + snprintf(bus_info, bus_info_size, "PCI:%s", dev_name(dev)); +} + #endif -- cgit v1.2.3 From cef699749f3789add5ecaf0a2f73a659cae1c7ae Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Sat, 22 Jan 2022 11:31:37 +0000 Subject: media: mc: Set bus_info in media_device_init() Set bus_info field based on struct device in media_device_init() and remove corresponding code from drivers. Also update media_device_init() documentation: the dev field must be now initialised before calling it. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/media-device.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/media/media-device.h b/include/media/media-device.h index f0baee6771ef..a10b30507524 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -225,6 +225,9 @@ static inline __must_check int media_entity_enum_init( * * - dev must point to the parent device * - model must be filled with the device model name + * + * The bus_info field is set by media_device_init() for PCI and platform devices + * if the field begins with '\0'. */ void media_device_init(struct media_device *mdev); @@ -249,9 +252,6 @@ void media_device_cleanup(struct media_device *mdev); * The caller is responsible for initializing the &media_device structure * before registration. The following fields of &media_device must be set: * - * - &media_device.dev must point to the parent device (usually a &pci_dev, - * &usb_interface or &platform_device instance). - * * - &media_device.model must be filled with the device model name as a * NUL-terminated UTF-8 string. The device/model revision must not be * stored in this field. -- cgit v1.2.3 From dadd47d46818c7587f769287aa4acca152d48039 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:40 +0100 Subject: media: v4l2-subdev: fix #endif comments Add comments after #endifs to clarify their scope. Signed-off-by: Tomi Valkeinen Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 6c153b33bb04..a986fdd652e6 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -1023,7 +1023,7 @@ v4l2_subdev_get_try_compose(struct v4l2_subdev *sd, return &state->pads[pad].try_compose; } -#endif +#endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */ extern const struct v4l2_file_operations v4l2_subdev_fops; @@ -1204,4 +1204,4 @@ extern const struct v4l2_subdev_ops v4l2_subdev_call_wrappers; void v4l2_subdev_notify_event(struct v4l2_subdev *sd, const struct v4l2_event *ev); -#endif +#endif /* _V4L2_SUBDEV_H */ -- cgit v1.2.3 From 40aaab9d773b07e9b106eac4256bb50fb1ba8cff Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:42 +0100 Subject: media: subdev: rename subdev-state alloc & free v4l2_subdev_alloc_state() and v4l2_subdev_free_state() are not supposed to be used by the drivers. However, we do have a few drivers that use those at the moment, so we need to expose these functions for the time being. Prefix the functions with __ to mark the functions as internal. At the same time, rename them to v4l2_subdev_state_alloc and v4l2_subdev_state_free to match the style used for other functions like video_device_alloc() and media_request_alloc(). Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Reviewed-by: Hans Verkuil Reviewed-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index a986fdd652e6..ac3bcc54ea07 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -1122,20 +1122,24 @@ int v4l2_subdev_link_validate_default(struct v4l2_subdev *sd, int v4l2_subdev_link_validate(struct media_link *link); /** - * v4l2_subdev_alloc_state - allocate v4l2_subdev_state + * __v4l2_subdev_state_alloc - allocate v4l2_subdev_state * * @sd: pointer to &struct v4l2_subdev for which the state is being allocated. * - * Must call v4l2_subdev_free_state() when state is no longer needed. + * Must call __v4l2_subdev_state_free() when state is no longer needed. + * + * Not to be called directly by the drivers. */ -struct v4l2_subdev_state *v4l2_subdev_alloc_state(struct v4l2_subdev *sd); +struct v4l2_subdev_state *__v4l2_subdev_state_alloc(struct v4l2_subdev *sd); /** - * v4l2_subdev_free_state - free a v4l2_subdev_state + * __v4l2_subdev_state_free - free a v4l2_subdev_state * * @state: v4l2_subdev_state to be freed. + * + * Not to be called directly by the drivers. */ -void v4l2_subdev_free_state(struct v4l2_subdev_state *state); +void __v4l2_subdev_state_free(struct v4l2_subdev_state *state); #endif /* CONFIG_MEDIA_CONTROLLER */ -- cgit v1.2.3 From f69952a4dc1ef13b69497408fedbd12c7ceb294d Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:43 +0100 Subject: media: subdev: add active state to struct v4l2_subdev Add a new 'active_state' field to struct v4l2_subdev to which we can store the active state of a subdev. This will place the subdev configuration into a known place, allowing us to use the state directly from the v4l2 framework, thus simplifying the drivers. Also add functions v4l2_subdev_init_finalize() and v4l2_subdev_cleanup(), which will allocate and free the active state. The functions are named in a generic way so that they can be also used for other subdev initialization work. Signed-off-by: Tomi Valkeinen Reviewed-by: Hans Verkuil Reviewed-by: Jacopo Mondi Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 58 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index ac3bcc54ea07..d0d0e4caf893 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -645,6 +645,9 @@ struct v4l2_subdev_ir_ops { * This structure only needs to be passed to the pad op if the 'which' field * of the main argument is set to %V4L2_SUBDEV_FORMAT_TRY. For * %V4L2_SUBDEV_FORMAT_ACTIVE it is safe to pass %NULL. + * + * Note: This struct is also used in active state, and the 'try' prefix is + * historical and to be removed. */ struct v4l2_subdev_pad_config { struct v4l2_mbus_framefmt try_fmt; @@ -885,6 +888,9 @@ struct v4l2_subdev_platform_data { * @subdev_notifier: A sub-device notifier implicitly registered for the sub- * device using v4l2_async_register_subdev_sensor(). * @pdata: common part of subdevice platform data + * @active_state: Active state for the subdev (NULL for subdevs tracking the + * state internally). Initialized by calling + * v4l2_subdev_init_finalize(). * * Each instance of a subdev driver should create this struct, either * stand-alone or embedded in a larger struct. @@ -916,6 +922,19 @@ struct v4l2_subdev { struct v4l2_async_notifier *notifier; struct v4l2_async_notifier *subdev_notifier; struct v4l2_subdev_platform_data *pdata; + + /* + * The fields below are private, and should only be accessed via + * appropriate functions. + */ + + /* + * TODO: active_state should most likely be changed from a pointer to an + * embedded field. For the time being it's kept as a pointer to more + * easily catch uses of active_state in the cases where the driver + * doesn't support it. + */ + struct v4l2_subdev_state *active_state; }; @@ -1141,6 +1160,45 @@ struct v4l2_subdev_state *__v4l2_subdev_state_alloc(struct v4l2_subdev *sd); */ void __v4l2_subdev_state_free(struct v4l2_subdev_state *state); +/** + * v4l2_subdev_init_finalize() - Finalizes the initialization of the subdevice + * @sd: The subdev + * + * This function finalizes the initialization of the subdev, including + * allocation of the active state for the subdev. + * + * This function must be called by the subdev drivers that use the centralized + * active state, after the subdev struct has been initialized and + * media_entity_pads_init() has been called, but before registering the + * subdev. + * + * The user must call v4l2_subdev_cleanup() when the subdev is being removed. + */ +int v4l2_subdev_init_finalize(struct v4l2_subdev *sd); + +/** + * v4l2_subdev_cleanup() - Releases the resources allocated by the subdevice + * @sd: The subdevice + * + * This function will release the resources allocated in + * v4l2_subdev_init_finalize. + */ +void v4l2_subdev_cleanup(struct v4l2_subdev *sd); + +/** + * v4l2_subdev_get_active_state() - Returns the active subdev state for + * subdevice + * @sd: The subdevice + * + * Returns the active state for the subdevice, or NULL if the subdev does not + * support active state. + */ +static inline struct v4l2_subdev_state * +v4l2_subdev_get_active_state(struct v4l2_subdev *sd) +{ + return sd->active_state; +} + #endif /* CONFIG_MEDIA_CONTROLLER */ /** -- cgit v1.2.3 From 2f91838c3b717b4b0b5dab005a7e50d3933bbdcd Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:44 +0100 Subject: media: subdev: rename v4l2_subdev_get_pad_* helpers The subdev state is now used for both try and active cases. Rename rename v4l2_subdev_get_try_* helpers to v4l2_subdev_get_pad_*. Temporary wapper helper macros are added to keep the drivers using v4l2_subdev_get_try_* compiling. The next step is to change the uses in th drivers, and then drop the helpers. Signed-off-by: Tomi Valkeinen Reviewed-by: Hans Verkuil Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index d0d0e4caf893..eab8e4342613 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -989,7 +989,7 @@ struct v4l2_subdev_fh { #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API) /** - * v4l2_subdev_get_try_format - ancillary routine to call + * v4l2_subdev_get_pad_format - ancillary routine to call * &struct v4l2_subdev_pad_config->try_fmt * * @sd: pointer to &struct v4l2_subdev @@ -997,7 +997,7 @@ struct v4l2_subdev_fh { * @pad: index of the pad in the &struct v4l2_subdev_state->pads array */ static inline struct v4l2_mbus_framefmt * -v4l2_subdev_get_try_format(struct v4l2_subdev *sd, +v4l2_subdev_get_pad_format(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { @@ -1007,7 +1007,7 @@ v4l2_subdev_get_try_format(struct v4l2_subdev *sd, } /** - * v4l2_subdev_get_try_crop - ancillary routine to call + * v4l2_subdev_get_pad_crop - ancillary routine to call * &struct v4l2_subdev_pad_config->try_crop * * @sd: pointer to &struct v4l2_subdev @@ -1015,7 +1015,7 @@ v4l2_subdev_get_try_format(struct v4l2_subdev *sd, * @pad: index of the pad in the &struct v4l2_subdev_state->pads array. */ static inline struct v4l2_rect * -v4l2_subdev_get_try_crop(struct v4l2_subdev *sd, +v4l2_subdev_get_pad_crop(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { @@ -1025,7 +1025,7 @@ v4l2_subdev_get_try_crop(struct v4l2_subdev *sd, } /** - * v4l2_subdev_get_try_compose - ancillary routine to call + * v4l2_subdev_get_pad_compose - ancillary routine to call * &struct v4l2_subdev_pad_config->try_compose * * @sd: pointer to &struct v4l2_subdev @@ -1033,7 +1033,7 @@ v4l2_subdev_get_try_crop(struct v4l2_subdev *sd, * @pad: index of the pad in the &struct v4l2_subdev_state->pads array. */ static inline struct v4l2_rect * -v4l2_subdev_get_try_compose(struct v4l2_subdev *sd, +v4l2_subdev_get_pad_compose(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { @@ -1042,6 +1042,19 @@ v4l2_subdev_get_try_compose(struct v4l2_subdev *sd, return &state->pads[pad].try_compose; } +/* + * Temprary helpers until uses of v4l2_subdev_get_try_* functions have been + * renamed + */ +#define v4l2_subdev_get_try_format(sd, state, pad) \ + v4l2_subdev_get_pad_format(sd, state, pad) + +#define v4l2_subdev_get_try_crop(sd, state, pad) \ + v4l2_subdev_get_pad_crop(sd, state, pad) + +#define v4l2_subdev_get_try_compose(sd, state, pad) \ + v4l2_subdev_get_pad_compose(sd, state, pad) + #endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */ extern const struct v4l2_file_operations v4l2_subdev_fops; -- cgit v1.2.3 From ed647ea668fb27cd21408d5cb7cc7d4c30417332 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:46 +0100 Subject: media: subdev: add subdev state locking The V4L2 subdevs have managed without centralized locking for the state (previously pad_config), as the try-state is supposedly safe (although I believe two TRY ioctls for the same fd would race), and the active-state, and its locking, is managed by the drivers internally. We now have active-state in a centralized position, and need locking. Strictly speaking the locking is only needed for new drivers that use the new state, as the current drivers continue behaving as they used to. However, active-state locking is complicated by the fact that currently the real active-state of a subdev is split into multiple parts: the new v4l2_subdev_state, subdev control state, and subdev's internal state. In the future all these three states should be combined into one state (the v4l2_subdev_state), and then a single lock for the state should be sufficient. But to solve the current split-state situation we need to share locks between the three states. This is accomplished by using the same lock management as the control handler does: we use a pointer to a mutex, allowing the driver to override the default mutex. Thus the driver can do e.g.: sd->state_lock = sd->ctrl_handler->lock; before calling v4l2_subdev_init_finalize(), resulting in sharing the same lock between the states and the controls. The locking model for active-state is such that any subdev op that gets the state as a parameter expects the state to be already locked by the caller, and expects the caller to release the lock. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Reviewed-by: Hans Verkuil Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 133 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 127 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index eab8e4342613..f967c27e41c3 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -658,6 +658,8 @@ struct v4l2_subdev_pad_config { /** * struct v4l2_subdev_state - Used for storing subdev state information. * + * @_lock: default for 'lock' + * @lock: mutex for the state. May be replaced by the user. * @pads: &struct v4l2_subdev_pad_config array * * This structure only needs to be passed to the pad op if the 'which' field @@ -665,6 +667,9 @@ struct v4l2_subdev_pad_config { * %V4L2_SUBDEV_FORMAT_ACTIVE it is safe to pass %NULL. */ struct v4l2_subdev_state { + /* lock for the struct v4l2_subdev_state fields */ + struct mutex _lock; + struct mutex *lock; struct v4l2_subdev_pad_config *pads; }; @@ -888,6 +893,9 @@ struct v4l2_subdev_platform_data { * @subdev_notifier: A sub-device notifier implicitly registered for the sub- * device using v4l2_async_register_subdev_sensor(). * @pdata: common part of subdevice platform data + * @state_lock: A pointer to a lock used for all the subdev's states, set by the + * driver. This is optional. If NULL, each state instance will get + * a lock of its own. * @active_state: Active state for the subdev (NULL for subdevs tracking the * state internally). Initialized by calling * v4l2_subdev_init_finalize(). @@ -922,6 +930,7 @@ struct v4l2_subdev { struct v4l2_async_notifier *notifier; struct v4l2_async_notifier *subdev_notifier; struct v4l2_subdev_platform_data *pdata; + struct mutex *state_lock; /* * The fields below are private, and should only be accessed via @@ -1157,12 +1166,16 @@ int v4l2_subdev_link_validate(struct media_link *link); * __v4l2_subdev_state_alloc - allocate v4l2_subdev_state * * @sd: pointer to &struct v4l2_subdev for which the state is being allocated. + * @lock_name: name of the state lock + * @key: lock_class_key for the lock * * Must call __v4l2_subdev_state_free() when state is no longer needed. * * Not to be called directly by the drivers. */ -struct v4l2_subdev_state *__v4l2_subdev_state_alloc(struct v4l2_subdev *sd); +struct v4l2_subdev_state *__v4l2_subdev_state_alloc(struct v4l2_subdev *sd, + const char *lock_name, + struct lock_class_key *key); /** * __v4l2_subdev_state_free - free a v4l2_subdev_state @@ -1187,7 +1200,16 @@ void __v4l2_subdev_state_free(struct v4l2_subdev_state *state); * * The user must call v4l2_subdev_cleanup() when the subdev is being removed. */ -int v4l2_subdev_init_finalize(struct v4l2_subdev *sd); +#define v4l2_subdev_init_finalize(sd) \ + ({ \ + static struct lock_class_key __key; \ + const char *name = KBUILD_BASENAME \ + ":" __stringify(__LINE__) ":sd->active_state->lock"; \ + __v4l2_subdev_init_finalize(sd, name, &__key); \ + }) + +int __v4l2_subdev_init_finalize(struct v4l2_subdev *sd, const char *name, + struct lock_class_key *key); /** * v4l2_subdev_cleanup() - Releases the resources allocated by the subdevice @@ -1199,16 +1221,85 @@ int v4l2_subdev_init_finalize(struct v4l2_subdev *sd); void v4l2_subdev_cleanup(struct v4l2_subdev *sd); /** - * v4l2_subdev_get_active_state() - Returns the active subdev state for - * subdevice + * v4l2_subdev_lock_state() - Locks the subdev state + * @state: The subdevice state + * + * Locks the given subdev state. + * + * The state must be unlocked with v4l2_subdev_unlock_state() after use. + */ +static inline void v4l2_subdev_lock_state(struct v4l2_subdev_state *state) +{ + mutex_lock(state->lock); +} + +/** + * v4l2_subdev_unlock_state() - Unlocks the subdev state + * @state: The subdevice state + * + * Unlocks the given subdev state. + */ +static inline void v4l2_subdev_unlock_state(struct v4l2_subdev_state *state) +{ + mutex_unlock(state->lock); +} + +/** + * v4l2_subdev_get_unlocked_active_state() - Checks that the active subdev state + * is unlocked and returns it + * @sd: The subdevice + * + * Returns the active state for the subdevice, or NULL if the subdev does not + * support active state. If the state is not NULL, calls + * lockdep_assert_not_held() to issue a warning if the state is locked. + * + * This function is to be used e.g. when getting the active state for the sole + * purpose of passing it forward, without accessing the state fields. + */ +static inline struct v4l2_subdev_state * +v4l2_subdev_get_unlocked_active_state(struct v4l2_subdev *sd) +{ + if (sd->active_state) + lockdep_assert_not_held(sd->active_state->lock); + return sd->active_state; +} + +/** + * v4l2_subdev_get_locked_active_state() - Checks that the active subdev state + * is locked and returns it + * * @sd: The subdevice * * Returns the active state for the subdevice, or NULL if the subdev does not - * support active state. + * support active state. If the state is not NULL, calls lockdep_assert_held() + * to issue a warning if the state is not locked. + * + * This function is to be used when the caller knows that the active state is + * already locked. + */ +static inline struct v4l2_subdev_state * +v4l2_subdev_get_locked_active_state(struct v4l2_subdev *sd) +{ + if (sd->active_state) + lockdep_assert_held(sd->active_state->lock); + return sd->active_state; +} + +/** + * v4l2_subdev_lock_and_get_active_state() - Locks and returns the active subdev + * state for the subdevice + * @sd: The subdevice + * + * Returns the locked active state for the subdevice, or NULL if the subdev + * does not support active state. + * + * The state must be unlocked with v4l2_subdev_unlock_state() after use. */ static inline struct v4l2_subdev_state * -v4l2_subdev_get_active_state(struct v4l2_subdev *sd) +v4l2_subdev_lock_and_get_active_state(struct v4l2_subdev *sd) { + if (sd->active_state) + v4l2_subdev_lock_state(sd->active_state); return sd->active_state; } @@ -1255,6 +1346,36 @@ extern const struct v4l2_subdev_ops v4l2_subdev_call_wrappers; __result; \ }) +/** + * v4l2_subdev_call_state_active - call an operation of a v4l2_subdev which + * takes state as a parameter, passing the + * subdev its active state. + * + * @sd: pointer to the &struct v4l2_subdev + * @o: name of the element at &struct v4l2_subdev_ops that contains @f. + * Each element there groups a set of callbacks functions. + * @f: callback function to be called. + * The callback functions are defined in groups, according to + * each element at &struct v4l2_subdev_ops. + * @args: arguments for @f. + * + * This is similar to v4l2_subdev_call(), except that this version can only be + * used for ops that take a subdev state as a parameter. The macro will get the + * active state, lock it before calling the op and unlock it after the call. + */ +#define v4l2_subdev_call_state_active(sd, o, f, args...) \ + ({ \ + int __result; \ + struct v4l2_subdev_state *state; \ + state = v4l2_subdev_get_unlocked_active_state(sd); \ + if (state) \ + v4l2_subdev_lock_state(state); \ + __result = v4l2_subdev_call(sd, o, f, state, ##args); \ + if (state) \ + v4l2_subdev_unlock_state(state); \ + __result; \ + }) + /** * v4l2_subdev_has_op - Checks if a subdev defines a certain operation. * -- cgit v1.2.3 From 14a6fca77ad122208a6db10e2abda2d7369c48a4 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:48 +0100 Subject: media: subdev: add v4l2_subdev_get_fmt() helper function Add v4l2_subdev_get_fmt() helper function which implements v4l2_subdev_pad_ops.get_fmt using active state. Subdev drivers that support active state and do not need to do anything special in their get_fmt op can use this helper directly for v4l2_subdev_pad_ops.get_fmt. Signed-off-by: Tomi Valkeinen Reviewed-by: Hans Verkuil Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index f967c27e41c3..33a7201edb61 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -1303,6 +1303,27 @@ v4l2_subdev_lock_and_get_active_state(struct v4l2_subdev *sd) return sd->active_state; } +#if defined(CONFIG_VIDEO_V4L2_SUBDEV_API) + +/** + * v4l2_subdev_get_fmt() - Fill format based on state + * @sd: subdevice + * @state: subdevice state + * @format: pointer to &struct v4l2_subdev_format + * + * Fill @format->format field based on the information in the @format struct. + * + * This function can be used by the subdev drivers which support active state to + * implement v4l2_subdev_pad_ops.get_fmt if the subdev driver does not need to + * do anything special in their get_fmt op. + * + * Returns 0 on success, error value otherwise. + */ +int v4l2_subdev_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, + struct v4l2_subdev_format *format); + +#endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */ + #endif /* CONFIG_MEDIA_CONTROLLER */ /** -- cgit v1.2.3 From 4d19e0662fcc9e2f3bdada2c4e45dab36bd64a71 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 13 Mar 2022 16:04:57 +0000 Subject: media: i2c: cleanup comments For spdx, remove leading space Replacements parametrize to parameterize Signed-off-by: Tom Rix Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/i2c/mt9t112.h | 2 +- include/media/i2c/wm8775.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/i2c/mt9t112.h b/include/media/i2c/mt9t112.h index e678b6ae8e2f..825b4a169da8 100644 --- a/include/media/i2c/mt9t112.h +++ b/include/media/i2c/mt9t112.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 */ /* mt9t112 Camera * * Copyright (C) 2009 Renesas Solutions Corp. diff --git a/include/media/i2c/wm8775.h b/include/media/i2c/wm8775.h index 83675817639e..6ccdeb3817ab 100644 --- a/include/media/i2c/wm8775.h +++ b/include/media/i2c/wm8775.h @@ -23,7 +23,7 @@ struct wm8775_platform_data { /* - * FIXME: Instead, we should parametrize the params + * FIXME: Instead, we should parameterize the params * that need different settings between ivtv, pvrusb2, and Nova-S */ bool is_nova_s; -- cgit v1.2.3 From 3d22dd432889f2f538b53f36f9f6bcd54825fc22 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 28 Mar 2022 17:01:53 +0100 Subject: media: media.h: remove unneeded inclusion Commit b3b7a9f138b7 ("[media] media-device: Use u64 ints for pointers") added this #include , presumably in order to use uintptr_t. Now that it is gone, we can compile this for userspace without . Signed-off-by: Masahiro Yamada Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index afbae7213d35..3ddadaea849f 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -20,9 +20,6 @@ #ifndef __LINUX_MEDIA_H #define __LINUX_MEDIA_H -#ifndef __KERNEL__ -#include -#endif #include #include -- cgit v1.2.3 From 3c9b04d9631ef49e8b3aad72607b09099c18e40d Mon Sep 17 00:00:00 2001 From: Ian Jamison Date: Fri, 8 Apr 2022 18:53:45 +0100 Subject: media: media-entity.h: Fix documentation for media_create_intf_link The documentation comment was inserted between the return type and the function name. Reunite the lines. Signed-off-by: Ian Jamison Fixes: db7ee32aa185 ("[media] media-device.h: Improve documentation and update it") Reviewed-by: Kieran Bingham Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/media-entity.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 1d13b8939a11..a9a1c0ec5d1c 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -1030,7 +1030,6 @@ __must_check media_devnode_create(struct media_device *mdev, * removed. */ void media_devnode_remove(struct media_intf_devnode *devnode); -struct media_link * /** * media_create_intf_link() - creates a link between an entity and an interface @@ -1061,6 +1060,7 @@ struct media_link * * the interface and media_device_register_entity() should be called for the * interface that will be part of the link. */ +struct media_link * __must_check media_create_intf_link(struct media_entity *entity, struct media_interface *intf, u32 flags); -- cgit v1.2.3 From 2308d5aff8d083a44aa02197d2f5687b73d98f82 Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Thu, 3 Mar 2022 15:06:31 +0000 Subject: media: v4l: Add Qualcomm custom compressed pixel formats Add custom Qualcomm raw compressed pixel formats. They are used in Qualcomm SoCs to optimize the interconnect bandwidth. Signed-off-by: Stanimir Varbanov Acked-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 3768a0a80830..6d465dc443b7 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -746,6 +746,8 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_INZI v4l2_fourcc('I', 'N', 'Z', 'I') /* Intel Planar Greyscale 10-bit and Depth 16-bit */ #define V4L2_PIX_FMT_CNF4 v4l2_fourcc('C', 'N', 'F', '4') /* Intel 4-bit packed depth confidence information */ #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* BTTV 8-bit dithered RGB */ +#define V4L2_PIX_FMT_QC08C v4l2_fourcc('Q', '0', '8', 'C') /* Qualcomm 8-bit compressed */ +#define V4L2_PIX_FMT_QC10C v4l2_fourcc('Q', '1', '0', 'C') /* Qualcomm 10-bit compressed */ /* 10bit raw bayer packed, 32 bytes for every 25 pixels, last LSB 6 bits unused */ #define V4L2_PIX_FMT_IPU3_SBGGR10 v4l2_fourcc('i', 'p', '3', 'b') /* IPU3 packed 10-bit BGGR bayer */ -- cgit v1.2.3 From fcbc4acf8b8dff5fc420a14026bd4ab1798cf465 Mon Sep 17 00:00:00 2001 From: Dikshita Agarwal Date: Tue, 19 Apr 2022 06:06:42 +0100 Subject: media: v4l2-ctrls: Add intra-refresh type control Add a control to set intra-refresh type. Signed-off-by: Dikshita Agarwal Reviewed-by: Nicolas Dufresne Acked-by: Hans Verkuil Signed-off-by: Stanimir Varbanov Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-controls.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index bb40129446d4..dfff69ed88f7 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -449,6 +449,11 @@ enum v4l2_mpeg_video_multi_slice_mode { #define V4L2_CID_MPEG_VIDEO_USE_LTR_FRAMES (V4L2_CID_CODEC_BASE+234) #define V4L2_CID_MPEG_VIDEO_DEC_CONCEAL_COLOR (V4L2_CID_CODEC_BASE+235) #define V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD (V4L2_CID_CODEC_BASE+236) +#define V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE (V4L2_CID_CODEC_BASE+237) +enum v4l2_mpeg_video_intra_refresh_period_type { + V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_RANDOM = 0, + V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_CYCLIC = 1, +}; /* CIDs for the MPEG-2 Part 2 (H.262) codec */ #define V4L2_CID_MPEG_VIDEO_MPEG2_LEVEL (V4L2_CID_CODEC_BASE+270) -- cgit v1.2.3 From 8e29da69feade64ec7fe9e1a2824b967c5183a21 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Apr 2022 10:44:00 -0600 Subject: io_uring: add support for IORING_ASYNC_CANCEL_ALL The current cancelation will lookup and cancel the first request it finds based on the key passed in. Add a flag that allows to cancel any request that matches they key. It completes with the number of requests found and canceled, or res < 0 if an error occured. Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/20220418164402.75259-4-axboe@kernel.dk --- include/uapi/linux/io_uring.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 1845cf7c80ba..476e58a2837f 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -187,6 +187,13 @@ enum { #define IORING_POLL_UPDATE_EVENTS (1U << 1) #define IORING_POLL_UPDATE_USER_DATA (1U << 2) +/* + * ASYNC_CANCEL flags. + * + * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key + */ +#define IORING_ASYNC_CANCEL_ALL (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ -- cgit v1.2.3 From 4bf94615b8886305199ed5755cb72fea88258d15 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Apr 2022 10:44:01 -0600 Subject: io_uring: allow IORING_OP_ASYNC_CANCEL with 'fd' key Currently sqe->addr must contain the user_data of the request being canceled. Introduce the IORING_ASYNC_CANCEL_FD flag, which tells the kernel that we're keying off the file fd instead for cancelation. This allows canceling any request that a) uses a file, and b) was assigned the file based on the value being passed in. Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/20220418164402.75259-5-axboe@kernel.dk --- include/uapi/linux/io_uring.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 476e58a2837f..cc7fe82a1798 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -191,8 +191,11 @@ enum { * ASYNC_CANCEL flags. * * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key + * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the + * request 'user_data' */ #define IORING_ASYNC_CANCEL_ALL (1U << 0) +#define IORING_ASYNC_CANCEL_FD (1U << 1) /* * IO completion data structure (Completion Queue Entry) -- cgit v1.2.3 From 970f256edb8c1259c8ed48d52b38215135396126 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Apr 2022 10:44:02 -0600 Subject: io_uring: add support for IORING_ASYNC_CANCEL_ANY Rather than match on a specific key, be it user_data or file, allow canceling any request that we can lookup. Works like IORING_ASYNC_CANCEL_ALL in that it cancels multiple requests, but it doesn't key off user_data or the file. Can't be set with IORING_ASYNC_CANCEL_FD, as that's a key selector. Only one may be used at the time. Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/20220418164402.75259-6-axboe@kernel.dk Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index cc7fe82a1798..980d82eb196e 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -193,9 +193,11 @@ enum { * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the * request 'user_data' + * IORING_ASYNC_CANCEL_ANY Match any request */ #define IORING_ASYNC_CANCEL_ALL (1U << 0) #define IORING_ASYNC_CANCEL_FD (1U << 1) +#define IORING_ASYNC_CANCEL_ANY (1U << 2) /* * IO completion data structure (Completion Queue Entry) -- cgit v1.2.3 From 47894438e916ca3fe44db33c2d4a1670fd296d6f Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 21 Apr 2022 02:13:40 -0700 Subject: io_uring: add trace support for CQE overflow Add trace function for overflowing CQ ring. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220421091345.2115755-2-dylany@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 42 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index cddf5b6fbeb4..42534ec2ab9d 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -530,7 +530,7 @@ TRACE_EVENT(io_uring_req_failed, ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", __entry->ctx, __entry->req, __entry->user_data, @@ -543,6 +543,46 @@ TRACE_EVENT(io_uring_req_failed, (unsigned long long) __entry->pad2, __entry->error) ); + +/* + * io_uring_cqe_overflow - a CQE overflowed + * + * @ctx: pointer to a ring context structure + * @user_data: user data associated with the request + * @res: CQE result + * @cflags: CQE flags + * @ocqe: pointer to the overflow cqe (if available) + * + */ +TRACE_EVENT(io_uring_cqe_overflow, + + TP_PROTO(void *ctx, unsigned long long user_data, s32 res, u32 cflags, + void *ocqe), + + TP_ARGS(ctx, user_data, res, cflags, ocqe), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( unsigned long long, user_data ) + __field( s32, res ) + __field( u32, cflags ) + __field( void *, ocqe ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->user_data = user_data; + __entry->res = res; + __entry->cflags = cflags; + __entry->ocqe = ocqe; + ), + + TP_printk("ring %p, user_data 0x%llx, res %d, flags %x, " + "overflow_cqe %p", + __entry->ctx, __entry->user_data, __entry->res, + __entry->cflags, __entry->ocqe) +); + #endif /* _TRACE_IO_URING_H */ /* This part must be outside protection */ -- cgit v1.2.3 From e9621e2bec80fe63f677a759066a5089b292f43a Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Wed, 23 Mar 2022 08:44:19 -0700 Subject: io_uring: add fsetxattr and setxattr support This adds support to io_uring for the fsetxattr and setxattr API. Signed-off-by: Stefan Roesch Acked-by: Christian Brauner Link: https://lore.kernel.org/r/20220323154420.3301504-4-shr@fb.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 980d82eb196e..864bd6a4d4ff 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -45,6 +45,7 @@ struct io_uring_sqe { __u32 rename_flags; __u32 unlink_flags; __u32 hardlink_flags; + __u32 xattr_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -60,7 +61,8 @@ struct io_uring_sqe { __s32 splice_fd_in; __u32 file_index; }; - __u64 __pad2[2]; + __u64 addr3; + __u64 __pad2[1]; }; enum { @@ -145,6 +147,8 @@ enum { IORING_OP_SYMLINKAT, IORING_OP_LINKAT, IORING_OP_MSG_RING, + IORING_OP_FSETXATTR, + IORING_OP_SETXATTR, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3 From a56834e0fafe0adf7f22a28a5dbec3e8c3031a0e Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Wed, 23 Mar 2022 08:44:20 -0700 Subject: io_uring: add fgetxattr and getxattr support This adds support to io_uring for the fgetxattr and getxattr API. Signed-off-by: Stefan Roesch Acked-by: Christian Brauner Link: https://lore.kernel.org/r/20220323154420.3301504-5-shr@fb.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 864bd6a4d4ff..8ca1d9ae56d6 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -149,6 +149,8 @@ enum { IORING_OP_MSG_RING, IORING_OP_FSETXATTR, IORING_OP_SETXATTR, + IORING_OP_FGETXATTR, + IORING_OP_GETXATTR, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3 From 0200ce6a57c5de802f4e438485c14cc9d63d5f4b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 24 Apr 2022 18:16:57 -0600 Subject: io_uring: fix trace for reduced sqe padding __pad2 is only 1 u64 now, the other one is addr3. Adjust the trace so that it matches up. Fixes: a56834e0fafe ("io_uring: add fgetxattr and getxattr support") Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 42534ec2ab9d..05b786f8b0bf 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -506,7 +506,7 @@ TRACE_EVENT(io_uring_req_failed, __field( u16, personality ) __field( u32, file_index ) __field( u64, pad1 ) - __field( u64, pad2 ) + __field( u64, addr3 ) __field( int, error ) ), @@ -525,14 +525,15 @@ TRACE_EVENT(io_uring_req_failed, __entry->personality = sqe->personality; __entry->file_index = sqe->file_index; __entry->pad1 = sqe->__pad2[0]; - __entry->pad2 = sqe->__pad2[1]; + __entry->addr3 = sqe->addr3; __entry->error = error; ), TP_printk("ring %p, req %p, user_data 0x%llx, " "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " - "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", + "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " + "error=%d", __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, @@ -540,7 +541,7 @@ TRACE_EVENT(io_uring_req_failed, __entry->op_flags, __entry->buf_index, __entry->personality, __entry->file_index, (unsigned long long) __entry->pad1, - (unsigned long long) __entry->pad2, __entry->error) + (unsigned long long) __entry->addr3, __entry->error) ); -- cgit v1.2.3 From da214a475f8bd1d3e9e7a19ddfeb4d1617551bab Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 Apr 2022 14:22:39 -0600 Subject: net: add __sys_socket_file() This works like __sys_socket(), except instead of allocating and returning a socket fd, it just returns the file associated with the socket. No fd is installed into the process file table. This is similar to do_accept(), and allows io_uring to use this without instantiating a file descriptor in the process file table. Signed-off-by: Jens Axboe Acked-by: David S. Miller Link: https://lore.kernel.org/r/20220412202240.234207-2-axboe@kernel.dk --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index 6f85f5d957ef..a1882e1e71d2 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -434,6 +434,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags, extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); +extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); -- cgit v1.2.3 From 1374e08e2d44863c931910797852589803997668 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 Apr 2022 14:22:40 -0600 Subject: io_uring: add socket(2) support Supports both regular socket(2) where a normal file descriptor is instantiated when called, or direct descriptors. Link: https://lore.kernel.org/r/20220412202240.234207-3-axboe@kernel.dk Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8ca1d9ae56d6..5fb52bf32435 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -151,6 +151,7 @@ enum { IORING_OP_SETXATTR, IORING_OP_FGETXATTR, IORING_OP_GETXATTR, + IORING_OP_SOCKET, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3 From 90715507cb899df6c726494c0225d30130ad0cc5 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Mon, 25 Apr 2022 15:41:55 +0900 Subject: dt-bindings: power: Add r8a779g0 SYSC power domain definitions Add power domain indices for R-Car V4H (r8a779g0). Signed-off-by: Yoshihiro Shimoda Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220425064201.459633-2-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/power/r8a779g0-sysc.h | 45 +++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 include/dt-bindings/power/r8a779g0-sysc.h (limited to 'include') diff --git a/include/dt-bindings/power/r8a779g0-sysc.h b/include/dt-bindings/power/r8a779g0-sysc.h new file mode 100644 index 000000000000..7daa70f1814e --- /dev/null +++ b/include/dt-bindings/power/r8a779g0-sysc.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (C) 2022 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_POWER_R8A779G0_SYSC_H__ +#define __DT_BINDINGS_POWER_R8A779G0_SYSC_H__ + +/* + * These power domain indices match the Power Domain Register Numbers (PDR) + */ + +#define R8A779G0_PD_A1E0D0C0 0 +#define R8A779G0_PD_A1E0D0C1 1 +#define R8A779G0_PD_A1E0D1C0 2 +#define R8A779G0_PD_A1E0D1C1 3 +#define R8A779G0_PD_A2E0D0 16 +#define R8A779G0_PD_A2E0D1 17 +#define R8A779G0_PD_A3E0 20 +#define R8A779G0_PD_A33DGA 24 +#define R8A779G0_PD_A23DGB 25 +#define R8A779G0_PD_A1DSP0 33 +#define R8A779G0_PD_A2IMP01 34 +#define R8A779G0_PD_A2PSC 35 +#define R8A779G0_PD_A2CV0 36 +#define R8A779G0_PD_A2CV1 37 +#define R8A779G0_PD_A1CNN0 41 +#define R8A779G0_PD_A2CN0 42 +#define R8A779G0_PD_A3IR 43 +#define R8A779G0_PD_A1DSP1 45 +#define R8A779G0_PD_A2IMP23 46 +#define R8A779G0_PD_A2DMA 47 +#define R8A779G0_PD_A2CV2 48 +#define R8A779G0_PD_A2CV3 49 +#define R8A779G0_PD_A1DSP2 53 +#define R8A779G0_PD_A1DSP3 54 +#define R8A779G0_PD_A3VIP0 56 +#define R8A779G0_PD_A3VIP1 57 +#define R8A779G0_PD_A3VIP2 58 +#define R8A779G0_PD_A3ISP0 60 +#define R8A779G0_PD_A3ISP1 61 + +/* Always-on power area */ +#define R8A779G0_PD_ALWAYS_ON 64 + +#endif /* __DT_BINDINGS_POWER_R8A779G0_SYSC_H__*/ -- cgit v1.2.3 From f2afa78d5a0c0b0b2461a5c532d7a84214a1b633 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Mon, 25 Apr 2022 15:41:56 +0900 Subject: dt-bindings: clock: Add r8a779g0 CPG Core Clock Definitions Add all Clock Pulse Generator Core Clock Outputs for the Renesas R-Car V4H (R8A779G0) SoC. Signed-off-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/20220425064201.459633-3-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/clock/r8a779g0-cpg-mssr.h | 90 +++++++++++++++++++++++++++ 1 file changed, 90 insertions(+) create mode 100644 include/dt-bindings/clock/r8a779g0-cpg-mssr.h (limited to 'include') diff --git a/include/dt-bindings/clock/r8a779g0-cpg-mssr.h b/include/dt-bindings/clock/r8a779g0-cpg-mssr.h new file mode 100644 index 000000000000..754c54a6eb06 --- /dev/null +++ b/include/dt-bindings/clock/r8a779g0-cpg-mssr.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (C) 2022 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_CLOCK_R8A779G0_CPG_MSSR_H__ +#define __DT_BINDINGS_CLOCK_R8A779G0_CPG_MSSR_H__ + +#include + +/* r8a779g0 CPG Core Clocks */ + +#define R8A779G0_CLK_ZX 0 +#define R8A779G0_CLK_ZS 1 +#define R8A779G0_CLK_ZT 2 +#define R8A779G0_CLK_ZTR 3 +#define R8A779G0_CLK_S0D2 4 +#define R8A779G0_CLK_S0D3 5 +#define R8A779G0_CLK_S0D4 6 +#define R8A779G0_CLK_S0D1_VIO 7 +#define R8A779G0_CLK_S0D2_VIO 8 +#define R8A779G0_CLK_S0D4_VIO 9 +#define R8A779G0_CLK_S0D8_VIO 10 +#define R8A779G0_CLK_S0D1_VC 11 +#define R8A779G0_CLK_S0D2_VC 12 +#define R8A779G0_CLK_S0D4_VC 13 +#define R8A779G0_CLK_S0D2_MM 14 +#define R8A779G0_CLK_S0D4_MM 15 +#define R8A779G0_CLK_S0D2_U3DG 16 +#define R8A779G0_CLK_S0D4_U3DG 17 +#define R8A779G0_CLK_S0D2_RT 18 +#define R8A779G0_CLK_S0D3_RT 19 +#define R8A779G0_CLK_S0D4_RT 20 +#define R8A779G0_CLK_S0D6_RT 21 +#define R8A779G0_CLK_S0D24_RT 22 +#define R8A779G0_CLK_S0D2_PER 23 +#define R8A779G0_CLK_S0D3_PER 24 +#define R8A779G0_CLK_S0D4_PER 25 +#define R8A779G0_CLK_S0D6_PER 26 +#define R8A779G0_CLK_S0D12_PER 27 +#define R8A779G0_CLK_S0D24_PER 28 +#define R8A779G0_CLK_S0D1_HSC 29 +#define R8A779G0_CLK_S0D2_HSC 30 +#define R8A779G0_CLK_S0D4_HSC 31 +#define R8A779G0_CLK_S0D2_CC 32 +#define R8A779G0_CLK_SVD1_IR 33 +#define R8A779G0_CLK_SVD2_IR 34 +#define R8A779G0_CLK_SVD1_VIP 35 +#define R8A779G0_CLK_SVD2_VIP 36 +#define R8A779G0_CLK_CL 37 +#define R8A779G0_CLK_CL16M 38 +#define R8A779G0_CLK_CL16M_MM 39 +#define R8A779G0_CLK_CL16M_RT 40 +#define R8A779G0_CLK_CL16M_PER 41 +#define R8A779G0_CLK_CL16M_HSC 42 +#define R8A779G0_CLK_Z0 43 +#define R8A779G0_CLK_ZB3 44 +#define R8A779G0_CLK_ZB3D2 45 +#define R8A779G0_CLK_ZB3D4 46 +#define R8A779G0_CLK_ZG 47 +#define R8A779G0_CLK_SD0H 48 +#define R8A779G0_CLK_SD0 49 +#define R8A779G0_CLK_RPC 50 +#define R8A779G0_CLK_RPCD2 51 +#define R8A779G0_CLK_MSO 52 +#define R8A779G0_CLK_CANFD 53 +#define R8A779G0_CLK_CSI 54 +#define R8A779G0_CLK_FRAY 55 +#define R8A779G0_CLK_IPC 56 +#define R8A779G0_CLK_SASYNCRT 57 +#define R8A779G0_CLK_SASYNCPERD1 58 +#define R8A779G0_CLK_SASYNCPERD2 59 +#define R8A779G0_CLK_SASYNCPERD4 60 +#define R8A779G0_CLK_VIOBUS 61 +#define R8A779G0_CLK_VIOBUSD2 62 +#define R8A779G0_CLK_VCBUS 63 +#define R8A779G0_CLK_VCBUSD2 64 +#define R8A779G0_CLK_DSIEXT 65 +#define R8A779G0_CLK_DSIREF 66 +#define R8A779G0_CLK_ADGH 67 +#define R8A779G0_CLK_OSC 68 +#define R8A779G0_CLK_ZR0 69 +#define R8A779G0_CLK_ZR1 70 +#define R8A779G0_CLK_ZR2 71 +#define R8A779G0_CLK_IMPA 72 +#define R8A779G0_CLK_IMPAD4 73 +#define R8A779G0_CLK_CPEX 74 +#define R8A779G0_CLK_CBFUSA 75 +#define R8A779G0_CLK_R 76 + +#endif /* __DT_BINDINGS_CLOCK_R8A779G0_CPG_MSSR_H__ */ -- cgit v1.2.3 From da32b5817253697671af961715517bfbb308a592 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Sat, 23 Apr 2022 11:07:49 +0100 Subject: mm: Add fault_in_subpage_writeable() to probe at sub-page granularity On hardware with features like arm64 MTE or SPARC ADI, an access fault can be triggered at sub-page granularity. Depending on how the fault_in_writeable() function is used, the caller can get into a live-lock by continuously retrying the fault-in on an address different from the one where the uaccess failed. In the majority of cases progress is ensured by the following conditions: 1. copy_to_user_nofault() guarantees at least one byte access if the user address is not faulting. 2. The fault_in_writeable() loop is resumed from the first address that could not be accessed by copy_to_user_nofault(). If the loop iteration is restarted from an earlier (initial) point, the loop is repeated with the same conditions and it would live-lock. Introduce an arch-specific probe_subpage_writeable() and call it from the newly added fault_in_subpage_writeable() function. The arch code with sub-page faults will have to implement the specific probing functionality. Note that no other fault_in_subpage_*() functions are added since they have no callers currently susceptible to a live-lock. Signed-off-by: Catalin Marinas Cc: Andrew Morton Link: https://lore.kernel.org/r/20220423100751.1870771-2-catalin.marinas@arm.com Signed-off-by: Catalin Marinas --- include/linux/pagemap.h | 1 + include/linux/uaccess.h | 22 ++++++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 993994cd943a..6165283bdb6f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1046,6 +1046,7 @@ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); +size_t fault_in_subpage_writeable(char __user *uaddr, size_t size); size_t fault_in_safe_writeable(const char __user *uaddr, size_t size); size_t fault_in_readable(const char __user *uaddr, size_t size); diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 546179418ffa..5a328cf02b75 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -231,6 +231,28 @@ static inline bool pagefault_disabled(void) */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) +#ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS + +/** + * probe_subpage_writeable: probe the user range for write faults at sub-page + * granularity (e.g. arm64 MTE) + * @uaddr: start of address range + * @size: size of address range + * + * Returns 0 on success, the number of bytes not probed on fault. + * + * It is expected that the caller checked for the write permission of each + * page in the range either by put_user() or GUP. The architecture port can + * implement a more efficient get_user() probing if the same sub-page faults + * are triggered by either a read or a write. + */ +static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) +{ + return 0; +} + +#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ + #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long -- cgit v1.2.3 From 8d92e4fbcf0fb7ecb24223b7b1ce95b9beb4dfa2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Apr 2022 06:44:21 +0300 Subject: devlink: introduce line card devices support Line card can contain one or more devices that makes sense to make visible to the user. For example, this can be a gearbox with flash memory, which could be updated. Provide the driver possibility to attach such devices to a line card and expose those to user. Example: $ devlink lc show pci/0000:01:00.0 lc 8 pci/0000:01:00.0: lc 8 state active type 16x100G supported_types: 16x100G devices: device 0 device 1 device 2 device 3 Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 7 +++++++ include/uapi/linux/devlink.h | 3 +++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 2a2a2a0c93f7..c84b52fb9ff0 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1578,6 +1578,13 @@ struct devlink_linecard * devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, const struct devlink_linecard_ops *ops, void *priv); void devlink_linecard_destroy(struct devlink_linecard *linecard); +struct devlink_linecard_device; +struct devlink_linecard_device * +devlink_linecard_device_create(struct devlink_linecard *linecard, + unsigned int device_index); +void +devlink_linecard_device_destroy(struct devlink_linecard *linecard, + struct devlink_linecard_device *linecard_device); void devlink_linecard_provision_set(struct devlink_linecard *linecard, const char *type); void devlink_linecard_provision_clear(struct devlink_linecard *linecard); diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index b3d40a5d72ff..cd578645f94f 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -575,6 +575,9 @@ enum devlink_attr { DEVLINK_ATTR_LINECARD_STATE, /* u8 */ DEVLINK_ATTR_LINECARD_TYPE, /* string */ DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES, /* nested */ + DEVLINK_ATTR_LINECARD_DEVICE_LIST, /* nested */ + DEVLINK_ATTR_LINECARD_DEVICE, /* nested */ + DEVLINK_ATTR_LINECARD_DEVICE_INDEX, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From 276910aecc6a4076f5fbfd8160ff70695d6c1eb5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Apr 2022 06:44:22 +0300 Subject: devlink: introduce line card info get message Allow the driver to provide per line card info get op to fill-up info, similar to the "devlink dev info". Example: $ devlink lc info pci/0000:01:00.0 lc 8 pci/0000:01:00.0: lc 8 versions: fixed: hw.revision 0 running: ini.version 4 Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 7 ++++++- include/uapi/linux/devlink.h | 2 ++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index c84b52fb9ff0..f96dcb376630 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -150,6 +150,8 @@ struct devlink_port_new_attrs { sfnum_valid:1; }; +struct devlink_info_req; + /** * struct devlink_linecard_ops - Linecard operations * @provision: callback to provision the linecard slot with certain @@ -168,6 +170,7 @@ struct devlink_port_new_attrs { * provisioned. * @types_count: callback to get number of supported types * @types_get: callback to get next type in list + * @info_get: callback to get linecard info */ struct devlink_linecard_ops { int (*provision)(struct devlink_linecard *linecard, void *priv, @@ -182,6 +185,9 @@ struct devlink_linecard_ops { void (*types_get)(struct devlink_linecard *linecard, void *priv, unsigned int index, const char **type, const void **type_priv); + int (*info_get)(struct devlink_linecard *linecard, void *priv, + struct devlink_info_req *req, + struct netlink_ext_ack *extack); }; struct devlink_sb_pool_info { @@ -628,7 +634,6 @@ struct devlink_flash_update_params { #define DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK BIT(1) struct devlink_region; -struct devlink_info_req; /** * struct devlink_region_ops - Region operations diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cd578645f94f..fb8c3864457f 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -136,6 +136,8 @@ enum devlink_command { DEVLINK_CMD_LINECARD_NEW, DEVLINK_CMD_LINECARD_DEL, + DEVLINK_CMD_LINECARD_INFO_GET, /* can dump */ + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 -- cgit v1.2.3 From 28b2d1f1ac41dda0b239830765d85c7ae4434182 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Apr 2022 06:44:23 +0300 Subject: devlink: introduce line card device info infrastructure Extend the line card info message with information (e.g., FW version) about devices found on the line card. Example: $ devlink lc info pci/0000:01:00.0 lc 8 pci/0000:01:00.0: lc 8 versions: fixed: hw.revision 0 running: ini.version 4 devices: device 0 versions: running: fw 19.2010.1310 device 1 versions: running: fw 19.2010.1310 device 2 versions: running: fw 19.2010.1310 device 3 versions: running: fw 19.2010.1310 Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index f96dcb376630..062895973656 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -151,6 +151,7 @@ struct devlink_port_new_attrs { }; struct devlink_info_req; +struct devlink_linecard_device; /** * struct devlink_linecard_ops - Linecard operations @@ -171,6 +172,7 @@ struct devlink_info_req; * @types_count: callback to get number of supported types * @types_get: callback to get next type in list * @info_get: callback to get linecard info + * @device_info_get: callback to get linecard device info */ struct devlink_linecard_ops { int (*provision)(struct devlink_linecard *linecard, void *priv, @@ -188,6 +190,9 @@ struct devlink_linecard_ops { int (*info_get)(struct devlink_linecard *linecard, void *priv, struct devlink_info_req *req, struct netlink_ext_ack *extack); + int (*device_info_get)(struct devlink_linecard_device *device, + void *priv, struct devlink_info_req *req, + struct netlink_ext_ack *extack); }; struct devlink_sb_pool_info { @@ -1583,10 +1588,9 @@ struct devlink_linecard * devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, const struct devlink_linecard_ops *ops, void *priv); void devlink_linecard_destroy(struct devlink_linecard *linecard); -struct devlink_linecard_device; struct devlink_linecard_device * devlink_linecard_device_create(struct devlink_linecard *linecard, - unsigned int device_index); + unsigned int device_index, void *priv); void devlink_linecard_device_destroy(struct devlink_linecard *linecard, struct devlink_linecard_device *linecard_device); -- cgit v1.2.3 From e8e7fbb6a39cd6761c843d97851eb40c5885e922 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 12 Apr 2022 11:49:43 +0200 Subject: PCI: Add PCI_EXP_SLTCTL_ASPL_DISABLE macro MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add macro defining Auto Slot Power Limit Disable bit in Slot Control Register. Link: https://lore.kernel.org/r/20220412094946.27069-2-pali@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Acked-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index bee1a9ed6e66..108f8523fa04 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -616,6 +616,7 @@ #define PCI_EXP_SLTCTL_PWR_OFF 0x0400 /* Power Off */ #define PCI_EXP_SLTCTL_EIC 0x0800 /* Electromechanical Interlock Control */ #define PCI_EXP_SLTCTL_DLLSCE 0x1000 /* Data Link Layer State Changed Enable */ +#define PCI_EXP_SLTCTL_ASPL_DISABLE 0x2000 /* Auto Slot Power Limit Disable */ #define PCI_EXP_SLTCTL_IBPD_DISABLE 0x4000 /* In-band PD disable */ #define PCI_EXP_SLTSTA 0x1a /* Slot Status */ #define PCI_EXP_SLTSTA_ABP 0x0001 /* Attention Button Pressed */ -- cgit v1.2.3 From 3c938cc5cebcbd2291fe97f523c0705a2c24c77d Mon Sep 17 00:00:00 2001 From: Schspa Shi Date: Tue, 19 Apr 2022 09:28:10 +0800 Subject: gpio: use raw spinlock for gpio chip shadowed data In case of PREEMPT_RT, there is a raw_spinlock -> spinlock dependency as the lockdep report shows. __irq_set_handler irq_get_desc_buslock __irq_get_desc_lock raw_spin_lock_irqsave(&desc->lock, *flags); // raw spinlock get here __irq_do_set_handler mask_ack_irq dwapb_irq_ack spin_lock_irqsave(&gc->bgpio_lock, flags); // sleep able spinlock irq_put_desc_busunlock Replace with a raw lock to avoid BUGs. This lock is only used to access registers, and It's safe to replace with the raw lock without bad influence. [ 15.090359][ T1] ============================= [ 15.090365][ T1] [ BUG: Invalid wait context ] [ 15.090373][ T1] 5.10.59-rt52-00983-g186a6841c682-dirty #3 Not tainted [ 15.090386][ T1] ----------------------------- [ 15.090392][ T1] swapper/0/1 is trying to lock: [ 15.090402][ T1] 70ff00018507c188 (&gc->bgpio_lock){....}-{3:3}, at: _raw_spin_lock_irqsave+0x1c/0x28 [ 15.090470][ T1] other info that might help us debug this: [ 15.090477][ T1] context-{5:5} [ 15.090485][ T1] 3 locks held by swapper/0/1: [ 15.090497][ T1] #0: c2ff0001816de1a0 (&dev->mutex){....}-{4:4}, at: __device_driver_lock+0x98/0x104 [ 15.090553][ T1] #1: ffff90001485b4b8 (irq_domain_mutex){+.+.}-{4:4}, at: irq_domain_associate+0xbc/0x6d4 [ 15.090606][ T1] #2: 4bff000185d7a8e0 (lock_class){....}-{2:2}, at: _raw_spin_lock_irqsave+0x1c/0x28 [ 15.090654][ T1] stack backtrace: [ 15.090661][ T1] CPU: 4 PID: 1 Comm: swapper/0 Not tainted 5.10.59-rt52-00983-g186a6841c682-dirty #3 [ 15.090682][ T1] Hardware name: Horizon Robotics Journey 5 DVB (DT) [ 15.090692][ T1] Call trace: ...... [ 15.090811][ T1] _raw_spin_lock_irqsave+0x1c/0x28 [ 15.090828][ T1] dwapb_irq_ack+0xb4/0x300 [ 15.090846][ T1] __irq_do_set_handler+0x494/0xb2c [ 15.090864][ T1] __irq_set_handler+0x74/0x114 [ 15.090881][ T1] irq_set_chip_and_handler_name+0x44/0x58 [ 15.090900][ T1] gpiochip_irq_map+0x210/0x644 Signed-off-by: Schspa Shi Reviewed-by: Andy Shevchenko Acked-by: Linus Walleij Acked-by: Doug Berger Acked-by: Serge Semin Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..991d374dcf71 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -436,7 +436,7 @@ struct gpio_chip { void __iomem *reg_dir_in; bool bgpio_dir_unreadable; int bgpio_bits; - spinlock_t bgpio_lock; + raw_spinlock_t bgpio_lock; unsigned long bgpio_data; unsigned long bgpio_dir; #endif /* CONFIG_GPIO_GENERIC */ -- cgit v1.2.3 From 38035c04f5865c4ef9597d6beed6a7178f90f64a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:13 +0300 Subject: inotify: move control flags from mask to mark flags The inotify control flags in the mark mask (e.g. FS_IN_ONE_SHOT) are not relevant to object interest mask, so move them to the mark flags. This frees up some bits in the object interest mask. Link: https://lore.kernel.org/r/20220422120327.3459282-3-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 0805b74cae44..b1c72edd9784 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -55,7 +55,6 @@ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ -#define FS_EXCL_UNLINK 0x04000000 /* do not send events if object is unlinked */ /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. @@ -66,7 +65,6 @@ #define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ -#define FS_IN_ONESHOT 0x80000000 /* only send event once */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) @@ -106,8 +104,7 @@ FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ -#define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ - FS_DN_MULTISHOT | FS_EVENT_ON_CHILD) +#define ALL_FSNOTIFY_FLAGS (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) @@ -473,9 +470,14 @@ struct fsnotify_mark { struct fsnotify_mark_connector *connector; /* Events types to ignore [mark->lock, group->mark_mutex] */ __u32 ignored_mask; -#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x01 -#define FSNOTIFY_MARK_FLAG_ALIVE 0x02 -#define FSNOTIFY_MARK_FLAG_ATTACHED 0x04 + /* General fsnotify mark flags */ +#define FSNOTIFY_MARK_FLAG_ALIVE 0x0001 +#define FSNOTIFY_MARK_FLAG_ATTACHED 0x0002 + /* inotify mark flags */ +#define FSNOTIFY_MARK_FLAG_EXCL_UNLINK 0x0010 +#define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 + /* fanotify mark flags */ +#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 unsigned int flags; /* flags [mark->lock] */ }; -- cgit v1.2.3 From 867a448d587e7fa845bceaf4ee1c632448f2a9fa Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:15 +0300 Subject: fsnotify: pass flags argument to fsnotify_alloc_group() Add flags argument to fsnotify_alloc_group(), define and use the flag FSNOTIFY_GROUP_USER in inotify and fanotify instead of the helper fsnotify_alloc_user_group() to indicate user allocation. Although the flag FSNOTIFY_GROUP_USER is currently not used after group allocation, we store the flags argument in the group struct for future use of other group flags. Link: https://lore.kernel.org/r/20220422120327.3459282-5-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b1c72edd9784..f0bf557af009 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -210,6 +210,9 @@ struct fsnotify_group { unsigned int priority; bool shutdown; /* group is being shut down, don't queue more events */ +#define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ + int flags; + /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t user_waits; /* Number of tasks waiting for user @@ -543,8 +546,9 @@ static inline void fsnotify_update_flags(struct dentry *dentry) /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ -extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops); -extern struct fsnotify_group *fsnotify_alloc_user_group(const struct fsnotify_ops *ops); +extern struct fsnotify_group *fsnotify_alloc_group( + const struct fsnotify_ops *ops, + int flags); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ -- cgit v1.2.3 From f3010343d9e119da35ee864b3a28993bb5c78ed7 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:16 +0300 Subject: fsnotify: make allow_dups a property of the group Instead of passing the allow_dups argument to fsnotify_add_mark() as an argument, define the group flag FSNOTIFY_GROUP_DUPS to express the allow_dups behavior and set this behavior at group creation time for all calls of fsnotify_add_mark(). Rename the allow_dups argument to generic add_flags argument for future use. Link: https://lore.kernel.org/r/20220422120327.3459282-6-amir73il@gmail.com Suggested-by: Jan Kara Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index f0bf557af009..dd440e6ff528 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -211,6 +211,7 @@ struct fsnotify_group { bool shutdown; /* group is being shut down, don't queue more events */ #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ +#define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ int flags; /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ @@ -641,26 +642,26 @@ extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn, /* attach the mark to the object */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, - int allow_dups, __kernel_fsid_t *fsid); + int add_flags, __kernel_fsid_t *fsid); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, - unsigned int obj_type, int allow_dups, + unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, - int allow_dups) + int add_flags) { return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, allow_dups, NULL); + FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, - int allow_dups) + int add_flags) { return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, allow_dups, + FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } -- cgit v1.2.3 From 43b245a788e2d8f1bb742668a9bdace02fcb3e96 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:17 +0300 Subject: fsnotify: create helpers for group mark_mutex lock Create helpers to take and release the group mark_mutex lock. Define a flag FSNOTIFY_GROUP_NOFS in fsnotify_group that determines if the mark_mutex lock is fs reclaim safe or not. If not safe, the lock helpers take the lock and disable direct fs reclaim. In that case we annotate the mutex with a different lockdep class to express to lockdep that an allocation of mark of an fs reclaim safe group may take the group lock of another "NOFS" group to evict inodes. For now, converted only the callers in common code and no backend defines the NOFS flag. It is intended to be set by fanotify for evictable marks support. Link: https://lore.kernel.org/r/20220422120327.3459282-7-amir73il@gmail.com Suggested-by: Jan Kara Link: https://lore.kernel.org/r/20220321112310.vpr7oxro2xkz5llh@quack3.lan/ Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index dd440e6ff528..d62111e83244 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -20,6 +20,7 @@ #include #include #include +#include /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily @@ -212,7 +213,9 @@ struct fsnotify_group { #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ #define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ +#define FSNOTIFY_GROUP_NOFS 0x04 /* group lock is not direct reclaim safe */ int flags; + unsigned int owner_flags; /* stored flags of mark_mutex owner */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ @@ -254,6 +257,31 @@ struct fsnotify_group { }; }; +/* + * These helpers are used to prevent deadlock when reclaiming inodes with + * evictable marks of the same group that is allocating a new mark. + */ +static inline void fsnotify_group_lock(struct fsnotify_group *group) +{ + mutex_lock(&group->mark_mutex); + if (group->flags & FSNOTIFY_GROUP_NOFS) + group->owner_flags = memalloc_nofs_save(); +} + +static inline void fsnotify_group_unlock(struct fsnotify_group *group) +{ + if (group->flags & FSNOTIFY_GROUP_NOFS) + memalloc_nofs_restore(group->owner_flags); + mutex_unlock(&group->mark_mutex); +} + +static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) +{ + WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); + if (group->flags & FSNOTIFY_GROUP_NOFS) + WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); +} + /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, -- cgit v1.2.3 From c3638b5b13740fa31762d414bbce8b7a694e582a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:22 +0300 Subject: fsnotify: allow adding an inode mark without pinning inode fsnotify_add_mark() and variants implicitly take a reference on inode when attaching a mark to an inode. Make that behavior opt-out with the mark flag FSNOTIFY_MARK_FLAG_NO_IREF. Instead of taking the inode reference when attaching connector to inode and dropping the inode reference when detaching connector from inode, take the inode reference on attach of the first mark that wants to hold an inode reference and drop the inode reference on detach of the last mark that wants to hold an inode reference. Backends can "upgrade" an existing mark to take an inode reference, but cannot "downgrade" a mark with inode reference to release the refernce. This leaves the choice to the backend whether or not to pin the inode when adding an inode mark. This is intended to be used when adding a mark with ignored mask that is used for optimization in cases where group can afford getting unneeded events and reinstate the mark with ignored mask when inode is accessed again after being evicted. Link: https://lore.kernel.org/r/20220422120327.3459282-12-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index d62111e83244..9a1a9e78f69f 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -456,6 +456,7 @@ struct fsnotify_mark_connector { spinlock_t lock; unsigned short type; /* Type of object [lock] */ #define FSNOTIFY_CONN_FLAG_HAS_FSID 0x01 +#define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ __kernel_fsid_t fsid; /* fsid of filesystem containing object */ union { @@ -510,6 +511,7 @@ struct fsnotify_mark { #define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 /* fanotify mark flags */ #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 +#define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200 unsigned int flags; /* flags [mark->lock] */ }; -- cgit v1.2.3 From 7d5e005d982527e4029b0139823d179986e34cdc Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:25 +0300 Subject: fanotify: implement "evictable" inode marks When an inode mark is created with flag FAN_MARK_EVICTABLE, it will not pin the marked inode to inode cache, so when inode is evicted from cache due to memory pressure, the mark will be lost. When an inode mark with flag FAN_MARK_EVICATBLE is updated without using this flag, the marked inode is pinned to inode cache. When an inode mark is updated with flag FAN_MARK_EVICTABLE but an existing mark already has the inode pinned, the mark update fails with error EEXIST. Evictable inode marks can be used to setup inode marks with ignored mask to suppress events from uninteresting files or directories in a lazy manner, upon receiving the first event, without having to iterate all the uninteresting files or directories before hand. The evictbale inode mark feature allows performing this lazy marks setup without exhausting the system memory with pinned inodes. This change does not enable the feature yet. Link: https://lore.kernel.org/linux-fsdevel/CAOQ4uxiRDpuS=2uA6+ZUM7yG9vVU-u212tkunBmSnP_u=mkv=Q@mail.gmail.com/ Link: https://lore.kernel.org/r/20220422120327.3459282-15-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/uapi/linux/fanotify.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index e8ac38cc2fd6..f1f89132d60e 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -82,6 +82,7 @@ #define FAN_MARK_IGNORED_SURV_MODIFY 0x00000040 #define FAN_MARK_FLUSH 0x00000080 /* FAN_MARK_FILESYSTEM is 0x00000100 */ +#define FAN_MARK_EVICTABLE 0x00000200 /* These are NOT bitwise flags. Both bits can be used togther. */ #define FAN_MARK_INODE 0x00000000 -- cgit v1.2.3 From 5f9d3bd520261fd7a850818c71809fd580e0f30c Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:27 +0300 Subject: fanotify: enable "evictable" inode marks Now that the direct reclaim path is handled we can enable evictable inode marks. Link: https://lore.kernel.org/r/20220422120327.3459282-17-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 419cadcd7ff5..edc28555814c 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -66,6 +66,7 @@ FAN_MARK_ONLYDIR | \ FAN_MARK_IGNORED_MASK | \ FAN_MARK_IGNORED_SURV_MODIFY | \ + FAN_MARK_EVICTABLE | \ FAN_MARK_FLUSH) /* -- cgit v1.2.3 From cf51406ccb083941102fc101718d4c0a25b17917 Mon Sep 17 00:00:00 2001 From: Simon Trimmer Date: Mon, 25 Apr 2022 13:50:11 +0100 Subject: ASoC: soc.h: Introduce SOC_DOUBLE_R_S_EXT_TLV() macro A straightforward extension of the SOC_DOUBLE_R_S_TLV() macro that allows the get and put functions to be customised. Signed-off-by: Simon Trimmer Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20220425125012.3044919-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 2d3261799d2c..8368b69dfef8 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -282,6 +282,17 @@ .get = xhandler_get, .put = xhandler_put, \ .private_value = SOC_DOUBLE_R_VALUE(reg_left, reg_right, xshift, \ xmax, xinvert) } +#define SOC_DOUBLE_R_S_EXT_TLV(xname, reg_left, reg_right, xshift, xmin, xmax, \ + xsign_bit, xinvert, xhandler_get, xhandler_put, \ + tlv_array) \ +{ .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = (xname), \ + .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \ + SNDRV_CTL_ELEM_ACCESS_READWRITE, \ + .tlv.p = (tlv_array), \ + .info = snd_soc_info_volsw, \ + .get = xhandler_get, .put = xhandler_put, \ + .private_value = SOC_DOUBLE_R_S_VALUE(reg_left, reg_right, xshift, \ + xmin, xmax, xsign_bit, xinvert) } #define SOC_SINGLE_BOOL_EXT(xname, xdata, xhandler_get, xhandler_put) \ { .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname, \ .info = snd_soc_info_bool_ext, \ -- cgit v1.2.3 From 5349c0c93d15dff27d99fec12fc82040fab340bd Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Mon, 25 Apr 2022 13:50:12 +0100 Subject: ASoC: soc.h: Add SOC_SINGLE_S_EXT_TLV macro Add a SOC_SINGLE_S_EXT_TLV macro as a convenience wrapper around SOC_DOUBLE_R_S_EXT_TLV for mono volume controls. Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20220425125012.3044919-3-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 8368b69dfef8..f906e5a70830 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -293,6 +293,12 @@ .get = xhandler_get, .put = xhandler_put, \ .private_value = SOC_DOUBLE_R_S_VALUE(reg_left, reg_right, xshift, \ xmin, xmax, xsign_bit, xinvert) } +#define SOC_SINGLE_S_EXT_TLV(xname, xreg, xshift, xmin, xmax, \ + xsign_bit, xinvert, xhandler_get, xhandler_put, \ + tlv_array) \ + SOC_DOUBLE_R_S_EXT_TLV(xname, xreg, xreg, xshift, xmin, xmax, \ + xsign_bit, xinvert, xhandler_get, xhandler_put, \ + tlv_array) #define SOC_SINGLE_BOOL_EXT(xname, xdata, xhandler_get, xhandler_put) \ { .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname, \ .info = snd_soc_info_bool_ext, \ -- cgit v1.2.3 From 430c3500995484962bdbccf358201afef8055535 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Mon, 25 Apr 2022 10:51:59 +0100 Subject: firmware: cirrus: cs_dsp: Avoid padding bytes in cs_dsp_coeff_ctl Change the order of members in struct cs_dsp_coeff_ctl to avoid the compiler having to insert alignment padding bytes. On a x86_64 build this saves 16 bytes per control. - Pointers are collected to the top of the struct (with the exception of priv, as noted below), so that they are inherently aligned. - The set and enable bitflags are placed together so they can be merged. - priv is placed at the end of the struct - it is for use by the client so it is helpful to make it stand out, and since the compiler will always pad the struct size to an alignment multiple putting a pointer last won't introduce any more padding. - struct cs_dsp_alg_region is placed at the end, right before priv, for the same reasoning as priv. Signed-off-by: Richard Fitzgerald Reviewed-by: Charles Keepax Link: https://lore.kernel.org/r/20220425095159.3044527-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/linux/firmware/cirrus/cs_dsp.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 38b4da3ddfe4..30055706cce2 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -68,36 +68,36 @@ struct cs_dsp_alg_region { /** * struct cs_dsp_coeff_ctl - Describes a coefficient control + * @list: List node for internal use + * @dsp: DSP instance associated with this control + * @cache: Cached value of the control * @fw_name: Name of the firmware * @subname: Name of the control parsed from the WMFW * @subname_len: Length of subname - * @alg_region: Logical region associated with this control - * @dsp: DSP instance associated with this control - * @enabled: Flag indicating whether control is enabled - * @list: List node for internal use - * @cache: Cached value of the control * @offset: Offset of control within alg_region in words * @len: Length of the cached value in bytes - * @set: Flag indicating the value has been written by the user - * @flags: Bitfield of WMFW_CTL_FLAG_ control flags defined in wmfw.h * @type: One of the WMFW_CTL_TYPE_ control types defined in wmfw.h + * @flags: Bitfield of WMFW_CTL_FLAG_ control flags defined in wmfw.h + * @set: Flag indicating the value has been written by the user + * @enabled: Flag indicating whether control is enabled + * @alg_region: Logical region associated with this control * @priv: For use by the client */ struct cs_dsp_coeff_ctl { + struct list_head list; + struct cs_dsp *dsp; + void *cache; const char *fw_name; /* Subname is needed to match with firmware */ const char *subname; unsigned int subname_len; - struct cs_dsp_alg_region alg_region; - struct cs_dsp *dsp; - unsigned int enabled:1; - struct list_head list; - void *cache; unsigned int offset; size_t len; - unsigned int set:1; - unsigned int flags; unsigned int type; + unsigned int flags; + unsigned int set:1; + unsigned int enabled:1; + struct cs_dsp_alg_region alg_region; void *priv; }; -- cgit v1.2.3 From 66200bbcde697dea7f48071d325ea4dec6f66b11 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Tue, 12 Apr 2022 19:49:00 -0700 Subject: Drivers: hv: vmbus: Add VMbus IMC device to unsupported list Hyper-V may offer an Initial Machine Configuration (IMC) synthetic device to guest VMs. The device may be used by Windows guests to get specialization information, such as the hostname. But the device is not used in Linux and there is no Linux driver, so it is unsupported. Currently, the IMC device GUID is not recognized by the VMbus driver, which results in an "Unknown GUID" error message during boot. Add the GUID to the list of known but unsupported devices so that the error message is not generated. Other than avoiding the error message, there is no change in guest behavior. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1649818140-100953-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index fe2e0179ed51..2d085d951ee4 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1451,12 +1451,14 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size); 0x80, 0x2e, 0x27, 0xed, 0xe1, 0x9f) /* - * Linux doesn't support the 3 devices: the first two are for - * Automatic Virtual Machine Activation, and the third is for - * Remote Desktop Virtualization. + * Linux doesn't support these 4 devices: the first two are for + * Automatic Virtual Machine Activation, the third is for + * Remote Desktop Virtualization, and the fourth is Initial + * Machine Configuration (IMC) used only by Windows guests. * {f8e65716-3cb3-4a06-9a60-1889c5cccab5} * {3375baf4-9e15-4b30-b765-67acb10d607b} * {276aacf4-ac15-426c-98dd-7521ad3f01fe} + * {c376c1c3-d276-48d2-90a9-c04748072c60} */ #define HV_AVMA1_GUID \ @@ -1471,6 +1473,10 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size); .guid = GUID_INIT(0x276aacf4, 0xac15, 0x426c, 0x98, 0xdd, \ 0x75, 0x21, 0xad, 0x3f, 0x01, 0xfe) +#define HV_IMC_GUID \ + .guid = GUID_INIT(0xc376c1c3, 0xd276, 0x48d2, 0x90, 0xa9, \ + 0xc0, 0x47, 0x48, 0x07, 0x2c, 0x60) + /* * Common header for Hyper-V ICs */ -- cgit v1.2.3 From b03afa57c65e1e045e02df49777e953742745f4c Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Tue, 19 Apr 2022 14:23:22 +0200 Subject: Drivers: hv: vmbus: Introduce vmbus_sendpacket_getid() The function can be used to send a VMbus packet and retrieve the corresponding transaction ID. It will be used by hv_pci. No functional change. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20220419122325.10078-4-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2d085d951ee4..7cb8718825ee 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1161,6 +1161,13 @@ extern int vmbus_open(struct vmbus_channel *channel, extern void vmbus_close(struct vmbus_channel *channel); +extern int vmbus_sendpacket_getid(struct vmbus_channel *channel, + void *buffer, + u32 bufferLen, + u64 requestid, + u64 *trans_id, + enum vmbus_packet_type type, + u32 flags); extern int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, u32 bufferLen, -- cgit v1.2.3 From 0aadb6a7bb811554cf39318b5d18e8ec50dd9f02 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Tue, 19 Apr 2022 14:23:23 +0200 Subject: Drivers: hv: vmbus: Introduce vmbus_request_addr_match() The function can be used to retrieve and clear/remove a transation ID from a channel requestor, provided the memory address corresponding to the ID equals a specified address. The function, and its 'lockless' variant __vmbus_request_addr_match(), will be used by hv_pci. Refactor vmbus_request_addr() to reuse the 'newly' introduced code. No functional change. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20220419122325.10078-5-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 7cb8718825ee..2e4962a2fbec 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -788,6 +788,7 @@ struct vmbus_requestor { #define VMBUS_NO_RQSTOR U64_MAX #define VMBUS_RQST_ERROR (U64_MAX - 1) +#define VMBUS_RQST_ADDR_ANY U64_MAX /* NetVSC-specific */ #define VMBUS_RQST_ID_NO_RESPONSE (U64_MAX - 2) /* StorVSC-specific */ @@ -1042,6 +1043,10 @@ struct vmbus_channel { }; u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr); +u64 __vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, + u64 rqst_addr); +u64 vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, + u64 rqst_addr); u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id); static inline bool is_hvsock_channel(const struct vmbus_channel *c) -- cgit v1.2.3 From b91eaf7267cf7aec0a4e087decf7770dfb694d78 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Tue, 19 Apr 2022 14:23:24 +0200 Subject: Drivers: hv: vmbus: Introduce {lock,unlock}_requestor() To abtract the lock and unlock operations on the requestor spin lock. The helpers will come in handy in hv_pci. No functional change. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20220419122325.10078-6-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2e4962a2fbec..460a716f4748 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1042,6 +1042,21 @@ struct vmbus_channel { u32 max_pkt_size; }; +#define lock_requestor(channel, flags) \ +do { \ + struct vmbus_requestor *rqstor = &(channel)->requestor; \ + \ + spin_lock_irqsave(&rqstor->req_lock, flags); \ +} while (0) + +static __always_inline void unlock_requestor(struct vmbus_channel *channel, + unsigned long flags) +{ + struct vmbus_requestor *rqstor = &channel->requestor; + + spin_unlock_irqrestore(&rqstor->req_lock, flags); +} + u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr); u64 __vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, u64 rqst_addr); -- cgit v1.2.3 From 067c098766c6af667a9002d4e33cf1f3c998abbe Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Wed, 20 Apr 2022 17:25:05 -0500 Subject: of: overlay: rework overlay apply and remove kfree()s Fix various kfree() issues related to of_overlay_apply(). - Double kfree() of fdt and tree when init_overlay_changeset() returns an error. - free_overlay_changeset() free the root of the unflattened overlay (variable tree) instead of the memory that contains the unflattened overlay. - For the case of a failure during applying an overlay, move kfree() of new_fdt and overlay_mem into free_overlay_changeset(), which is called by the function that allocated them. - For the case of removing an overlay, the kfree() of new_fdt and overlay_mem remains in free_overlay_changeset(). - Check return value of of_fdt_unflatten_tree() for error instead of checking the returned value of overlay_root. - When storing pointers to allocated objects in ovcs, do so as near to the allocation as possible instead of in deeply layered function. More clearly document policy related to lifetime of pointers into overlay memory. Double kfree() Reported-by: Slawomir Stepien Signed-off-by: Frank Rowand Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20220420222505.928492-3-frowand.list@gmail.com --- include/linux/of.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index 04971e85fbc9..17741eee0ca4 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1543,7 +1543,8 @@ static inline bool of_device_is_system_power_controller(const struct device_node */ enum of_overlay_notify_action { - OF_OVERLAY_PRE_APPLY = 0, + OF_OVERLAY_INIT = 0, /* kzalloc() of ovcs sets this value */ + OF_OVERLAY_PRE_APPLY, OF_OVERLAY_POST_APPLY, OF_OVERLAY_PRE_REMOVE, OF_OVERLAY_POST_REMOVE, -- cgit v1.2.3 From 5b0e58542acb3672f42e08cb1cd57784f5e08d6b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 Apr 2022 12:08:54 +0200 Subject: net: ieee802154: Enhance/fix the names of the MLME return codes Let's keep these definitions as close to the specification as possible while they are not yet in use. The names get slightly longer, but we gain the minor cost of being able to search the spec more easily. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220407100903.1695973-2-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/linux/ieee802154.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 95c831162212..01d945c8b2e1 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -136,16 +136,16 @@ enum { IEEE802154_SUCCESS = 0x0, /* The beacon was lost following a synchronization request. */ - IEEE802154_BEACON_LOSS = 0xe0, + IEEE802154_BEACON_LOST = 0xe0, /* * A transmission could not take place due to activity on the * channel, i.e., the CSMA-CA mechanism has failed. */ - IEEE802154_CHNL_ACCESS_FAIL = 0xe1, + IEEE802154_CHANNEL_ACCESS_FAILURE = 0xe1, /* The GTS request has been denied by the PAN coordinator. */ - IEEE802154_DENINED = 0xe2, + IEEE802154_DENIED = 0xe2, /* The attempt to disable the transceiver has failed. */ - IEEE802154_DISABLE_TRX_FAIL = 0xe3, + IEEE802154_DISABLE_TRX_FAILURE = 0xe3, /* * The received frame induces a failed security check according to * the security suite. @@ -185,9 +185,9 @@ enum { * A PAN identifier conflict has been detected and communicated to the * PAN coordinator. */ - IEEE802154_PANID_CONFLICT = 0xee, + IEEE802154_PAN_ID_CONFLICT = 0xee, /* A coordinator realignment command has been received. */ - IEEE802154_REALIGMENT = 0xef, + IEEE802154_REALIGNMENT = 0xef, /* The transaction has expired and its information discarded. */ IEEE802154_TRANSACTION_EXPIRED = 0xf0, /* There is no capacity to store the transaction. */ @@ -203,7 +203,7 @@ enum { * A SET/GET request was issued with the identifier of a PIB attribute * that is not supported. */ - IEEE802154_UNSUPPORTED_ATTR = 0xf4, + IEEE802154_UNSUPPORTED_ATTRIBUTE = 0xf4, /* * A request to perform a scan operation failed because the MLME was * in the process of performing a previously initiated scan operation. -- cgit v1.2.3 From f06cfc233ac67e26ed137f4e098c047939cf1530 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 Apr 2022 12:08:55 +0200 Subject: net: ieee802154: Fill the list of MLME return codes There are more codes than already listed, let's be a bit more exhaustive. This will allow to drop device drivers local definitions of these codes. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220407100903.1695973-3-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/linux/ieee802154.h | 67 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 66 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 01d945c8b2e1..f1f9412b6ac6 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -134,7 +134,35 @@ enum { * a successful transmission. */ IEEE802154_SUCCESS = 0x0, - + /* The requested operation failed. */ + IEEE802154_MAC_ERROR = 0x1, + /* The requested operation has been cancelled. */ + IEEE802154_CANCELLED = 0x2, + /* + * Device is ready to poll the coordinator for data in a non beacon + * enabled PAN. + */ + IEEE802154_READY_FOR_POLL = 0x3, + /* Wrong frame counter. */ + IEEE802154_COUNTER_ERROR = 0xdb, + /* + * The frame does not conforms to the incoming key usage policy checking + * procedure. + */ + IEEE802154_IMPROPER_KEY_TYPE = 0xdc, + /* + * The frame does not conforms to the incoming security level usage + * policy checking procedure. + */ + IEEE802154_IMPROPER_SECURITY_LEVEL = 0xdd, + /* Secured frame received with an empty Frame Version field. */ + IEEE802154_UNSUPPORTED_LEGACY = 0xde, + /* + * A secured frame is received or must be sent but security is not + * enabled in the device. Or, the Auxiliary Security Header has security + * level of zero in it. + */ + IEEE802154_UNSUPPORTED_SECURITY = 0xdf, /* The beacon was lost following a synchronization request. */ IEEE802154_BEACON_LOST = 0xe0, /* @@ -204,11 +232,48 @@ enum { * that is not supported. */ IEEE802154_UNSUPPORTED_ATTRIBUTE = 0xf4, + /* Missing source or destination address or address mode. */ + IEEE802154_INVALID_ADDRESS = 0xf5, + /* + * MLME asked to turn the receiver on, but the on time duration is too + * big compared to the macBeaconOrder. + */ + IEEE802154_ON_TIME_TOO_LONG = 0xf6, + /* + * MLME asaked to turn the receiver on, but the request was delayed for + * too long before getting processed. + */ + IEEE802154_PAST_TIME = 0xf7, + /* + * The StartTime parameter is nonzero, and the MLME is not currently + * tracking the beacon of the coordinator through which it is + * associated. + */ + IEEE802154_TRACKING_OFF = 0xf8, + /* + * The index inside the hierarchical values in PIBAttribute is out of + * range. + */ + IEEE802154_INVALID_INDEX = 0xf9, + /* + * The number of PAN descriptors discovered during a scan has been + * reached. + */ + IEEE802154_LIMIT_REACHED = 0xfa, + /* + * The PIBAttribute parameter specifies an attribute that is a read-only + * attribute. + */ + IEEE802154_READ_ONLY = 0xfb, /* * A request to perform a scan operation failed because the MLME was * in the process of performing a previously initiated scan operation. */ IEEE802154_SCAN_IN_PROGRESS = 0xfc, + /* The outgoing superframe overlaps the incoming superframe. */ + IEEE802154_SUPERFRAME_OVERLAP = 0xfd, + /* Any other error situation. */ + IEEE802154_SYSTEM_ERROR = 0xff, }; /* frame control handling */ -- cgit v1.2.3 From 30ca44eb2480ede838c7c8c131a7d25589a98f0a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 Apr 2022 12:08:57 +0200 Subject: net: mac802154: Create an offloaded transmission error helper So far there is only a helper for successful transmissions, which led device drivers to implement their own handling in case of error. Unfortunately, we really need all the drivers to give the hand back to the core once they are done in order to be able to build a proper synchronous API. So let's create a _xmit_error() helper and take this opportunity to fill the new device-global field storing Tx statuses. Suggested-by: Alexander Aring Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220407100903.1695973-5-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/mac802154.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 2c3bbc6645ba..29f289d58720 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -498,4 +498,14 @@ void ieee802154_stop_queue(struct ieee802154_hw *hw); void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, bool ifs_handling); +/** + * ieee802154_xmit_error - offloaded frame transmission failed + * + * @hw: pointer as obtained from ieee802154_alloc_hw(). + * @skb: buffer for transmission + * @reason: error code + */ +void ieee802154_xmit_error(struct ieee802154_hw *hw, struct sk_buff *skb, + int reason); + #endif /* NET_MAC802154_H */ -- cgit v1.2.3 From 5a1b57c0dde9b93ba8261fa1c81f9aae2bac284a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 Apr 2022 12:08:58 +0200 Subject: net: mac802154: Create an error helper for asynchronous offloading errors A few drivers do the full transmit operation asynchronously, which means that a bus error that happens when forwarding the packet to the transmitter or a timeout happening when offloading the request to the transmitter will not be reported immediately. The solution in this case is to call this new helper to free the necessary resources, restart the queue and always return the same generic TRAC error code: IEEE802154_SYSTEM_ERROR. Suggested-by: Alexander Aring Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220407100903.1695973-6-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/mac802154.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 29f289d58720..bdac0ddbdcdb 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -508,4 +508,13 @@ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, void ieee802154_xmit_error(struct ieee802154_hw *hw, struct sk_buff *skb, int reason); +/** + * ieee802154_xmit_hw_error - frame could not be offloaded to the transmitter + * because of a hardware error (bus error, timeout, etc) + * + * @hw: pointer as obtained from ieee802154_alloc_hw(). + * @skb: buffer for transmission + */ +void ieee802154_xmit_hw_error(struct ieee802154_hw *hw, struct sk_buff *skb); + #endif /* NET_MAC802154_H */ -- cgit v1.2.3 From c83227a5d05ed77b634ce4c2fc5f143ae2a4d6f5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 21 Apr 2022 22:06:54 +0200 Subject: irq/gpio: ixp4xx: Drop boardfile probe path The boardfiles for IXP4xx have been deleted. Delete all the quirks and code dealing with that boot path and rely solely on device tree boot. Fix some missing static keywords that the kernel test robot was complaining about while we're at it. Cc: Bartosz Golaszewski Acked-by: Marc Zyngier Signed-off-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- include/linux/irqchip/irq-ixp4xx.h | 12 ------------ 1 file changed, 12 deletions(-) delete mode 100644 include/linux/irqchip/irq-ixp4xx.h (limited to 'include') diff --git a/include/linux/irqchip/irq-ixp4xx.h b/include/linux/irqchip/irq-ixp4xx.h deleted file mode 100644 index 9395917d6936..000000000000 --- a/include/linux/irqchip/irq-ixp4xx.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __IRQ_IXP4XX_H -#define __IRQ_IXP4XX_H - -#include -struct irq_domain; - -void ixp4xx_irq_init(resource_size_t irqbase, - bool is_356); -struct irq_domain *ixp4xx_get_irq_domain(void); - -#endif /* __IRQ_IXP4XX_H */ -- cgit v1.2.3 From fae74fb5d525f979085b6e70b883d7a7049bf15f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 25 Apr 2022 19:32:55 +0200 Subject: gpio: pcf857x: Make teardown callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All teardown functions return 0. Also there is little sense in returning a negative error code from an i2c remove function as this only results in emitting an error message but the device is removed nevertheless. This patch is a preparation for making i2c remove callbacks return void. Signed-off-by: Uwe Kleine-König Signed-off-by: Bartosz Golaszewski --- include/linux/platform_data/pcf857x.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/pcf857x.h b/include/linux/platform_data/pcf857x.h index 11d4ed78c7f4..01d0a3ea3aef 100644 --- a/include/linux/platform_data/pcf857x.h +++ b/include/linux/platform_data/pcf857x.h @@ -36,7 +36,7 @@ struct pcf857x_platform_data { int (*setup)(struct i2c_client *client, int gpio, unsigned ngpio, void *context); - int (*teardown)(struct i2c_client *client, + void (*teardown)(struct i2c_client *client, int gpio, unsigned ngpio, void *context); void *context; -- cgit v1.2.3 From 0f40ba48de3b8a4c5793013768cd62805033869c Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Wed, 6 Apr 2022 15:10:19 +0530 Subject: drm/msm/dsi: Pass DSC params to drm_panel When DSC is enabled, we need to get the DSC parameters from the panel driver, so add a dsc parameter in panel to fetch and pass DSC configuration for DSI panels to DPU encoder, which will enable and then configure DSC hardware blocks accordingly. Signed-off-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Signed-off-by: Vinod Koul Patchwork: https://patchwork.freedesktop.org/patch/480910/ Link: https://lore.kernel.org/r/20220406094031.1027376-3-vkoul@kernel.org Signed-off-by: Dmitry Baryshkov --- include/drm/drm_panel.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h index 1ba2d424a53f..d279ee455f01 100644 --- a/include/drm/drm_panel.h +++ b/include/drm/drm_panel.h @@ -179,6 +179,13 @@ struct drm_panel { * Panel entry in registry. */ struct list_head list; + + /** + * @dsc: + * + * Panel DSC pps payload to be sent + */ + struct drm_dsc_config *dsc; }; void drm_panel_init(struct drm_panel *panel, struct device *dev, -- cgit v1.2.3 From c277f1411d7bc2831d48bde5c18d3b7f87c61646 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Mon, 21 Mar 2022 15:13:06 -0700 Subject: f2fs: introduce data read/write showing path info This was used in Android for a long time. Let's upstream it. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 94 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 1779e133cea0..4d1ad64d4cab 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -2067,6 +2067,100 @@ TRACE_EVENT(f2fs_fiemap, __entry->ret) ); +DECLARE_EVENT_CLASS(f2fs__rw_start, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + + TP_ARGS(inode, offset, bytes, pid, pathname, command), + + TP_STRUCT__entry( + __string(pathbuf, pathname) + __field(loff_t, offset) + __field(int, bytes) + __field(loff_t, i_size) + __string(cmdline, command) + __field(pid_t, pid) + __field(ino_t, ino) + ), + + TP_fast_assign( + /* + * Replace the spaces in filenames and cmdlines + * because this screws up the tooling that parses + * the traces. + */ + __assign_str(pathbuf, pathname); + (void)strreplace(__get_str(pathbuf), ' ', '_'); + __entry->offset = offset; + __entry->bytes = bytes; + __entry->i_size = i_size_read(inode); + __assign_str(cmdline, command); + (void)strreplace(__get_str(cmdline), ' ', '_'); + __entry->pid = pid; + __entry->ino = inode->i_ino; + ), + + TP_printk("entry_name %s, offset %llu, bytes %d, cmdline %s," + " pid %d, i_size %llu, ino %lu", + __get_str(pathbuf), __entry->offset, __entry->bytes, + __get_str(cmdline), __entry->pid, __entry->i_size, + (unsigned long) __entry->ino) +); + +DECLARE_EVENT_CLASS(f2fs__rw_end, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + + TP_ARGS(inode, offset, bytes), + + TP_STRUCT__entry( + __field(ino_t, ino) + __field(loff_t, offset) + __field(int, bytes) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->offset = offset; + __entry->bytes = bytes; + ), + + TP_printk("ino %lu, offset %llu, bytes %d", + (unsigned long) __entry->ino, + __entry->offset, __entry->bytes) +); + +DEFINE_EVENT(f2fs__rw_start, f2fs_dataread_start, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + + TP_ARGS(inode, offset, bytes, pid, pathname, command) +); + +DEFINE_EVENT(f2fs__rw_end, f2fs_dataread_end, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + + TP_ARGS(inode, offset, bytes) +); + +DEFINE_EVENT(f2fs__rw_start, f2fs_datawrite_start, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + + TP_ARGS(inode, offset, bytes, pid, pathname, command) +); + +DEFINE_EVENT(f2fs__rw_end, f2fs_datawrite_end, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + + TP_ARGS(inode, offset, bytes) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 7335631fcd5eecfa84555bd57433e6446d06ad21 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 15 Apr 2022 00:17:47 +0200 Subject: dt-bindings: clock: u8500: Add clkout clock bindings This adds device tree bindings for the externally routed clocks CLKOUT1 and CLKOUT2 clocks found in the DB8500. Cc: devicetree@vger.kernel.org Reviewed-by: Ulf Hansson Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220414221751.323525-2-linus.walleij@linaro.org Reviewed-by: Rob Herring Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/ste-db8500-clkout.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/dt-bindings/clock/ste-db8500-clkout.h (limited to 'include') diff --git a/include/dt-bindings/clock/ste-db8500-clkout.h b/include/dt-bindings/clock/ste-db8500-clkout.h new file mode 100644 index 000000000000..ca07cb2bd1bc --- /dev/null +++ b/include/dt-bindings/clock/ste-db8500-clkout.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __STE_CLK_DB8500_CLKOUT_H__ +#define __STE_CLK_DB8500_CLKOUT_H__ + +#define DB8500_CLKOUT_1 0 +#define DB8500_CLKOUT_2 1 + +#define DB8500_CLKOUT_SRC_CLK38M 0 +#define DB8500_CLKOUT_SRC_ACLK 1 +#define DB8500_CLKOUT_SRC_SYSCLK 2 +#define DB8500_CLKOUT_SRC_LCDCLK 3 +#define DB8500_CLKOUT_SRC_SDMMCCLK 4 +#define DB8500_CLKOUT_SRC_TVCLK 5 +#define DB8500_CLKOUT_SRC_TIMCLK 6 +#define DB8500_CLKOUT_SRC_CLK009 7 + +#endif -- cgit v1.2.3 From f113a51aa2cfbd22c376d8722b5c9fef469be162 Mon Sep 17 00:00:00 2001 From: Chun-Jie Chen Date: Sat, 9 Apr 2022 21:22:37 +0800 Subject: dt-bindings: ARM: MediaTek: Add new document bindings of MT8186 clock This patch adds the new binding documentation for system clock and functional clock on MediaTek MT8186. Signed-off-by: Chun-Jie Chen Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20220409132251.31725-2-chun-jie.chen@mediatek.com Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/mt8186-clk.h | 445 +++++++++++++++++++++++++++++++++ 1 file changed, 445 insertions(+) create mode 100644 include/dt-bindings/clock/mt8186-clk.h (limited to 'include') diff --git a/include/dt-bindings/clock/mt8186-clk.h b/include/dt-bindings/clock/mt8186-clk.h new file mode 100644 index 000000000000..a70bf67af47d --- /dev/null +++ b/include/dt-bindings/clock/mt8186-clk.h @@ -0,0 +1,445 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Chun-Jie Chen + */ + +#ifndef _DT_BINDINGS_CLK_MT8186_H +#define _DT_BINDINGS_CLK_MT8186_H + +/* MCUSYS */ + +#define CLK_MCU_ARMPLL_LL_SEL 0 +#define CLK_MCU_ARMPLL_BL_SEL 1 +#define CLK_MCU_ARMPLL_BUS_SEL 2 +#define CLK_MCU_NR_CLK 3 + +/* TOPCKGEN */ + +#define CLK_TOP_AXI 0 +#define CLK_TOP_SCP 1 +#define CLK_TOP_MFG 2 +#define CLK_TOP_CAMTG 3 +#define CLK_TOP_CAMTG1 4 +#define CLK_TOP_CAMTG2 5 +#define CLK_TOP_CAMTG3 6 +#define CLK_TOP_CAMTG4 7 +#define CLK_TOP_CAMTG5 8 +#define CLK_TOP_CAMTG6 9 +#define CLK_TOP_UART 10 +#define CLK_TOP_SPI 11 +#define CLK_TOP_MSDC50_0_HCLK 12 +#define CLK_TOP_MSDC50_0 13 +#define CLK_TOP_MSDC30_1 14 +#define CLK_TOP_AUDIO 15 +#define CLK_TOP_AUD_INTBUS 16 +#define CLK_TOP_AUD_1 17 +#define CLK_TOP_AUD_2 18 +#define CLK_TOP_AUD_ENGEN1 19 +#define CLK_TOP_AUD_ENGEN2 20 +#define CLK_TOP_DISP_PWM 21 +#define CLK_TOP_SSPM 22 +#define CLK_TOP_DXCC 23 +#define CLK_TOP_USB_TOP 24 +#define CLK_TOP_SRCK 25 +#define CLK_TOP_SPM 26 +#define CLK_TOP_I2C 27 +#define CLK_TOP_PWM 28 +#define CLK_TOP_SENINF 29 +#define CLK_TOP_SENINF1 30 +#define CLK_TOP_SENINF2 31 +#define CLK_TOP_SENINF3 32 +#define CLK_TOP_AES_MSDCFDE 33 +#define CLK_TOP_PWRAP_ULPOSC 34 +#define CLK_TOP_CAMTM 35 +#define CLK_TOP_VENC 36 +#define CLK_TOP_CAM 37 +#define CLK_TOP_IMG1 38 +#define CLK_TOP_IPE 39 +#define CLK_TOP_DPMAIF 40 +#define CLK_TOP_VDEC 41 +#define CLK_TOP_DISP 42 +#define CLK_TOP_MDP 43 +#define CLK_TOP_AUDIO_H 44 +#define CLK_TOP_UFS 45 +#define CLK_TOP_AES_FDE 46 +#define CLK_TOP_AUDIODSP 47 +#define CLK_TOP_DVFSRC 48 +#define CLK_TOP_DSI_OCC 49 +#define CLK_TOP_SPMI_MST 50 +#define CLK_TOP_SPINOR 51 +#define CLK_TOP_NNA 52 +#define CLK_TOP_NNA1 53 +#define CLK_TOP_NNA2 54 +#define CLK_TOP_SSUSB_XHCI 55 +#define CLK_TOP_SSUSB_TOP_1P 56 +#define CLK_TOP_SSUSB_XHCI_1P 57 +#define CLK_TOP_WPE 58 +#define CLK_TOP_DPI 59 +#define CLK_TOP_U3_OCC_250M 60 +#define CLK_TOP_U3_OCC_500M 61 +#define CLK_TOP_ADSP_BUS 62 +#define CLK_TOP_APLL_I2S0_MCK_SEL 63 +#define CLK_TOP_APLL_I2S1_MCK_SEL 64 +#define CLK_TOP_APLL_I2S2_MCK_SEL 65 +#define CLK_TOP_APLL_I2S4_MCK_SEL 66 +#define CLK_TOP_APLL_TDMOUT_MCK_SEL 67 +#define CLK_TOP_MAINPLL_D2 68 +#define CLK_TOP_MAINPLL_D2_D2 69 +#define CLK_TOP_MAINPLL_D2_D4 70 +#define CLK_TOP_MAINPLL_D2_D16 71 +#define CLK_TOP_MAINPLL_D3 72 +#define CLK_TOP_MAINPLL_D3_D2 73 +#define CLK_TOP_MAINPLL_D3_D4 74 +#define CLK_TOP_MAINPLL_D5 75 +#define CLK_TOP_MAINPLL_D5_D2 76 +#define CLK_TOP_MAINPLL_D5_D4 77 +#define CLK_TOP_MAINPLL_D7 78 +#define CLK_TOP_MAINPLL_D7_D2 79 +#define CLK_TOP_MAINPLL_D7_D4 80 +#define CLK_TOP_UNIVPLL 81 +#define CLK_TOP_UNIVPLL_D2 82 +#define CLK_TOP_UNIVPLL_D2_D2 83 +#define CLK_TOP_UNIVPLL_D2_D4 84 +#define CLK_TOP_UNIVPLL_D3 85 +#define CLK_TOP_UNIVPLL_D3_D2 86 +#define CLK_TOP_UNIVPLL_D3_D4 87 +#define CLK_TOP_UNIVPLL_D3_D8 88 +#define CLK_TOP_UNIVPLL_D3_D32 89 +#define CLK_TOP_UNIVPLL_D5 90 +#define CLK_TOP_UNIVPLL_D5_D2 91 +#define CLK_TOP_UNIVPLL_D5_D4 92 +#define CLK_TOP_UNIVPLL_D7 93 +#define CLK_TOP_UNIVPLL_192M 94 +#define CLK_TOP_UNIVPLL_192M_D4 95 +#define CLK_TOP_UNIVPLL_192M_D8 96 +#define CLK_TOP_UNIVPLL_192M_D16 97 +#define CLK_TOP_UNIVPLL_192M_D32 98 +#define CLK_TOP_APLL1_D2 99 +#define CLK_TOP_APLL1_D4 100 +#define CLK_TOP_APLL1_D8 101 +#define CLK_TOP_APLL2_D2 102 +#define CLK_TOP_APLL2_D4 103 +#define CLK_TOP_APLL2_D8 104 +#define CLK_TOP_MMPLL_D2 105 +#define CLK_TOP_TVDPLL_D2 106 +#define CLK_TOP_TVDPLL_D4 107 +#define CLK_TOP_TVDPLL_D8 108 +#define CLK_TOP_TVDPLL_D16 109 +#define CLK_TOP_TVDPLL_D32 110 +#define CLK_TOP_MSDCPLL_D2 111 +#define CLK_TOP_ULPOSC1 112 +#define CLK_TOP_ULPOSC1_D2 113 +#define CLK_TOP_ULPOSC1_D4 114 +#define CLK_TOP_ULPOSC1_D8 115 +#define CLK_TOP_ULPOSC1_D10 116 +#define CLK_TOP_ULPOSC1_D16 117 +#define CLK_TOP_ULPOSC1_D32 118 +#define CLK_TOP_ADSPPLL_D2 119 +#define CLK_TOP_ADSPPLL_D4 120 +#define CLK_TOP_ADSPPLL_D8 121 +#define CLK_TOP_NNAPLL_D2 122 +#define CLK_TOP_NNAPLL_D4 123 +#define CLK_TOP_NNAPLL_D8 124 +#define CLK_TOP_NNA2PLL_D2 125 +#define CLK_TOP_NNA2PLL_D4 126 +#define CLK_TOP_NNA2PLL_D8 127 +#define CLK_TOP_F_BIST2FPC 128 +#define CLK_TOP_466M_FMEM 129 +#define CLK_TOP_MPLL 130 +#define CLK_TOP_APLL12_CK_DIV0 131 +#define CLK_TOP_APLL12_CK_DIV1 132 +#define CLK_TOP_APLL12_CK_DIV2 133 +#define CLK_TOP_APLL12_CK_DIV4 134 +#define CLK_TOP_APLL12_CK_DIV_TDMOUT_M 135 +#define CLK_TOP_NR_CLK 136 + +/* INFRACFG_AO */ + +#define CLK_INFRA_AO_PMIC_TMR 0 +#define CLK_INFRA_AO_PMIC_AP 1 +#define CLK_INFRA_AO_PMIC_MD 2 +#define CLK_INFRA_AO_PMIC_CONN 3 +#define CLK_INFRA_AO_SCP_CORE 4 +#define CLK_INFRA_AO_SEJ 5 +#define CLK_INFRA_AO_APXGPT 6 +#define CLK_INFRA_AO_ICUSB 7 +#define CLK_INFRA_AO_GCE 8 +#define CLK_INFRA_AO_THERM 9 +#define CLK_INFRA_AO_I2C_AP 10 +#define CLK_INFRA_AO_I2C_CCU 11 +#define CLK_INFRA_AO_I2C_SSPM 12 +#define CLK_INFRA_AO_I2C_RSV 13 +#define CLK_INFRA_AO_PWM_HCLK 14 +#define CLK_INFRA_AO_PWM1 15 +#define CLK_INFRA_AO_PWM2 16 +#define CLK_INFRA_AO_PWM3 17 +#define CLK_INFRA_AO_PWM4 18 +#define CLK_INFRA_AO_PWM5 19 +#define CLK_INFRA_AO_PWM 20 +#define CLK_INFRA_AO_UART0 21 +#define CLK_INFRA_AO_UART1 22 +#define CLK_INFRA_AO_UART2 23 +#define CLK_INFRA_AO_GCE_26M 24 +#define CLK_INFRA_AO_CQ_DMA_FPC 25 +#define CLK_INFRA_AO_BTIF 26 +#define CLK_INFRA_AO_SPI0 27 +#define CLK_INFRA_AO_MSDC0 28 +#define CLK_INFRA_AO_MSDCFDE 29 +#define CLK_INFRA_AO_MSDC1 30 +#define CLK_INFRA_AO_DVFSRC 31 +#define CLK_INFRA_AO_GCPU 32 +#define CLK_INFRA_AO_TRNG 33 +#define CLK_INFRA_AO_AUXADC 34 +#define CLK_INFRA_AO_CPUM 35 +#define CLK_INFRA_AO_CCIF1_AP 36 +#define CLK_INFRA_AO_CCIF1_MD 37 +#define CLK_INFRA_AO_AUXADC_MD 38 +#define CLK_INFRA_AO_AP_DMA 39 +#define CLK_INFRA_AO_XIU 40 +#define CLK_INFRA_AO_DEVICE_APC 41 +#define CLK_INFRA_AO_CCIF_AP 42 +#define CLK_INFRA_AO_DEBUGTOP 43 +#define CLK_INFRA_AO_AUDIO 44 +#define CLK_INFRA_AO_CCIF_MD 45 +#define CLK_INFRA_AO_DXCC_SEC_CORE 46 +#define CLK_INFRA_AO_DXCC_AO 47 +#define CLK_INFRA_AO_IMP_IIC 48 +#define CLK_INFRA_AO_DRAMC_F26M 49 +#define CLK_INFRA_AO_RG_PWM_FBCLK6 50 +#define CLK_INFRA_AO_SSUSB_TOP_HCLK 51 +#define CLK_INFRA_AO_DISP_PWM 52 +#define CLK_INFRA_AO_CLDMA_BCLK 53 +#define CLK_INFRA_AO_AUDIO_26M_BCLK 54 +#define CLK_INFRA_AO_SSUSB_TOP_P1_HCLK 55 +#define CLK_INFRA_AO_SPI1 56 +#define CLK_INFRA_AO_I2C4 57 +#define CLK_INFRA_AO_MODEM_TEMP_SHARE 58 +#define CLK_INFRA_AO_SPI2 59 +#define CLK_INFRA_AO_SPI3 60 +#define CLK_INFRA_AO_SSUSB_TOP_REF 61 +#define CLK_INFRA_AO_SSUSB_TOP_XHCI 62 +#define CLK_INFRA_AO_SSUSB_TOP_P1_REF 63 +#define CLK_INFRA_AO_SSUSB_TOP_P1_XHCI 64 +#define CLK_INFRA_AO_SSPM 65 +#define CLK_INFRA_AO_SSUSB_TOP_P1_SYS 66 +#define CLK_INFRA_AO_I2C5 67 +#define CLK_INFRA_AO_I2C5_ARBITER 68 +#define CLK_INFRA_AO_I2C5_IMM 69 +#define CLK_INFRA_AO_I2C1_ARBITER 70 +#define CLK_INFRA_AO_I2C1_IMM 71 +#define CLK_INFRA_AO_I2C2_ARBITER 72 +#define CLK_INFRA_AO_I2C2_IMM 73 +#define CLK_INFRA_AO_SPI4 74 +#define CLK_INFRA_AO_SPI5 75 +#define CLK_INFRA_AO_CQ_DMA 76 +#define CLK_INFRA_AO_BIST2FPC 77 +#define CLK_INFRA_AO_MSDC0_SELF 78 +#define CLK_INFRA_AO_SPINOR 79 +#define CLK_INFRA_AO_SSPM_26M_SELF 80 +#define CLK_INFRA_AO_SSPM_32K_SELF 81 +#define CLK_INFRA_AO_I2C6 82 +#define CLK_INFRA_AO_AP_MSDC0 83 +#define CLK_INFRA_AO_MD_MSDC0 84 +#define CLK_INFRA_AO_MSDC0_SRC 85 +#define CLK_INFRA_AO_MSDC1_SRC 86 +#define CLK_INFRA_AO_SEJ_F13M 87 +#define CLK_INFRA_AO_AES_TOP0_BCLK 88 +#define CLK_INFRA_AO_MCU_PM_BCLK 89 +#define CLK_INFRA_AO_CCIF2_AP 90 +#define CLK_INFRA_AO_CCIF2_MD 91 +#define CLK_INFRA_AO_CCIF3_AP 92 +#define CLK_INFRA_AO_CCIF3_MD 93 +#define CLK_INFRA_AO_FADSP_26M 94 +#define CLK_INFRA_AO_FADSP_32K 95 +#define CLK_INFRA_AO_CCIF4_AP 96 +#define CLK_INFRA_AO_CCIF4_MD 97 +#define CLK_INFRA_AO_FADSP 98 +#define CLK_INFRA_AO_FLASHIF_133M 99 +#define CLK_INFRA_AO_FLASHIF_66M 100 +#define CLK_INFRA_AO_NR_CLK 101 + +/* APMIXEDSYS */ + +#define CLK_APMIXED_ARMPLL_LL 0 +#define CLK_APMIXED_ARMPLL_BL 1 +#define CLK_APMIXED_CCIPLL 2 +#define CLK_APMIXED_MAINPLL 3 +#define CLK_APMIXED_UNIV2PLL 4 +#define CLK_APMIXED_MSDCPLL 5 +#define CLK_APMIXED_MMPLL 6 +#define CLK_APMIXED_NNAPLL 7 +#define CLK_APMIXED_NNA2PLL 8 +#define CLK_APMIXED_ADSPPLL 9 +#define CLK_APMIXED_MFGPLL 10 +#define CLK_APMIXED_TVDPLL 11 +#define CLK_APMIXED_APLL1 12 +#define CLK_APMIXED_APLL2 13 +#define CLK_APMIXED_NR_CLK 14 + +/* IMP_IIC_WRAP */ + +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C0 0 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C1 1 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C2 2 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C3 3 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C4 4 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C5 5 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C6 6 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C7 7 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C8 8 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C9 9 +#define CLK_IMP_IIC_WRAP_NR_CLK 10 + +/* MFGCFG */ + +#define CLK_MFG_BG3D 0 +#define CLK_MFG_NR_CLK 1 + +/* MMSYS */ + +#define CLK_MM_DISP_MUTEX0 0 +#define CLK_MM_APB_MM_BUS 1 +#define CLK_MM_DISP_OVL0 2 +#define CLK_MM_DISP_RDMA0 3 +#define CLK_MM_DISP_OVL0_2L 4 +#define CLK_MM_DISP_WDMA0 5 +#define CLK_MM_DISP_RSZ0 6 +#define CLK_MM_DISP_AAL0 7 +#define CLK_MM_DISP_CCORR0 8 +#define CLK_MM_DISP_COLOR0 9 +#define CLK_MM_SMI_INFRA 10 +#define CLK_MM_DISP_DSC_WRAP0 11 +#define CLK_MM_DISP_GAMMA0 12 +#define CLK_MM_DISP_POSTMASK0 13 +#define CLK_MM_DISP_DITHER0 14 +#define CLK_MM_SMI_COMMON 15 +#define CLK_MM_DSI0 16 +#define CLK_MM_DISP_FAKE_ENG0 17 +#define CLK_MM_DISP_FAKE_ENG1 18 +#define CLK_MM_SMI_GALS 19 +#define CLK_MM_SMI_IOMMU 20 +#define CLK_MM_DISP_RDMA1 21 +#define CLK_MM_DISP_DPI 22 +#define CLK_MM_DSI0_DSI_CK_DOMAIN 23 +#define CLK_MM_DISP_26M 24 +#define CLK_MM_NR_CLK 25 + +/* WPESYS */ + +#define CLK_WPE_CK_EN 0 +#define CLK_WPE_SMI_LARB8_CK_EN 1 +#define CLK_WPE_SYS_EVENT_TX_CK_EN 2 +#define CLK_WPE_SMI_LARB8_PCLK_EN 3 +#define CLK_WPE_NR_CLK 4 + +/* IMGSYS1 */ + +#define CLK_IMG1_LARB9_IMG1 0 +#define CLK_IMG1_LARB10_IMG1 1 +#define CLK_IMG1_DIP 2 +#define CLK_IMG1_GALS_IMG1 3 +#define CLK_IMG1_NR_CLK 4 + +/* IMGSYS2 */ + +#define CLK_IMG2_LARB9_IMG2 0 +#define CLK_IMG2_LARB10_IMG2 1 +#define CLK_IMG2_MFB 2 +#define CLK_IMG2_WPE 3 +#define CLK_IMG2_MSS 4 +#define CLK_IMG2_GALS_IMG2 5 +#define CLK_IMG2_NR_CLK 6 + +/* VDECSYS */ + +#define CLK_VDEC_LARB1_CKEN 0 +#define CLK_VDEC_LAT_CKEN 1 +#define CLK_VDEC_LAT_ACTIVE 2 +#define CLK_VDEC_LAT_CKEN_ENG 3 +#define CLK_VDEC_MINI_MDP_CKEN_CFG_RG 4 +#define CLK_VDEC_CKEN 5 +#define CLK_VDEC_ACTIVE 6 +#define CLK_VDEC_CKEN_ENG 7 +#define CLK_VDEC_NR_CLK 8 + +/* VENCSYS */ + +#define CLK_VENC_CKE0_LARB 0 +#define CLK_VENC_CKE1_VENC 1 +#define CLK_VENC_CKE2_JPGENC 2 +#define CLK_VENC_CKE5_GALS 3 +#define CLK_VENC_NR_CLK 4 + +/* CAMSYS */ + +#define CLK_CAM_LARB13 0 +#define CLK_CAM_DFP_VAD 1 +#define CLK_CAM_LARB14 2 +#define CLK_CAM 3 +#define CLK_CAMTG 4 +#define CLK_CAM_SENINF 5 +#define CLK_CAMSV1 6 +#define CLK_CAMSV2 7 +#define CLK_CAMSV3 8 +#define CLK_CAM_CCU0 9 +#define CLK_CAM_CCU1 10 +#define CLK_CAM_MRAW0 11 +#define CLK_CAM_FAKE_ENG 12 +#define CLK_CAM_CCU_GALS 13 +#define CLK_CAM2MM_GALS 14 +#define CLK_CAM_NR_CLK 15 + +/* CAMSYS_RAWA */ + +#define CLK_CAM_RAWA_LARBX_RAWA 0 +#define CLK_CAM_RAWA 1 +#define CLK_CAM_RAWA_CAMTG_RAWA 2 +#define CLK_CAM_RAWA_NR_CLK 3 + +/* CAMSYS_RAWB */ + +#define CLK_CAM_RAWB_LARBX_RAWB 0 +#define CLK_CAM_RAWB 1 +#define CLK_CAM_RAWB_CAMTG_RAWB 2 +#define CLK_CAM_RAWB_NR_CLK 3 + +/* MDPSYS */ + +#define CLK_MDP_RDMA0 0 +#define CLK_MDP_TDSHP0 1 +#define CLK_MDP_IMG_DL_ASYNC0 2 +#define CLK_MDP_IMG_DL_ASYNC1 3 +#define CLK_MDP_DISP_RDMA 4 +#define CLK_MDP_HMS 5 +#define CLK_MDP_SMI0 6 +#define CLK_MDP_APB_BUS 7 +#define CLK_MDP_WROT0 8 +#define CLK_MDP_RSZ0 9 +#define CLK_MDP_HDR0 10 +#define CLK_MDP_MUTEX0 11 +#define CLK_MDP_WROT1 12 +#define CLK_MDP_RSZ1 13 +#define CLK_MDP_FAKE_ENG0 14 +#define CLK_MDP_AAL0 15 +#define CLK_MDP_DISP_WDMA 16 +#define CLK_MDP_COLOR 17 +#define CLK_MDP_IMG_DL_ASYNC2 18 +#define CLK_MDP_IMG_DL_RELAY0_ASYNC0 19 +#define CLK_MDP_IMG_DL_RELAY1_ASYNC1 20 +#define CLK_MDP_IMG_DL_RELAY2_ASYNC2 21 +#define CLK_MDP_NR_CLK 22 + +/* IPESYS */ + +#define CLK_IPE_LARB19 0 +#define CLK_IPE_LARB20 1 +#define CLK_IPE_SMI_SUBCOM 2 +#define CLK_IPE_FD 3 +#define CLK_IPE_FE 4 +#define CLK_IPE_RSC 5 +#define CLK_IPE_DPE 6 +#define CLK_IPE_GALS_IPE 7 +#define CLK_IPE_NR_CLK 8 + +#endif /* _DT_BINDINGS_CLK_MT8186_H */ -- cgit v1.2.3 From d9d31cf88702ae071bec033e5c8714048aa71285 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 25 Apr 2022 15:04:48 -0700 Subject: bpf: Use bpf_prog_run_array_cg_flags everywhere Rename bpf_prog_run_array_cg_flags to bpf_prog_run_array_cg and use it everywhere. check_return_code already enforces sane return ranges for all cgroup types. (only egress and bind hooks have uncanonical return ranges, the rest is using [0, 1]) No functional changes. v2: - 'func_ret & 1' under explicit test (Andrii & Martin) Suggested-by: Alexei Starovoitov Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220425220448.3669032-1-sdf@google.com --- include/linux/bpf-cgroup.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 88a51b242adc..669d96d074ad 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -225,24 +225,20 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) \ ({ \ - u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - NULL, \ - &__unused_flags); \ + NULL, NULL); \ __ret; \ }) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) \ ({ \ - u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - t_ctx, \ - &__unused_flags); \ + t_ctx, NULL); \ release_sock(sk); \ } \ __ret; \ -- cgit v1.2.3 From 61df10c7799e27807ad5e459eec9d77cddf8bf45 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:49 +0530 Subject: bpf: Allow storing unreferenced kptr in map This commit introduces a new pointer type 'kptr' which can be embedded in a map value to hold a PTR_TO_BTF_ID stored by a BPF program during its invocation. When storing such a kptr, BPF program's PTR_TO_BTF_ID register must have the same type as in the map value's BTF, and loading a kptr marks the destination register as PTR_TO_BTF_ID with the correct kernel BTF and BTF ID. Such kptr are unreferenced, i.e. by the time another invocation of the BPF program loads this pointer, the object which the pointer points to may not longer exist. Since PTR_TO_BTF_ID loads (using BPF_LDX) are patched to PROBE_MEM loads by the verifier, it would safe to allow user to still access such invalid pointer, but passing such pointers into BPF helpers and kfuncs should not be permitted. A future patch in this series will close this gap. The flexibility offered by allowing programs to dereference such invalid pointers while being safe at runtime frees the verifier from doing complex lifetime tracking. As long as the user may ensure that the object remains valid, it can ensure data read by it from the kernel object is valid. The user indicates that a certain pointer must be treated as kptr capable of accepting stores of PTR_TO_BTF_ID of a certain type, by using a BTF type tag 'kptr' on the pointed to type of the pointer. Then, this information is recorded in the object BTF which will be passed into the kernel by way of map's BTF information. The name and kind from the map value BTF is used to look up the in-kernel type, and the actual BTF and BTF ID is recorded in the map struct in a new kptr_off_tab member. For now, only storing pointers to structs is permitted. An example of this specification is shown below: #define __kptr __attribute__((btf_type_tag("kptr"))) struct map_value { ... struct task_struct __kptr *task; ... }; Then, in a BPF program, user may store PTR_TO_BTF_ID with the type task_struct into the map, and then load it later. Note that the destination register is marked PTR_TO_BTF_ID_OR_NULL, as the verifier cannot know whether the value is NULL or not statically, it must treat all potential loads at that map value offset as loading a possibly NULL pointer. Only BPF_LDX, BPF_STX, and BPF_ST (with insn->imm = 0 to denote NULL) are allowed instructions that can access such a pointer. On BPF_LDX, the destination register is updated to be a PTR_TO_BTF_ID, and on BPF_STX, it is checked whether the source register type is a PTR_TO_BTF_ID with same BTF type as specified in the map BTF. The access size must always be BPF_DW. For the map in map support, the kptr_off_tab for outer map is copied from the inner map's kptr_off_tab. It was chosen to do a deep copy instead of introducing a refcount to kptr_off_tab, because the copy only needs to be done when paramterizing using inner_map_fd in the map in map case, hence would be unnecessary for all other users. It is not permitted to use MAP_FREEZE command and mmap for BPF map having kptrs, similar to the bpf_timer case. A kptr also requires that BPF program has both read and write access to the map (hence both BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG are disallowed). Note that check_map_access must be called from both check_helper_mem_access and for the BPF instructions, hence the kptr check must distinguish between ACCESS_DIRECT and ACCESS_HELPER, and reject ACCESS_HELPER cases. We rename stack_access_src to bpf_access_src and reuse it for this purpose. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-2-memxor@gmail.com --- include/linux/bpf.h | 31 ++++++++++++++++++++++++++++++- include/linux/btf.h | 2 ++ 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7bf441563ffc..ce12124048c0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -155,6 +155,24 @@ struct bpf_map_ops { const struct bpf_iter_seq_info *iter_seq_info; }; +enum { + /* Support at most 8 pointers in a BPF map value */ + BPF_MAP_VALUE_OFF_MAX = 8, +}; + +struct bpf_map_value_off_desc { + u32 offset; + struct { + struct btf *btf; + u32 btf_id; + } kptr; +}; + +struct bpf_map_value_off { + u32 nr_off; + struct bpf_map_value_off_desc off[]; +}; + struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). @@ -171,6 +189,7 @@ struct bpf_map { u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ + struct bpf_map_value_off *kptr_off_tab; int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; @@ -184,7 +203,7 @@ struct bpf_map { char name[BPF_OBJ_NAME_LEN]; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ - /* 14 bytes hole */ + /* 6 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. @@ -217,6 +236,11 @@ static inline bool map_value_has_timer(const struct bpf_map *map) return map->timer_off >= 0; } +static inline bool map_value_has_kptrs(const struct bpf_map *map) +{ + return !IS_ERR_OR_NULL(map->kptr_off_tab); +} + static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { if (unlikely(map_value_has_spin_lock(map))) @@ -1396,6 +1420,11 @@ void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); +struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset); +void bpf_map_free_kptr_off_tab(struct bpf_map *map); +struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map); +bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b); + struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); diff --git a/include/linux/btf.h b/include/linux/btf.h index 36bc09b8e890..19c297f9a52f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -123,6 +123,8 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); int btf_find_timer(const struct btf *btf, const struct btf_type *t); +struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, + const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, -- cgit v1.2.3 From 8f14852e89113d738c99c375b4c8b8b7e1073df1 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:50 +0530 Subject: bpf: Tag argument to be released in bpf_func_proto Add a new type flag for bpf_arg_type that when set tells verifier that for a release function, that argument's register will be the one for which meta.ref_obj_id will be set, and which will then be released using release_reference. To capture the regno, introduce a new field release_regno in bpf_call_arg_meta. This would be required in the next patch, where we may either pass NULL or a refcounted pointer as an argument to the release function bpf_kptr_xchg. Just releasing only when meta.ref_obj_id is set is not enough, as there is a case where the type of argument needed matches, but the ref_obj_id is set to 0. Hence, we must enforce that whenever meta.ref_obj_id is zero, the register that is to be released can only be NULL for a release function. Since we now indicate whether an argument is to be released in bpf_func_proto itself, is_release_function helper has lost its utitlity, hence refactor code to work without it, and just rely on meta.release_regno to know when to release state for a ref_obj_id. Still, the restriction of one release argument and only one ref_obj_id passed to BPF helper or kfunc remains. This may be lifted in the future. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-3-memxor@gmail.com --- include/linux/bpf.h | 5 ++++- include/linux/bpf_verifier.h | 3 +-- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ce12124048c0..492edd2c5713 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -366,7 +366,10 @@ enum bpf_type_flag { */ MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = MEM_PERCPU, + /* Indicates that the argument will be released. */ + OBJ_RELEASE = BIT(5 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = OBJ_RELEASE, }; /* Max number of base types. */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 3a9d2d7cc6b7..1f1e7f2ea967 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -523,8 +523,7 @@ int check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); int check_func_arg_reg_off(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, - enum bpf_arg_type arg_type, - bool is_release_func); + enum bpf_arg_type arg_type); int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, -- cgit v1.2.3 From 565138ac5f8a5330669a20e5f94759764e9165ec Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 21 Apr 2022 18:03:52 +0300 Subject: scsi: iscsi: Fix harmless double shift bug These flags are supposed to be bit numbers. Right now they cause a double shift bug where we use BIT(BIT(2)) instead of BIT(2). Fortunately, the bit numbers are small and it's done consistently so it does not cause an issue at run time. Link: https://lore.kernel.org/r/YmFyWHf8nrrx+SHa@kili Fixes: 5bd856256f8c ("scsi: iscsi: Merge suspend fields") Reviewed-by: Mike Christie Reviewed-by: Lee Duncan Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen --- include/scsi/libiscsi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index d0a24779c52d..c0703cd20a99 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -54,9 +54,9 @@ enum { #define ISID_SIZE 6 /* Connection flags */ -#define ISCSI_CONN_FLAG_SUSPEND_TX BIT(0) -#define ISCSI_CONN_FLAG_SUSPEND_RX BIT(1) -#define ISCSI_CONN_FLAG_BOUND BIT(2) +#define ISCSI_CONN_FLAG_SUSPEND_TX 0 +#define ISCSI_CONN_FLAG_SUSPEND_RX 1 +#define ISCSI_CONN_FLAG_BOUND 2 #define ISCSI_ITT_MASK 0x1fff #define ISCSI_TOTAL_CMDS_MAX 4096 -- cgit v1.2.3 From c976e588b34e4ff2fdd2922edab4b983244a17e6 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 21 Apr 2022 11:30:20 -0700 Subject: scsi: sd: sd_zbc: Hide gap zones ZBC-2 allows host-managed disks to report gap zones. This allow zoned disks to report an offset between data zone starts that is a power of two even if the number of logical blocks with data per zone is not a power of two. Another new feature in ZBC-2 is support for constant zone starting LBA offsets. For zoned disks that report a constant zone starting LBA offset, hide the gap zones from the block layer. Report the offset between data zone starts as zone size and report the number of logical blocks with data per zone as the zone capacity. Link: https://lore.kernel.org/r/20220421183023.3462291-7-bvanassche@acm.org Acked-by: Douglas Gilbert Signed-off-by: Damien Le Moal [ bvanassche: Reworked this patch ] Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/scsi/scsi_proto.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_proto.h b/include/scsi/scsi_proto.h index f017843a8124..c03e35fc382c 100644 --- a/include/scsi/scsi_proto.h +++ b/include/scsi/scsi_proto.h @@ -307,7 +307,9 @@ enum zbc_zone_type { ZBC_ZONE_TYPE_CONV = 0x1, ZBC_ZONE_TYPE_SEQWRITE_REQ = 0x2, ZBC_ZONE_TYPE_SEQWRITE_PREF = 0x3, - /* 0x4 to 0xf are reserved */ + ZBC_ZONE_TYPE_SEQ_OR_BEFORE_REQ = 0x4, + ZBC_ZONE_TYPE_GAP = 0x5, + /* 0x6 to 0xf are reserved */ }; /* Zone conditions of REPORT ZONES zone descriptors */ @@ -323,6 +325,11 @@ enum zbc_zone_cond { ZBC_ZONE_COND_OFFLINE = 0xf, }; +enum zbc_zone_alignment_method { + ZBC_CONSTANT_ZONE_LENGTH = 0x1, + ZBC_CONSTANT_ZONE_START_OFFSET = 0x8, +}; + /* Version descriptor values for INQUIRY */ enum scsi_version_descriptor { SCSI_VERSION_DESCRIPTOR_FCP4 = 0x0a40, -- cgit v1.2.3 From c0a5a21c25f37c9fd7b36072f9968cdff1e4aa13 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:51 +0530 Subject: bpf: Allow storing referenced kptr in map Extending the code in previous commits, introduce referenced kptr support, which needs to be tagged using 'kptr_ref' tag instead. Unlike unreferenced kptr, referenced kptr have a lot more restrictions. In addition to the type matching, only a newly introduced bpf_kptr_xchg helper is allowed to modify the map value at that offset. This transfers the referenced pointer being stored into the map, releasing the references state for the program, and returning the old value and creating new reference state for the returned pointer. Similar to unreferenced pointer case, return value for this case will also be PTR_TO_BTF_ID_OR_NULL. The reference for the returned pointer must either be eventually released by calling the corresponding release function, otherwise it must be transferred into another map. It is also allowed to call bpf_kptr_xchg with a NULL pointer, to clear the value, and obtain the old value if any. BPF_LDX, BPF_STX, and BPF_ST cannot access referenced kptr. A future commit will permit using BPF_LDX for such pointers, but attempt at making it safe, since the lifetime of object won't be guaranteed. There are valid reasons to enforce the restriction of permitting only bpf_kptr_xchg to operate on referenced kptr. The pointer value must be consistent in face of concurrent modification, and any prior values contained in the map must also be released before a new one is moved into the map. To ensure proper transfer of this ownership, bpf_kptr_xchg returns the old value, which the verifier would require the user to either free or move into another map, and releases the reference held for the pointer being moved in. In the future, direct BPF_XCHG instruction may also be permitted to work like bpf_kptr_xchg helper. Note that process_kptr_func doesn't have to call check_helper_mem_access, since we already disallow rdonly/wronly flags for map, which is what check_map_access_type checks, and we already ensure the PTR_TO_MAP_VALUE refers to kptr by obtaining its off_desc, so check_map_access is also not required. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-4-memxor@gmail.com --- include/linux/bpf.h | 8 ++++++++ include/uapi/linux/bpf.h | 12 ++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 492edd2c5713..24310837bafc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -160,8 +160,14 @@ enum { BPF_MAP_VALUE_OFF_MAX = 8, }; +enum bpf_kptr_type { + BPF_KPTR_UNREF, + BPF_KPTR_REF, +}; + struct bpf_map_value_off_desc { u32 offset; + enum bpf_kptr_type type; struct { struct btf *btf; u32 btf_id; @@ -418,6 +424,7 @@ enum bpf_arg_type { ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ + ARG_PTR_TO_KPTR, /* pointer to referenced kptr */ __BPF_ARG_TYPE_MAX, /* Extended arg_types. */ @@ -427,6 +434,7 @@ enum bpf_arg_type { ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, + ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d14b10b85e51..444fe6f1cf35 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5143,6 +5143,17 @@ union bpf_attr { * The **hash_algo** is returned on success, * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. + * + * void *bpf_kptr_xchg(void *map_value, void *ptr) + * Description + * Exchange kptr at pointer *map_value* with *ptr*, and return the + * old value. *ptr* can be NULL, otherwise it must be a referenced + * pointer which will be released when this helper is called. + * Return + * The old value of kptr (which can be NULL). The returned pointer + * if not NULL, is a reference which must be released using its + * corresponding release function, or moved into a BPF map before + * program exit. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5339,6 +5350,7 @@ union bpf_attr { FN(copy_from_user_task), \ FN(skb_set_tstamp), \ FN(ima_file_hash), \ + FN(kptr_xchg), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 6efe152d4061a83a2c5db6a0e5b58f9345c9742f Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:52 +0530 Subject: bpf: Prevent escaping of kptr loaded from maps While we can guarantee that even for unreferenced kptr, the object pointer points to being freed etc. can be handled by the verifier's exception handling (normal load patching to PROBE_MEM loads), we still cannot allow the user to pass these pointers to BPF helpers and kfunc, because the same exception handling won't be done for accesses inside the kernel. The same is true if a referenced pointer is loaded using normal load instruction. Since the reference is not guaranteed to be held while the pointer is used, it must be marked as untrusted. Hence introduce a new type flag, PTR_UNTRUSTED, which is used to mark all registers loading unreferenced and referenced kptr from BPF maps, and ensure they can never escape the BPF program and into the kernel by way of calling stable/unstable helpers. In check_ptr_to_btf_access, the !type_may_be_null check to reject type flags is still correct, as apart from PTR_MAYBE_NULL, only MEM_USER, MEM_PERCPU, and PTR_UNTRUSTED may be set for PTR_TO_BTF_ID. The first two are checked inside the function and rejected using a proper error message, but we still want to allow dereference of untrusted case. Also, we make sure to inherit PTR_UNTRUSTED when chain of pointers are walked, so that this flag is never dropped once it has been set on a PTR_TO_BTF_ID (i.e. trusted to untrusted transition can only be in one direction). In convert_ctx_accesses, extend the switch case to consider untrusted PTR_TO_BTF_ID in addition to normal PTR_TO_BTF_ID for PROBE_MEM conversion for BPF_LDX. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-5-memxor@gmail.com --- include/linux/bpf.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 24310837bafc..e13a5cbd4ebb 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -375,7 +375,15 @@ enum bpf_type_flag { /* Indicates that the argument will be released. */ OBJ_RELEASE = BIT(5 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = OBJ_RELEASE, + /* PTR is not trusted. This is only used with PTR_TO_BTF_ID, to mark + * unreferenced and referenced kptr loaded from map value using a load + * instruction, so that they can only be dereferenced but not escape the + * BPF program into the kernel (i.e. cannot be passed as arguments to + * kfunc or bpf helpers). + */ + PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = PTR_UNTRUSTED, }; /* Max number of base types. */ -- cgit v1.2.3 From 4d7d7f69f4b104b2ddeec6a1e7fcfd2d044ed8c4 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:53 +0530 Subject: bpf: Adapt copy_map_value for multiple offset case Since now there might be at most 10 offsets that need handling in copy_map_value, the manual shuffling and special case is no longer going to work. Hence, let's generalise the copy_map_value function by using a sorted array of offsets to skip regions that must be avoided while copying into and out of a map value. When the map is created, we populate the offset array in struct map, Then, copy_map_value uses this sorted offset array is used to memcpy while skipping timer, spin lock, and kptr. The array is allocated as in most cases none of these special fields would be present in map value, hence we can save on space for the common case by not embedding the entire object inside bpf_map struct. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-6-memxor@gmail.com --- include/linux/bpf.h | 56 ++++++++++++++++++++++++++++------------------------- 1 file changed, 30 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e13a5cbd4ebb..4e12b27a5de6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -158,6 +158,9 @@ struct bpf_map_ops { enum { /* Support at most 8 pointers in a BPF map value */ BPF_MAP_VALUE_OFF_MAX = 8, + BPF_MAP_OFF_ARR_MAX = BPF_MAP_VALUE_OFF_MAX + + 1 + /* for bpf_spin_lock */ + 1, /* for bpf_timer */ }; enum bpf_kptr_type { @@ -179,6 +182,12 @@ struct bpf_map_value_off { struct bpf_map_value_off_desc off[]; }; +struct bpf_map_off_arr { + u32 cnt; + u32 field_off[BPF_MAP_OFF_ARR_MAX]; + u8 field_sz[BPF_MAP_OFF_ARR_MAX]; +}; + struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). @@ -207,10 +216,7 @@ struct bpf_map { struct mem_cgroup *memcg; #endif char name[BPF_OBJ_NAME_LEN]; - bool bypass_spec_v1; - bool frozen; /* write-once; write-protected by freeze_mutex */ - /* 6 bytes hole */ - + struct bpf_map_off_arr *off_arr; /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ @@ -230,6 +236,8 @@ struct bpf_map { bool jited; bool xdp_has_frags; } owner; + bool bypass_spec_v1; + bool frozen; /* write-once; write-protected by freeze_mutex */ }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -253,37 +261,33 @@ static inline void check_and_init_map_value(struct bpf_map *map, void *dst) memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); if (unlikely(map_value_has_timer(map))) memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); + if (unlikely(map_value_has_kptrs(map))) { + struct bpf_map_value_off *tab = map->kptr_off_tab; + int i; + + for (i = 0; i < tab->nr_off; i++) + *(u64 *)(dst + tab->off[i].offset) = 0; + } } /* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { - u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0; + u32 curr_off = 0; + int i; - if (unlikely(map_value_has_spin_lock(map))) { - s_off = map->spin_lock_off; - s_sz = sizeof(struct bpf_spin_lock); - } - if (unlikely(map_value_has_timer(map))) { - t_off = map->timer_off; - t_sz = sizeof(struct bpf_timer); + if (likely(!map->off_arr)) { + memcpy(dst, src, map->value_size); + return; } - if (unlikely(s_sz || t_sz)) { - if (s_off < t_off || !s_sz) { - swap(s_off, t_off); - swap(s_sz, t_sz); - } - memcpy(dst, src, t_off); - memcpy(dst + t_off + t_sz, - src + t_off + t_sz, - s_off - t_off - t_sz); - memcpy(dst + s_off + s_sz, - src + s_off + s_sz, - map->value_size - s_off - s_sz); - } else { - memcpy(dst, src, map->value_size); + for (i = 0; i < map->off_arr->cnt; i++) { + u32 next_off = map->off_arr->field_off[i]; + + memcpy(dst + curr_off, src + curr_off, next_off - curr_off); + curr_off += map->off_arr->field_sz[i]; } + memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off); } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); -- cgit v1.2.3 From 5ce937d613a423ca3102f53d9f3daf4210c1b6e2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:54 +0530 Subject: bpf: Populate pairs of btf_id and destructor kfunc in btf To support storing referenced PTR_TO_BTF_ID in maps, we require associating a specific BTF ID with a 'destructor' kfunc. This is because we need to release a live referenced pointer at a certain offset in map value from the map destruction path, otherwise we end up leaking resources. Hence, introduce support for passing an array of btf_id, kfunc_btf_id pairs that denote a BTF ID and its associated release function. Then, add an accessor 'btf_find_dtor_kfunc' which can be used to look up the destructor kfunc of a certain BTF ID. If found, we can use it to free the object from the map free path. The registration of these pairs also serve as a whitelist of structures which are allowed as referenced PTR_TO_BTF_ID in a BPF map, because without finding the destructor kfunc, we will bail and return an error. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-7-memxor@gmail.com --- include/linux/btf.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index 19c297f9a52f..fea424681d66 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -40,6 +40,11 @@ struct btf_kfunc_id_set { }; }; +struct btf_id_dtor_kfunc { + u32 btf_id; + u32 kfunc_btf_id; +}; + extern const struct file_operations btf_fops; void btf_get(struct btf *btf); @@ -346,6 +351,9 @@ bool btf_kfunc_id_set_contains(const struct btf *btf, enum btf_kfunc_type type, u32 kfunc_btf_id); int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, const struct btf_kfunc_id_set *s); +s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); +int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, + struct module *owner); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -369,6 +377,15 @@ static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, { return 0; } +static inline s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id) +{ + return -ENOENT; +} +static inline int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, + u32 add_cnt, struct module *owner) +{ + return 0; +} #endif #endif -- cgit v1.2.3 From 14a324f6a67ef6a53e04362a70160a47eb8afffa Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:55 +0530 Subject: bpf: Wire up freeing of referenced kptr A destructor kfunc can be defined as void func(type *), where type may be void or any other pointer type as per convenience. In this patch, we ensure that the type is sane and capture the function pointer into off_desc of ptr_off_tab for the specific pointer offset, with the invariant that the dtor pointer is always set when 'kptr_ref' tag is applied to the pointer's pointee type, which is indicated by the flag BPF_MAP_VALUE_OFF_F_REF. Note that only BTF IDs whose destructor kfunc is registered, thus become the allowed BTF IDs for embedding as referenced kptr. Hence it serves the purpose of finding dtor kfunc BTF ID, as well acting as a check against the whitelist of allowed BTF IDs for this purpose. Finally, wire up the actual freeing of the referenced pointer if any at all available offsets, so that no references are leaked after the BPF map goes away and the BPF program previously moved the ownership a referenced pointer into it. The behavior is similar to BPF timers, where bpf_map_{update,delete}_elem will free any existing referenced kptr. The same case is with LRU map's bpf_lru_push_free/htab_lru_push_free functions, which are extended to reset unreferenced and free referenced kptr. Note that unlike BPF timers, kptr is not reset or freed when map uref drops to zero. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-8-memxor@gmail.com --- include/linux/bpf.h | 4 ++++ include/linux/btf.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4e12b27a5de6..6141564c76c8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -23,6 +23,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -173,6 +174,8 @@ struct bpf_map_value_off_desc { enum bpf_kptr_type type; struct { struct btf *btf; + struct module *module; + btf_dtor_kfunc_t dtor; u32 btf_id; } kptr; }; @@ -1447,6 +1450,7 @@ struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u3 void bpf_map_free_kptr_off_tab(struct bpf_map *map); struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map); bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b); +void bpf_map_free_kptrs(struct bpf_map *map, void *map_value); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); diff --git a/include/linux/btf.h b/include/linux/btf.h index fea424681d66..f70625dd5bb4 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -45,6 +45,8 @@ struct btf_id_dtor_kfunc { u32 kfunc_btf_id; }; +typedef void (*btf_dtor_kfunc_t)(void *); + extern const struct file_operations btf_fops; void btf_get(struct btf *btf); -- cgit v1.2.3 From a1ef195996526da45bbc9710849254023df75aea Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:56 +0530 Subject: bpf: Teach verifier about kptr_get kfunc helpers We introduce a new style of kfunc helpers, namely *_kptr_get, where they take pointer to the map value which points to a referenced kernel pointer contained in the map. Since this is referenced, only bpf_kptr_xchg from BPF side and xchg from kernel side is allowed to change the current value, and each pointer that resides in that location would be referenced, and RCU protected (this must be kept in mind while adding kernel types embeddable as reference kptr in BPF maps). This means that if do the load of the pointer value in an RCU read section, and find a live pointer, then as long as we hold RCU read lock, it won't be freed by a parallel xchg + release operation. This allows us to implement a safe refcount increment scheme. Hence, enforce that first argument of all such kfunc is a proper PTR_TO_MAP_VALUE pointing at the right offset to referenced pointer. For the rest of the arguments, they are subjected to typical kfunc argument checks, hence allowing some flexibility in passing more intent into how the reference should be taken. For instance, in case of struct nf_conn, it is not freed until RCU grace period ends, but can still be reused for another tuple once refcount has dropped to zero. Hence, a bpf_ct_kptr_get helper not only needs to call refcount_inc_not_zero, but also do a tuple match after incrementing the reference, and when it fails to match it, put the reference again and return NULL. This can be implemented easily if we allow passing additional parameters to the bpf_ct_kptr_get kfunc, like a struct bpf_sock_tuple * and a tuple__sz pair. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-9-memxor@gmail.com --- include/linux/btf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index f70625dd5bb4..2611cea2c2b6 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -17,6 +17,7 @@ enum btf_kfunc_type { BTF_KFUNC_TYPE_ACQUIRE, BTF_KFUNC_TYPE_RELEASE, BTF_KFUNC_TYPE_RET_NULL, + BTF_KFUNC_TYPE_KPTR_ACQUIRE, BTF_KFUNC_TYPE_MAX, }; @@ -35,6 +36,7 @@ struct btf_kfunc_id_set { struct btf_id_set *acquire_set; struct btf_id_set *release_set; struct btf_id_set *ret_null_set; + struct btf_id_set *kptr_acquire_set; }; struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX]; }; -- cgit v1.2.3 From 2ab3b3808eb17f729edfd69e061667ca0a427195 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:57 +0530 Subject: bpf: Make BTF type match stricter for release arguments The current of behavior of btf_struct_ids_match for release arguments is that when type match fails, it retries with first member type again (recursively). Since the offset is already 0, this is akin to just casting the pointer in normal C, since if type matches it was just embedded inside parent sturct as an object. However, we want to reject cases for release function type matching, be it kfunc or BPF helpers. An example is the following: struct foo { struct bar b; }; struct foo *v = acq_foo(); rel_bar(&v->b); // btf_struct_ids_match fails btf_types_are_same, then // retries with first member type and succeeds, while // it should fail. Hence, don't walk the struct and only rely on btf_types_are_same for strict mode. All users of strict mode must be dealing with zero offset anyway, since otherwise they would want the struct to be walked. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-10-memxor@gmail.com --- include/linux/bpf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6141564c76c8..0af5793ba417 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1748,7 +1748,8 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, u32 *next_btf_id, enum bpf_type_flag *flag); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, - const struct btf *need_btf, u32 need_type_id); + const struct btf *need_btf, u32 need_type_id, + bool strict); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, -- cgit v1.2.3 From 66eb6df79aefd6b3f7d2e749da7104e90cedc0ff Mon Sep 17 00:00:00 2001 From: Andrew Davis Date: Mon, 25 Apr 2022 09:16:16 -0500 Subject: tee: remove tee_shm_va2pa() and tee_shm_pa2va() We should not need to index into SHMs based on absolute VA/PA. These functions are not used and this kind of usage should not be encouraged anyway. Remove these functions. Signed-off-by: Andrew Davis Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 911cad324acc..17eb1c5205d3 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -298,24 +298,6 @@ void tee_shm_free(struct tee_shm *shm); */ void tee_shm_put(struct tee_shm *shm); -/** - * tee_shm_va2pa() - Get physical address of a virtual address - * @shm: Shared memory handle - * @va: Virtual address to tranlsate - * @pa: Returned physical address - * @returns 0 on success and < 0 on failure - */ -int tee_shm_va2pa(struct tee_shm *shm, void *va, phys_addr_t *pa); - -/** - * tee_shm_pa2va() - Get virtual address of a physical address - * @shm: Shared memory handle - * @pa: Physical address to tranlsate - * @va: Returned virtual address - * @returns 0 on success and < 0 on failure - */ -int tee_shm_pa2va(struct tee_shm *shm, phys_addr_t pa, void **va); - /** * tee_shm_get_va() - Get virtual address of a shared memory plus an offset * @shm: Shared memory handle -- cgit v1.2.3 From d8fc1c7c4c9b705ce5f5bba772ad66a0137c685d Mon Sep 17 00:00:00 2001 From: Andrew Davis Date: Mon, 25 Apr 2022 09:16:17 -0500 Subject: tee: remove flags TEE_IOCTL_SHM_MAPPED and TEE_IOCTL_SHM_DMA_BUF These look to be leftover from an early edition of this driver. Userspace does not need this information. Checking all users of this that I have access to I have verified no one is using them. They leak internal use flags out to userspace. Even more they are not correct anymore after a45ea4efa358. Lets drop these flags before someone does try to use them for something and they become ABI. Signed-off-by: Andrew Davis Acked-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/uapi/linux/tee.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index 25a6c534beb1..23e57164693c 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -42,10 +42,6 @@ #define TEE_IOC_MAGIC 0xa4 #define TEE_IOC_BASE 0 -/* Flags relating to shared memory */ -#define TEE_IOCTL_SHM_MAPPED 0x1 /* memory mapped in normal world */ -#define TEE_IOCTL_SHM_DMA_BUF 0x2 /* dma-buf handle on shared memory */ - #define TEE_MAX_ARG_SIZE 1024 #define TEE_GEN_CAP_GP (1 << 0)/* GlobalPlatform compliant TEE */ -- cgit v1.2.3 From 97730bbb242cde22b7140acd202ffd88823886c9 Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Thu, 21 Apr 2022 14:22:00 -0700 Subject: firmware_loader: Add firmware-upload support Extend the firmware subsystem to support a persistent sysfs interface that userspace may use to initiate a firmware update. For example, FPGA based PCIe cards load firmware and FPGA images from local FLASH when the card boots. The images in FLASH may be updated with new images provided by the user at his/her convenience. A device driver may call firmware_upload_register() to expose persistent "loading" and "data" sysfs files. These files are used in the same way as the fallback sysfs "loading" and "data" files. When 0 is written to "loading" to complete the write of firmware data, the data is transferred to the lower-level driver using pre-registered call-back functions. The data transfer is done in the context of a kernel worker thread. Reviewed-by: Luis Chamberlain Reviewed-by: Tianfei zhang Tested-by: Matthew Gerlach Signed-off-by: Russ Weight Link: https://lore.kernel.org/r/20220421212204.36052-5-russell.h.weight@intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware.h | 82 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) (limited to 'include') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index ec2ccfebef65..de7fea3bca51 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -17,6 +17,64 @@ struct firmware { void *priv; }; +/** + * enum fw_upload_err - firmware upload error codes + * @FW_UPLOAD_ERR_NONE: returned to indicate success + * @FW_UPLOAD_ERR_HW_ERROR: error signalled by hardware, see kernel log + * @FW_UPLOAD_ERR_TIMEOUT: SW timed out on handshake with HW/firmware + * @FW_UPLOAD_ERR_CANCELED: upload was cancelled by the user + * @FW_UPLOAD_ERR_BUSY: there is an upload operation already in progress + * @FW_UPLOAD_ERR_INVALID_SIZE: invalid firmware image size + * @FW_UPLOAD_ERR_RW_ERROR: read or write to HW failed, see kernel log + * @FW_UPLOAD_ERR_WEAROUT: FLASH device is approaching wear-out, wait & retry + * @FW_UPLOAD_ERR_MAX: Maximum error code marker + */ +enum fw_upload_err { + FW_UPLOAD_ERR_NONE, + FW_UPLOAD_ERR_HW_ERROR, + FW_UPLOAD_ERR_TIMEOUT, + FW_UPLOAD_ERR_CANCELED, + FW_UPLOAD_ERR_BUSY, + FW_UPLOAD_ERR_INVALID_SIZE, + FW_UPLOAD_ERR_RW_ERROR, + FW_UPLOAD_ERR_WEAROUT, + FW_UPLOAD_ERR_MAX +}; + +struct fw_upload { + void *dd_handle; /* reference to parent driver */ + void *priv; /* firmware loader private fields */ +}; + +/** + * struct fw_upload_ops - device specific operations to support firmware upload + * @prepare: Required: Prepare secure update + * @write: Required: The write() op receives the remaining + * size to be written and must return the actual + * size written or a negative error code. The write() + * op will be called repeatedly until all data is + * written. + * @poll_complete: Required: Check for the completion of the + * HW authentication/programming process. + * @cancel: Required: Request cancellation of update. This op + * is called from the context of a different kernel + * thread, so race conditions need to be considered. + * @cleanup: Optional: Complements the prepare() + * function and is called at the completion + * of the update, on success or failure, if the + * prepare function succeeded. + */ +struct fw_upload_ops { + enum fw_upload_err (*prepare)(struct fw_upload *fw_upload, + const u8 *data, u32 size); + enum fw_upload_err (*write)(struct fw_upload *fw_upload, + const u8 *data, u32 offset, + u32 size, u32 *written); + enum fw_upload_err (*poll_complete)(struct fw_upload *fw_upload); + void (*cancel)(struct fw_upload *fw_upload); + void (*cleanup)(struct fw_upload *fw_upload); +}; + struct module; struct device; @@ -112,6 +170,30 @@ static inline int request_partial_firmware_into_buf #endif +#ifdef CONFIG_FW_UPLOAD + +struct fw_upload * +firmware_upload_register(struct module *module, struct device *parent, + const char *name, const struct fw_upload_ops *ops, + void *dd_handle); +void firmware_upload_unregister(struct fw_upload *fw_upload); + +#else + +static inline struct fw_upload * +firmware_upload_register(struct module *module, struct device *parent, + const char *name, const struct fw_upload_ops *ops, + void *dd_handle) +{ + return ERR_PTR(-EINVAL); +} + +static inline void firmware_upload_unregister(struct fw_upload *fw_upload) +{ +} + +#endif + int firmware_request_cache(struct device *device, const char *name); #endif -- cgit v1.2.3 From d405ac52ab19301622bddabf4bf925d199937823 Mon Sep 17 00:00:00 2001 From: Rohit Agarwal Date: Wed, 13 Apr 2022 18:23:34 +0530 Subject: dt-bindings: interconnect: Add Qualcomm SDX65 DT bindings Add interconnect IDs for Qualcomm SDX65 platform. Signed-off-by: Rohit Agarwal Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/1649854415-11174-2-git-send-email-quic_rohiagar@quicinc.com Signed-off-by: Georgi Djakov --- include/dt-bindings/interconnect/qcom,sdx65.h | 67 +++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) create mode 100644 include/dt-bindings/interconnect/qcom,sdx65.h (limited to 'include') diff --git a/include/dt-bindings/interconnect/qcom,sdx65.h b/include/dt-bindings/interconnect/qcom,sdx65.h new file mode 100644 index 000000000000..b25288aa7d74 --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,sdx65.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */ +/* + * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SDX65_H +#define __DT_BINDINGS_INTERCONNECT_QCOM_SDX65_H + +#define MASTER_LLCC 0 +#define SLAVE_EBI1 1 + +#define MASTER_TCU_0 0 +#define MASTER_SNOC_GC_MEM_NOC 1 +#define MASTER_APPSS_PROC 2 +#define SLAVE_LLCC 3 +#define SLAVE_MEM_NOC_SNOC 4 +#define SLAVE_MEM_NOC_PCIE_SNOC 5 + +#define MASTER_AUDIO 0 +#define MASTER_BLSP_1 1 +#define MASTER_QDSS_BAM 2 +#define MASTER_QPIC 3 +#define MASTER_SNOC_CFG 4 +#define MASTER_SPMI_FETCHER 5 +#define MASTER_ANOC_SNOC 6 +#define MASTER_IPA 7 +#define MASTER_MEM_NOC_SNOC 8 +#define MASTER_MEM_NOC_PCIE_SNOC 9 +#define MASTER_CRYPTO 10 +#define MASTER_IPA_PCIE 11 +#define MASTER_PCIE_0 12 +#define MASTER_QDSS_ETR 13 +#define MASTER_SDCC_1 14 +#define MASTER_USB3 15 +#define SLAVE_AOSS 16 +#define SLAVE_APPSS 17 +#define SLAVE_AUDIO 18 +#define SLAVE_BLSP_1 19 +#define SLAVE_CLK_CTL 20 +#define SLAVE_CRYPTO_0_CFG 21 +#define SLAVE_CNOC_DDRSS 22 +#define SLAVE_ECC_CFG 23 +#define SLAVE_IMEM_CFG 24 +#define SLAVE_IPA_CFG 25 +#define SLAVE_CNOC_MSS 26 +#define SLAVE_PCIE_PARF 27 +#define SLAVE_PDM 28 +#define SLAVE_PRNG 29 +#define SLAVE_QDSS_CFG 30 +#define SLAVE_QPIC 31 +#define SLAVE_SDCC_1 32 +#define SLAVE_SNOC_CFG 33 +#define SLAVE_SPMI_FETCHER 34 +#define SLAVE_SPMI_VGI_COEX 35 +#define SLAVE_TCSR 36 +#define SLAVE_TLMM 37 +#define SLAVE_USB3 38 +#define SLAVE_USB3_PHY_CFG 39 +#define SLAVE_ANOC_SNOC 40 +#define SLAVE_SNOC_MEM_NOC_GC 41 +#define SLAVE_IMEM 42 +#define SLAVE_SERVICE_SNOC 43 +#define SLAVE_PCIE_0 44 +#define SLAVE_QDSS_STM 45 +#define SLAVE_TCU 46 + +#endif -- cgit v1.2.3 From d434743e5cac3558381b767f343eef5af246a4dc Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:37 +0530 Subject: bus: mhi: ep: Add support for registering MHI endpoint controllers This commit adds support for registering MHI endpoint controller drivers with the MHI endpoint stack. MHI endpoint controller drivers manage the interaction with the host machines (such as x86). They are also the MHI endpoint bus master in charge of managing the physical link between the host and endpoint device. Eventhough the MHI spec is bus agnostic, the current implementation is entirely based on PCIe bus. The endpoint controller driver encloses all information about the underlying physical bus like PCIe. The registration process involves parsing the channel configuration and allocating an MHI EP device. Channels used in the endpoint stack follows the perspective of the MHI host stack. i.e., UL - From host to endpoint DL - From endpoint to host Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-2-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 136 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 136 insertions(+) create mode 100644 include/linux/mhi_ep.h (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h new file mode 100644 index 000000000000..891b199a9703 --- /dev/null +++ b/include/linux/mhi_ep.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022, Linaro Ltd. + * + */ +#ifndef _MHI_EP_H_ +#define _MHI_EP_H_ + +#include +#include + +#define MHI_EP_DEFAULT_MTU 0x8000 + +/** + * struct mhi_ep_channel_config - Channel configuration structure for controller + * @name: The name of this channel + * @num: The number assigned to this channel + * @num_elements: The number of elements that can be queued to this channel + * @dir: Direction that data may flow on this channel + */ +struct mhi_ep_channel_config { + char *name; + u32 num; + u32 num_elements; + enum dma_data_direction dir; +}; + +/** + * struct mhi_ep_cntrl_config - MHI Endpoint controller configuration + * @mhi_version: MHI spec version supported by the controller + * @max_channels: Maximum number of channels supported + * @num_channels: Number of channels defined in @ch_cfg + * @ch_cfg: Array of defined channels + */ +struct mhi_ep_cntrl_config { + u32 mhi_version; + u32 max_channels; + u32 num_channels; + const struct mhi_ep_channel_config *ch_cfg; +}; + +/** + * struct mhi_ep_db_info - MHI Endpoint doorbell info + * @mask: Mask of the doorbell interrupt + * @status: Status of the doorbell interrupt + */ +struct mhi_ep_db_info { + u32 mask; + u32 status; +}; + +/** + * struct mhi_ep_cntrl - MHI Endpoint controller structure + * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI + * Endpoint controller + * @mhi_dev: MHI Endpoint device instance for the controller + * @mmio: MMIO region containing the MHI registers + * @mhi_chan: Points to the channel configuration table + * @mhi_event: Points to the event ring configurations table + * @mhi_cmd: Points to the command ring configurations table + * @sm: MHI Endpoint state machine + * @raise_irq: CB function for raising IRQ to the host + * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it + * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context + * @read_from_host: CB function for reading from host memory from endpoint + * @write_to_host: CB function for writing to host memory from endpoint + * @mhi_state: MHI Endpoint state + * @max_chan: Maximum channels supported by the endpoint controller + * @mru: MRU (Maximum Receive Unit) value of the endpoint controller + * @index: MHI Endpoint controller index + */ +struct mhi_ep_cntrl { + struct device *cntrl_dev; + struct mhi_ep_device *mhi_dev; + void __iomem *mmio; + + struct mhi_ep_chan *mhi_chan; + struct mhi_ep_event *mhi_event; + struct mhi_ep_cmd *mhi_cmd; + struct mhi_ep_sm *sm; + + void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); + int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, + void __iomem **virt, size_t size); + void (*unmap_free)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t phys, + void __iomem *virt, size_t size); + int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, u64 from, void *to, size_t size); + int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, void *from, u64 to, size_t size); + + enum mhi_state mhi_state; + + u32 max_chan; + u32 mru; + u32 index; +}; + +/** + * struct mhi_ep_device - Structure representing an MHI Endpoint device that binds + * to channels or is associated with controllers + * @dev: Driver model device node for the MHI Endpoint device + * @mhi_cntrl: Controller the device belongs to + * @id: Pointer to MHI Endpoint device ID struct + * @name: Name of the associated MHI Endpoint device + * @ul_chan: UL channel for the device + * @dl_chan: DL channel for the device + * @dev_type: MHI device type + */ +struct mhi_ep_device { + struct device dev; + struct mhi_ep_cntrl *mhi_cntrl; + const struct mhi_device_id *id; + const char *name; + struct mhi_ep_chan *ul_chan; + struct mhi_ep_chan *dl_chan; + enum mhi_device_type dev_type; +}; + +#define to_mhi_ep_device(dev) container_of(dev, struct mhi_ep_device, dev) + +/** + * mhi_ep_register_controller - Register MHI Endpoint controller + * @mhi_cntrl: MHI Endpoint controller to register + * @config: Configuration to use for the controller + * + * Return: 0 if controller registrations succeeds, a negative error code otherwise. + */ +int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl, + const struct mhi_ep_cntrl_config *config); + +/** + * mhi_ep_unregister_controller - Unregister MHI Endpoint controller + * @mhi_cntrl: MHI Endpoint controller to unregister + */ +void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl); + +#endif -- cgit v1.2.3 From ee0360b20b3fa08e2eee300eacb45e812ae44578 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:38 +0530 Subject: bus: mhi: ep: Add support for registering MHI endpoint client drivers This commit adds support for registering MHI endpoint client drivers with the MHI endpoint stack. MHI endpoint client drivers bind to one or more MHI endpoint devices inorder to send and receive the upper-layer protocol packets like IP packets, modem control messages, and diagnostics messages over MHI bus. Reviewed-by: Hemant Kumar Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-3-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 57 ++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 55 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 891b199a9703..e2b94f9eb846 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -101,8 +101,8 @@ struct mhi_ep_cntrl { * @mhi_cntrl: Controller the device belongs to * @id: Pointer to MHI Endpoint device ID struct * @name: Name of the associated MHI Endpoint device - * @ul_chan: UL channel for the device - * @dl_chan: DL channel for the device + * @ul_chan: UL (from host to endpoint) channel for the device + * @dl_chan: DL (from endpoint to host) channel for the device * @dev_type: MHI device type */ struct mhi_ep_device { @@ -115,7 +115,60 @@ struct mhi_ep_device { enum mhi_device_type dev_type; }; +/** + * struct mhi_ep_driver - Structure representing a MHI Endpoint client driver + * @id_table: Pointer to MHI Endpoint device ID table + * @driver: Device driver model driver + * @probe: CB function for client driver probe function + * @remove: CB function for client driver remove function + * @ul_xfer_cb: CB function for UL (from host to endpoint) data transfer + * @dl_xfer_cb: CB function for DL (from endpoint to host) data transfer + */ +struct mhi_ep_driver { + const struct mhi_device_id *id_table; + struct device_driver driver; + int (*probe)(struct mhi_ep_device *mhi_ep, + const struct mhi_device_id *id); + void (*remove)(struct mhi_ep_device *mhi_ep); + void (*ul_xfer_cb)(struct mhi_ep_device *mhi_dev, + struct mhi_result *result); + void (*dl_xfer_cb)(struct mhi_ep_device *mhi_dev, + struct mhi_result *result); +}; + #define to_mhi_ep_device(dev) container_of(dev, struct mhi_ep_device, dev) +#define to_mhi_ep_driver(drv) container_of(drv, struct mhi_ep_driver, driver) + +/* + * module_mhi_ep_driver() - Helper macro for drivers that don't do + * anything special other than using default mhi_ep_driver_register() and + * mhi_ep_driver_unregister(). This eliminates a lot of boilerplate. + * Each module may only use this macro once. + */ +#define module_mhi_ep_driver(mhi_drv) \ + module_driver(mhi_drv, mhi_ep_driver_register, \ + mhi_ep_driver_unregister) + +/* + * Macro to avoid include chaining to get THIS_MODULE + */ +#define mhi_ep_driver_register(mhi_drv) \ + __mhi_ep_driver_register(mhi_drv, THIS_MODULE) + +/** + * __mhi_ep_driver_register - Register a driver with MHI Endpoint bus + * @mhi_drv: Driver to be associated with the device + * @owner: The module owner + * + * Return: 0 if driver registrations succeeds, a negative error code otherwise. + */ +int __mhi_ep_driver_register(struct mhi_ep_driver *mhi_drv, struct module *owner); + +/** + * mhi_ep_driver_unregister - Unregister a driver from MHI Endpoint bus + * @mhi_drv: Driver associated with the device + */ +void mhi_ep_driver_unregister(struct mhi_ep_driver *mhi_drv); /** * mhi_ep_register_controller - Register MHI Endpoint controller -- cgit v1.2.3 From e9e4da23cd65ea76ba658346f5c182791bd1cea9 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:40 +0530 Subject: bus: mhi: ep: Add support for managing MMIO registers Add support for managing the Memory Mapped Input Output (MMIO) registers of the MHI bus. All MHI operations are carried out using the MMIO registers by both host and the endpoint device. The MMIO registers reside inside the endpoint device memory (fixed location based on the platform) and the address is passed by the MHI EP controller driver during its registration. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-5-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index e2b94f9eb846..5db048e258e4 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -59,6 +59,10 @@ struct mhi_ep_db_info { * @mhi_event: Points to the event ring configurations table * @mhi_cmd: Points to the command ring configurations table * @sm: MHI Endpoint state machine + * @ch_ctx_host_pa: Physical address of host channel context data structure + * @ev_ctx_host_pa: Physical address of host event context data structure + * @cmd_ctx_host_pa: Physical address of host command context data structure + * @chdb: Array of channel doorbell interrupt info * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -67,6 +71,10 @@ struct mhi_ep_db_info { * @mhi_state: MHI Endpoint state * @max_chan: Maximum channels supported by the endpoint controller * @mru: MRU (Maximum Receive Unit) value of the endpoint controller + * @event_rings: Number of event rings supported by the endpoint controller + * @hw_event_rings: Number of hardware event rings supported by the endpoint controller + * @chdb_offset: Channel doorbell offset set by the host + * @erdb_offset: Event ring doorbell offset set by the host * @index: MHI Endpoint controller index */ struct mhi_ep_cntrl { @@ -79,6 +87,12 @@ struct mhi_ep_cntrl { struct mhi_ep_cmd *mhi_cmd; struct mhi_ep_sm *sm; + u64 ch_ctx_host_pa; + u64 ev_ctx_host_pa; + u64 cmd_ctx_host_pa; + + struct mhi_ep_db_info chdb[4]; + void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, void __iomem **virt, size_t size); @@ -91,6 +105,10 @@ struct mhi_ep_cntrl { u32 max_chan; u32 mru; + u32 event_rings; + u32 hw_event_rings; + u32 chdb_offset; + u32 erdb_offset; u32 index; }; -- cgit v1.2.3 From 961aeb6892242e0a667f5b8eb62b9b0a6041752c Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:42 +0530 Subject: bus: mhi: ep: Add support for sending events to the host Add support for sending the events to the host over MHI bus from the endpoint. Following events are supported: 1. Transfer completion event 2. Command completion event 3. State change event 4. Execution Environment (EE) change event An event is sent whenever an operation has been completed in the MHI EP device. Event is sent using the MHI event ring and additionally the host is notified using an IRQ if required. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-7-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 5db048e258e4..46236ffb528a 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -59,10 +59,14 @@ struct mhi_ep_db_info { * @mhi_event: Points to the event ring configurations table * @mhi_cmd: Points to the command ring configurations table * @sm: MHI Endpoint state machine + * @ch_ctx_cache: Cache of host channel context data structure + * @ev_ctx_cache: Cache of host event context data structure + * @cmd_ctx_cache: Cache of host command context data structure * @ch_ctx_host_pa: Physical address of host channel context data structure * @ev_ctx_host_pa: Physical address of host event context data structure * @cmd_ctx_host_pa: Physical address of host command context data structure * @chdb: Array of channel doorbell interrupt info + * @event_lock: Lock for protecting event rings * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -87,11 +91,15 @@ struct mhi_ep_cntrl { struct mhi_ep_cmd *mhi_cmd; struct mhi_ep_sm *sm; + struct mhi_chan_ctxt *ch_ctx_cache; + struct mhi_event_ctxt *ev_ctx_cache; + struct mhi_cmd_ctxt *cmd_ctx_cache; u64 ch_ctx_host_pa; u64 ev_ctx_host_pa; u64 cmd_ctx_host_pa; struct mhi_ep_db_info chdb[4]; + struct mutex event_lock; void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, -- cgit v1.2.3 From f9baa4f737950523ca648866dfa345ac378e4487 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:43 +0530 Subject: bus: mhi: ep: Add support for managing MHI state machine Add support for managing the MHI state machine by controlling the state transitions. Only the following MHI state transitions are supported: 1. Ready state 2. M0 state 3. M3 state 4. SYS_ERR state Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-8-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 46236ffb528a..2880d2aa88b8 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -67,6 +67,11 @@ struct mhi_ep_db_info { * @cmd_ctx_host_pa: Physical address of host command context data structure * @chdb: Array of channel doorbell interrupt info * @event_lock: Lock for protecting event rings + * @list_lock: Lock for protecting state transition and channel doorbell lists + * @state_lock: Lock for protecting state transitions + * @st_transition_list: List of state transitions + * @wq: Dedicated workqueue for handling rings and state changes + * @state_work: State transition worker * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -100,6 +105,13 @@ struct mhi_ep_cntrl { struct mhi_ep_db_info chdb[4]; struct mutex event_lock; + spinlock_t list_lock; + spinlock_t state_lock; + + struct list_head st_transition_list; + + struct workqueue_struct *wq; + struct work_struct state_work; void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, -- cgit v1.2.3 From 4799e71b082615445dc40ba0bbb86cbb76c24724 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:44 +0530 Subject: bus: mhi: ep: Add support for processing MHI endpoint interrupts Add support for processing MHI endpoint interrupts such as control interrupt, command interrupt and channel interrupt from the host. The interrupts will be generated in the endpoint device whenever host writes to the corresponding doorbell registers. The doorbell logic is handled inside the hardware internally. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-9-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 2880d2aa88b8..137bd3ee2e43 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -70,6 +70,7 @@ struct mhi_ep_db_info { * @list_lock: Lock for protecting state transition and channel doorbell lists * @state_lock: Lock for protecting state transitions * @st_transition_list: List of state transitions + * @ch_db_list: List of queued channel doorbells * @wq: Dedicated workqueue for handling rings and state changes * @state_work: State transition worker * @raise_irq: CB function for raising IRQ to the host @@ -85,6 +86,7 @@ struct mhi_ep_db_info { * @chdb_offset: Channel doorbell offset set by the host * @erdb_offset: Event ring doorbell offset set by the host * @index: MHI Endpoint controller index + * @irq: IRQ used by the endpoint controller */ struct mhi_ep_cntrl { struct device *cntrl_dev; @@ -109,6 +111,7 @@ struct mhi_ep_cntrl { spinlock_t state_lock; struct list_head st_transition_list; + struct list_head ch_db_list; struct workqueue_struct *wq; struct work_struct state_work; @@ -130,6 +133,7 @@ struct mhi_ep_cntrl { u32 chdb_offset; u32 erdb_offset; u32 index; + int irq; }; /** -- cgit v1.2.3 From fb3a26b7e8aff11e44d582604f61c38f63bd507c Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:45 +0530 Subject: bus: mhi: ep: Add support for powering up the MHI endpoint stack Add support for MHI endpoint power_up that includes initializing the MMIO and rings, caching the host MHI registers, and setting the MHI state to M0. After registering the MHI EP controller, the stack has to be powered up for usage. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-10-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 137bd3ee2e43..3b065f82fbeb 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -65,6 +65,9 @@ struct mhi_ep_db_info { * @ch_ctx_host_pa: Physical address of host channel context data structure * @ev_ctx_host_pa: Physical address of host event context data structure * @cmd_ctx_host_pa: Physical address of host command context data structure + * @ch_ctx_cache_phys: Physical address of the host channel context cache + * @ev_ctx_cache_phys: Physical address of the host event context cache + * @cmd_ctx_cache_phys: Physical address of the host command context cache * @chdb: Array of channel doorbell interrupt info * @event_lock: Lock for protecting event rings * @list_lock: Lock for protecting state transition and channel doorbell lists @@ -87,6 +90,7 @@ struct mhi_ep_db_info { * @erdb_offset: Event ring doorbell offset set by the host * @index: MHI Endpoint controller index * @irq: IRQ used by the endpoint controller + * @enabled: Check if the endpoint controller is enabled or not */ struct mhi_ep_cntrl { struct device *cntrl_dev; @@ -104,6 +108,9 @@ struct mhi_ep_cntrl { u64 ch_ctx_host_pa; u64 ev_ctx_host_pa; u64 cmd_ctx_host_pa; + phys_addr_t ch_ctx_cache_phys; + phys_addr_t ev_ctx_cache_phys; + phys_addr_t cmd_ctx_cache_phys; struct mhi_ep_db_info chdb[4]; struct mutex event_lock; @@ -134,6 +141,7 @@ struct mhi_ep_cntrl { u32 erdb_offset; u32 index; int irq; + bool enabled; }; /** @@ -228,4 +236,12 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl, */ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl); +/** + * mhi_ep_power_up - Power up the MHI endpoint stack + * @mhi_cntrl: MHI Endpoint controller + * + * Return: 0 if power up succeeds, a negative error code otherwise. + */ +int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl); + #endif -- cgit v1.2.3 From 5d507ee04894e166f8c5a29f05c6b06ce91d5833 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:46 +0530 Subject: bus: mhi: ep: Add support for powering down the MHI endpoint stack Add support for MHI endpoint power_down that includes stopping all available channels, destroying the channels, resetting the event and transfer rings and freeing the host cache. The stack will be powered down whenever the physical bus link goes down. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-11-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 3b065f82fbeb..9da683e8302c 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -244,4 +244,10 @@ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl); */ int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl); +/** + * mhi_ep_power_down - Power down the MHI endpoint stack + * @mhi_cntrl: MHI controller + */ +void mhi_ep_power_down(struct mhi_ep_cntrl *mhi_cntrl); + #endif -- cgit v1.2.3 From 7a97b6b47353c60dd1b53ada6180741437e377f2 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:47 +0530 Subject: bus: mhi: ep: Add support for handling MHI_RESET Add support for handling MHI_RESET in MHI endpoint stack. MHI_RESET will be issued by the host during shutdown and during error scenario so that it can recover the endpoint device without restarting the whole device. MHI_RESET handling involves resetting the internal MHI registers, data structures, state machines, resetting all channels/rings and setting MHICTRL.RESET bit to 0. Additionally the device will also move to READY state if the reset was due to SYS_ERR. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-12-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 9da683e8302c..2f31a54c205f 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -76,6 +76,7 @@ struct mhi_ep_db_info { * @ch_db_list: List of queued channel doorbells * @wq: Dedicated workqueue for handling rings and state changes * @state_work: State transition worker + * @reset_work: Worker for MHI Endpoint reset * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -122,6 +123,7 @@ struct mhi_ep_cntrl { struct workqueue_struct *wq; struct work_struct state_work; + struct work_struct reset_work; void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, -- cgit v1.2.3 From e827569062a804c67b51930ce83a4cb886113cb7 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:49 +0530 Subject: bus: mhi: ep: Add support for processing command rings Add support for processing the command rings. Command ring is used by the host to issue channel specific commands to the ep device. Following commands are supported: 1. Start channel 2. Stop channel 3. Reset channel Once the device receives the command doorbell interrupt from host, it executes the command and generates a command completion event to the host in the primary event ring. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-14-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 2f31a54c205f..8c6406d9c51f 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -77,6 +77,7 @@ struct mhi_ep_db_info { * @wq: Dedicated workqueue for handling rings and state changes * @state_work: State transition worker * @reset_work: Worker for MHI Endpoint reset + * @cmd_ring_work: Worker for processing command rings * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -124,6 +125,7 @@ struct mhi_ep_cntrl { struct workqueue_struct *wq; struct work_struct state_work; struct work_struct reset_work; + struct work_struct cmd_ring_work; void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, -- cgit v1.2.3 From 530125889977365cb6db32d7d0bd84c9f54c8aab Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:50 +0530 Subject: bus: mhi: ep: Add support for reading from the host Data transfer between host and the ep device happens over the transfer ring associated with each bi-directional channel pair. Host defines the transfer ring by allocating memory for it. The read and write pointer addresses of the transfer ring are stored in the channel context. Once host places the elements in the transfer ring, it increments the write pointer and rings the channel doorbell. Device will receive the doorbell interrupt and will process the transfer ring elements. This commit adds support for reading the transfer ring elements from the transfer ring till write pointer, incrementing the read pointer and finally sending the completion event to the host through corresponding event ring. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-15-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 8c6406d9c51f..fc7d197413eb 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -254,4 +254,13 @@ int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl); */ void mhi_ep_power_down(struct mhi_ep_cntrl *mhi_cntrl); +/** + * mhi_ep_queue_is_empty - Determine whether the transfer queue is empty + * @mhi_dev: Device associated with the channels + * @dir: DMA direction for the channel + * + * Return: true if the queue is empty, false otherwise. + */ +bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_direction dir); + #endif -- cgit v1.2.3 From 03c0bb8ec983f993a704417d73cc0a3511453d3e Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:51 +0530 Subject: bus: mhi: ep: Add support for processing channel rings Add support for processing the channel rings from host. For the channel ring associated with DL channel, the xfer callback will simply invoked. For the case of UL channel, the ring elements will be read in a buffer till the write pointer and later passed to the client driver using the xfer callback. The client drivers should provide the callbacks for both UL and DL channels during registration. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-16-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index fc7d197413eb..eecc8f35d630 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -78,6 +78,7 @@ struct mhi_ep_db_info { * @state_work: State transition worker * @reset_work: Worker for MHI Endpoint reset * @cmd_ring_work: Worker for processing command rings + * @ch_ring_work: Worker for processing channel rings * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -126,6 +127,7 @@ struct mhi_ep_cntrl { struct work_struct state_work; struct work_struct reset_work; struct work_struct cmd_ring_work; + struct work_struct ch_ring_work; void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, -- cgit v1.2.3 From 2d945a394d9c1c59d88397cb383b11216d018a6b Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:52 +0530 Subject: bus: mhi: ep: Add support for queueing SKBs to the host Add support for queueing SKBs to the host over the transfer ring of the relevant channel. The mhi_ep_queue_skb() API will be used by the client networking drivers to queue the SKBs to the host over MHI bus. The host will add ring elements to the transfer ring periodically for the device and the device will write SKBs to the ring elements. If a single SKB doesn't fit in a ring element (TRE), it will be placed in multiple ring elements and the overflow event will be sent for all ring elements except the last one. For the last ring element, the EOT event will be sent indicating the packet boundary. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-17-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index eecc8f35d630..478aece17046 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -265,4 +265,13 @@ void mhi_ep_power_down(struct mhi_ep_cntrl *mhi_cntrl); */ bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_direction dir); +/** + * mhi_ep_queue_skb - Send SKBs to host over MHI Endpoint + * @mhi_dev: Device associated with the DL channel + * @skb: SKBs to be queued + * + * Return: 0 if the SKBs has been sent successfully, a negative error code otherwise. + */ +int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb); + #endif -- cgit v1.2.3 From c268c0a8a33047cd957fecc1349d09a68eb6ad9e Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:54 +0530 Subject: bus: mhi: ep: Add uevent support for module autoloading Add uevent support to MHI endpoint bus so that the client drivers can be autoloaded by udev when the MHI endpoint devices gets created. The client drivers are expected to provide MODULE_DEVICE_TABLE with the MHI id_table struct so that the alias can be exported. The MHI endpoint reused the mhi_device_id structure of the MHI bus. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-19-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 5da5d990ff58..549590e9c644 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -835,6 +835,8 @@ struct wmi_device_id { #define MHI_DEVICE_MODALIAS_FMT "mhi:%s" #define MHI_NAME_SIZE 32 +#define MHI_EP_DEVICE_MODALIAS_FMT "mhi_ep:%s" + /** * struct mhi_device_id - MHI device identification * @chan: MHI channel name -- cgit v1.2.3 From 31f6bd7fad3b149a1eb6f67fc2e742e4df369b3d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 25 Apr 2022 17:33:58 +0300 Subject: serial: Store character timing information to uart_port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Struct uart_port currently stores FIFO timeout. Having character timing information readily available is useful. Even serial core itself determines char_time from port->timeout using inverse calculation. Store frame_time directly into uart_port. Character time is stored in nanoseconds to have reasonable precision with high rates. To avoid overflow, 64-bit math is necessary. It might be possible to determine timeout from frame_time by multiplying it with fifosize as needed but only part of the users seem to be protected by a lock. Thus, this patch does not pursue storing only frame_time in uart_port. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220425143410.12703-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index d4828e69087a..cbd5070bc87f 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -232,6 +232,7 @@ struct uart_port { int hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ unsigned int timeout; /* character-based timeout */ + unsigned int frame_time; /* frame timing in ns */ unsigned int type; /* port type */ const struct uart_ops *ops; unsigned int custom_divisor; -- cgit v1.2.3 From 7a20917d30fb627bebff6bacbe860ad4eb3a04d6 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 22 Apr 2022 15:23:45 -0700 Subject: device property: Add helper to match multiple connections In some cases multiple connections with the same connection id needs to be resolved from a fwnode graph. One such example is when separate hardware is used for performing muxing and/or orientation switching of the SuperSpeed and SBU lines in a USB Type-C connector. In this case the connector needs to belong to a graph with multiple matching remote endpoints, and the Type-C controller needs to be able to resolve them both. Add a new API that allows this kind of lookup. Reviewed-by: Andy Shevchenko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220422222351.1297276-2-bjorn.andersson@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/property.h b/include/linux/property.h index 4cd4b326941f..de7ff336d2c8 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -447,6 +447,11 @@ static inline void *device_connection_find_match(struct device *dev, return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match); } +int fwnode_connection_find_matches(struct fwnode_handle *fwnode, + const char *con_id, void *data, + devcon_match_fn_t match, + void **matches, unsigned int matches_len); + /* -------------------------------------------------------------------------- */ /* Software fwnode support - when HW description is incomplete or missing */ -- cgit v1.2.3 From 713fd49b430c37263c6cae2c82954f4e1cbcd90d Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 22 Apr 2022 15:23:48 -0700 Subject: usb: typec: mux: Introduce indirection Rather than directly exposing the implementation's representation of the typec muxes to the controller/clients, introduce an indirection object. This enables the introduction of turning this relationship into a one-to-many in the following patch. Acked-by: Heikki Krogerus Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220422222351.1297276-5-bjorn.andersson@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec_mux.h | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/usb/typec_mux.h b/include/linux/usb/typec_mux.h index a9d9957933dc..ee57781dcf28 100644 --- a/include/linux/usb/typec_mux.h +++ b/include/linux/usb/typec_mux.h @@ -8,11 +8,13 @@ struct device; struct typec_mux; +struct typec_mux_dev; struct typec_switch; +struct typec_switch_dev; struct typec_altmode; struct fwnode_handle; -typedef int (*typec_switch_set_fn_t)(struct typec_switch *sw, +typedef int (*typec_switch_set_fn_t)(struct typec_switch_dev *sw, enum typec_orientation orientation); struct typec_switch_desc { @@ -32,13 +34,13 @@ static inline struct typec_switch *typec_switch_get(struct device *dev) return fwnode_typec_switch_get(dev_fwnode(dev)); } -struct typec_switch * +struct typec_switch_dev * typec_switch_register(struct device *parent, const struct typec_switch_desc *desc); -void typec_switch_unregister(struct typec_switch *sw); +void typec_switch_unregister(struct typec_switch_dev *sw); -void typec_switch_set_drvdata(struct typec_switch *sw, void *data); -void *typec_switch_get_drvdata(struct typec_switch *sw); +void typec_switch_set_drvdata(struct typec_switch_dev *sw, void *data); +void *typec_switch_get_drvdata(struct typec_switch_dev *sw); struct typec_mux_state { struct typec_altmode *alt; @@ -46,7 +48,7 @@ struct typec_mux_state { void *data; }; -typedef int (*typec_mux_set_fn_t)(struct typec_mux *mux, +typedef int (*typec_mux_set_fn_t)(struct typec_mux_dev *mux, struct typec_mux_state *state); struct typec_mux_desc { @@ -67,11 +69,11 @@ typec_mux_get(struct device *dev, const struct typec_altmode_desc *desc) return fwnode_typec_mux_get(dev_fwnode(dev), desc); } -struct typec_mux * +struct typec_mux_dev * typec_mux_register(struct device *parent, const struct typec_mux_desc *desc); -void typec_mux_unregister(struct typec_mux *mux); +void typec_mux_unregister(struct typec_mux_dev *mux); -void typec_mux_set_drvdata(struct typec_mux *mux, void *data); -void *typec_mux_get_drvdata(struct typec_mux *mux); +void typec_mux_set_drvdata(struct typec_mux_dev *mux, void *data); +void *typec_mux_get_drvdata(struct typec_mux_dev *mux); #endif /* __USB_TYPEC_MUX */ -- cgit v1.2.3 From af1969a2d734d6272c0640b50c3ed31e59e203a9 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Sat, 23 Apr 2022 20:42:03 -0400 Subject: USB: gadget: Rename usb_gadget_probe_driver() In preparation for adding a "gadget" bus, this patch renames usb_gadget_probe_driver() to usb_gadget_register_driver(). The new name will be more accurate, since gadget drivers will be registered on the gadget bus and the probing will be done by the driver core, not the UDC core. Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/YmSc29YZvxgT5fEJ@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 10fe57cf40be..5830b8a903da 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -745,7 +745,7 @@ struct usb_gadget_driver { */ /** - * usb_gadget_probe_driver - probe a gadget driver + * usb_gadget_register_driver - register a gadget driver * @driver: the driver being registered * Context: can sleep * @@ -755,7 +755,7 @@ struct usb_gadget_driver { * registration call returns. It's expected that the @bind() function will * be in init sections. */ -int usb_gadget_probe_driver(struct usb_gadget_driver *driver); +int usb_gadget_register_driver(struct usb_gadget_driver *driver); /** * usb_gadget_unregister_driver - unregister a gadget driver -- cgit v1.2.3 From fc274c1e997314bf47f6a62c79b5d7e554ed59c4 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Sat, 23 Apr 2022 21:35:51 -0400 Subject: USB: gadget: Add a new bus for gadgets This patch adds a "gadget" bus and uses it for registering gadgets and their drivers. From now on, bindings will be managed by the driver core rather than through ad-hoc manipulations in the UDC core. As part of this change, the driver_pending_list is removed. The UDC core won't need to keep track of unbound drivers for later binding, because the driver core handles all of that for us. However, we do need one new feature: a way to prevent gadget drivers from being bound to more than one gadget at a time. The existing code does this automatically, but the driver core doesn't -- it's perfectly happy to bind a single driver to all the matching devices on the bus. The patch adds a new bitflag to the usb_gadget_driver structure for this purpose. A nice side effect of this change is a reduction in the total lines of code, since now the driver core will do part of the work that the UDC used to do. A possible future patch could add udc devices to the gadget bus, say as a separate device type. Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/YmSpdxaDNeC2BBOf@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 5830b8a903da..cf7af8a0a6e9 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -664,9 +664,9 @@ static inline int usb_gadget_check_config(struct usb_gadget *gadget) * @driver: Driver model state for this driver. * @udc_name: A name of UDC this driver should be bound to. If udc_name is NULL, * this driver will be bound to any available UDC. - * @pending: UDC core private data used for deferred probe of this driver. - * @match_existing_only: If udc is not found, return an error and don't add this - * gadget driver to list of pending driver + * @match_existing_only: If udc is not found, return an error and fail + * the driver registration + * @is_bound: Allow a driver to be bound to only one gadget * * Devices are disabled till a gadget driver successfully bind()s, which * means the driver will handle setup() requests needed to enumerate (and @@ -729,8 +729,8 @@ struct usb_gadget_driver { struct device_driver driver; char *udc_name; - struct list_head pending; unsigned match_existing_only:1; + bool is_bound:1; }; @@ -740,22 +740,30 @@ struct usb_gadget_driver { /* driver modules register and unregister, as usual. * these calls must be made in a context that can sleep. * - * these will usually be implemented directly by the hardware-dependent - * usb bus interface driver, which will only support a single driver. + * A gadget driver can be bound to only one gadget at a time. */ /** - * usb_gadget_register_driver - register a gadget driver + * usb_gadget_register_driver_owner - register a gadget driver * @driver: the driver being registered + * @owner: the driver module + * @mod_name: the driver module's build name * Context: can sleep * * Call this in your gadget driver's module initialization function, - * to tell the underlying usb controller driver about your driver. + * to tell the underlying UDC controller driver about your driver. * The @bind() function will be called to bind it to a gadget before this * registration call returns. It's expected that the @bind() function will * be in init sections. + * + * Use the macro defined below instead of calling this directly. */ -int usb_gadget_register_driver(struct usb_gadget_driver *driver); +int usb_gadget_register_driver_owner(struct usb_gadget_driver *driver, + struct module *owner, const char *mod_name); + +/* use a define to avoid include chaining to get THIS_MODULE & friends */ +#define usb_gadget_register_driver(driver) \ + usb_gadget_register_driver_owner(driver, THIS_MODULE, KBUILD_MODNAME) /** * usb_gadget_unregister_driver - unregister a gadget driver -- cgit v1.2.3 From 8e8b11956486e3fe8cacf54a1d492ebdd8cc1fb2 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Thu, 17 Feb 2022 10:42:52 -0800 Subject: of/platform: Add stubs for of_platform_device_create/destroy() Code for platform_device_create() and of_platform_device_destroy() is only generated if CONFIG_OF_ADDRESS=y. Add stubs to avoid unresolved symbols when CONFIG_OF_ADDRESS is not set. Reviewed-by: Stephen Boyd Reviewed-by: Douglas Anderson Acked-by: Rob Herring Signed-off-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/20220217104219.v21.1.I08fd2e1c775af04f663730e9fb4d00e6bbb38541@changeid Signed-off-by: Greg Kroah-Hartman --- include/linux/of_platform.h | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 84a966623e78..d15b6cd5e1c3 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -61,16 +61,18 @@ static inline struct platform_device *of_find_device_by_node(struct device_node } #endif +extern int of_platform_bus_probe(struct device_node *root, + const struct of_device_id *matches, + struct device *parent); + +#ifdef CONFIG_OF_ADDRESS /* Platform devices and busses creation */ extern struct platform_device *of_platform_device_create(struct device_node *np, const char *bus_id, struct device *parent); extern int of_platform_device_destroy(struct device *dev, void *data); -extern int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent); -#ifdef CONFIG_OF_ADDRESS + extern int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, @@ -84,6 +86,18 @@ extern int devm_of_platform_populate(struct device *dev); extern void devm_of_platform_depopulate(struct device *dev); #else +/* Platform devices and busses creation */ +static inline struct platform_device *of_platform_device_create(struct device_node *np, + const char *bus_id, + struct device *parent) +{ + return NULL; +} +static inline int of_platform_device_destroy(struct device *dev, void *data) +{ + return -ENODEV; +} + static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, -- cgit v1.2.3 From 0298b4b95cb373c21e6323c905589f8dac42c5b4 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Thu, 17 Feb 2022 10:42:53 -0800 Subject: usb: misc: Add onboard_usb_hub driver The main issue this driver addresses is that a USB hub needs to be powered before it can be discovered. For discrete onboard hubs (an example for such a hub is the Realtek RTS5411) this is often solved by supplying the hub with an 'always-on' regulator, which is kind of a hack. Some onboard hubs may require further initialization steps, like changing the state of a GPIO or enabling a clock, which requires even more hacks. This driver creates a platform device representing the hub which performs the necessary initialization. Currently it only supports switching on a single regulator, support for multiple regulators or other actions can be added as needed. Different initialization sequences can be supported based on the compatible string. Besides performing the initialization the driver can be configured to power the hub off during system suspend. This can help to extend battery life on battery powered devices which have no requirements to keep the hub powered during suspend. The driver can also be configured to leave the hub powered when a wakeup capable USB device is connected when suspending, and power it off otherwise. Technically the driver consists of two drivers, the platform driver described above and a very thin USB driver that subclasses the generic driver. The purpose of this driver is to provide the platform driver with the USB devices corresponding to the hub(s) (a hub controller may provide multiple 'logical' hubs, e.g. one to support USB 2.0 and another for USB 3.x). Note: the current series only supports hubs connected directly to a root hub, support for other configurations could be added if needed. Co-developed-by: Ravi Chandra Sadineni Reviewed-by: Douglas Anderson Acked-by: Alan Stern Signed-off-by: Ravi Chandra Sadineni Signed-off-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/20220217104219.v21.2.I7c9a1f1d6ced41dd8310e8a03da666a32364e790@changeid Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/onboard_hub.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/usb/onboard_hub.h (limited to 'include') diff --git a/include/linux/usb/onboard_hub.h b/include/linux/usb/onboard_hub.h new file mode 100644 index 000000000000..d9373230556e --- /dev/null +++ b/include/linux/usb/onboard_hub.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_USB_ONBOARD_HUB_H +#define __LINUX_USB_ONBOARD_HUB_H + +struct usb_device; +struct list_head; + +#if IS_ENABLED(CONFIG_USB_ONBOARD_HUB) +void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list); +void onboard_hub_destroy_pdevs(struct list_head *pdev_list); +#else +static inline void onboard_hub_create_pdevs(struct usb_device *parent_hub, + struct list_head *pdev_list) {} +static inline void onboard_hub_destroy_pdevs(struct list_head *pdev_list) {} +#endif + +#endif /* __LINUX_USB_ONBOARD_HUB_H */ -- cgit v1.2.3 From c40b62216c1aecc0dc00faf33d71bd71cb440337 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Thu, 17 Feb 2022 10:42:54 -0800 Subject: usb: core: hcd: Create platform devices for onboard hubs in probe() Call onboard_hub_create/destroy_pdevs() from usb_add/remove_hcd() for primary HCDs to create/destroy platform devices for onboard USB hubs that may be connected to the root hub of the controller. These functions are a NOP unless CONFIG_USB_ONBOARD_HUB=y/m. Also add a field to struct usb_hcd to keep track of the onboard hub platform devices that are owned by the HCD. Reviewed-by: Douglas Anderson Reviewed-by: Stephen Boyd Signed-off-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/20220217104219.v21.3.I7a3a7d9d2126c34079b1cab87aa0b2ec3030f9b7@changeid Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 548a028f2dab..4ebc91c09182 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -198,6 +198,7 @@ struct usb_hcd { struct usb_hcd *shared_hcd; struct usb_hcd *primary_hcd; + struct list_head onboard_hub_devs; #define HCD_BUFFER_POOLS 4 struct dma_pool *pool[HCD_BUFFER_POOLS]; -- cgit v1.2.3 From 9723f69d1de37ca25474372ad1753ea39bb0dce1 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 8 Apr 2022 10:00:43 +0200 Subject: mmc: core: improve API to make clear that mmc_sw_reset is for cards To make it unambiguous that mmc_sw_reset() is for cards and not for controllers, we make the function argument mmc_card instead of mmc_host. There are no users to convert currently. Suggested-by: Ulf Hansson Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20220408080045.6497-3-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- include/linux/mmc/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index de5c64bbdb72..6efec0b9820c 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -176,7 +176,7 @@ int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); int mmc_hw_reset(struct mmc_card *card); -int mmc_sw_reset(struct mmc_host *host); +int mmc_sw_reset(struct mmc_card *card); void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card); #endif /* LINUX_MMC_CORE_H */ -- cgit v1.2.3 From 32f18e596141f40dbc5d8700b2730371ffd3055f Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 8 Apr 2022 10:00:44 +0200 Subject: mmc: improve API to make clear hw_reset callback is for cards To make it unambiguous that the hw_reset callback is for cards and not for controllers, we add 'card' to the callback name and convert all users in one go. We keep the argument as mmc_host, though, because the callback is used very early when mmc_card is not yet populated. Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20220408080045.6497-4-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 7afb57cab00b..c193c50ccd78 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -181,7 +181,7 @@ struct mmc_host_ops { unsigned int max_dtr, int host_drv, int card_drv, int *drv_type); /* Reset the eMMC card via RST_n */ - void (*hw_reset)(struct mmc_host *host); + void (*card_hw_reset)(struct mmc_host *host); void (*card_event)(struct mmc_host *host); /* -- cgit v1.2.3 From 13acb62ce1ee7377ef03034fbbad6f5499464b86 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 12 Apr 2022 11:31:02 +0200 Subject: mmc: sh_mmcif: move platform_data header to proper location We have a dedicated directory for platform_data meanwhile, don't spoil the MMC directory with it. Reviewed-by: Geert Uytterhoeven Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20220412093102.3428-1-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- include/linux/mmc/sh_mmcif.h | 209 --------------------------------- include/linux/platform_data/sh_mmcif.h | 207 ++++++++++++++++++++++++++++++++ 2 files changed, 207 insertions(+), 209 deletions(-) delete mode 100644 include/linux/mmc/sh_mmcif.h create mode 100644 include/linux/platform_data/sh_mmcif.h (limited to 'include') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h deleted file mode 100644 index e25533b95d9f..000000000000 --- a/include/linux/mmc/sh_mmcif.h +++ /dev/null @@ -1,209 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * include/linux/mmc/sh_mmcif.h - * - * platform data for eMMC driver - * - * Copyright (C) 2010 Renesas Solutions Corp. - */ - -#ifndef LINUX_MMC_SH_MMCIF_H -#define LINUX_MMC_SH_MMCIF_H - -#include -#include - -/* - * MMCIF : CE_CLK_CTRL [19:16] - * 1000 : Peripheral clock / 512 - * 0111 : Peripheral clock / 256 - * 0110 : Peripheral clock / 128 - * 0101 : Peripheral clock / 64 - * 0100 : Peripheral clock / 32 - * 0011 : Peripheral clock / 16 - * 0010 : Peripheral clock / 8 - * 0001 : Peripheral clock / 4 - * 0000 : Peripheral clock / 2 - * 1111 : Peripheral clock (sup_pclk set '1') - */ - -struct sh_mmcif_plat_data { - unsigned int slave_id_tx; /* embedded slave_id_[tr]x */ - unsigned int slave_id_rx; - u8 sup_pclk; /* 1 :SH7757, 0: SH7724/SH7372 */ - unsigned long caps; - u32 ocr; -}; - -#define MMCIF_CE_CMD_SET 0x00000000 -#define MMCIF_CE_ARG 0x00000008 -#define MMCIF_CE_ARG_CMD12 0x0000000C -#define MMCIF_CE_CMD_CTRL 0x00000010 -#define MMCIF_CE_BLOCK_SET 0x00000014 -#define MMCIF_CE_CLK_CTRL 0x00000018 -#define MMCIF_CE_BUF_ACC 0x0000001C -#define MMCIF_CE_RESP3 0x00000020 -#define MMCIF_CE_RESP2 0x00000024 -#define MMCIF_CE_RESP1 0x00000028 -#define MMCIF_CE_RESP0 0x0000002C -#define MMCIF_CE_RESP_CMD12 0x00000030 -#define MMCIF_CE_DATA 0x00000034 -#define MMCIF_CE_INT 0x00000040 -#define MMCIF_CE_INT_MASK 0x00000044 -#define MMCIF_CE_HOST_STS1 0x00000048 -#define MMCIF_CE_HOST_STS2 0x0000004C -#define MMCIF_CE_CLK_CTRL2 0x00000070 -#define MMCIF_CE_VERSION 0x0000007C - -/* CE_BUF_ACC */ -#define BUF_ACC_DMAWEN (1 << 25) -#define BUF_ACC_DMAREN (1 << 24) -#define BUF_ACC_BUSW_32 (0 << 17) -#define BUF_ACC_BUSW_16 (1 << 17) -#define BUF_ACC_ATYP (1 << 16) - -/* CE_CLK_CTRL */ -#define CLK_ENABLE (1 << 24) /* 1: output mmc clock */ -#define CLK_CLEAR (0xf << 16) -#define CLK_SUP_PCLK (0xf << 16) -#define CLKDIV_4 (1 << 16) /* mmc clock frequency. - * n: bus clock/(2^(n+1)) */ -#define CLKDIV_256 (7 << 16) /* mmc clock frequency. (see above) */ -#define SRSPTO_256 (2 << 12) /* resp timeout */ -#define SRBSYTO_29 (0xf << 8) /* resp busy timeout */ -#define SRWDTO_29 (0xf << 4) /* read/write timeout */ -#define SCCSTO_29 (0xf << 0) /* ccs timeout */ - -/* CE_VERSION */ -#define SOFT_RST_ON (1 << 31) -#define SOFT_RST_OFF 0 - -static inline u32 sh_mmcif_readl(void __iomem *addr, int reg) -{ - return __raw_readl(addr + reg); -} - -static inline void sh_mmcif_writel(void __iomem *addr, int reg, u32 val) -{ - __raw_writel(val, addr + reg); -} - -#define SH_MMCIF_BBS 512 /* boot block size */ - -static inline void sh_mmcif_boot_cmd_send(void __iomem *base, - unsigned long cmd, unsigned long arg) -{ - sh_mmcif_writel(base, MMCIF_CE_INT, 0); - sh_mmcif_writel(base, MMCIF_CE_ARG, arg); - sh_mmcif_writel(base, MMCIF_CE_CMD_SET, cmd); -} - -static inline int sh_mmcif_boot_cmd_poll(void __iomem *base, unsigned long mask) -{ - unsigned long tmp; - int cnt; - - for (cnt = 0; cnt < 1000000; cnt++) { - tmp = sh_mmcif_readl(base, MMCIF_CE_INT); - if (tmp & mask) { - sh_mmcif_writel(base, MMCIF_CE_INT, tmp & ~mask); - return 0; - } - } - - return -1; -} - -static inline int sh_mmcif_boot_cmd(void __iomem *base, - unsigned long cmd, unsigned long arg) -{ - sh_mmcif_boot_cmd_send(base, cmd, arg); - return sh_mmcif_boot_cmd_poll(base, 0x00010000); -} - -static inline int sh_mmcif_boot_do_read_single(void __iomem *base, - unsigned int block_nr, - unsigned long *buf) -{ - int k; - - /* CMD13 - Status */ - sh_mmcif_boot_cmd(base, 0x0d400000, 0x00010000); - - if (sh_mmcif_readl(base, MMCIF_CE_RESP0) != 0x0900) - return -1; - - /* CMD17 - Read */ - sh_mmcif_boot_cmd(base, 0x11480000, block_nr * SH_MMCIF_BBS); - if (sh_mmcif_boot_cmd_poll(base, 0x00100000) < 0) - return -1; - - for (k = 0; k < (SH_MMCIF_BBS / 4); k++) - buf[k] = sh_mmcif_readl(base, MMCIF_CE_DATA); - - return 0; -} - -static inline int sh_mmcif_boot_do_read(void __iomem *base, - unsigned long first_block, - unsigned long nr_blocks, - void *buf) -{ - unsigned long k; - int ret = 0; - - /* In data transfer mode: Set clock to Bus clock/4 (about 20Mhz) */ - sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, - CLK_ENABLE | CLKDIV_4 | SRSPTO_256 | - SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); - - /* CMD9 - Get CSD */ - sh_mmcif_boot_cmd(base, 0x09806000, 0x00010000); - - /* CMD7 - Select the card */ - sh_mmcif_boot_cmd(base, 0x07400000, 0x00010000); - - /* CMD16 - Set the block size */ - sh_mmcif_boot_cmd(base, 0x10400000, SH_MMCIF_BBS); - - for (k = 0; !ret && k < nr_blocks; k++) - ret = sh_mmcif_boot_do_read_single(base, first_block + k, - buf + (k * SH_MMCIF_BBS)); - - return ret; -} - -static inline void sh_mmcif_boot_init(void __iomem *base) -{ - /* reset */ - sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_ON); - sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_OFF); - - /* byte swap */ - sh_mmcif_writel(base, MMCIF_CE_BUF_ACC, BUF_ACC_ATYP); - - /* Set block size in MMCIF hardware */ - sh_mmcif_writel(base, MMCIF_CE_BLOCK_SET, SH_MMCIF_BBS); - - /* Enable the clock, set it to Bus clock/256 (about 325Khz). */ - sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, - CLK_ENABLE | CLKDIV_256 | SRSPTO_256 | - SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); - - /* CMD0 */ - sh_mmcif_boot_cmd(base, 0x00000040, 0); - - /* CMD1 - Get OCR */ - do { - sh_mmcif_boot_cmd(base, 0x01405040, 0x40300000); /* CMD1 */ - } while ((sh_mmcif_readl(base, MMCIF_CE_RESP0) & 0x80000000) - != 0x80000000); - - /* CMD2 - Get CID */ - sh_mmcif_boot_cmd(base, 0x02806040, 0); - - /* CMD3 - Set card relative address */ - sh_mmcif_boot_cmd(base, 0x03400040, 0x00010000); -} - -#endif /* LINUX_MMC_SH_MMCIF_H */ diff --git a/include/linux/platform_data/sh_mmcif.h b/include/linux/platform_data/sh_mmcif.h new file mode 100644 index 000000000000..6eb914f958f9 --- /dev/null +++ b/include/linux/platform_data/sh_mmcif.h @@ -0,0 +1,207 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * platform data for eMMC driver + * + * Copyright (C) 2010 Renesas Solutions Corp. + */ + +#ifndef LINUX_MMC_SH_MMCIF_H +#define LINUX_MMC_SH_MMCIF_H + +#include +#include + +/* + * MMCIF : CE_CLK_CTRL [19:16] + * 1000 : Peripheral clock / 512 + * 0111 : Peripheral clock / 256 + * 0110 : Peripheral clock / 128 + * 0101 : Peripheral clock / 64 + * 0100 : Peripheral clock / 32 + * 0011 : Peripheral clock / 16 + * 0010 : Peripheral clock / 8 + * 0001 : Peripheral clock / 4 + * 0000 : Peripheral clock / 2 + * 1111 : Peripheral clock (sup_pclk set '1') + */ + +struct sh_mmcif_plat_data { + unsigned int slave_id_tx; /* embedded slave_id_[tr]x */ + unsigned int slave_id_rx; + u8 sup_pclk; /* 1 :SH7757, 0: SH7724/SH7372 */ + unsigned long caps; + u32 ocr; +}; + +#define MMCIF_CE_CMD_SET 0x00000000 +#define MMCIF_CE_ARG 0x00000008 +#define MMCIF_CE_ARG_CMD12 0x0000000C +#define MMCIF_CE_CMD_CTRL 0x00000010 +#define MMCIF_CE_BLOCK_SET 0x00000014 +#define MMCIF_CE_CLK_CTRL 0x00000018 +#define MMCIF_CE_BUF_ACC 0x0000001C +#define MMCIF_CE_RESP3 0x00000020 +#define MMCIF_CE_RESP2 0x00000024 +#define MMCIF_CE_RESP1 0x00000028 +#define MMCIF_CE_RESP0 0x0000002C +#define MMCIF_CE_RESP_CMD12 0x00000030 +#define MMCIF_CE_DATA 0x00000034 +#define MMCIF_CE_INT 0x00000040 +#define MMCIF_CE_INT_MASK 0x00000044 +#define MMCIF_CE_HOST_STS1 0x00000048 +#define MMCIF_CE_HOST_STS2 0x0000004C +#define MMCIF_CE_CLK_CTRL2 0x00000070 +#define MMCIF_CE_VERSION 0x0000007C + +/* CE_BUF_ACC */ +#define BUF_ACC_DMAWEN (1 << 25) +#define BUF_ACC_DMAREN (1 << 24) +#define BUF_ACC_BUSW_32 (0 << 17) +#define BUF_ACC_BUSW_16 (1 << 17) +#define BUF_ACC_ATYP (1 << 16) + +/* CE_CLK_CTRL */ +#define CLK_ENABLE (1 << 24) /* 1: output mmc clock */ +#define CLK_CLEAR (0xf << 16) +#define CLK_SUP_PCLK (0xf << 16) +#define CLKDIV_4 (1 << 16) /* mmc clock frequency. + * n: bus clock/(2^(n+1)) */ +#define CLKDIV_256 (7 << 16) /* mmc clock frequency. (see above) */ +#define SRSPTO_256 (2 << 12) /* resp timeout */ +#define SRBSYTO_29 (0xf << 8) /* resp busy timeout */ +#define SRWDTO_29 (0xf << 4) /* read/write timeout */ +#define SCCSTO_29 (0xf << 0) /* ccs timeout */ + +/* CE_VERSION */ +#define SOFT_RST_ON (1 << 31) +#define SOFT_RST_OFF 0 + +static inline u32 sh_mmcif_readl(void __iomem *addr, int reg) +{ + return __raw_readl(addr + reg); +} + +static inline void sh_mmcif_writel(void __iomem *addr, int reg, u32 val) +{ + __raw_writel(val, addr + reg); +} + +#define SH_MMCIF_BBS 512 /* boot block size */ + +static inline void sh_mmcif_boot_cmd_send(void __iomem *base, + unsigned long cmd, unsigned long arg) +{ + sh_mmcif_writel(base, MMCIF_CE_INT, 0); + sh_mmcif_writel(base, MMCIF_CE_ARG, arg); + sh_mmcif_writel(base, MMCIF_CE_CMD_SET, cmd); +} + +static inline int sh_mmcif_boot_cmd_poll(void __iomem *base, unsigned long mask) +{ + unsigned long tmp; + int cnt; + + for (cnt = 0; cnt < 1000000; cnt++) { + tmp = sh_mmcif_readl(base, MMCIF_CE_INT); + if (tmp & mask) { + sh_mmcif_writel(base, MMCIF_CE_INT, tmp & ~mask); + return 0; + } + } + + return -1; +} + +static inline int sh_mmcif_boot_cmd(void __iomem *base, + unsigned long cmd, unsigned long arg) +{ + sh_mmcif_boot_cmd_send(base, cmd, arg); + return sh_mmcif_boot_cmd_poll(base, 0x00010000); +} + +static inline int sh_mmcif_boot_do_read_single(void __iomem *base, + unsigned int block_nr, + unsigned long *buf) +{ + int k; + + /* CMD13 - Status */ + sh_mmcif_boot_cmd(base, 0x0d400000, 0x00010000); + + if (sh_mmcif_readl(base, MMCIF_CE_RESP0) != 0x0900) + return -1; + + /* CMD17 - Read */ + sh_mmcif_boot_cmd(base, 0x11480000, block_nr * SH_MMCIF_BBS); + if (sh_mmcif_boot_cmd_poll(base, 0x00100000) < 0) + return -1; + + for (k = 0; k < (SH_MMCIF_BBS / 4); k++) + buf[k] = sh_mmcif_readl(base, MMCIF_CE_DATA); + + return 0; +} + +static inline int sh_mmcif_boot_do_read(void __iomem *base, + unsigned long first_block, + unsigned long nr_blocks, + void *buf) +{ + unsigned long k; + int ret = 0; + + /* In data transfer mode: Set clock to Bus clock/4 (about 20Mhz) */ + sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, + CLK_ENABLE | CLKDIV_4 | SRSPTO_256 | + SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); + + /* CMD9 - Get CSD */ + sh_mmcif_boot_cmd(base, 0x09806000, 0x00010000); + + /* CMD7 - Select the card */ + sh_mmcif_boot_cmd(base, 0x07400000, 0x00010000); + + /* CMD16 - Set the block size */ + sh_mmcif_boot_cmd(base, 0x10400000, SH_MMCIF_BBS); + + for (k = 0; !ret && k < nr_blocks; k++) + ret = sh_mmcif_boot_do_read_single(base, first_block + k, + buf + (k * SH_MMCIF_BBS)); + + return ret; +} + +static inline void sh_mmcif_boot_init(void __iomem *base) +{ + /* reset */ + sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_ON); + sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_OFF); + + /* byte swap */ + sh_mmcif_writel(base, MMCIF_CE_BUF_ACC, BUF_ACC_ATYP); + + /* Set block size in MMCIF hardware */ + sh_mmcif_writel(base, MMCIF_CE_BLOCK_SET, SH_MMCIF_BBS); + + /* Enable the clock, set it to Bus clock/256 (about 325Khz). */ + sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, + CLK_ENABLE | CLKDIV_256 | SRSPTO_256 | + SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); + + /* CMD0 */ + sh_mmcif_boot_cmd(base, 0x00000040, 0); + + /* CMD1 - Get OCR */ + do { + sh_mmcif_boot_cmd(base, 0x01405040, 0x40300000); /* CMD1 */ + } while ((sh_mmcif_readl(base, MMCIF_CE_RESP0) & 0x80000000) + != 0x80000000); + + /* CMD2 - Get CID */ + sh_mmcif_boot_cmd(base, 0x02806040, 0); + + /* CMD3 - Set card relative address */ + sh_mmcif_boot_cmd(base, 0x03400040, 0x00010000); +} + +#endif /* LINUX_MMC_SH_MMCIF_H */ -- cgit v1.2.3 From 8e274732115f63c1d09136284431b3555bd5cc56 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Mon, 25 Apr 2022 23:04:28 +0206 Subject: printk: extend console_lock for per-console locking Currently threaded console printers synchronize against each other using console_lock(). However, different console drivers are unrelated and do not require any synchronization between each other. Removing the synchronization between the threaded console printers will allow each console to print at its own speed. But the threaded consoles printers do still need to synchronize against console_lock() callers. Introduce a per-console mutex and a new console boolean field @blocked to provide this synchronization. console_lock() is modified so that it must acquire the mutex of each console in order to set the @blocked field. Console printing threads will acquire their mutex while printing a record. If @blocked was set, the thread will go back to sleep instead of printing. The reason for the @blocked boolean field is so that console_lock() callers do not need to acquire multiple console mutexes simultaneously, which would introduce unnecessary complexity due to nested mutex locking. Also, a new field was chosen instead of adding a new @flags value so that the blocked status could be checked without concern of reading inconsistent values due to @flags updates from other contexts. Threaded console printers also need to synchronize against console_trylock() callers. Since console_trylock() may be called from any context, the per-console mutex cannot be used for this synchronization. (mutex_trylock() cannot be called from atomic contexts.) Introduce a global atomic counter to identify if any threaded printers are active. The threaded printers will also check the atomic counter to identify if the console has been locked by another task via console_trylock(). Note that @console_sem is still used to provide synchronization between console_lock() and console_trylock() callers. A locking overview for console_lock(), console_trylock(), and the threaded printers is as follows (pseudo code): console_lock() { down(&console_sem); for_each_console(con) { mutex_lock(&con->lock); con->blocked = true; mutex_unlock(&con->lock); } /* console_lock acquired */ } console_trylock() { if (down_trylock(&console_sem) == 0) { if (atomic_cmpxchg(&console_kthreads_active, 0, -1) == 0) { /* console_lock acquired */ } } } threaded_printer() { mutex_lock(&con->lock); if (!con->blocked) { /* console_lock() callers blocked */ if (atomic_inc_unless_negative(&console_kthreads_active)) { /* console_trylock() callers blocked */ con->write(); atomic_dec(&console_lock_count); } } mutex_unlock(&con->lock); } The console owner and waiter logic now only applies between contexts that have taken the console_lock via console_trylock(). Threaded printers never take the console_lock, so they do not have a console_lock to handover. Tasks that have used console_lock() will block the threaded printers using a mutex and if the console_lock is handed over to an atomic context, it would be unable to unblock the threaded printers. However, the console_trylock() case is really the only scenario that is interesting for handovers anyway. @panic_console_dropped must change to atomic_t since it is no longer protected exclusively by the console_lock. Since threaded printers remain asleep if they see that the console is locked, they now must be explicitly woken in __console_unlock(). This means wake_up_klogd() calls following a console_unlock() are no longer necessary and are removed. Also note that threaded printers no longer need to check @console_suspended. The check for the @blocked field implicitly covers the suspended console case. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/878rrs6ft7.fsf@jogness.linutronix.de --- include/linux/console.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/console.h b/include/linux/console.h index 9a251e70c090..143653090c48 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -16,6 +16,7 @@ #include #include +#include struct vc_data; struct console_font_op; @@ -154,6 +155,20 @@ struct console { u64 seq; unsigned long dropped; struct task_struct *thread; + bool blocked; + + /* + * The per-console lock is used by printing kthreads to synchronize + * this console with callers of console_lock(). This is necessary in + * order to allow printing kthreads to run in parallel to each other, + * while each safely accessing the @blocked field and synchronizing + * against direct printing via console_lock/console_unlock. + * + * Note: For synchronizing against direct printing via + * console_trylock/console_unlock, see the static global + * variable @console_kthreads_active. + */ + struct mutex lock; void *data; struct console *next; -- cgit v1.2.3 From cc51eaa8b530bf070e76847a717adcbf603469b7 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 26 Apr 2022 01:29:04 -0700 Subject: io_uring: add type to op enum It is useful to have a type enum for opcodes, to allow the compiler to assert that every value is used in a switch statement. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220426082907.3600028-2-dylany@fb.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 5fb52bf32435..49d1f3994f8d 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -105,7 +105,7 @@ enum { #define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ #define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ -enum { +enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, IORING_OP_WRITEV, -- cgit v1.2.3 From 33337d03f04f9ea3a50ac2d3490a5d7a3ba9be82 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 26 Apr 2022 01:29:05 -0700 Subject: io_uring: add io_uring_get_opcode In some debug scenarios it is useful to have the text representation of the opcode. Add this function in preparation. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220426082907.3600028-3-dylany@fb.com Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 1814e698d861..24651c229ed2 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -10,6 +10,7 @@ struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); +const char *io_uring_get_opcode(u8 opcode); static inline void io_uring_files_cancel(void) { @@ -42,6 +43,10 @@ static inline void io_uring_files_cancel(void) static inline void io_uring_free(struct task_struct *tsk) { } +static inline const char *io_uring_get_opcode(u8 opcode) +{ + return ""; +} #endif #endif -- cgit v1.2.3 From 1460af7de6ab33da82b8a1f03ce0f8e831a9e29e Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 26 Apr 2022 01:29:06 -0700 Subject: io_uring: rename op -> opcode do this for consistency with the other trace messages Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220426082907.3600028-4-dylany@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 05b786f8b0bf..42c7e1a3c6ae 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -530,7 +530,7 @@ TRACE_EVENT(io_uring_req_failed, ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "opcode %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " "error=%d", -- cgit v1.2.3 From 54c861f930180e096483a6e1744c9c4b76e20da5 Mon Sep 17 00:00:00 2001 From: Daniel Ammann Date: Tue, 5 Apr 2022 14:54:25 +0200 Subject: mfd: tps65218: Fix trivial typo in comment The driver is for TPS65218, not TPS65219. Signed-off-by: Daniel Ammann Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20220405125426.28016-1-daniel.ammann@bytesatwork.ch --- include/linux/mfd/tps65218.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index f4ca367e3473..122e24ddbd4b 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -1,7 +1,7 @@ /* * linux/mfd/tps65218.h * - * Functions to access TPS65219 power management chip. + * Functions to access TPS65218 power management chip. * * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com/ * -- cgit v1.2.3 From 7f5aaa4a0ae6948eace6cf30f40a3ec27ece8441 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ma=C3=ADra=20Canal?= Date: Wed, 6 Apr 2022 11:40:41 -0300 Subject: mfd: hi655x-pmic: Replace legacy gpio interface for gpiod interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Considering the current transition of the GPIO subsystem, remove all dependencies of the legacy GPIO interface (linux/gpio.h and linux /of_gpio.h) and replace it with the descriptor-based GPIO approach. Signed-off-by: Maíra Canal Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/Yk2maZuf+5FGL+eg@fedora --- include/linux/mfd/hi655x-pmic.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/hi655x-pmic.h b/include/linux/mfd/hi655x-pmic.h index af5d97239c0d..6a012784dd1b 100644 --- a/include/linux/mfd/hi655x-pmic.h +++ b/include/linux/mfd/hi655x-pmic.h @@ -12,6 +12,8 @@ #ifndef __HI655X_PMIC_H #define __HI655X_PMIC_H +#include + /* Hi655x registers are mapped to memory bus in 4 bytes stride */ #define HI655X_STRIDE 4 #define HI655X_BUS_ADDR(x) ((x) << 2) @@ -53,7 +55,7 @@ struct hi655x_pmic { struct resource *res; struct device *dev; struct regmap *regmap; - int gpio; + struct gpio_desc *gpio; unsigned int ver; struct regmap_irq_chip_data *irq_data; }; -- cgit v1.2.3 From 54db804d5d7d36709d1ce70bde3b9a6c61b290b6 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 3 Mar 2022 17:55:21 -0600 Subject: scsi: fcoe: Fix Wstringop-overflow warnings in fcoe_wwn_from_mac() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following Wstringop-overflow warnings when building with GCC-11: drivers/scsi/fcoe/fcoe.c: In function ‘fcoe_netdev_config’: drivers/scsi/fcoe/fcoe.c:744:32: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 744 | wwnn = fcoe_wwn_from_mac(ctlr->ctl_src_addr, 1, 0); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/fcoe/fcoe.c:744:32: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/fcoe/fcoe.c:36: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ drivers/scsi/fcoe/fcoe.c:747:32: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 747 | wwpn = fcoe_wwn_from_mac(ctlr->ctl_src_addr, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 748 | 2, 0); | ~~~~~ drivers/scsi/fcoe/fcoe.c:747:32: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/fcoe/fcoe.c:36: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ CC drivers/scsi/bnx2fc/bnx2fc_io.o In function ‘bnx2fc_net_config’, inlined from ‘bnx2fc_if_create’ at drivers/scsi/bnx2fc/bnx2fc_fcoe.c:1543:7: drivers/scsi/bnx2fc/bnx2fc_fcoe.c:833:32: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 833 | wwnn = fcoe_wwn_from_mac(ctlr->ctl_src_addr, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 834 | 1, 0); | ~~~~~ drivers/scsi/bnx2fc/bnx2fc_fcoe.c: In function ‘bnx2fc_if_create’: drivers/scsi/bnx2fc/bnx2fc_fcoe.c:833:32: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/bnx2fc/bnx2fc.h:53, from drivers/scsi/bnx2fc/bnx2fc_fcoe.c:17: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ In function ‘bnx2fc_net_config’, inlined from ‘bnx2fc_if_create’ at drivers/scsi/bnx2fc/bnx2fc_fcoe.c:1543:7: drivers/scsi/bnx2fc/bnx2fc_fcoe.c:839:32: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 839 | wwpn = fcoe_wwn_from_mac(ctlr->ctl_src_addr, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 840 | 2, 0); | ~~~~~ drivers/scsi/bnx2fc/bnx2fc_fcoe.c: In function ‘bnx2fc_if_create’: drivers/scsi/bnx2fc/bnx2fc_fcoe.c:839:32: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/bnx2fc/bnx2fc.h:53, from drivers/scsi/bnx2fc/bnx2fc_fcoe.c:17: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ drivers/scsi/qedf/qedf_main.c: In function ‘__qedf_probe’: drivers/scsi/qedf/qedf_main.c:3520:30: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 3520 | qedf->wwnn = fcoe_wwn_from_mac(qedf->mac, 1, 0); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/qedf/qedf_main.c:3520:30: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/qedf/qedf.h:9, from drivers/scsi/qedf/qedf_main.c:23: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ drivers/scsi/qedf/qedf_main.c:3521:30: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 3521 | qedf->wwpn = fcoe_wwn_from_mac(qedf->mac, 2, 0); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/qedf/qedf_main.c:3521:30: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/qedf/qedf.h:9, from drivers/scsi/qedf/qedf_main.c:23: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ by changing the array size to the correct value of ETH_ALEN in the argument declaration. Also, fix a couple of checkpatch warnings: WARNING: function definition argument 'unsigned int' should also have an identifier name This helps with the ongoing efforts to globally enable -Wstringop-overflow. Link: https://github.com/KSPP/linux/issues/181 Fixes: 85b4aa4926a5 ("[SCSI] fcoe: Fibre Channel over Ethernet") Signed-off-by: Gustavo A. R. Silva --- include/scsi/libfcoe.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index fac8e89aed81..310e0dbffda9 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -249,7 +249,8 @@ int fcoe_ctlr_recv_flogi(struct fcoe_ctlr *, struct fc_lport *, struct fc_frame *); /* libfcoe funcs */ -u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); +u64 fcoe_wwn_from_mac(unsigned char mac[ETH_ALEN], unsigned int scheme, + unsigned int port); int fcoe_libfc_config(struct fc_lport *, struct fcoe_ctlr *, const struct libfc_function_template *, int init_fcp); u32 fcoe_fc_crc(struct fc_frame *fp); -- cgit v1.2.3 From 82028ba4d590c4e9eb3c93326019db7c26d02e35 Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Fri, 15 Apr 2022 17:36:24 +0200 Subject: mfd: mt6359: Add missing defines necessary for mtk-pmic-keys support Add 2 missing MT6359 registers that are needed to implement the keyboard driver. Signed-off-by: Fabien Parent Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20220415153629.1817202-3-fparent@baylibre.com --- include/linux/mfd/mt6359/registers.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/mt6359/registers.h b/include/linux/mfd/mt6359/registers.h index 2135c9695918..2a4394a27b1c 100644 --- a/include/linux/mfd/mt6359/registers.h +++ b/include/linux/mfd/mt6359/registers.h @@ -8,6 +8,8 @@ /* PMIC Registers */ #define MT6359_SWCID 0xa +#define MT6359_TOPSTATUS 0x2a +#define MT6359_TOP_RST_MISC 0x14c #define MT6359_MISC_TOP_INT_CON0 0x188 #define MT6359_MISC_TOP_INT_STATUS0 0x194 #define MT6359_TOP_INT_STATUS0 0x19e -- cgit v1.2.3 From c317ab71facc2cd0a94145973318a4c914e11acc Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Mon, 25 Apr 2022 21:32:47 +0800 Subject: bpf: Compute map_btf_id during build time For now, the field 'map_btf_id' in 'struct bpf_map_ops' for all map types are computed during vmlinux-btf init: btf_parse_vmlinux() -> btf_vmlinux_map_ids_init() It will lookup the btf_type according to the 'map_btf_name' field in 'struct bpf_map_ops'. This process can be done during build time, thanks to Jiri's resolve_btfids. selftest of map_ptr has passed: $96 map_ptr:OK Summary: 1/0 PASSED, 0 SKIPPED, 0 FAILED Reported-by: kernel test robot Signed-off-by: Menglong Dong Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0af5793ba417..be94833d390a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -148,8 +148,7 @@ struct bpf_map_ops { bpf_callback_t callback_fn, void *callback_ctx, u64 flags); - /* BTF name and id of struct allocated by map_alloc */ - const char * const map_btf_name; + /* BTF id of struct allocated by map_alloc */ int *map_btf_id; /* bpf_iter info used to open a seq_file */ -- cgit v1.2.3 From 9f79b8b7233942e9c4b071f1f331f17e7282bbfa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 5 Apr 2022 15:12:55 +0800 Subject: uapi: simplify __ARCH_FLOCK{,64}_PAD a little Don't bother to define the symbols empty, just don't use them. That makes the intent a little more clear. Remove the unused HAVE_ARCH_STRUCT_FLOCK64 define and merge the 32-bit mips struct flock into the generic one. Add a new __ARCH_FLOCK_EXTRA_SYSID macro following the style of __ARCH_FLOCK_PAD to avoid having a separate definition just for one architecture. Signed-off-by: Christoph Hellwig Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Tested-by: Heiko Stuebner Link: https://lore.kernel.org/r/20220405071314.3225832-2-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/uapi/asm-generic/fcntl.h | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index ecd0f5bdfc1d..77aa9f2ff98d 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -192,25 +192,19 @@ struct f_owner_ex { #define F_LINUX_SPECIFIC_BASE 1024 -#ifndef HAVE_ARCH_STRUCT_FLOCK -#ifndef __ARCH_FLOCK_PAD -#define __ARCH_FLOCK_PAD -#endif - struct flock { short l_type; short l_whence; __kernel_off_t l_start; __kernel_off_t l_len; __kernel_pid_t l_pid; - __ARCH_FLOCK_PAD -}; +#ifdef __ARCH_FLOCK_EXTRA_SYSID + __ARCH_FLOCK_EXTRA_SYSID #endif - -#ifndef HAVE_ARCH_STRUCT_FLOCK64 -#ifndef __ARCH_FLOCK64_PAD -#define __ARCH_FLOCK64_PAD +#ifdef __ARCH_FLOCK_PAD + __ARCH_FLOCK_PAD #endif +}; struct flock64 { short l_type; @@ -218,8 +212,9 @@ struct flock64 { __kernel_loff_t l_start; __kernel_loff_t l_len; __kernel_pid_t l_pid; +#ifdef __ARCH_FLOCK64_PAD __ARCH_FLOCK64_PAD -}; #endif +}; #endif /* _ASM_GENERIC_FCNTL_H */ -- cgit v1.2.3 From 306f7cc1e9061313c46d19e9bdffc819880794c1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 5 Apr 2022 15:12:56 +0800 Subject: uapi: always define F_GETLK64/F_SETLK64/F_SETLKW64 in fcntl.h The F_GETLK64/F_SETLK64/F_SETLKW64 fcntl opcodes are only implemented for the 32-bit syscall APIs, but are also needed for compat handling on 64-bit kernels. Consolidate them in unistd.h instead of definining the internal compat definitions in compat.h, which is rather error prone (e.g. parisc gets the values wrong currently). Note that before this change they were never visible to userspace due to the fact that CONFIG_64BIT is only set for kernel builds. Signed-off-by: Christoph Hellwig Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Tested-by: Heiko Stuebner Link: https://lore.kernel.org/r/20220405071314.3225832-3-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/uapi/asm-generic/fcntl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index 77aa9f2ff98d..f13d37b60775 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -116,13 +116,13 @@ #define F_GETSIG 11 /* for sockets. */ #endif -#ifndef CONFIG_64BIT +#if __BITS_PER_LONG == 32 || defined(__KERNEL__) #ifndef F_GETLK64 #define F_GETLK64 12 /* using 'struct flock64' */ #define F_SETLK64 13 #define F_SETLKW64 14 #endif -#endif +#endif /* __BITS_PER_LONG == 32 || defined(__KERNEL__) */ #ifndef F_SETOWN_EX #define F_SETOWN_EX 15 -- cgit v1.2.3 From 3ce0f2373f7073f04715b1ffd7b1812d3183f79a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 5 Apr 2022 15:12:57 +0800 Subject: compat: consolidate the compat_flock{,64} definition Provide a single common definition for the compat_flock and compat_flock64 structures using the same tricks as for the native variants. Another extra define is added for the packing required on x86. Signed-off-by: Christoph Hellwig Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Tested-by: Heiko Stuebner Acked-by: Helge Deller # parisc Link: https://lore.kernel.org/r/20220405071314.3225832-4-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/linux/compat.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index 1c758b0e0359..a0481fe6c5d5 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -258,6 +258,37 @@ struct compat_rlimit { compat_ulong_t rlim_max; }; +#ifdef __ARCH_NEED_COMPAT_FLOCK64_PACKED +#define __ARCH_COMPAT_FLOCK64_PACK __attribute__((packed)) +#else +#define __ARCH_COMPAT_FLOCK64_PACK +#endif + +struct compat_flock { + short l_type; + short l_whence; + compat_off_t l_start; + compat_off_t l_len; +#ifdef __ARCH_COMPAT_FLOCK_EXTRA_SYSID + __ARCH_COMPAT_FLOCK_EXTRA_SYSID +#endif + compat_pid_t l_pid; +#ifdef __ARCH_COMPAT_FLOCK_PAD + __ARCH_COMPAT_FLOCK_PAD +#endif +}; + +struct compat_flock64 { + short l_type; + short l_whence; + compat_loff_t l_start; + compat_loff_t l_len; + compat_pid_t l_pid; +#ifdef __ARCH_COMPAT_FLOCK64_PAD + __ARCH_COMPAT_FLOCK64_PAD +#endif +} __ARCH_COMPAT_FLOCK64_PACK; + struct compat_rusage { struct old_timeval32 ru_utime; struct old_timeval32 ru_stime; -- cgit v1.2.3 From 84a0c977ab9821a4b57f69d9a6108f64188d1e71 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Tue, 5 Apr 2022 15:13:00 +0800 Subject: asm-generic: compat: Cleanup duplicate definitions There are 7 64bit architectures that support Linux COMPAT mode to run 32bit applications. A lot of definitions are duplicate: - COMPAT_USER_HZ - COMPAT_RLIM_INFINITY - COMPAT_OFF_T_MAX - __compat_uid_t, __compat_uid_t - compat_dev_t - compat_ipc_pid_t - struct compat_flock - struct compat_flock64 - struct compat_statfs - struct compat_ipc64_perm, compat_semid64_ds, compat_msqid64_ds, compat_shmid64_ds Cleanup duplicate definitions and merge them into asm-generic. Signed-off-by: Guo Ren Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Tested-by: Heiko Stuebner Acked-by: Helge Deller # parisc Link: https://lore.kernel.org/r/20220405071314.3225832-7-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/asm-generic/compat.h | 106 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) (limited to 'include') diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index d46c0201cc34..11653d6846cc 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -2,6 +2,18 @@ #ifndef __ASM_GENERIC_COMPAT_H #define __ASM_GENERIC_COMPAT_H +#ifndef COMPAT_USER_HZ +#define COMPAT_USER_HZ 100 +#endif + +#ifndef COMPAT_RLIM_INFINITY +#define COMPAT_RLIM_INFINITY 0xffffffff +#endif + +#ifndef COMPAT_OFF_T_MAX +#define COMPAT_OFF_T_MAX 0x7fffffff +#endif + /* These types are common across all compat ABIs */ typedef u32 compat_size_t; typedef s32 compat_ssize_t; @@ -24,6 +36,11 @@ typedef u32 compat_caddr_t; typedef u32 compat_aio_context_t; typedef u32 compat_old_sigset_t; +#ifndef __compat_uid_t +typedef u32 __compat_uid_t; +typedef u32 __compat_gid_t; +#endif + #ifndef __compat_uid32_t typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; @@ -47,4 +64,93 @@ typedef u32 compat_sigset_word; #define _COMPAT_NSIG_BPW 32 #endif +#ifndef compat_dev_t +typedef u32 compat_dev_t; +#endif + +#ifndef compat_ipc_pid_t +typedef s32 compat_ipc_pid_t; +#endif + +#ifndef compat_fsid_t +typedef __kernel_fsid_t compat_fsid_t; +#endif + +#ifndef compat_statfs +struct compat_statfs { + compat_int_t f_type; + compat_int_t f_bsize; + compat_int_t f_blocks; + compat_int_t f_bfree; + compat_int_t f_bavail; + compat_int_t f_files; + compat_int_t f_ffree; + compat_fsid_t f_fsid; + compat_int_t f_namelen; + compat_int_t f_frsize; + compat_int_t f_flags; + compat_int_t f_spare[4]; +}; +#endif + +#ifndef compat_ipc64_perm +struct compat_ipc64_perm { + compat_key_t key; + __compat_uid32_t uid; + __compat_gid32_t gid; + __compat_uid32_t cuid; + __compat_gid32_t cgid; + compat_mode_t mode; + unsigned char __pad1[4 - sizeof(compat_mode_t)]; + compat_ushort_t seq; + compat_ushort_t __pad2; + compat_ulong_t unused1; + compat_ulong_t unused2; +}; + +struct compat_semid64_ds { + struct compat_ipc64_perm sem_perm; + compat_ulong_t sem_otime; + compat_ulong_t sem_otime_high; + compat_ulong_t sem_ctime; + compat_ulong_t sem_ctime_high; + compat_ulong_t sem_nsems; + compat_ulong_t __unused3; + compat_ulong_t __unused4; +}; + +struct compat_msqid64_ds { + struct compat_ipc64_perm msg_perm; + compat_ulong_t msg_stime; + compat_ulong_t msg_stime_high; + compat_ulong_t msg_rtime; + compat_ulong_t msg_rtime_high; + compat_ulong_t msg_ctime; + compat_ulong_t msg_ctime_high; + compat_ulong_t msg_cbytes; + compat_ulong_t msg_qnum; + compat_ulong_t msg_qbytes; + compat_pid_t msg_lspid; + compat_pid_t msg_lrpid; + compat_ulong_t __unused4; + compat_ulong_t __unused5; +}; + +struct compat_shmid64_ds { + struct compat_ipc64_perm shm_perm; + compat_size_t shm_segsz; + compat_ulong_t shm_atime; + compat_ulong_t shm_atime_high; + compat_ulong_t shm_dtime; + compat_ulong_t shm_dtime_high; + compat_ulong_t shm_ctime; + compat_ulong_t shm_ctime_high; + compat_pid_t shm_cpid; + compat_pid_t shm_lpid; + compat_ulong_t shm_nattch; + compat_ulong_t __unused4; + compat_ulong_t __unused5; +}; +#endif + #endif -- cgit v1.2.3 From c86d2cad193a5c7f9b92467955bb7fb6642b9e80 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Tue, 5 Apr 2022 15:13:01 +0800 Subject: syscalls: compat: Fix the missing part for __SYSCALL_COMPAT Make "uapi asm unistd.h" could be used for architectures' COMPAT mode. The __SYSCALL_COMPAT is first used in riscv. Signed-off-by: Guo Ren Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Tested-by: Heiko Stuebner Link: https://lore.kernel.org/r/20220405071314.3225832-8-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/uapi/asm-generic/unistd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 1c48b0ae3ba3..45fa180cc56a 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -383,7 +383,7 @@ __SYSCALL(__NR_syslog, sys_syslog) /* kernel/ptrace.c */ #define __NR_ptrace 117 -__SYSCALL(__NR_ptrace, sys_ptrace) +__SC_COMP(__NR_ptrace, sys_ptrace, compat_sys_ptrace) /* kernel/sched/core.c */ #define __NR_sched_setparam 118 @@ -779,7 +779,7 @@ __SYSCALL(__NR_rseq, sys_rseq) #define __NR_kexec_file_load 294 __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) /* 295 through 402 are unassigned to sync up with generic numbers, don't use */ -#if __BITS_PER_LONG == 32 +#if defined(__SYSCALL_COMPAT) || __BITS_PER_LONG == 32 #define __NR_clock_gettime64 403 __SYSCALL(__NR_clock_gettime64, sys_clock_gettime) #define __NR_clock_settime64 404 -- cgit v1.2.3 From 59c10c52f573faca862cda5ebcdd43831608eb5a Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Tue, 5 Apr 2022 15:13:05 +0800 Subject: riscv: compat: syscall: Add compat_sys_call_table implementation Implement compat sys_call_table and some system call functions: truncate64, ftruncate64, fallocate, pread64, pwrite64, sync_file_range, readahead, fadvise64_64 which need argument translation. Signed-off-by: Guo Ren Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Tested-by: Heiko Stuebner Link: https://lore.kernel.org/r/20220405071314.3225832-12-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/asm-generic/compat.h | 7 +++++++ include/linux/compat.h | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+) (limited to 'include') diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index 11653d6846cc..d06308a2a7a8 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -14,6 +14,13 @@ #define COMPAT_OFF_T_MAX 0x7fffffff #endif +#if !defined(compat_arg_u64) && !defined(CONFIG_CPU_BIG_ENDIAN) +#define compat_arg_u64(name) u32 name##_lo, u32 name##_hi +#define compat_arg_u64_dual(name) u32, name##_lo, u32, name##_hi +#define compat_arg_u64_glue(name) (((u64)name##_lo & 0xffffffffUL) | \ + ((u64)name##_hi << 32)) +#endif + /* These types are common across all compat ABIs */ typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/include/linux/compat.h b/include/linux/compat.h index a0481fe6c5d5..ce6cd9b30d27 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -926,6 +926,43 @@ asmlinkage long compat_sys_sigaction(int sig, /* obsolete: net/socket.c */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); +#ifdef __ARCH_WANT_COMPAT_TRUNCATE64 +asmlinkage long compat_sys_truncate64(const char __user *pathname, compat_arg_u64(len)); +#endif + +#ifdef __ARCH_WANT_COMPAT_FTRUNCATE64 +asmlinkage long compat_sys_ftruncate64(unsigned int fd, compat_arg_u64(len)); +#endif + +#ifdef __ARCH_WANT_COMPAT_FALLOCATE +asmlinkage long compat_sys_fallocate(int fd, int mode, compat_arg_u64(offset), + compat_arg_u64(len)); +#endif + +#ifdef __ARCH_WANT_COMPAT_PREAD64 +asmlinkage long compat_sys_pread64(unsigned int fd, char __user *buf, size_t count, + compat_arg_u64(pos)); +#endif + +#ifdef __ARCH_WANT_COMPAT_PWRITE64 +asmlinkage long compat_sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, + compat_arg_u64(pos)); +#endif + +#ifdef __ARCH_WANT_COMPAT_SYNC_FILE_RANGE +asmlinkage long compat_sys_sync_file_range(int fd, compat_arg_u64(pos), + compat_arg_u64(nbytes), unsigned int flags); +#endif + +#ifdef __ARCH_WANT_COMPAT_FADVISE64_64 +asmlinkage long compat_sys_fadvise64_64(int fd, compat_arg_u64(pos), + compat_arg_u64(len), int advice); +#endif + +#ifdef __ARCH_WANT_COMPAT_READAHEAD +asmlinkage long compat_sys_readahead(int fd, compat_arg_u64(offset), size_t count); +#endif + #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ /** -- cgit v1.2.3 From a2a9d67a26ec94a99ed29efbd61cf5be0a575678 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 6 Apr 2022 11:31:19 +0900 Subject: bootconfig: Support embedding a bootconfig file in kernel This allows kernel developer to embed a default bootconfig file in the kernel instead of embedding it in the initrd. This will be good for who are using the kernel without initrd, or who needs a default bootconfigs. This needs to set two kconfigs: CONFIG_BOOT_CONFIG_EMBED=y and set the file path to CONFIG_BOOT_CONFIG_EMBED_FILE. Note that you still need 'bootconfig' command line option to load the embedded bootconfig. Also if you boot using an initrd with a different bootconfig, the kernel will use the bootconfig in the initrd, instead of the default bootconfig. Link: https://lkml.kernel.org/r/164921227943.1090670.14035119557571329218.stgit@devnote2 Cc: Padmanabha Srinivasaiah Cc: Jonathan Corbet Cc: Randy Dunlap Cc: Nick Desaulniers Cc: Sami Tolvanen Cc: Nathan Chancellor Cc: Masahiro Yamada Cc: Linux Kbuild mailing list Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (Google) --- include/linux/bootconfig.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index a4665c7ab07c..1611f9db878e 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -289,4 +289,14 @@ int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ void __init xbc_exit(void); +/* XBC embedded bootconfig data in kernel */ +#ifdef CONFIG_BOOT_CONFIG_EMBED +const char * __init xbc_get_embedded_bootconfig(size_t *size); +#else +static inline const char *xbc_get_embedded_bootconfig(size_t *size) +{ + return NULL; +} +#endif + #endif -- cgit v1.2.3 From 68822bdf76f10c3dc80609d4e2cdc1e847429086 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 22 Apr 2022 13:12:37 -0700 Subject: net: generalize skb freeing deferral to per-cpu lists Logic added in commit f35f821935d8 ("tcp: defer skb freeing after socket lock is released") helped bulk TCP flows to move the cost of skbs frees outside of critical section where socket lock was held. But for RPC traffic, or hosts with RFS enabled, the solution is far from being ideal. For RPC traffic, recvmsg() has to return to user space right after skb payload has been consumed, meaning that BH handler has no chance to pick the skb before recvmsg() thread. This issue is more visible with BIG TCP, as more RPC fit one skb. For RFS, even if BH handler picks the skbs, they are still picked from the cpu on which user thread is running. Ideally, it is better to free the skbs (and associated page frags) on the cpu that originally allocated them. This patch removes the per socket anchor (sk->defer_list) and instead uses a per-cpu list, which will hold more skbs per round. This new per-cpu list is drained at the end of net_action_rx(), after incoming packets have been processed, to lower latencies. In normal conditions, skbs are added to the per-cpu list with no further action. In the (unlikely) cases where the cpu does not run net_action_rx() handler fast enough, we use an IPI to raise NET_RX_SOFTIRQ on the remote cpu. Also, we do not bother draining the per-cpu list from dev_cpu_dead() This is because skbs in this list have no requirement on how fast they should be freed. Note that we can add in the future a small per-cpu cache if we see any contention on sd->defer_lock. Tested on a pair of hosts with 100Gbit NIC, RFS enabled, and /proc/sys/net/ipv4/tcp_rmem[2] tuned to 16MB to work around page recycling strategy used by NIC driver (its page pool capacity being too small compared to number of skbs/pages held in sockets receive queues) Note that this tuning was only done to demonstrate worse conditions for skb freeing for this particular test. These conditions can happen in more general production workload. 10 runs of one TCP_STREAM flow Before: Average throughput: 49685 Mbit. Kernel profiles on cpu running user thread recvmsg() show high cost for skb freeing related functions (*) 57.81% [kernel] [k] copy_user_enhanced_fast_string (*) 12.87% [kernel] [k] skb_release_data (*) 4.25% [kernel] [k] __free_one_page (*) 3.57% [kernel] [k] __list_del_entry_valid 1.85% [kernel] [k] __netif_receive_skb_core 1.60% [kernel] [k] __skb_datagram_iter (*) 1.59% [kernel] [k] free_unref_page_commit (*) 1.16% [kernel] [k] __slab_free 1.16% [kernel] [k] _copy_to_iter (*) 1.01% [kernel] [k] kfree (*) 0.88% [kernel] [k] free_unref_page 0.57% [kernel] [k] ip6_rcv_core 0.55% [kernel] [k] ip6t_do_table 0.54% [kernel] [k] flush_smp_call_function_queue (*) 0.54% [kernel] [k] free_pcppages_bulk 0.51% [kernel] [k] llist_reverse_order 0.38% [kernel] [k] process_backlog (*) 0.38% [kernel] [k] free_pcp_prepare 0.37% [kernel] [k] tcp_recvmsg_locked (*) 0.37% [kernel] [k] __list_add_valid 0.34% [kernel] [k] sock_rfree 0.34% [kernel] [k] _raw_spin_lock_irq (*) 0.33% [kernel] [k] __page_cache_release 0.33% [kernel] [k] tcp_v6_rcv (*) 0.33% [kernel] [k] __put_page (*) 0.29% [kernel] [k] __mod_zone_page_state 0.27% [kernel] [k] _raw_spin_lock After patch: Average throughput: 73076 Mbit. Kernel profiles on cpu running user thread recvmsg() looks better: 81.35% [kernel] [k] copy_user_enhanced_fast_string 1.95% [kernel] [k] _copy_to_iter 1.95% [kernel] [k] __skb_datagram_iter 1.27% [kernel] [k] __netif_receive_skb_core 1.03% [kernel] [k] ip6t_do_table 0.60% [kernel] [k] sock_rfree 0.50% [kernel] [k] tcp_v6_rcv 0.47% [kernel] [k] ip6_rcv_core 0.45% [kernel] [k] read_tsc 0.44% [kernel] [k] _raw_spin_lock_irqsave 0.37% [kernel] [k] _raw_spin_lock 0.37% [kernel] [k] native_irq_return_iret 0.33% [kernel] [k] __inet6_lookup_established 0.31% [kernel] [k] ip6_protocol_deliver_rcu 0.29% [kernel] [k] tcp_rcv_established 0.29% [kernel] [k] llist_reverse_order v2: kdoc issue (kernel bots) do not defer if (alloc_cpu == smp_processor_id()) (Paolo) replace the sk_buff_head with a single-linked list (Jakub) add a READ_ONCE()/WRITE_ONCE() for the lockless read of sd->defer_list Signed-off-by: Eric Dumazet Acked-by: Paolo Abeni Link: https://lore.kernel.org/r/20220422201237.416238-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 5 +++++ include/linux/skbuff.h | 3 +++ include/net/sock.h | 2 -- include/net/tcp.h | 12 ------------ 4 files changed, 8 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7dccbfd1bf56..ac8a5f71220a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3081,6 +3081,11 @@ struct softnet_data { struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + /* Another possibly contended cache line */ + spinlock_t defer_lock ____cacheline_aligned_in_smp; + int defer_count; + struct sk_buff *defer_list; + call_single_data_t defer_csd; }; static inline void input_queue_head_incr(struct softnet_data *sd) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 84d78df60453..5cbc184ca685 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -888,6 +888,7 @@ typedef unsigned char *sk_buff_data_t; * delivery_time at egress. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS + * @alloc_cpu: CPU which did the skb allocation. * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available @@ -1080,6 +1081,7 @@ struct sk_buff { unsigned int sender_cpu; }; #endif + u16 alloc_cpu; #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif @@ -1321,6 +1323,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); +void skb_attempt_defer_free(struct sk_buff *skb); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); diff --git a/include/net/sock.h b/include/net/sock.h index a01d6c421aa2..f9f8ecae0f8d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -292,7 +292,6 @@ struct sk_filter; * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held - * @defer_list: head of llist storing skbs to be freed * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, @@ -417,7 +416,6 @@ struct sock { struct sk_buff *head; struct sk_buff *tail; } sk_backlog; - struct llist_head defer_list; #define sk_rmem_alloc sk_backlog.rmem_alloc diff --git a/include/net/tcp.h b/include/net/tcp.h index 679b1964d494..94a52ad1101c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1375,18 +1375,6 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); -#ifdef CONFIG_INET -void __sk_defer_free_flush(struct sock *sk); - -static inline void sk_defer_free_flush(struct sock *sk) -{ - if (llist_empty(&sk->defer_list)) - return; - __sk_defer_free_flush(sk); -} -#else -static inline void sk_defer_free_flush(struct sock *sk) {} -#endif int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); -- cgit v1.2.3 From 9bf2eed995f9f8136f00110214c120f2d7912ad8 Mon Sep 17 00:00:00 2001 From: Brendan Higgins Date: Mon, 18 Apr 2022 21:05:15 -0700 Subject: kunit: add support for kunit_suites that reference init code Add support for a new kind of kunit_suite registration macro called kunit_test_init_section_suite(); this new registration macro allows the registration of kunit_suites that reference functions marked __init and data marked __initdata. Signed-off-by: Brendan Higgins Tested-by: Martin Fernandez Reviewed-by: Kees Cook Reviewed-by: David Gow Signed-off-by: Shuah Khan --- include/kunit/test.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 97cd76461886..17749b4467ad 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -308,6 +308,34 @@ static inline int kunit_run_all_tests(void) #define kunit_test_suite(suite) kunit_test_suites(&suite) +/** + * kunit_test_init_section_suites() - used to register one or more &struct + * kunit_suite containing init functions or + * init data. + * + * @__suites: a statically allocated list of &struct kunit_suite. + * + * This functions identically as &kunit_test_suites() except that it suppresses + * modpost warnings for referencing functions marked __init or data marked + * __initdata; this is OK because currently KUnit only runs tests upon boot + * during the init phase or upon loading a module during the init phase. + * + * NOTE TO KUNIT DEVS: If we ever allow KUnit tests to be run after boot, these + * tests must be excluded. + * + * The only thing this macro does that's different from kunit_test_suites is + * that it suffixes the array and suite declarations it makes with _probe; + * modpost suppresses warnings about referencing init data for symbols named in + * this manner. + */ +#define kunit_test_init_section_suites(__suites...) \ + __kunit_test_suites(CONCATENATE(__UNIQUE_ID(array), _probe), \ + CONCATENATE(__UNIQUE_ID(suites), _probe), \ + ##__suites) + +#define kunit_test_init_section_suite(suite) \ + kunit_test_init_section_suites(&suite) + #define kunit_suite_for_each_test_case(suite, test_case) \ for (test_case = suite->test_cases; test_case->run_case; test_case++) -- cgit v1.2.3 From 6423d2951087231706246f81851067f7f0593d4a Mon Sep 17 00:00:00 2001 From: Won Chung Date: Mon, 14 Mar 2022 19:54:58 +0000 Subject: driver core: Add sysfs support for physical location of a device When ACPI table includes _PLD fields for a device, create a new directory (physical_location) in sysfs to share _PLD fields. Currently without PLD information, when there are multiple of same devices, it is hard to distinguish which device corresponds to which physical device at which location. For example, when there are two Type C connectors, it is hard to find out which connector corresponds to the Type C port on the left panel versus the Type C port on the right panel. With PLD information provided, we can determine which specific device at which location is doing what. _PLD output includes much more fields, but only generic fields are added and exposed to sysfs, so that non-ACPI devices can also support it in the future. The minimal generic fields needed for locating a device are the following. - panel - vertical_position - horizontal_position - dock - lid Signed-off-by: Won Chung Link: https://lore.kernel.org/r/20220314195458.271430-1-wonchung@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 73 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 93459724dcde..766fbea6ca83 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -386,6 +386,75 @@ struct dev_msi_info { #endif }; +/** + * enum device_physical_location_panel - Describes which panel surface of the + * system's housing the device connection point resides on. + * @DEVICE_PANEL_TOP: Device connection point is on the top panel. + * @DEVICE_PANEL_BOTTOM: Device connection point is on the bottom panel. + * @DEVICE_PANEL_LEFT: Device connection point is on the left panel. + * @DEVICE_PANEL_RIGHT: Device connection point is on the right panel. + * @DEVICE_PANEL_FRONT: Device connection point is on the front panel. + * @DEVICE_PANEL_BACK: Device connection point is on the back panel. + * @DEVICE_PANEL_UNKNOWN: The panel with device connection point is unknown. + */ +enum device_physical_location_panel { + DEVICE_PANEL_TOP, + DEVICE_PANEL_BOTTOM, + DEVICE_PANEL_LEFT, + DEVICE_PANEL_RIGHT, + DEVICE_PANEL_FRONT, + DEVICE_PANEL_BACK, + DEVICE_PANEL_UNKNOWN, +}; + +/** + * enum device_physical_location_vertical_position - Describes vertical + * position of the device connection point on the panel surface. + * @DEVICE_VERT_POS_UPPER: Device connection point is at upper part of panel. + * @DEVICE_VERT_POS_CENTER: Device connection point is at center part of panel. + * @DEVICE_VERT_POS_LOWER: Device connection point is at lower part of panel. + */ +enum device_physical_location_vertical_position { + DEVICE_VERT_POS_UPPER, + DEVICE_VERT_POS_CENTER, + DEVICE_VERT_POS_LOWER, +}; + +/** + * enum device_physical_location_horizontal_position - Describes horizontal + * position of the device connection point on the panel surface. + * @DEVICE_HORI_POS_LEFT: Device connection point is at left part of panel. + * @DEVICE_HORI_POS_CENTER: Device connection point is at center part of panel. + * @DEVICE_HORI_POS_RIGHT: Device connection point is at right part of panel. + */ +enum device_physical_location_horizontal_position { + DEVICE_HORI_POS_LEFT, + DEVICE_HORI_POS_CENTER, + DEVICE_HORI_POS_RIGHT, +}; + +/** + * struct device_physical_location - Device data related to physical location + * of the device connection point. + * @panel: Panel surface of the system's housing that the device connection + * point resides on. + * @vertical_position: Vertical position of the device connection point within + * the panel. + * @horizontal_position: Horizontal position of the device connection point + * within the panel. + * @dock: Set if the device connection point resides in a docking station or + * port replicator. + * @lid: Set if this device connection point resides on the lid of laptop + * system. + */ +struct device_physical_location { + enum device_physical_location_panel panel; + enum device_physical_location_vertical_position vertical_position; + enum device_physical_location_horizontal_position horizontal_position; + bool dock; + bool lid; +}; + /** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. @@ -453,6 +522,8 @@ struct dev_msi_info { * device (i.e. the bus driver that discovered the device). * @iommu_group: IOMMU group the device belongs to. * @iommu: Per device generic IOMMU runtime data + * @physical_location: Describes physical location of the device connection + * point in the system housing. * @removable: Whether the device can be removed from the system. This * should be set by the subsystem / bus driver that discovered * the device. @@ -567,6 +638,8 @@ struct device { struct iommu_group *iommu_group; struct dev_iommu *iommu; + struct device_physical_location *physical_location; + enum device_removable removable; bool offline_disabled:1; -- cgit v1.2.3 From 052e1f01bfae8be6f31b61ed3a2356edfca855dc Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 26 Apr 2022 10:54:33 -0700 Subject: net: atm: remove support for ZeitNet ZN122x ATM devices This driver received nothing but automated fixes in the last 15 years. Since it's using virt_to_bus it's unlikely to be used on any modern platform. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/atm_zatm.h | 47 ------------------------------------------- 1 file changed, 47 deletions(-) delete mode 100644 include/uapi/linux/atm_zatm.h (limited to 'include') diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h deleted file mode 100644 index 5135027b93c1..000000000000 --- a/include/uapi/linux/atm_zatm.h +++ /dev/null @@ -1,47 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* atm_zatm.h - Driver-specific declarations of the ZATM driver (for use by - driver-specific utilities) */ - -/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */ - - -#ifndef LINUX_ATM_ZATM_H -#define LINUX_ATM_ZATM_H - -/* - * Note: non-kernel programs including this file must also include - * sys/types.h for struct timeval - */ - -#include -#include - -#define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc) - /* get pool statistics */ -#define ZATM_GETPOOLZ _IOW('a',ATMIOC_SARPRV+2,struct atmif_sioc) - /* get statistics and zero */ -#define ZATM_SETPOOL _IOW('a',ATMIOC_SARPRV+3,struct atmif_sioc) - /* set pool parameters */ - -struct zatm_pool_info { - int ref_count; /* free buffer pool usage counters */ - int low_water,high_water; /* refill parameters */ - int rqa_count,rqu_count; /* queue condition counters */ - int offset,next_off; /* alignment optimizations: offset */ - int next_cnt,next_thres; /* repetition counter and threshold */ -}; - -struct zatm_pool_req { - int pool_num; /* pool number */ - struct zatm_pool_info info; /* actual information */ -}; - -#define ZATM_OAM_POOL 0 /* free buffer pool for OAM cells */ -#define ZATM_AAL0_POOL 1 /* free buffer pool for AAL0 cells */ -#define ZATM_AAL5_POOL_BASE 2 /* first AAL5 free buffer pool */ -#define ZATM_LAST_POOL ZATM_AAL5_POOL_BASE+10 /* max. 64 kB */ - -#define ZATM_TIMER_HISTORY_SIZE 16 /* number of timer adjustments to - record; must be 2^n */ - -#endif -- cgit v1.2.3 From afe57ecab58b976c54fcbc31d718f936a0cc98cc Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 26 Apr 2022 13:36:31 -0500 Subject: ASoC: SOF: bump SOF_ABI_MINOR Commit a0f84dfb3f6d9 ("ASoC: SOF: IPC: dai: Expand DAI_CONFIG IPC flags") did not update the SOF_ABI_MINOR, bump to version 20 before new changes are added. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Daniel Baluta Reviewed-by: Kai Vehmanen Link: https://lore.kernel.org/r/20220426183631.102356-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/uapi/sound/sof/abi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/sound/sof/abi.h b/include/uapi/sound/sof/abi.h index e052653a6e4c..b87e46684623 100644 --- a/include/uapi/sound/sof/abi.h +++ b/include/uapi/sound/sof/abi.h @@ -26,8 +26,8 @@ /* SOF ABI version major, minor and patch numbers */ #define SOF_ABI_MAJOR 3 -#define SOF_ABI_MINOR 19 -#define SOF_ABI_PATCH 1 +#define SOF_ABI_MINOR 20 +#define SOF_ABI_PATCH 0 /* SOF ABI version number. Format within 32bit word is MMmmmppp */ #define SOF_ABI_MAJOR_SHIFT 24 -- cgit v1.2.3 From 2d3694fdeef599ef5a1352b699bdd493a51ab8cb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Amadeusz=20S=C5=82awi=C5=84ski?= Date: Tue, 26 Apr 2022 22:05:38 +0200 Subject: ALSA: hda: intel-nhlt: Move structs out of #define block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As functions prototypes regerdless of CONFIG options as well as some code depend on structures defined in sound/intel-nhlt.h header, move them out of #define block. This allows to compile code depending on mentioned header with "depends on ACPI || COMPILE_TEST" in Kconfig. Fixes: 47a1886a610a ("ASoC: Intel: avs: Enable AVS driver only on x86 platforms") Reported-by: kernel test robot Suggested-by: Pierre-Louis Bossart Reviewed-by: Cezary Rojewski Signed-off-by: Amadeusz Sławiński Link: https://lore.kernel.org/r/20220426200539.894010-1-amadeuszx.slawinski@linux.intel.com Signed-off-by: Mark Brown --- include/sound/intel-nhlt.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/sound/intel-nhlt.h b/include/sound/intel-nhlt.h index 6fb2d5e378fd..3d5cf201cd80 100644 --- a/include/sound/intel-nhlt.h +++ b/include/sound/intel-nhlt.h @@ -25,8 +25,6 @@ enum nhlt_device_type { NHLT_DEVICE_INVALID }; -#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SND_INTEL_NHLT) - struct wav_fmt { u16 fmt_tag; u16 channels; @@ -126,6 +124,8 @@ enum { NHLT_MIC_ARRAY_VENDOR_DEFINED = 0xf, }; +#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SND_INTEL_NHLT) + struct nhlt_acpi_table *intel_nhlt_init(struct device *dev); void intel_nhlt_free(struct nhlt_acpi_table *addr); @@ -143,8 +143,6 @@ intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt, #else -struct nhlt_acpi_table; - static inline struct nhlt_acpi_table *intel_nhlt_init(struct device *dev) { return NULL; -- cgit v1.2.3 From b041b525dab95352fbd666b14dc73ab898df465f Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Thu, 10 Mar 2022 12:48:53 -0800 Subject: x86/split_lock: Make life miserable for split lockers In https://lore.kernel.org/all/87y22uujkm.ffs@tglx/ Thomas said: Its's simply wishful thinking that stuff gets fixed because of a WARN_ONCE(). This has never worked. The only thing which works is to make stuff fail hard or slow it down in a way which makes it annoying enough to users to complain. He was talking about WBINVD. But it made me think about how we use the split lock detection feature in Linux. Existing code has three options for applications: 1) Don't enable split lock detection (allow arbitrary split locks) 2) Warn once when a process uses split lock, but let the process keep running with split lock detection disabled 3) Kill process that use split locks Option 2 falls into the "wishful thinking" territory that Thomas warns does nothing. But option 3 might not be viable in a situation with legacy applications that need to run. Hence make option 2 much stricter to "slow it down in a way which makes it annoying". Primary reason for this change is to provide better quality of service to the rest of the applications running on the system. Internal testing shows that even with many processes splitting locks, performance for the rest of the system is much more responsive. The new "warn" mode operates like this. When an application tries to execute a bus lock the #AC handler. 1) Delays (interruptibly) 10 ms before moving to next step. 2) Blocks (interruptibly) until it can get the semaphore If interrupted, just return. Assume the signal will either kill the task, or direct execution away from the instruction that is trying to get the bus lock. 3) Disables split lock detection for the current core 4) Schedules a work queue to re-enable split lock detect in 2 jiffies 5) Returns The work queue that re-enables split lock detection also releases the semaphore. There is a corner case where a CPU may be taken offline while split lock detection is disabled. A CPU hotplug handler handles this case. Old behaviour was to only print the split lock warning on the first occurrence of a split lock from a task. Preserve that by adding a flag to the task structure that suppresses subsequent split lock messages from that task. Signed-off-by: Tony Luck Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220310204854.31752-2-tony.luck@intel.com --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index a8911b1f35aa..23e03c7824c4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -941,6 +941,9 @@ struct task_struct { #ifdef CONFIG_IOMMU_SVA unsigned pasid_activated:1; #endif +#ifdef CONFIG_CPU_SUP_INTEL + unsigned reported_split_lock:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ -- cgit v1.2.3 From 4fd62f15afa0d0da4823f429a2fb4c3492a84edf Mon Sep 17 00:00:00 2001 From: Chuanhong Guo Date: Sun, 24 Apr 2022 11:25:23 +0800 Subject: mtd: nand: make mtk_ecc.c a separated module this code will be used in mediatek snfi spi-mem controller with pipelined ECC engine. Signed-off-by: Chuanhong Guo Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20220424032527.673605-2-gch981213@gmail.com --- include/linux/mtd/nand-ecc-mtk.h | 47 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 include/linux/mtd/nand-ecc-mtk.h (limited to 'include') diff --git a/include/linux/mtd/nand-ecc-mtk.h b/include/linux/mtd/nand-ecc-mtk.h new file mode 100644 index 000000000000..0e48c36e6ca0 --- /dev/null +++ b/include/linux/mtd/nand-ecc-mtk.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* + * MTK SDG1 ECC controller + * + * Copyright (c) 2016 Mediatek + * Authors: Xiaolei Li + * Jorge Ramirez-Ortiz + */ + +#ifndef __DRIVERS_MTD_NAND_MTK_ECC_H__ +#define __DRIVERS_MTD_NAND_MTK_ECC_H__ + +#include + +enum mtk_ecc_mode {ECC_DMA_MODE = 0, ECC_NFI_MODE = 1}; +enum mtk_ecc_operation {ECC_ENCODE, ECC_DECODE}; + +struct device_node; +struct mtk_ecc; + +struct mtk_ecc_stats { + u32 corrected; + u32 bitflips; + u32 failed; +}; + +struct mtk_ecc_config { + enum mtk_ecc_operation op; + enum mtk_ecc_mode mode; + dma_addr_t addr; + u32 strength; + u32 sectors; + u32 len; +}; + +int mtk_ecc_encode(struct mtk_ecc *, struct mtk_ecc_config *, u8 *, u32); +void mtk_ecc_get_stats(struct mtk_ecc *, struct mtk_ecc_stats *, int); +int mtk_ecc_wait_done(struct mtk_ecc *, enum mtk_ecc_operation); +int mtk_ecc_enable(struct mtk_ecc *, struct mtk_ecc_config *); +void mtk_ecc_disable(struct mtk_ecc *); +void mtk_ecc_adjust_strength(struct mtk_ecc *ecc, u32 *p); +unsigned int mtk_ecc_get_parity_bits(struct mtk_ecc *ecc); + +struct mtk_ecc *of_mtk_ecc_get(struct device_node *); +void mtk_ecc_release(struct mtk_ecc *); + +#endif -- cgit v1.2.3 From 7d84c1ebf9ddafca27b481e6da7d24a023dacaa2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 15 Apr 2022 21:20:02 +0200 Subject: x86/aperfmperf: Replace aperfmperf_get_khz() The frequency invariance infrastructure provides the APERF/MPERF samples already. Utilize them for the cpu frequency display in /proc/cpuinfo. The sample is considered valid for 20ms. So for idle or isolated NOHZ full CPUs the function returns 0, which is matching the previous behaviour. This gets rid of the mass IPIs and a delay of 20ms for stabilizing observed by Eric when reading /proc/cpuinfo. Reported-by: Eric Dumazet Signed-off-by: Thomas Gleixner Tested-by: Eric Dumazet Reviewed-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) Acked-by: Paul E. McKenney Link: https://lore.kernel.org/r/20220415161206.875029458@linutronix.de --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 35c7d6db4139..d5595d57f4e5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1199,7 +1199,6 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, struct cpufreq_governor *old_gov) { } #endif -extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); #ifndef arch_set_freq_scale -- cgit v1.2.3 From b941820ec938d175fd6e4e7ba5b4a6ca9d092afd Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 25 Apr 2022 14:45:44 +0300 Subject: ACPI: OSL: Remove the helper for deactivating memory region There are no more users for acpi_release_memory(). Signed-off-by: Heikki Krogerus Reviewed-by: Greg Kroah-Hartman Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d7136d13aa44..fadda404bcc9 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -520,9 +520,6 @@ int acpi_check_resource_conflict(const struct resource *res); int acpi_check_region(resource_size_t start, resource_size_t n, const char *name); -acpi_status acpi_release_memory(acpi_handle handle, struct resource *res, - u32 level); - int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION -- cgit v1.2.3 From 1bc4ae0ccbc661b58d3e8f7b633c7786eaf7929f Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Mon, 25 Apr 2022 14:12:50 -0700 Subject: drm/i915: Add first set of DG2 PCI IDs The IDs added here are the subset reserved for 'motherboard down' designs of DG2. We have all the necessary support upstream to enable these now (although they'll continue to require force_probe until the usual requirements are met). The remaining DG2 IDs for add-in cards will come in a future patch once some additional required functionality has fully landed. Bspec: 44477 Cc: Lucas De Marchi Cc: Daniel Vetter Cc: Dave Airlie Cc: Rodrigo Vivi Cc: Joonas Lahtinen Cc: Jani Nikula Cc: Tvrtko Ursulin Signed-off-by: Matt Roper Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20220425211251.77154-3-matthew.d.roper@intel.com --- include/drm/i915_pciids.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index a7b5eea7ffaa..283dadfbb4db 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -692,4 +692,26 @@ INTEL_VGA_DEVICE(0xA7A8, info), \ INTEL_VGA_DEVICE(0xA7A9, info) +/* DG2 */ +#define INTEL_DG2_G10_IDS(info) \ + INTEL_VGA_DEVICE(0x5690, info), \ + INTEL_VGA_DEVICE(0x5691, info), \ + INTEL_VGA_DEVICE(0x5692, info) + +#define INTEL_DG2_G11_IDS(info) \ + INTEL_VGA_DEVICE(0x5693, info), \ + INTEL_VGA_DEVICE(0x5694, info), \ + INTEL_VGA_DEVICE(0x5695, info), \ + INTEL_VGA_DEVICE(0x56B0, info) + +#define INTEL_DG2_G12_IDS(info) \ + INTEL_VGA_DEVICE(0x5696, info), \ + INTEL_VGA_DEVICE(0x5697, info), \ + INTEL_VGA_DEVICE(0x56B2, info) + +#define INTEL_DG2_IDS(info) \ + INTEL_DG2_G10_IDS(info), \ + INTEL_DG2_G11_IDS(info), \ + INTEL_DG2_G12_IDS(info) + #endif /* _I915_PCIIDS_H */ -- cgit v1.2.3 From 0a8e98305f63deaf0a799d5cf5532cc83af035d1 Mon Sep 17 00:00:00 2001 From: Tokunori Ikegami Date: Thu, 24 Mar 2022 02:04:56 +0900 Subject: mtd: cfi_cmdset_0002: Use chip_ready() for write on S29GL064N Since commit dfeae1073583("mtd: cfi_cmdset_0002: Change write buffer to check correct value") buffered writes fail on S29GL064N. This is because, on S29GL064N, reads return 0xFF at the end of DQ polling for write completion, where as, chip_good() check expects actual data written to the last location to be returned post DQ polling completion. Fix is to revert to using chip_good() for S29GL064N which only checks for DQ lines to settle down to determine write completion. Link: https://lore.kernel.org/r/b687c259-6413-26c9-d4c9-b3afa69ea124@pengutronix.de/ Fixes: dfeae1073583("mtd: cfi_cmdset_0002: Change write buffer to check correct value") Cc: stable@vger.kernel.org Signed-off-by: Tokunori Ikegami Acked-by: Vignesh Raghavendra Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20220323170458.5608-3-ikegami.t@gmail.com --- include/linux/mtd/cfi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index fd1ecb821106..d88bb56c18e2 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -286,6 +286,7 @@ struct cfi_private { map_word sector_erase_cmd; unsigned long chipshift; /* Because they're of the same type */ const char *im_name; /* inter_module name for cmdset_setup */ + unsigned long quirks; struct flchip chips[]; /* per-chip data structure for each chip */ }; -- cgit v1.2.3 From ed36d04e8f8d7b00db451b0fa56a54e8e02ec43e Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 25 Apr 2022 13:42:02 +0100 Subject: iommu: Introduce device_iommu_capable() iommu_capable() only really works for systems where all IOMMU instances are completely homogeneous, and all devices are IOMMU-mapped. Implement the new variant which will be able to give a more accurate answer for whichever device the caller is actually interested in, and even more so once all the external users have been converted and we can reliably pass the device pointer through the internal driver interface too. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/8407eb9586677995b7a9fd70d0fd82d85929a9bb.1650878781.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9208eca4b0d1..e26cf84e5d82 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -417,6 +417,7 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); +extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); extern struct iommu_group *iommu_group_get_by_id(int id); @@ -689,6 +690,11 @@ static inline bool iommu_present(struct bus_type *bus) return false; } +static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) +{ + return false; +} + static inline bool iommu_capable(struct bus_type *bus, enum iommu_cap cap) { return false; -- cgit v1.2.3 From d0be55fbeb6ac694d15af5d1aad19cdec8cd64e5 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 25 Apr 2022 13:42:03 +0100 Subject: iommu: Add capability for pre-boot DMA protection VT-d's dmar_platform_optin() actually represents a combination of properties fairly well standardised by Microsoft as "Pre-boot DMA Protection" and "Kernel DMA Protection"[1]. As such, we can provide interested consumers with an abstracted capability rather than driver-specific interfaces that won't scale. We name it for the former aspect since that's what external callers are most likely to be interested in; the latter is for the IOMMU layer to handle itself. [1] https://docs.microsoft.com/en-us/windows-hardware/design/device-experiences/oem-kernel-dma-protection Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: Lu Baolu Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/d6218dff2702472da80db6aec2c9589010684551.1650878781.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index e26cf84e5d82..4123693ae319 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -107,6 +107,8 @@ enum iommu_cap { transactions */ IOMMU_CAP_INTR_REMAP, /* IOMMU supports interrupt isolation */ IOMMU_CAP_NOEXEC, /* IOMMU_NOEXEC flag */ + IOMMU_CAP_PRE_BOOT_PROTECTION, /* Firmware says it used the IOMMU for + DMA protection and we should too */ }; /* These are the possible reserved region types */ -- cgit v1.2.3 From 86eaf4a5b4312bea8676fb79399d9e08b53d8e71 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 25 Apr 2022 13:42:04 +0100 Subject: thunderbolt: Make iommu_dma_protection more accurate Between me trying to get rid of iommu_present() and Mario wanting to support the AMD equivalent of DMAR_PLATFORM_OPT_IN, scrutiny has shown that the iommu_dma_protection attribute is being far too optimistic. Even if an IOMMU might be present for some PCI segment in the system, that doesn't necessarily mean it provides translation for the device(s) we care about. Furthermore, all that DMAR_PLATFORM_OPT_IN really does is tell us that memory was protected before the kernel was loaded, and prevent the user from disabling the intel-iommu driver entirely. While that lets us assume kernel integrity, what matters for actual runtime DMA protection is whether we trust individual devices, based on the "external facing" property that we expect firmware to describe for Thunderbolt ports. It's proven challenging to determine the appropriate ports accurately given the variety of possible topologies, so while still not getting a perfect answer, by putting enough faith in firmware we can at least get a good bit closer. If we can see that any device near a Thunderbolt NHI has all the requisites for Kernel DMA Protection, chances are that it *is* a relevant port, but moreover that implies that firmware is playing the game overall, so we'll use that to assume that all Thunderbolt ports should be correctly marked and thus will end up fully protected. CC: Mario Limonciello Reviewed-by: Christoph Hellwig Acked-by: Mika Westerberg Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/b153f208bc9eafab5105bad0358b77366509d2d4.1650878781.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/thunderbolt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 124e13cb1469..7a8ad984e651 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -465,6 +465,7 @@ static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc) * @msix_ida: Used to allocate MSI-X vectors for rings * @going_away: The host controller device is about to disappear so when * this flag is set, avoid touching the hardware anymore. + * @iommu_dma_protection: An IOMMU will isolate external-facing ports. * @interrupt_work: Work scheduled to handle ring interrupt when no * MSI-X is used. * @hop_count: Number of rings (end point hops) supported by NHI. @@ -479,6 +480,7 @@ struct tb_nhi { struct tb_ring **rx_rings; struct ida msix_ida; bool going_away; + bool iommu_dma_protection; struct work_struct interrupt_work; u32 hop_count; unsigned long quirks; -- cgit v1.2.3 From 2147c438fde135d6c145a96e373d9348e7076f7f Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 25 Apr 2022 16:40:02 -0700 Subject: x86/speculation: Add missing prototype for unpriv_ebpf_notify() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following warnings seen with "make W=1": kernel/sysctl.c:183:13: warning: no previous prototype for ‘unpriv_ebpf_notify’ [-Wmissing-prototypes] 183 | void __weak unpriv_ebpf_notify(int new_state) | ^~~~~~~~~~~~~~~~~~ arch/x86/kernel/cpu/bugs.c:659:6: warning: no previous prototype for ‘unpriv_ebpf_notify’ [-Wmissing-prototypes] 659 | void unpriv_ebpf_notify(int new_state) | ^~~~~~~~~~~~~~~~~~ Fixes: 44a3918c8245 ("x86/speculation: Include unprivileged eBPF status in Spectre v2 mitigation reporting") Reported-by: kernel test robot Signed-off-by: Josh Poimboeuf Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/5689d065f739602ececaee1e05e68b8644009608.1650930000.git.jpoimboe@redhat.com --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdb5298735ce..ecc3d3ec41cf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2085,6 +2085,8 @@ void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); +void unpriv_ebpf_notify(int new_state); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); -- cgit v1.2.3 From 1ea2a07a532b0e22aabe7e8483f935c672b9e7ed Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:50 +0800 Subject: iommu: Add DMA ownership management interfaces Multiple devices may be placed in the same IOMMU group because they cannot be isolated from each other. These devices must either be entirely under kernel control or userspace control, never a mixture. This adds dma ownership management in iommu core and exposes several interfaces for the device drivers and the device userspace assignment framework (i.e. VFIO), so that any conflict between user and kernel controlled dma could be detected at the beginning. The device driver oriented interfaces are, int iommu_device_use_default_domain(struct device *dev); void iommu_device_unuse_default_domain(struct device *dev); By calling iommu_device_use_default_domain(), the device driver tells the iommu layer that the device dma is handled through the kernel DMA APIs. The iommu layer will manage the IOVA and use the default domain for DMA address translation. The device user-space assignment framework oriented interfaces are, int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); void iommu_group_release_dma_owner(struct iommu_group *group); bool iommu_group_dma_owner_claimed(struct iommu_group *group); The device userspace assignment must be disallowed if the DMA owner claiming interface returns failure. Signed-off-by: Jason Gunthorpe Signed-off-by: Kevin Tian Signed-off-by: Lu Baolu Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20220418005000.897664-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9208eca4b0d1..77972ef978b5 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -675,6 +675,13 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, void iommu_sva_unbind_device(struct iommu_sva *handle); u32 iommu_sva_get_pasid(struct iommu_sva *handle); +int iommu_device_use_default_domain(struct device *dev); +void iommu_device_unuse_default_domain(struct device *dev); + +int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); +void iommu_group_release_dma_owner(struct iommu_group *group); +bool iommu_group_dma_owner_claimed(struct iommu_group *group); + #else /* CONFIG_IOMMU_API */ struct iommu_ops {}; @@ -1031,6 +1038,30 @@ static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) { return NULL; } + +static inline int iommu_device_use_default_domain(struct device *dev) +{ + return 0; +} + +static inline void iommu_device_unuse_default_domain(struct device *dev) +{ +} + +static inline int +iommu_group_claim_dma_owner(struct iommu_group *group, void *owner) +{ + return -ENODEV; +} + +static inline void iommu_group_release_dma_owner(struct iommu_group *group) +{ +} + +static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group) +{ + return false; +} #endif /* CONFIG_IOMMU_API */ /** -- cgit v1.2.3 From 25f3bcfc54bcf7b0e45d140ec8bfbbf10ba11869 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:51 +0800 Subject: driver core: Add dma_cleanup callback in bus_type The bus_type structure defines dma_configure() callback for bus drivers to configure DMA on the devices. This adds the paired dma_cleanup() callback and calls it during driver unbinding so that bus drivers can do some cleanup work. One use case for this paired DMA callbacks is for the bus driver to check for DMA ownership conflicts during driver binding, where multiple devices belonging to a same IOMMU group (the minimum granularity of isolation and protection) may be assigned to kernel drivers or user space respectively. Without this change, for example, the vfio driver has to listen to a bus BOUND_DRIVER event and then BUG_ON() in case of dma ownership conflict. This leads to bad user experience since careless driver binding operation may crash the system if the admin overlooks the group restriction. Aside from bad design, this leads to a security problem as a root user, even with lockdown=integrity, can force the kernel to BUG. With this change, the bus driver could check and set the DMA ownership in driver binding process and fail on ownership conflicts. The DMA ownership should be released during driver unbinding. Signed-off-by: Lu Baolu Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220418005000.897664-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/device/bus.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index a039ab809753..d8b29ccd07e5 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -59,6 +59,8 @@ struct fwnode_handle; * bus supports. * @dma_configure: Called to setup DMA configuration on a device on * this bus. + * @dma_cleanup: Called to cleanup DMA configuration on a device on + * this bus. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU @@ -103,6 +105,7 @@ struct bus_type { int (*num_vf)(struct device *dev); int (*dma_configure)(struct device *dev); + void (*dma_cleanup)(struct device *dev); const struct dev_pm_ops *pm; -- cgit v1.2.3 From 4a6d9dd564d0e7339fc15ecc5ce66db4ad842be2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:52 +0800 Subject: amba: Stop sharing platform_dma_configure() Stop sharing platform_dma_configure() helper as they are about to have their own bus dma_configure callbacks. Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220418005000.897664-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/platform_device.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 7c96f169d274..17fde717df68 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -328,8 +328,6 @@ extern int platform_pm_restore(struct device *dev); #define platform_pm_restore NULL #endif -extern int platform_dma_configure(struct device *dev); - #ifdef CONFIG_PM_SLEEP #define USE_PLATFORM_PM_SLEEP_OPS \ .suspend = platform_pm_suspend, \ -- cgit v1.2.3 From 512881eacfa72c2136b27b9934b7b27504a9efc2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:53 +0800 Subject: bus: platform,amba,fsl-mc,PCI: Add device DMA ownership management The devices on platform/amba/fsl-mc/PCI buses could be bound to drivers with the device DMA managed by kernel drivers or user-space applications. Unfortunately, multiple devices may be placed in the same IOMMU group because they cannot be isolated from each other. The DMA on these devices must either be entirely under kernel control or userspace control, never a mixture. Otherwise the driver integrity is not guaranteed because they could access each other through the peer-to-peer accesses which by-pass the IOMMU protection. This checks and sets the default DMA mode during driver binding, and cleanups during driver unbinding. In the default mode, the device DMA is managed by the device driver which handles DMA operations through the kernel DMA APIs (see Documentation/core-api/dma-api.rst). For cases where the devices are assigned for userspace control through the userspace driver framework(i.e. VFIO), the drivers(for example, vfio_pci/ vfio_platfrom etc.) may set a new flag (driver_managed_dma) to skip this default setting in the assumption that the drivers know what they are doing with the device DMA. Calling iommu_device_use_default_domain() before {of,acpi}_dma_configure is currently a problem. As things stand, the IOMMU driver ignored the initial iommu_probe_device() call when the device was added, since at that point it had no fwspec yet. In this situation, {of,acpi}_iommu_configure() are retriggering iommu_probe_device() after the IOMMU driver has seen the firmware data via .of_xlate to learn that it actually responsible for the given device. As the result, before that gets fixed, iommu_use_default_domain() goes at the end, and calls arch_teardown_dma_ops() if it fails. Cc: Greg Kroah-Hartman Cc: Bjorn Helgaas Cc: Stuart Yoder Cc: Laurentiu Tudor Signed-off-by: Lu Baolu Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Reviewed-by: Robin Murphy Tested-by: Eric Auger Link: https://lore.kernel.org/r/20220418005000.897664-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/amba/bus.h | 8 ++++++++ include/linux/fsl/mc.h | 8 ++++++++ include/linux/pci.h | 8 ++++++++ include/linux/platform_device.h | 8 ++++++++ 4 files changed, 32 insertions(+) (limited to 'include') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 6562f543c3e0..2ddce9bcd00e 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -79,6 +79,14 @@ struct amba_driver { void (*remove)(struct amba_device *); void (*shutdown)(struct amba_device *); const struct amba_id *id_table; + /* + * For most device drivers, no need to care about this flag as long as + * all DMAs are handled through the kernel DMA API. For some special + * ones, for example VFIO drivers, they know how to manage the DMA + * themselves and set this flag so that the IOMMU layer will allow them + * to setup and manage their own I/O address space. + */ + bool driver_managed_dma; }; /* diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 7b6c42bfb660..27efef8affb1 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -32,6 +32,13 @@ struct fsl_mc_io; * @shutdown: Function called at shutdown time to quiesce the device * @suspend: Function called when a device is stopped * @resume: Function called when a device is resumed + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. * * Generic DPAA device driver object for device drivers that are registered * with a DPRC bus. This structure is to be embedded in each device-specific @@ -45,6 +52,7 @@ struct fsl_mc_driver { void (*shutdown)(struct fsl_mc_device *dev); int (*suspend)(struct fsl_mc_device *dev, pm_message_t state); int (*resume)(struct fsl_mc_device *dev); + bool driver_managed_dma; }; #define to_fsl_mc_driver(_drv) \ diff --git a/include/linux/pci.h b/include/linux/pci.h index 60adf42460ab..b933d2b08d4d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -895,6 +895,13 @@ struct module; * created once it is bound to the driver. * @driver: Driver model structure. * @dynids: List of dynamically added device IDs. + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. */ struct pci_driver { struct list_head node; @@ -913,6 +920,7 @@ struct pci_driver { const struct attribute_group **dev_groups; struct device_driver driver; struct pci_dynids dynids; + bool driver_managed_dma; }; static inline struct pci_driver *to_pci_driver(struct device_driver *drv) diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 17fde717df68..b3d9c744f1e5 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -210,6 +210,14 @@ struct platform_driver { struct device_driver driver; const struct platform_device_id *id_table; bool prevent_deferred_probe; + /* + * For most device drivers, no need to care about this flag as long as + * all DMAs are handled through the kernel DMA API. For some special + * ones, for example VFIO drivers, they know how to manage the DMA + * themselves and set this flag so that the IOMMU layer will allow them + * to setup and manage their own I/O address space. + */ + bool driver_managed_dma; }; #define to_platform_driver(drv) (container_of((drv), struct platform_driver, \ -- cgit v1.2.3 From a5f1bd1afacd7b1e088f93f66af5453df0d8be9a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:50:00 +0800 Subject: iommu: Remove iommu group changes notifier The iommu group changes notifer is not referenced in the tree. Remove it to avoid dead code. Suggested-by: Christoph Hellwig Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220418005000.897664-12-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 77972ef978b5..6ef2df258673 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -407,13 +407,6 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) return dev->iommu->iommu_dev->ops; } -#define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ -#define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ -#define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ -#define IOMMU_GROUP_NOTIFY_BOUND_DRIVER 4 /* Post Driver bind */ -#define IOMMU_GROUP_NOTIFY_UNBIND_DRIVER 5 /* Pre Driver unbind */ -#define IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER 6 /* Post Driver unbind */ - extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); @@ -478,10 +471,6 @@ extern int iommu_group_for_each_dev(struct iommu_group *group, void *data, extern struct iommu_group *iommu_group_get(struct device *dev); extern struct iommu_group *iommu_group_ref_get(struct iommu_group *group); extern void iommu_group_put(struct iommu_group *group); -extern int iommu_group_register_notifier(struct iommu_group *group, - struct notifier_block *nb); -extern int iommu_group_unregister_notifier(struct iommu_group *group, - struct notifier_block *nb); extern int iommu_register_device_fault_handler(struct device *dev, iommu_dev_fault_handler_t handler, void *data); @@ -878,18 +867,6 @@ static inline void iommu_group_put(struct iommu_group *group) { } -static inline int iommu_group_register_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return -ENODEV; -} - -static inline int iommu_group_unregister_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return 0; -} - static inline int iommu_register_device_fault_handler(struct device *dev, iommu_dev_fault_handler_t handler, -- cgit v1.2.3 From 00675017e0aeba5305665c52ded4ddce6a4c0231 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 4 Apr 2022 12:51:40 +0200 Subject: fs: add two trivial lookup helpers Similar to the addition of lookup_one() add a version of lookup_one_unlocked() and lookup_one_positive_unlocked() that take idmapped mounts into account. This is required to port overlay to support idmapped base layers. Cc: Tested-by: Giuseppe Scrivano Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Miklos Szeredi --- include/linux/namei.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/namei.h b/include/linux/namei.h index e89329bb3134..caeb08a98536 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -69,6 +69,12 @@ extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); struct dentry *lookup_one(struct user_namespace *, const char *, struct dentry *, int); +struct dentry *lookup_one_unlocked(struct user_namespace *mnt_userns, + const char *name, struct dentry *base, + int len); +struct dentry *lookup_one_positive_unlocked(struct user_namespace *mnt_userns, + const char *name, + struct dentry *base, int len); extern int follow_down_one(struct path *); extern int follow_down(struct path *); -- cgit v1.2.3 From dbde6d0c7a5a462a1767a07c28eadd2c3dd08fb2 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Thu, 28 Apr 2022 16:51:05 +0200 Subject: hv_sock: Add validation for untrusted Hyper-V values For additional robustness in the face of Hyper-V errors or malicious behavior, validate all values that originate from packets that Hyper-V has sent to the guest in the host-to-guest ring buffer. Ensure that invalid values cannot cause data being copied out of the bounds of the source buffer in hvs_stream_dequeue(). Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Reviewed-by: Stefano Garzarella Link: https://lore.kernel.org/r/20220428145107.7878-4-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 460a716f4748..a01c9fd0a334 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1696,6 +1696,11 @@ static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc) return (desc->len8 << 3) - (desc->offset8 << 3); } +/* Get packet length associated with descriptor */ +static inline u32 hv_pkt_len(const struct vmpacket_descriptor *desc) +{ + return desc->len8 << 3; +} struct vmpacket_descriptor * hv_pkt_iter_first_raw(struct vmbus_channel *channel); -- cgit v1.2.3 From da795eb239d9e9496812e22cb582d38a71e0789a Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Thu, 28 Apr 2022 16:51:06 +0200 Subject: Drivers: hv: vmbus: Accept hv_sock offers in isolated guests So that isolated guests can communicate with the host via hv_sock channels. Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20220428145107.7878-5-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index a01c9fd0a334..b028905d8334 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1064,10 +1064,14 @@ u64 vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, u64 rqst_addr); u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id); +static inline bool is_hvsock_offer(const struct vmbus_channel_offer_channel *o) +{ + return !!(o->offer.chn_flags & VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER); +} + static inline bool is_hvsock_channel(const struct vmbus_channel *c) { - return !!(c->offermsg.offer.chn_flags & - VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER); + return is_hvsock_offer(&c->offermsg); } static inline bool is_sub_channel(const struct vmbus_channel *c) -- cgit v1.2.3 From 1c9de08f7f952b4101f092802581344033d84429 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Thu, 28 Apr 2022 16:51:07 +0200 Subject: Drivers: hv: vmbus: Refactor the ring-buffer iterator functions With no users of hv_pkt_iter_next_raw() and no "external" users of hv_pkt_iter_first_raw(), the iterator functions can be refactored and simplified to remove some indirection/code. Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20220428145107.7878-6-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 35 ++++------------------------------- 1 file changed, 4 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b028905d8334..c440c45887c2 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1706,55 +1706,28 @@ static inline u32 hv_pkt_len(const struct vmpacket_descriptor *desc) return desc->len8 << 3; } -struct vmpacket_descriptor * -hv_pkt_iter_first_raw(struct vmbus_channel *channel); - struct vmpacket_descriptor * hv_pkt_iter_first(struct vmbus_channel *channel); struct vmpacket_descriptor * __hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt, - bool copy); + const struct vmpacket_descriptor *pkt); void hv_pkt_iter_close(struct vmbus_channel *channel); static inline struct vmpacket_descriptor * -hv_pkt_iter_next_pkt(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt, - bool copy) +hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt) { struct vmpacket_descriptor *nxt; - nxt = __hv_pkt_iter_next(channel, pkt, copy); + nxt = __hv_pkt_iter_next(channel, pkt); if (!nxt) hv_pkt_iter_close(channel); return nxt; } -/* - * Get next packet descriptor without copying it out of the ring buffer - * If at end of list, return NULL and update host. - */ -static inline struct vmpacket_descriptor * -hv_pkt_iter_next_raw(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt) -{ - return hv_pkt_iter_next_pkt(channel, pkt, false); -} - -/* - * Get next packet descriptor from iterator - * If at end of list, return NULL and update host. - */ -static inline struct vmpacket_descriptor * -hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt) -{ - return hv_pkt_iter_next_pkt(channel, pkt, true); -} - #define foreach_vmbus_pkt(pkt, channel) \ for (pkt = hv_pkt_iter_first(channel); pkt; \ pkt = hv_pkt_iter_next(channel, pkt)) -- cgit v1.2.3 From 6043257b1de069fbb5a2a52d7211c0275bc8c0e0 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 12:16:05 -0300 Subject: iommu: Introduce the domain op enforce_cache_coherency() This new mechanism will replace using IOMMU_CAP_CACHE_COHERENCY and IOMMU_CACHE to control the no-snoop blocking behavior of the IOMMU. Currently only Intel and AMD IOMMUs are known to support this feature. They both implement it as an IOPTE bit, that when set, will cause PCIe TLPs to that IOVA with the no-snoop bit set to be treated as though the no-snoop bit was clear. The new API is triggered by calling enforce_cache_coherency() before mapping any IOVA to the domain which globally switches on no-snoop blocking. This allows other implementations that might block no-snoop globally and outside the IOPTE - AMD also documents such a HW capability. Leave AMD out of sync with Intel and have it block no-snoop even for in-kernel users. This can be trivially resolved in a follow up patch. Only VFIO needs to call this API because it does not have detailed control over the device to avoid requesting no-snoop behavior at the device level. Other places using domains with real kernel drivers should simply avoid asking their devices to set the no-snoop bit. Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Acked-by: Robin Murphy Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/1-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + include/linux/iommu.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 2f9891cb3d00..4c2baf2446c2 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -540,6 +540,7 @@ struct dmar_domain { u8 has_iotlb_device: 1; u8 iommu_coherency: 1; /* indicate coherency of iommu access */ u8 iommu_snooping: 1; /* indicate snooping control feature */ + u8 force_snooping : 1; /* Create IOPTEs with snoop control */ struct list_head devices; /* all devices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 4123693ae319..c7ad6b10e261 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -274,6 +274,9 @@ struct iommu_ops { * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue * @iova_to_phys: translate iova to physical address + * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE, + * including no-snoop TLPs on PCIe or other platform + * specific mechanisms. * @enable_nesting: Enable nesting * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) * @free: Release the domain after use. @@ -302,6 +305,7 @@ struct iommu_domain_ops { phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); + bool (*enforce_cache_coherency)(struct iommu_domain *domain); int (*enable_nesting)(struct iommu_domain *domain); int (*set_pgtable_quirks)(struct iommu_domain *domain, unsigned long quirks); -- cgit v1.2.3 From 71cfafda9c9bd9812cdb62ddb94daf65a1af12c1 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 12:16:06 -0300 Subject: vfio: Move the Intel no-snoop control off of IOMMU_CACHE IOMMU_CACHE means "normal DMA to this iommu_domain's IOVA should be cache coherent" and is used by the DMA API. The definition allows for special non-coherent DMA to exist - ie processing of the no-snoop flag in PCIe TLPs - so long as this behavior is opt-in by the device driver. The flag is mainly used by the DMA API to synchronize the IOMMU setting with the expected cache behavior of the DMA master. eg based on dev_is_dma_coherent() in some case. For Intel IOMMU IOMMU_CACHE was redefined to mean 'force all DMA to be cache coherent' which has the practical effect of causing the IOMMU to ignore the no-snoop bit in a PCIe TLP. x86 platforms are always IOMMU_CACHE, so Intel should ignore this flag. Instead use the new domain op enforce_cache_coherency() which causes every IOPTE created in the domain to have the no-snoop blocking behavior. Reconfigure VFIO to always use IOMMU_CACHE and call enforce_cache_coherency() to operate the special Intel behavior. Remove the IOMMU_CACHE test from Intel IOMMU. Ultimately VFIO plumbs the result of enforce_cache_coherency() back into the x86 platform code through kvm_arch_register_noncoherent_dma() which controls if the WBINVD instruction is available in the guest. No other archs implement kvm_arch_register_noncoherent_dma() nor are there any other known consumers of VFIO_DMA_CC_IOMMU that might be affected by the user visible result change on non-x86 archs. Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Acked-by: Alex Williamson Acked-by: Robin Murphy Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/2-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4c2baf2446c2..72e5d7900e71 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -539,7 +539,6 @@ struct dmar_domain { u8 has_iotlb_device: 1; u8 iommu_coherency: 1; /* indicate coherency of iommu access */ - u8 iommu_snooping: 1; /* indicate snooping control feature */ u8 force_snooping : 1; /* Create IOPTEs with snoop control */ struct list_head devices; /* all devices' list */ -- cgit v1.2.3 From f78dc1dad829e505d83e33dc0879887f074c52e1 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 12:16:07 -0300 Subject: iommu: Redefine IOMMU_CAP_CACHE_COHERENCY as the cap flag for IOMMU_CACHE While the comment was correct that this flag was intended to convey the block no-snoop support in the IOMMU, it has become widely implemented and used to mean the IOMMU supports IOMMU_CACHE as a map flag. Only the Intel driver was different. Now that the Intel driver is using enforce_cache_coherency() update the comment to make it clear that IOMMU_CAP_CACHE_COHERENCY is only about IOMMU_CACHE. Fix the Intel driver to return true since IOMMU_CACHE always works. The two places that test this flag, usnic and vdpa, are both assigning userspace pages to a driver controlled iommu_domain and require IOMMU_CACHE behavior as they offer no way for userspace to synchronize caches. Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Acked-by: Robin Murphy Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/3-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c7ad6b10e261..575ab27ede5b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -103,8 +103,7 @@ static inline bool iommu_is_dma_domain(struct iommu_domain *domain) } enum iommu_cap { - IOMMU_CAP_CACHE_COHERENCY, /* IOMMU can enforce cache coherent DMA - transactions */ + IOMMU_CAP_CACHE_COHERENCY, /* IOMMU_CACHE is supported */ IOMMU_CAP_INTR_REMAP, /* IOMMU supports interrupt isolation */ IOMMU_CAP_NOEXEC, /* IOMMU_NOEXEC flag */ IOMMU_CAP_PRE_BOOT_PROTECTION, /* Firmware says it used the IOMMU for -- cgit v1.2.3 From 992be5d3c818fcc277db246cb409659ca82abdbe Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 30 Mar 2022 16:05:35 +0100 Subject: firmware: arm_scmi: Make name_get operations return a const A few protocol operations are available that returns a pointer to an internal character array representing resource name. Make those functions return a const pointer to such array. Link: https://lore.kernel.org/r/20220330150551.2573938-7-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index b87551f41f9f..ced37d1de1fe 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -146,7 +146,8 @@ struct scmi_perf_proto_ops { */ struct scmi_power_proto_ops { int (*num_domains_get)(const struct scmi_protocol_handle *ph); - char *(*name_get)(const struct scmi_protocol_handle *ph, u32 domain); + const char *(*name_get)(const struct scmi_protocol_handle *ph, + u32 domain); #define SCMI_POWER_STATE_TYPE_SHIFT 30 #define SCMI_POWER_STATE_ID_MASK (BIT(28) - 1) #define SCMI_POWER_STATE_PARAM(type, id) \ @@ -484,7 +485,8 @@ struct scmi_sensor_proto_ops { */ struct scmi_reset_proto_ops { int (*num_domains_get)(const struct scmi_protocol_handle *ph); - char *(*name_get)(const struct scmi_protocol_handle *ph, u32 domain); + const char *(*name_get)(const struct scmi_protocol_handle *ph, + u32 domain); int (*latency_get)(const struct scmi_protocol_handle *ph, u32 domain); int (*reset)(const struct scmi_protocol_handle *ph, u32 domain); int (*assert)(const struct scmi_protocol_handle *ph, u32 domain); -- cgit v1.2.3 From b260fccaebdc2c838e62aaef24fedf497f181d10 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 30 Mar 2022 16:05:40 +0100 Subject: firmware: arm_scmi: Add SCMI v3.1 protocol extended names support Using the common protocol helper implementation add support for all new SCMIv3.1 extended names commands related to all protocols with the exception of SENSOR_AXIS_GET_NAME. Link: https://lore.kernel.org/r/20220330150551.2573938-12-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index ced37d1de1fe..56e6f13355b8 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -13,7 +13,7 @@ #include #include -#define SCMI_MAX_STR_SIZE 16 +#define SCMI_MAX_STR_SIZE 64 #define SCMI_MAX_NUM_RATES 16 /** -- cgit v1.2.3 From 7aa75496ea1f38dfd99b93c66f8d9bc525d11efc Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 30 Mar 2022 16:05:48 +0100 Subject: firmware: arm_scmi: Add SCMI v3.1 clock notifications Add SCMI v3.1 clock pre and post notifications. Link: https://lore.kernel.org/r/20220330150551.2573938-20-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 56e6f13355b8..0e20acc80d50 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -44,6 +44,8 @@ struct scmi_clock_info { char name[SCMI_MAX_STR_SIZE]; unsigned int enable_latency; bool rate_discrete; + bool rate_changed_notifications; + bool rate_change_requested_notifications; union { struct { int num_rates; @@ -744,6 +746,8 @@ void scmi_protocol_unregister(const struct scmi_protocol *proto); /* SCMI Notification API - Custom Event Reports */ enum scmi_notification_events { SCMI_EVENT_POWER_STATE_CHANGED = 0x0, + SCMI_EVENT_CLOCK_RATE_CHANGED = 0x0, + SCMI_EVENT_CLOCK_RATE_CHANGE_REQUESTED = 0x1, SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED = 0x0, SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1, SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0, @@ -760,6 +764,13 @@ struct scmi_power_state_changed_report { unsigned int power_state; }; +struct scmi_clock_rate_notif_report { + ktime_t timestamp; + unsigned int agent_id; + unsigned int clock_id; + unsigned long long rate; +}; + struct scmi_system_power_state_notifier_report { ktime_t timestamp; unsigned int agent_id; -- cgit v1.2.3 From 4c74701b1eb7636eb0cdd66b488b42920105122a Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 30 Mar 2022 16:05:49 +0100 Subject: firmware: arm_scmi: Add SCMI v3.1 VOLTAGE_LEVEL_SET_COMPLETE Add SCMI v3.1 voltage protocol support for asynchronous VOLTAGE_LEVEL_SET command. Note that, if a voltage domain is advertised to support the asynchronous version of VOLTAGE_LEVEL_SET, the command will be issued asynchronously unless explicitly requested to use the synchronous version by setting the mode to SCMI_VOLTAGE_LEVEL_SET_SYNC when calling voltage_ops->level_set. The SCMI regulator driver level_set invocation has been left unchanged so that it will transparently use the asynchronous version if available. Link: https://lore.kernel.org/r/20220330150551.2573938-21-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 0e20acc80d50..1c58646ba381 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -495,6 +495,11 @@ struct scmi_reset_proto_ops { int (*deassert)(const struct scmi_protocol_handle *ph, u32 domain); }; +enum scmi_voltage_level_mode { + SCMI_VOLTAGE_LEVEL_SET_AUTO, + SCMI_VOLTAGE_LEVEL_SET_SYNC, +}; + /** * struct scmi_voltage_info - describe one available SCMI Voltage Domain * @@ -507,7 +512,8 @@ struct scmi_reset_proto_ops { * supported voltage level * @negative_volts_allowed: True if any of the entries of @levels_uv represent * a negative voltage. - * @attributes: represents Voltage Domain advertised attributes + * @async_level_set: True when the voltage domain supports asynchronous level + * set commands. * @name: name assigned to the Voltage Domain by platform * @num_levels: number of total entries in @levels_uv. * @levels_uv: array of entries describing the available voltage levels for @@ -517,7 +523,7 @@ struct scmi_voltage_info { unsigned int id; bool segmented; bool negative_volts_allowed; - unsigned int attributes; + bool async_level_set; char name[SCMI_MAX_STR_SIZE]; unsigned int num_levels; #define SCMI_VOLTAGE_SEGMENT_LOW 0 @@ -548,7 +554,7 @@ struct scmi_voltage_proto_ops { int (*config_get)(const struct scmi_protocol_handle *ph, u32 domain_id, u32 *config); int (*level_set)(const struct scmi_protocol_handle *ph, u32 domain_id, - u32 flags, s32 volt_uV); + enum scmi_voltage_level_mode mode, s32 volt_uV); int (*level_get)(const struct scmi_protocol_handle *ph, u32 domain_id, s32 *volt_uV); }; -- cgit v1.2.3 From ac3e62f51b3fbda78a44fff62ece8f11d8f08a25 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:40 +0100 Subject: iio: core: Clarify the modes As part of a previous discussion with Jonathan Cameron [1], it appeared necessary to clarify the meaning of each mode so that new developers could understand better what they should use or not use and when. The idea of renaming these modes as been let aside because naming is a big deal and requires a lot of thinking. So for now let's focus on correctly explaining what each mode implies. [1] https://lore.kernel.org/linux-iio/20210930165510.2295e6c4@jic23-huawei/ Suggested-by: Jonathan Cameron Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-14-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 48 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 85cb924debd9..233d2e6b7721 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -315,7 +315,54 @@ static inline bool iio_channel_has_available(const struct iio_chan_spec *chan, s64 iio_get_time_ns(const struct iio_dev *indio_dev); unsigned int iio_get_time_res(const struct iio_dev *indio_dev); -/* Device operating modes */ +/* + * Device operating modes + * @INDIO_DIRECT_MODE: There is an access to either: + * a) The last single value available for devices that do not provide + * on-demand reads. + * b) A new value after performing an on-demand read otherwise. + * On most devices, this is a single-shot read. On some devices with data + * streams without an 'on-demand' function, this might also be the 'last value' + * feature. Above all, this mode internally means that we are not in any of the + * other modes, and sysfs reads should work. + * Device drivers should inform the core if they support this mode. + * @INDIO_BUFFER_TRIGGERED: Common mode when dealing with kfifo buffers. + * It indicates that an explicit trigger is required. This requests the core to + * attach a poll function when enabling the buffer, which is indicated by the + * _TRIGGERED suffix. + * The core will ensure this mode is set when registering a triggered buffer + * with iio_triggered_buffer_setup(). + * @INDIO_BUFFER_SOFTWARE: Another kfifo buffer mode, but not event triggered. + * No poll function can be attached because there is no triggered infrastructure + * we can use to cause capture. There is a kfifo that the driver will fill, but + * not "only one scan at a time". Typically, hardware will have a buffer that + * can hold multiple scans. Software may read one or more scans at a single time + * and push the available data to a Kfifo. This means the core will not attach + * any poll function when enabling the buffer. + * The core will ensure this mode is set when registering a simple kfifo buffer + * with devm_iio_kfifo_buffer_setup(). + * @INDIO_BUFFER_HARDWARE: For specific hardware, if unsure do not use this mode. + * Same as above but this time the buffer is not a kfifo where we have direct + * access to the data. Instead, the consumer driver must access the data through + * non software visible channels (or DMA when there is no demux possible in + * software) + * The core will ensure this mode is set when registering a dmaengine buffer + * with devm_iio_dmaengine_buffer_setup(). + * @INDIO_EVENT_TRIGGERED: Very unusual mode. + * Triggers usually refer to an external event which will start data capture. + * Here it is kind of the opposite as, a particular state of the data might + * produce an event which can be considered as an event. We don't necessarily + * have access to the data itself, but to the event produced. For example, this + * can be a threshold detector. The internal path of this mode is very close to + * the INDIO_BUFFER_TRIGGERED mode. + * The core will ensure this mode is set when registering a triggered event. + * @INDIO_HARDWARE_TRIGGERED: Very unusual mode. + * Here, triggers can result in data capture and can be routed to multiple + * hardware components, which make them close to regular triggers in the way + * they must be managed by the core, but without the entire interrupts/poll + * functions burden. Interrupts are irrelevant as the data flow is hardware + * mediated and distributed. + */ #define INDIO_DIRECT_MODE 0x01 #define INDIO_BUFFER_TRIGGERED 0x02 #define INDIO_BUFFER_SOFTWARE 0x04 -- cgit v1.2.3 From dbfb5f94e084287f0a3f23d14ef6692c43c98855 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 26 Apr 2022 16:35:06 -0700 Subject: dt-bindings: power: rpmpd: Add sc8280xp RPMh power-domains The sc8280xp has 13 power-domains controlled through the RPMh, document the compatible and provide definitions for the power-domains - and their active-only variants where applicable. The SA8540p differs slightly in the power domains exposed, so add a separate compatible for this, but reuse the constants to allow sharing the DeviceTree source. Signed-off-by: Bjorn Andersson Acked-by: Krzysztof Kozlowski Reviewed-by: Johan Hovold Link: https://lore.kernel.org/r/20220426233508.1762345-2-bjorn.andersson@linaro.org --- include/dt-bindings/power/qcom-rpmpd.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/qcom-rpmpd.h b/include/dt-bindings/power/qcom-rpmpd.h index 0a8978d0c78c..6cce5b7aa940 100644 --- a/include/dt-bindings/power/qcom-rpmpd.h +++ b/include/dt-bindings/power/qcom-rpmpd.h @@ -125,6 +125,24 @@ #define SC8180X_MX 9 #define SC8180X_MX_AO 10 +/* SC8280XP Power Domain Indexes */ +#define SC8280XP_CX 0 +#define SC8280XP_CX_AO 1 +#define SC8280XP_DDR 2 +#define SC8280XP_EBI 3 +#define SC8280XP_GFX 4 +#define SC8280XP_LCX 5 +#define SC8280XP_LMX 6 +#define SC8280XP_MMCX 7 +#define SC8280XP_MMCX_AO 8 +#define SC8280XP_MSS 9 +#define SC8280XP_MX 10 +#define SC8280XP_MXC 12 +#define SC8280XP_MX_AO 11 +#define SC8280XP_NSP 13 +#define SC8280XP_QPHY 14 +#define SC8280XP_XO 15 + /* SDM845 Power Domain performance levels */ #define RPMH_REGULATOR_LEVEL_RETENTION 16 #define RPMH_REGULATOR_LEVEL_MIN_SVS 48 -- cgit v1.2.3 From 6fd1d51cfa253b5ee7dae18d7cf1df830e9b6137 Mon Sep 17 00:00:00 2001 From: Erin MacNeil Date: Wed, 27 Apr 2022 16:02:37 -0400 Subject: net: SO_RCVMARK socket option for SO_MARK with recvmsg() Adding a new socket option, SO_RCVMARK, to indicate that SO_MARK should be included in the ancillary data returned by recvmsg(). Renamed the sock_recv_ts_and_drops() function to sock_recv_cmsgs(). Signed-off-by: Erin MacNeil Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Acked-by: Marc Kleine-Budde Link: https://lore.kernel.org/r/20220427200259.2564-1-lnx.erin@gmail.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 18 ++++++++++-------- include/uapi/asm-generic/socket.h | 2 ++ 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index f9f8ecae0f8d..663041b92c21 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -893,6 +893,7 @@ enum sock_flags { SOCK_TXTIME, SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ + SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) @@ -2647,20 +2648,21 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) __sock_recv_wifi_status(msg, sk, skb); } -void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, - struct sk_buff *skb); +void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb); #define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC) -static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, - struct sk_buff *skb) +static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) { -#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \ - (1UL << SOCK_RCVTSTAMP)) +#define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \ + (1UL << SOCK_RCVTSTAMP) | \ + (1UL << SOCK_RCVMARK)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) - if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY) - __sock_recv_ts_and_drops(msg, sk, skb); + if (sk->sk_flags & FLAGS_RECV_CMSGS || sk->sk_tsflags & TSFLAGS_ANY) + __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP)) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 467ca2f28760..638230899e98 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -130,6 +130,8 @@ #define SO_TXREHASH 74 +#define SO_RCVMARK 75 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) -- cgit v1.2.3 From cc10eee95204579fcd66fd5965073fdcbf629676 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Wed, 13 Apr 2022 01:36:16 -0600 Subject: PCI/ACPI: add a helper for retrieving _OSC Control DWORDs During _OSC negotiation, when the 'Control' DWORD is needed from the result buffer after running _OSC, a couple of places performed manual pointer arithmetic to offset into the right spot in the raw buffer. Add a acpi_osc_ctx_get_pci_control() helper to use the #define'd DWORD offsets to fetch the DWORDs needed from @acpi_osc_context, and replace the above instances of the open-coded arithmetic. Cc: "Rafael J. Wysocki" Suggested-by: Davidlohr Bueso Acked-by: Rafael J. Wysocki Reviewed-by: Rafael J. Wysocki Reviewed-by: Davidlohr Bueso Reviewed by: Adam Manzanares Signed-off-by: Vishal Verma Link: https://lore.kernel.org/r/20220413073618.291335-2-vishal.l.verma@intel.com Signed-off-by: Dan Williams --- include/linux/acpi.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d7136d13aa44..04e5a038dd57 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -608,6 +608,13 @@ extern u32 osc_sb_native_usb4_control; #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 +static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) +{ + u32 *ret = context->ret.pointer; + + return ret[OSC_CONTROL_DWORD]; +} + #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 #define ACPI_GSB_ACCESS_ATTRIB_BYTE 0x00000006 @@ -1004,6 +1011,12 @@ static inline int acpi_register_wakeup_handler(int wake_irq, static inline void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context) { } +struct acpi_osc_context; +static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) +{ + return 0; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC -- cgit v1.2.3 From 241d26bc26add2e2867c546f7474902406d37c60 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 13 Apr 2022 01:36:17 -0600 Subject: PCI/ACPI: Prefer CXL _OSC instead of PCIe _OSC for CXL host bridges OB In preparation for negotiating OS control of CXL _OSC features, do the minimal enabling to use CXL _OSC to handle the base PCIe feature negotiation. Recall that CXL _OSC is a super-set of PCIe _OSC and the CXL 2.0 specification mandates: "If a CXL Host Bridge device exposes CXL _OSC, CXL aware OSPM shall evaluate CXL _OSC and not evaluate PCIe _OSC." Rather than pass a boolean flag alongside @root to all the helper functions that need to consider PCIe specifics, add is_pcie() and is_cxl() helper functions to check the flavor of @root. This also allows for dynamic fallback to PCIe _OSC in cases where an attempt to use CXL _OXC fails. This can happen on CXL 1.1 platforms that publish ACPI0016 devices to indicate CXL host bridges, but do not publish the optional CXL _OSC method. CXL _OSC is mandatory for CXL 2.0 hosts. Cc: Bjorn Helgaas Cc: "Rafael J. Wysocki" Cc: Robert Moore Reviewed-by: Jonathan Cameron Reviewed-by: Rafael J. Wysocki Reviewed-by: Davidlohr Bueso Signed-off-by: Vishal Verma Link: https://lore.kernel.org/r/20220413073618.291335-3-vishal.l.verma@intel.com Signed-off-by: Dan Williams --- include/acpi/acpi_bus.h | 6 ++++++ include/linux/acpi.h | 4 ++++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index c4b78c21d793..305ebf2a3fa7 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -582,10 +582,16 @@ int unregister_acpi_bus_type(struct acpi_bus_type *); int acpi_bind_one(struct device *dev, struct acpi_device *adev); int acpi_unbind_one(struct device *dev); +enum acpi_bridge_type { + ACPI_BRIDGE_TYPE_PCIE = 1, + ACPI_BRIDGE_TYPE_CXL, +}; + struct acpi_pci_root { struct acpi_device * device; struct pci_bus *bus; u16 segment; + int bridge_type; struct resource secondary; /* downstream bus range */ u32 osc_support_set; /* _OSC state of support bits */ diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 04e5a038dd57..82d91d9ccce5 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -550,6 +550,10 @@ struct acpi_osc_context { acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); +/* Number of _OSC capability DWORDS depends on bridge type */ +#define OSC_PCI_CAPABILITY_DWORDS 3 +#define OSC_CXL_CAPABILITY_DWORDS 5 + /* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */ #define OSC_QUERY_DWORD 0 /* DWORD 1 */ #define OSC_SUPPORT_DWORD 1 /* DWORD 2 */ -- cgit v1.2.3 From 56368029d93bbb3246ee2e03268fa6dd9754be05 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Wed, 13 Apr 2022 01:36:18 -0600 Subject: PCI/ACPI: negotiate CXL _OSC Add full support for negotiating _OSC as defined in the CXL 2.0 spec, as applicable to CXL-enabled platforms. Advertise support for the CXL features we support - 'CXL 2.0 port/device register access', 'Protocol Error Reporting', and 'CXL Native Hot Plug'. Request control for 'CXL Memory Error Reporting'. The requests are dependent on CONFIG_* based prerequisites, and prior PCI enabling, similar to how the standard PCI _OSC bits are determined. The CXL specification does not define any additional constraints on the hotplug flow beyond PCIe native hotplug, so a kernel that supports native PCIe hotplug, supports CXL hotplug. For error handling protocol and link errors just use PCIe AER. There is nascent support for amending AER events with CXL specific status [1], but there's otherwise no additional OS responsibility for CXL errors beyond PCIe AER. CXL Memory Errors behave the same as typical memory errors so CONFIG_MEMORY_FAILURE is sufficient to indicate support to platform firmware. [1]: https://lore.kernel.org/linux-cxl/164740402242.3912056.8303625392871313860.stgit@dwillia2-desk3.amr.corp.intel.com/ Cc: Bjorn Helgaas Cc: "Rafael J. Wysocki" Cc: Robert Moore Cc: Dan Williams Reviewed-by: Rafael J. Wysocki Reviewed-by: Davidlohr Bueso Signed-off-by: Vishal Verma Link: https://lore.kernel.org/r/20220413073618.291335-4-vishal.l.verma@intel.com Signed-off-by: Dan Williams --- include/acpi/acpi_bus.h | 6 ++++-- include/linux/acpi.h | 25 ++++++++++++++++++++++++- 2 files changed, 28 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 305ebf2a3fa7..4c463ae2777b 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -594,8 +594,10 @@ struct acpi_pci_root { int bridge_type; struct resource secondary; /* downstream bus range */ - u32 osc_support_set; /* _OSC state of support bits */ - u32 osc_control_set; /* _OSC state of control bits */ + u32 osc_support_set; /* _OSC state of support bits */ + u32 osc_control_set; /* _OSC state of control bits */ + u32 osc_ext_support_set; /* _OSC state of extended support bits */ + u32 osc_ext_control_set; /* _OSC state of extended control bits */ phys_addr_t mcfg_addr; }; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 82d91d9ccce5..378a431666b3 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -554,10 +554,12 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_PCI_CAPABILITY_DWORDS 3 #define OSC_CXL_CAPABILITY_DWORDS 5 -/* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */ +/* Indexes into _OSC Capabilities Buffer (DWORDs 2 to 5 are device-specific) */ #define OSC_QUERY_DWORD 0 /* DWORD 1 */ #define OSC_SUPPORT_DWORD 1 /* DWORD 2 */ #define OSC_CONTROL_DWORD 2 /* DWORD 3 */ +#define OSC_EXT_SUPPORT_DWORD 3 /* DWORD 4 */ +#define OSC_EXT_CONTROL_DWORD 4 /* DWORD 5 */ /* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */ #define OSC_QUERY_ENABLE 0x00000001 /* input */ @@ -612,6 +614,15 @@ extern u32 osc_sb_native_usb4_control; #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 +/* CXL _OSC: Capabilities DWORD 4: Support Field */ +#define OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT 0x00000001 +#define OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT 0x00000002 +#define OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT 0x00000004 +#define OSC_CXL_NATIVE_HP_SUPPORT 0x00000008 + +/* CXL _OSC: Capabilities DWORD 5: Control Field */ +#define OSC_CXL_ERROR_REPORTING_CONTROL 0x00000001 + static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) { u32 *ret = context->ret.pointer; @@ -619,6 +630,13 @@ static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) return ret[OSC_CONTROL_DWORD]; } +static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) +{ + u32 *ret = context->ret.pointer; + + return ret[OSC_EXT_CONTROL_DWORD]; +} + #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 #define ACPI_GSB_ACCESS_ATTRIB_BYTE 0x00000006 @@ -1021,6 +1039,11 @@ static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) return 0; } +static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) +{ + return 0; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC -- cgit v1.2.3 From d864b8ea6468cf1dce614a58eec92a23d8e07fec Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 26 Apr 2022 12:22:44 -0700 Subject: cxl/acpi: Add root device lockdep validation The CXL "root" device, ACPI0017, is an attach point for coordinating platform level CXL resources and is the parent device for a CXL port topology tree. As such it has distinct locking rules relative to other CXL subsystem objects, but because it is an ACPI device the lock class is established well before it is given to the cxl_acpi driver. However, the lockdep API does support changing the lock class "live" for situations like this. Add a device_lock_set_class() helper that a driver can use in ->probe() to set a custom lock class, and device_lock_reset_class() to return to the default "no validate" class before the custom lock class key goes out of scope after ->remove(). Note the helpers are all macros to support dead code elimination in the CONFIG_PROVE_LOCKING=n case, however device_set_lock_class() still needs #ifdef CONFIG_PROVE_LOCKING since lockdep_match_class() explicitly does not have a helper in the CONFIG_PROVE_LOCKING=n case (see comment in lockdep.h). The lockdep API needs 2 small tweaks to prevent "unused" warnings for the @key argument to lock_set_class(), and a new lock_set_novalidate_class() is added to supplement lockdep_set_novalidate_class() in the cases where the lock class is converted while the lock is held. Suggested-by: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Ingo Molnar Cc: Will Deacon Cc: Waiman Long Cc: Boqun Feng Cc: Alison Schofield Cc: Vishal Verma Cc: Ben Widawsky Cc: Jonathan Cameron Reviewed-by: Greg Kroah-Hartman Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/165100081305.1528964.11138612430659737238.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/device.h | 43 +++++++++++++++++++++++++++++++++++++++++++ include/linux/lockdep.h | 6 +++++- 2 files changed, 48 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 93459724dcde..833b0b3b0193 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -850,6 +850,49 @@ static inline bool device_supports_offline(struct device *dev) return dev->bus && dev->bus->offline && dev->bus->online; } +#define __device_lock_set_class(dev, name, key) \ +do { \ + struct device *__d2 __maybe_unused = dev; \ + lock_set_class(&__d2->mutex.dep_map, name, key, 0, _THIS_IP_); \ +} while (0) + +/** + * device_lock_set_class - Specify a temporary lock class while a device + * is attached to a driver + * @dev: device to modify + * @key: lock class key data + * + * This must be called with the device_lock() already held, for example + * from driver ->probe(). Take care to only override the default + * lockdep_no_validate class. + */ +#ifdef CONFIG_LOCKDEP +#define device_lock_set_class(dev, key) \ +do { \ + struct device *__d = dev; \ + dev_WARN_ONCE(__d, !lockdep_match_class(&__d->mutex, \ + &__lockdep_no_validate__), \ + "overriding existing custom lock class\n"); \ + __device_lock_set_class(__d, #key, key); \ +} while (0) +#else +#define device_lock_set_class(dev, key) __device_lock_set_class(dev, #key, key) +#endif + +/** + * device_lock_reset_class - Return a device to the default lockdep novalidate state + * @dev: device to modify + * + * This must be called with the device_lock() already held, for example + * from driver ->remove(). + */ +#define device_lock_reset_class(dev) \ +do { \ + struct device *__d __maybe_unused = dev; \ + lock_set_novalidate_class(&__d->mutex.dep_map, "&dev->mutex", \ + _THIS_IP_); \ +} while (0) + void lock_device_hotplug(void); void unlock_device_hotplug(void); int lock_device_hotplug_sysfs(void); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 467b94257105..43b0dc6a0b21 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -290,6 +290,9 @@ extern void lock_set_class(struct lockdep_map *lock, const char *name, struct lock_class_key *key, unsigned int subclass, unsigned long ip); +#define lock_set_novalidate_class(l, n, i) \ + lock_set_class(l, n, &__lockdep_no_validate__, 0, i) + static inline void lock_set_subclass(struct lockdep_map *lock, unsigned int subclass, unsigned long ip) { @@ -357,7 +360,8 @@ static inline void lockdep_set_selftest_task(struct task_struct *task) # define lock_acquire(l, s, t, r, c, n, i) do { } while (0) # define lock_release(l, i) do { } while (0) # define lock_downgrade(l, i) do { } while (0) -# define lock_set_class(l, n, k, s, i) do { } while (0) +# define lock_set_class(l, n, key, s, i) do { (void)(key); } while (0) +# define lock_set_novalidate_class(l, n, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) # define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \ -- cgit v1.2.3 From fd3abd2cafa46955846d731b9a6ded2c19ab73d8 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 21 Apr 2022 08:33:45 -0700 Subject: device-core: Kill the lockdep_mutex Per Peter [1], the lockdep API has native support for all the use cases lockdep_mutex was attempting to enable. Now that all lockdep_mutex users have been converted to those APIs, drop this lock. Link: https://lore.kernel.org/r/Ylf0dewci8myLvoW@hirez.programming.kicks-ass.net [1] Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Suggested-by: Peter Zijlstra Reviewed-by: Ira Weiny Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/165055522548.3745911.14298368286915484086.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/device.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 833b0b3b0193..073f1b0126ac 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -400,8 +400,6 @@ struct dev_msi_info { * This identifies the device type and carries type-specific * information. * @mutex: Mutex to synchronize calls to its driver. - * @lockdep_mutex: An optional debug lock that a subsystem can use as a - * peer lock to gain localized lockdep coverage of the device_lock. * @bus: Type of bus device is on. * @driver: Which driver has allocated this * @platform_data: Platform data specific to the device. @@ -499,9 +497,6 @@ struct device { core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ -#ifdef CONFIG_PROVE_LOCKING - struct mutex lockdep_mutex; -#endif struct mutex mutex; /* mutex to synchronize calls to * its driver. */ -- cgit v1.2.3 From 033b87d24f7257c45506bd043ad85ed24a9925e2 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 26 Apr 2022 01:29:07 -0700 Subject: io_uring: use the text representation of ops in trace It is annoying to translate opcodes to textwhen tracing io_uring. Use the io_uring_get_opcode function instead to use the text representation. A downside here might have been that if the opcode is invalid it will not be obvious, however the opcode is already overridden in these cases to 0 (NOP) in io_init_req(). Therefore this is a non issue. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220426082907.3600028-5-dylany@fb.com [axboe: don't include register, those are not req opcodes] Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 36 +++++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 42c7e1a3c6ae..3f2961baebcc 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -7,6 +7,7 @@ #include #include +#include struct io_wq_work; @@ -169,8 +170,9 @@ TRACE_EVENT(io_uring_queue_async_work, __entry->rw = rw; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, flags 0x%x, %s queue, work %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work) ); @@ -205,8 +207,9 @@ TRACE_EVENT(io_uring_defer, __entry->opcode = opcode; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d", - __entry->ctx, __entry->req, __entry->data, __entry->opcode) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s", + __entry->ctx, __entry->req, __entry->data, + io_uring_get_opcode(__entry->opcode)) ); /** @@ -305,9 +308,9 @@ TRACE_EVENT(io_uring_fail_link, __entry->link = link; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, link %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, - __entry->link) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, link %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->link) ); /** @@ -389,9 +392,9 @@ TRACE_EVENT(io_uring_submit_sqe, __entry->sq_thread = sq_thread; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, flags 0x%x, " + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, " "non block %d, sq_thread %d", __entry->ctx, __entry->req, - __entry->user_data, __entry->opcode, + __entry->user_data, io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); @@ -433,8 +436,9 @@ TRACE_EVENT(io_uring_poll_arm, __entry->events = events; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask 0x%x, events 0x%x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask 0x%x, events 0x%x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask, __entry->events) ); @@ -470,8 +474,9 @@ TRACE_EVENT(io_uring_task_add, __entry->mask = mask; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask %x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask %x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask) ); @@ -530,12 +535,13 @@ TRACE_EVENT(io_uring_req_failed, ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "opcode %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "opcode %s, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " "error=%d", __entry->ctx, __entry->req, __entry->user_data, - __entry->opcode, __entry->flags, __entry->ioprio, + io_uring_get_opcode(__entry->opcode), + __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, (unsigned long long) __entry->addr, __entry->len, __entry->op_flags, -- cgit v1.2.3 From 9096bbe951ddd3f9dc813e73b5bde6d5715d1cdb Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 28 Apr 2022 23:15:58 -0700 Subject: mm: shmem: make shmem_init return void The return value of shmem_init is never used. So we can make it return void now. [akpm@linux-foundation.org: remove `return;' from void-returning function, per Muchun Song] Link: https://lkml.kernel.org/r/20220328112707.22217-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Cc: Muchun Song Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index ab51d3cd39bd..3e915cc550bc 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -56,7 +56,7 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) * Functions in mm/shmem.c called directly from elsewhere: */ extern const struct fs_parameter_spec shmem_fs_parameters[]; -extern int shmem_init(void); +extern void shmem_init(void); extern int shmem_init_fs_context(struct fs_context *fc); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); -- cgit v1.2.3 From ef7a4ffc4c7f969d61e297c53cb2de1d6f012a11 Mon Sep 17 00:00:00 2001 From: Lu Jialin Date: Thu, 28 Apr 2022 23:16:00 -0700 Subject: mm/memcontrol.c: make cgroup_memory_noswap static cgroup_memory_noswap is only used in mm/memcontrol.c, therefore just make it static, and remove export in include/linux/memcontrol.h Link: https://lkml.kernel.org/r/20220421124736.62180-1-lujialin4@huawei.com Signed-off-by: Lu Jialin Acked-by: Johannes Weiner Acked-by: Shakeel Butt Acked-by: Roman Gushchin Reviewed-by: Muchun Song Cc: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 89b14729d59f..fe580cb96683 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -937,10 +937,6 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); -#ifdef CONFIG_MEMCG_SWAP -extern bool cgroup_memory_noswap; -#endif - void folio_memcg_lock(struct folio *folio); void folio_memcg_unlock(struct folio *folio); void lock_page_memcg(struct page *page); -- cgit v1.2.3 From 2ba2b008a8bf5fd268a43d03ba79e0ad464d6836 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 28 Apr 2022 23:16:02 -0700 Subject: Revert "mm/memory-failure.c: fix race with changing page compound again" Reverts commit 888af2701db7 ("mm/memory-failure.c: fix race with changing page compound again") because now we fetch the page refcount under hugetlb_lock in try_memory_failure_hugetlb() so that the race check is no longer necessary. Link: https://lkml.kernel.org/r/20220408135323.1559401-4-naoya.horiguchi@linux.dev Signed-off-by: Naoya Horiguchi Suggested-by: Miaohe Lin Reviewed-by: Miaohe Lin Reviewed-by: Mike Kravetz Cc: Miaohe Lin Cc: Yang Shi Cc: Dan Carpenter Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 - include/ras/ras_event.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9f44254af8ce..d446e834a3e5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3251,7 +3251,6 @@ enum mf_action_page_type { MF_MSG_BUDDY, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, - MF_MSG_DIFFERENT_PAGE_SIZE, MF_MSG_UNKNOWN, }; diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 1e694fd239b9..d0337a41141c 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -374,7 +374,6 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_BUDDY, "free buddy page" ) \ EM ( MF_MSG_DAX, "dax page" ) \ EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \ - EM ( MF_MSG_DIFFERENT_PAGE_SIZE, "different page size" ) \ EMe ( MF_MSG_UNKNOWN, "unknown page" ) /* -- cgit v1.2.3 From 7d6e2d96384556a4f30547803be1f606eb805a62 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Thu, 28 Apr 2022 23:16:09 -0700 Subject: mm: untangle config dependencies for demote-on-reclaim At the time demote-on-reclaim was introduced, it was tied to CONFIG_HOTPLUG_CPU + CONFIG_MIGRATE, but that is not really accurate. The only two things we need to depend on are CONFIG_NUMA + CONFIG_MIGRATE, so clean this up. Furthermore, we only register the hotplug memory notifier when the system has CONFIG_MEMORY_HOTPLUG. Link: https://lkml.kernel.org/r/20220322224016.4574-1-osalvador@suse.de Signed-off-by: Oscar Salvador Suggested-by: "Huang, Ying" Reviewed-by: "Huang, Ying" Cc: Dave Hansen Cc: Abhishek Goel Cc: Baolin Wang Signed-off-by: Andrew Morton --- include/linux/migrate.h | 34 +++++++++++++++------------------- 1 file changed, 15 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 90e75d5a54d6..2707bfd43a0d 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -47,17 +47,8 @@ void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); -extern bool numa_demotion_enabled; -extern void migrate_on_reclaim_init(void); -#ifdef CONFIG_HOTPLUG_CPU -extern void set_migration_target_nodes(void); -#else -static inline void set_migration_target_nodes(void) {} -#endif #else -static inline void set_migration_target_nodes(void) {} - static inline void putback_movable_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, @@ -82,9 +73,23 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, return -ENOSYS; } -#define numa_demotion_enabled false #endif /* CONFIG_MIGRATION */ +#if defined(CONFIG_MIGRATION) && defined(CONFIG_NUMA) +extern void set_migration_target_nodes(void); +extern void migrate_on_reclaim_init(void); +extern bool numa_demotion_enabled; +extern int next_demotion_node(int node); +#else +static inline void set_migration_target_nodes(void) {} +static inline void migrate_on_reclaim_init(void) {} +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} +#define numa_demotion_enabled false +#endif + #ifdef CONFIG_COMPACTION extern int PageMovable(struct page *page); extern void __SetPageMovable(struct page *page, struct address_space *mapping); @@ -172,15 +177,6 @@ struct migrate_vma { int migrate_vma_setup(struct migrate_vma *args); void migrate_vma_pages(struct migrate_vma *migrate); void migrate_vma_finalize(struct migrate_vma *migrate); -int next_demotion_node(int node); - -#else /* CONFIG_MIGRATION disabled: */ - -static inline int next_demotion_node(int node) -{ - return NUMA_NO_NODE; -} - #endif /* CONFIG_MIGRATION */ #endif /* _LINUX_MIGRATE_H */ -- cgit v1.2.3 From 6a8e0596f00469c15ec556b9f3624acd2e9a04f9 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 28 Apr 2022 23:16:10 -0700 Subject: mm: rmap: introduce pfn_mkclean_range() to cleans PTEs The page_mkclean_one() is supposed to be used with the pfn that has a associated struct page, but not all the pfns (e.g. DAX) have a struct page. Introduce a new function pfn_mkclean_range() to cleans the PTEs (including PMDs) mapped with range of pfns which has no struct page associated with them. This helper will be used by DAX device in the next patch to make pfns clean. Link: https://lkml.kernel.org/r/20220403053957.10770-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alistair Popple Cc: Al Viro Cc: Christoph Hellwig Cc: Dan Williams Cc: Hugh Dickins Cc: Jan Kara Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Ralph Campbell Cc: Ross Zwisler Cc: Xiongchun Duan Cc: Xiyu Yang Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 17230c458341..8573aae50d96 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -261,6 +261,9 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); */ int folio_mkclean(struct folio *); +int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, + struct vm_area_struct *vma); + void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); /* -- cgit v1.2.3 From 0e5e64c0b0d7bb33a5e971ad17e771cf6e0a1127 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 28 Apr 2022 23:16:10 -0700 Subject: mm: simplify follow_invalidate_pte() The only user (DAX) of range and pmdpp parameters of follow_invalidate_pte() is gone, it is safe to remove them and make it static to simlify the code. This is revertant of the following commits: 097963959594 ("mm: add follow_pte_pmd()") a4d1a8852513 ("dax: update to new mmu_notifier semantic") There is only one caller of the follow_invalidate_pte(). So just fold it into follow_pte() and remove it. Link: https://lkml.kernel.org/r/20220403053957.10770-7-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Christoph Hellwig Cc: Alistair Popple Cc: Al Viro Cc: Dan Williams Cc: Hugh Dickins Cc: Jan Kara Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Ralph Campbell Cc: Ross Zwisler Cc: Xiongchun Duan Cc: Xiyu Yang Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/mm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index d446e834a3e5..16d6b46d2d3e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1845,9 +1845,6 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); -int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, - struct mmu_notifier_range *range, pte_t **ptepp, - pmd_t **pmdpp, spinlock_t **ptlp); int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, -- cgit v1.2.3 From 3afa793082e624f7bd83533010ff4a676451d4ee Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 28 Apr 2022 23:16:14 -0700 Subject: mm/mmap: drop arch_vm_get_page_pgprot() There are no platforms left which use arch_vm_get_page_prot(). Just drop generic arch_vm_get_page_prot(). Link: https://lkml.kernel.org/r/20220414062125.609297-8-anshuman.khandual@arm.com Cc: Andrew Morton Cc: linux-mm@kvack.org Cc: linux-kernel@vger.kernel.org Reviewed-by: Christophe Leroy Reviewed-by: Catalin Marinas Signed-off-by: Anshuman Khandual Cc: Christoph Hellwig Cc: David S. Miller Cc: Ingo Molnar Cc: Khalid Aziz Cc: Michael Ellerman Cc: Paul Mackerras Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mman.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/mman.h b/include/linux/mman.h index b66e91b8176c..58b3abd457a3 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -93,10 +93,6 @@ static inline void vm_unacct_memory(long pages) #define arch_calc_vm_flag_bits(flags) 0 #endif -#ifndef arch_vm_get_page_prot -#define arch_vm_get_page_prot(vm_flags) __pgprot(0) -#endif - #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have -- cgit v1.2.3 From 5981611d0a006472d367d7a8e6ead8afaecf17c7 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 28 Apr 2022 23:16:14 -0700 Subject: mm: hugetlb_vmemmap: cleanup hugetlb_vmemmap related functions Patch series "cleanup hugetlb_vmemmap". The word of "free" is not expressive enough to express the feature of optimizing vmemmap pages associated with each HugeTLB, rename this keywork to "optimize" is more clear. In this series, cheanup related codes to make it more clear and expressive. This is suggested by David. This patch (of 3): The word of "free" is not expressive enough to express the feature of optimizing vmemmap pages associated with each HugeTLB, rename this keywork to "optimize". And some function names are prefixed with "huge_page" instead of "hugetlb", it is easily to be confused with THP. In this patch, cheanup related functions to make code more clear and expressive. Link: https://lkml.kernel.org/r/20220404074652.68024-1-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20220404074652.68024-2-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: David Hildenbrand Cc: Mike Kravetz Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ac2a1d758a80..189bddb8eca4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -624,7 +624,7 @@ struct hstate { unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP - unsigned int nr_free_vmemmap_pages; + unsigned int optimize_vmemmap_pages; #endif #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ -- cgit v1.2.3 From f10f1442c309ccef7a80ba3dc4abde0978e86fb4 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 28 Apr 2022 23:16:15 -0700 Subject: mm: hugetlb_vmemmap: cleanup hugetlb_free_vmemmap_enabled* The word of "free" is not expressive enough to express the feature of optimizing vmemmap pages associated with each HugeTLB, rename this keywork to "optimize". In this patch , cheanup the static key and hugetlb_free_vmemmap_enabled() to make code more expressive. Link: https://lkml.kernel.org/r/20220404074652.68024-3-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: David Hildenbrand Cc: Mike Kravetz Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 9d8eeaa67d05..573f499d5a2d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -192,16 +192,16 @@ enum pageflags { #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, - hugetlb_free_vmemmap_enabled_key); + hugetlb_optimize_vmemmap_key); -static __always_inline bool hugetlb_free_vmemmap_enabled(void) +static __always_inline bool hugetlb_optimize_vmemmap_enabled(void) { return static_branch_maybe(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, - &hugetlb_free_vmemmap_enabled_key); + &hugetlb_optimize_vmemmap_key); } /* - * If the feature of freeing some vmemmap pages associated with each HugeTLB + * If the feature of optimizing vmemmap pages associated with each HugeTLB * page is enabled, the head vmemmap page frame is reused and all of the tail * vmemmap addresses map to the head vmemmap page frame (furture details can * refer to the figure at the head of the mm/hugetlb_vmemmap.c). In other @@ -218,7 +218,7 @@ static __always_inline bool hugetlb_free_vmemmap_enabled(void) */ static __always_inline const struct page *page_fixed_fake_head(const struct page *page) { - if (!hugetlb_free_vmemmap_enabled()) + if (!hugetlb_optimize_vmemmap_enabled()) return page; /* @@ -247,7 +247,7 @@ static inline const struct page *page_fixed_fake_head(const struct page *page) return page; } -static inline bool hugetlb_free_vmemmap_enabled(void) +static inline bool hugetlb_optimize_vmemmap_enabled(void) { return false; } -- cgit v1.2.3 From 47010c040dec8af6347ec6259104fc13f7e7e30a Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 28 Apr 2022 23:16:15 -0700 Subject: mm: hugetlb_vmemmap: cleanup CONFIG_HUGETLB_PAGE_FREE_VMEMMAP* The word of "free" is not expressive enough to express the feature of optimizing vmemmap pages associated with each HugeTLB, rename this keywork to "optimize". In this patch , cheanup configs to make code more expressive. Link: https://lkml.kernel.org/r/20220404074652.68024-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Mike Kravetz Cc: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 2 +- include/linux/mm.h | 2 +- include/linux/page-flags.h | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 189bddb8eca4..ac2ece9e9c79 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -623,7 +623,7 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP unsigned int optimize_vmemmap_pages; #endif #ifdef CONFIG_CGROUP_HUGETLB diff --git a/include/linux/mm.h b/include/linux/mm.h index 16d6b46d2d3e..a8f4c7e96ad5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3145,7 +3145,7 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) } #endif -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP int vmemmap_remap_free(unsigned long start, unsigned long end, unsigned long reuse); int vmemmap_remap_alloc(unsigned long start, unsigned long end, diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 573f499d5a2d..1ea896887ee4 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -190,13 +190,13 @@ enum pageflags { #ifndef __GENERATING_BOUNDS_H -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP -DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON, hugetlb_optimize_vmemmap_key); static __always_inline bool hugetlb_optimize_vmemmap_enabled(void) { - return static_branch_maybe(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, + return static_branch_maybe(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON, &hugetlb_optimize_vmemmap_key); } -- cgit v1.2.3 From e3246d8f52173a798710314a42fea83223036fc8 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Thu, 28 Apr 2022 23:16:15 -0700 Subject: mm/sparse-vmemmap: add a pgmap argument to section activation Patch series "sparse-vmemmap: memory savings for compound devmaps (device-dax)", v9. This series minimizes 'struct page' overhead by pursuing a similar approach as Muchun Song series "Free some vmemmap pages of hugetlb page" (now merged since v5.14), but applied to devmap with @vmemmap_shift (device-dax). The vmemmap dedpulication original idea (already used in HugeTLB) is to reuse/deduplicate tail page vmemmap areas, particular the area which only describes tail pages. So a vmemmap page describes 64 struct pages, and the first page for a given ZONE_DEVICE vmemmap would contain the head page and 63 tail pages. The second vmemmap page would contain only tail pages, and that's what gets reused across the rest of the subsection/section. The bigger the page size, the bigger the savings (2M hpage -> save 6 vmemmap pages; 1G hpage -> save 4094 vmemmap pages). This is done for PMEM /specifically only/ on device-dax configured namespaces, not fsdax. In other words, a devmap with a @vmemmap_shift. In terms of savings, per 1Tb of memory, the struct page cost would go down with compound devmap: * with 2M pages we lose 4G instead of 16G (0.39% instead of 1.5% of total memory) * with 1G pages we lose 40MB instead of 16G (0.0014% instead of 1.5% of total memory) The series is mostly summed up by patch 4, and to summarize what the series does: Patches 1 - 3: Minor cleanups in preparation for patch 4. Move the very nice docs of hugetlb_vmemmap.c into a Documentation/vm/ entry. Patch 4: Patch 4 is the one that takes care of the struct page savings (also referred to here as tail-page/vmemmap deduplication). Much like Muchun series, we reuse the second PTE tail page vmemmap areas across a given @vmemmap_shift On important difference though, is that contrary to the hugetlbfs series, there's no vmemmap for the area because we are late-populating it as opposed to remapping a system-ram range. IOW no freeing of pages of already initialized vmemmap like the case for hugetlbfs, which greatly simplifies the logic (besides not being arch-specific). altmap case unchanged and still goes via the vmemmap_populate(). Also adjust the newly added docs to the device-dax case. [Note that device-dax is still a little behind HugeTLB in terms of savings. I have an additional simple patch that reuses the head vmemmap page too, as a follow-up. That will double the savings and namespaces initialization.] Patch 5: Initialize fewer struct pages depending on the page size with DRAM backed struct pages -- because fewer pages are unique and most tail pages (with bigger vmemmap_shift). NVDIMM namespace bootstrap improves from ~268-358 ms to ~80-110/<1ms on 128G NVDIMMs with 2M and 1G respectivally. And struct page needed capacity will be 3.8x / 1071x smaller for 2M and 1G respectivelly. Tested on x86 with 1.5Tb of pmem (including pinning, and RDMA registration/deregistration scalability with 2M MRs) This patch (of 5): In support of using compound pages for devmap mappings, plumb the pgmap down to the vmemmap_populate implementation. Note that while altmap is retrievable from pgmap the memory hotplug code passes altmap without pgmap[*], so both need to be independently plumbed. So in addition to @altmap, pass @pgmap to sparse section populate functions namely: sparse_add_section section_activate populate_section_memmap __populate_section_memmap Passing @pgmap allows __populate_section_memmap() to both fetch the vmemmap_shift in which memmap metadata is created for and also to let sparse-vmemmap fetch pgmap ranges to co-relate to a given section and pick whether to just reuse tail pages from past onlined sections. While at it, fix the kdoc for @altmap for sparse_add_section(). [*] https://lore.kernel.org/linux-mm/20210319092635.6214-1-osalvador@suse.de/ Link: https://lkml.kernel.org/r/20220420155310.9712-1-joao.m.martins@oracle.com Link: https://lkml.kernel.org/r/20220420155310.9712-2-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Dan Williams Reviewed-by: Muchun Song Cc: Vishal Verma Cc: Matthew Wilcox Cc: Jason Gunthorpe Cc: Jane Chu Cc: Mike Kravetz Cc: Jonathan Corbet Cc: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/memory_hotplug.h | 5 ++++- include/linux/mm.h | 3 ++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 1ce6f8044f1e..e0b2209ab71c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -15,6 +15,7 @@ struct memory_block; struct memory_group; struct resource; struct vmem_altmap; +struct dev_pagemap; #ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION /* @@ -122,6 +123,7 @@ typedef int __bitwise mhp_t; struct mhp_params { struct vmem_altmap *altmap; pgprot_t pgprot; + struct dev_pagemap *pgmap; }; bool mhp_range_allowed(u64 start, u64 size, bool need_mapping); @@ -333,7 +335,8 @@ extern void remove_pfn_range_from_zone(struct zone *zone, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_section(int nid, unsigned long pfn, - unsigned long nr_pages, struct vmem_altmap *altmap); + unsigned long nr_pages, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap); extern void sparse_remove_section(struct mem_section *ms, unsigned long pfn, unsigned long nr_pages, unsigned long map_offset, struct vmem_altmap *altmap); diff --git a/include/linux/mm.h b/include/linux/mm.h index a8f4c7e96ad5..80bba49387e9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3154,7 +3154,8 @@ int vmemmap_remap_alloc(unsigned long start, unsigned long end, void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, - unsigned long nr_pages, int nid, struct vmem_altmap *altmap); + unsigned long nr_pages, int nid, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); -- cgit v1.2.3 From 4917f55b4ef963e2d2288fe4eb651728be8db406 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Thu, 28 Apr 2022 23:16:16 -0700 Subject: mm/sparse-vmemmap: improve memory savings for compound devmaps A compound devmap is a dev_pagemap with @vmemmap_shift > 0 and it means that pages are mapped at a given huge page alignment and utilize uses compound pages as opposed to order-0 pages. Take advantage of the fact that most tail pages look the same (except the first two) to minimize struct page overhead. Allocate a separate page for the vmemmap area which contains the head page and separate for the next 64 pages. The rest of the subsections then reuse this tail vmemmap page to initialize the rest of the tail pages. Sections are arch-dependent (e.g. on x86 it's 64M, 128M or 512M) and when initializing compound devmap with big enough @vmemmap_shift (e.g. 1G PUD) it may cross multiple sections. The vmemmap code needs to consult @pgmap so that multiple sections that all map the same tail data can refer back to the first copy of that data for a given gigantic page. On compound devmaps with 2M align, this mechanism lets 6 pages be saved out of the 8 necessary PFNs necessary to set the subsection's 512 struct pages being mapped. On a 1G compound devmap it saves 4094 pages. Altmap isn't supported yet, given various restrictions in altmap pfn allocator, thus fallback to the already in use vmemmap_populate(). It is worth noting that altmap for devmap mappings was there to relieve the pressure of inordinate amounts of memmap space to map terabytes of pmem. With compound pages the motivation for altmaps for pmem gets reduced. Link: https://lkml.kernel.org/r/20220420155310.9712-5-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Muchun Song Cc: Christoph Hellwig Cc: Dan Williams Cc: Jane Chu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Vishal Verma Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 80bba49387e9..b9316b2c11ce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3161,7 +3161,7 @@ p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, - struct vmem_altmap *altmap); + struct vmem_altmap *altmap, struct page *reuse); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, -- cgit v1.2.3 From ba91fb7dd03c4f463453f28af24851097a6547fb Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 28 Apr 2022 23:16:16 -0700 Subject: include/linux/swapops.h: remove stub for non_swap_entry() The stub for non_swap_entry() may not help much, because MAX_SWAPFILES has already contained all the information to decide whether a swap entry is real swap entry or pesudo ones (migrations, ...). There can be some performance influences on non_swap_entry() with below conditions all met: !CONFIG_MIGRATION && !CONFIG_MEMORY_FAILURE && !CONFIG_DEVICE_PRIVATE But that's definitely not the major config most machines will use, at the meantime it's already in a slow path of swap entry (being parsed from a swap pte), so IMHO it shouldn't be a major issue. Also according to the analysis from Alistair, somehow the stub didn't do the job right [1]. To make the code cleaner, let's drop the stub. [1] https://lore.kernel.org/lkml/8735ihbw6g.fsf@nvdebian.thelocal/ Note: the uffd-wp shmem & hugetlbfs series will need this patch to make sure swap entries work as expected with below config as spotted by Alistair: !CONFIG_MIGRATION && !CONFIG_MEMORY_FAILURE && !CONFIG_DEVICE_PRIVATE && CONFIG_PTE_MARKER (PS: this config should mostly never gonna happen, though, afaict..) Link: https://lkml.kernel.org/r/20220413191147.66645-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Alistair Popple Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/swapops.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index d356ab4047f7..5af852b68805 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -387,18 +387,10 @@ static inline void num_poisoned_pages_inc(void) } #endif -#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \ - defined(CONFIG_DEVICE_PRIVATE) static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; } -#else -static inline int non_swap_entry(swp_entry_t entry) -{ - return 0; -} -#endif #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ -- cgit v1.2.3 From 7609385337a4feb6236e42dcd0df2185683ce839 Mon Sep 17 00:00:00 2001 From: xu xin Date: Thu, 28 Apr 2022 23:16:16 -0700 Subject: ksm: count ksm merging pages for each process Some applications or containers want to use KSM by calling madvise() to advise areas of address space to be MERGEABLE. But they may not know which applications are more likely to cause real merges in the deployment. If this patch is applied, it helps them know their corresponding number of merged pages, and then optimize their app code. As current KSM only counts the number of KSM merging pages(e.g. ksm_pages_sharing and ksm_pages_shared) of the whole system, we cannot see the more fine-grained KSM merging, for the upper application optimization, the merging area cannot be set easily according to the KSM page merging probability of each process. Therefore, it is necessary to add extra statistical means so that the upper level users can know the detailed KSM merging information of each process. We add a new proc file named as ksm_merging_pages under /proc// to indicate the involved ksm merging pages of this process. [akpm@linux-foundation.org: fix comment typo, remove BUG_ON()s] Link: https://lkml.kernel.org/r/20220325082318.2352853-1-xu.xin16@zte.com.cn Signed-off-by: xu xin Reported-by: kernel test robot Reviewed-by: Yang Yang Reviewed-by: Ran Xiaokai Reported-by: Zeal Robot Cc: Kees Cook Cc: Alexey Dobriyan Cc: Stephen Rothwell Cc: Ohhoon Kwon Cc: Matthew Wilcox (Oracle) Cc: Stephen Brennan Cc: Vlastimil Babka Cc: Feng Tang Cc: Yang Yang Cc: Ran Xiaokai Cc: Zeal Robot Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8834e38c06a4..87eddd509de2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -654,6 +654,13 @@ struct mm_struct { #ifdef CONFIG_IOMMU_SVA u32 pasid; +#endif +#ifdef CONFIG_KSM + /* + * Represent how many pages of this process are involved in KSM + * merging. + */ + unsigned long ksm_merging_pages; #endif } __randomize_layout; -- cgit v1.2.3 From 94bfe85bde18a99612bb5d0ce348643c2d352836 Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Thu, 28 Apr 2022 23:16:16 -0700 Subject: mm/vmstat: add events for ksm cow Users may use ksm by calling madvise(, , MADV_MERGEABLE) when they want to save memory, it's a tradeoff by suffering delay on ksm cow. Users can get to know how much memory ksm saved by reading /sys/kernel/mm/ksm/pages_sharing, but they don't know what's the costs of ksm cow, and this is important of some delay sensitive tasks. So add ksm cow events to help users evaluate whether or how to use ksm. Also update Documentation/admin-guide/mm/ksm.rst with new added events. Link: https://lkml.kernel.org/r/20220331035616.2390805-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Reviewed-by: David Hildenbrand Reviewed-by: xu xin Reviewed-by: Ran Xiaokai Cc: Matthew Wilcox (Oracle) Cc: Jonathan Corbet Cc: Dave Hansen Cc: Saravanan D Cc: Minchan Kim Cc: John Hubbard Signed-off-by: Andrew Morton --- include/linux/vm_event_item.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 16a0a4fd000b..e83967e4c20e 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -133,6 +133,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, KSM_SWPIN_COPY, #endif #endif +#ifdef CONFIG_KSM + COW_KSM, +#endif #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, DIRECT_MAP_LEVEL3_SPLIT, -- cgit v1.2.3 From 024c61eaff17f6a8c73cb8b25137251f0c3ef039 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 28 Apr 2022 23:16:17 -0700 Subject: mm: compaction: remove unneeded return value of kcompactd_run Patch series "A few cleanup and fixup patches for compaction". This series contains a few patches to clean up some obsolete comment, remove unneeded return value and so on. Also we fix the possible NULL pointer dereference. More details can be found in the respective changelogs. This patch (of 12): The return value of kcompactd_run() is unused now. Clean it up. Link: https://lkml.kernel.org/r/20220418141253.24298-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20220418141253.24298-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Cc; Mel Gorman Cc: David Hildenbrand Cc: Vlastimil Babka Cc: Pintu Kumar Cc: Charan Teja Kalla Signed-off-by: Andrew Morton --- include/linux/compaction.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 34bce35c808d..52a9ff65faee 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -177,7 +177,7 @@ static inline bool compaction_withdrawn(enum compact_result result) bool compaction_zonelist_suitable(struct alloc_context *ac, int order, int alloc_flags); -extern int kcompactd_run(int nid); +extern void kcompactd_run(int nid); extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx); @@ -212,9 +212,8 @@ static inline bool compaction_withdrawn(enum compact_result result) return true; } -static inline int kcompactd_run(int nid) +static inline void kcompactd_run(int nid) { - return 0; } static inline void kcompactd_stop(int nid) { -- cgit v1.2.3 From 766475cb526b2fc5ca21374b5810d6d8557870fc Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 28 Apr 2022 12:28:59 +0200 Subject: ARM: omap1: add back omap_set_dma_priority() stub One of my multiplatform patches went a little too far and removed a declaration that is needed for compile-testing the omapfb driver on non-OMAP1 platforms: arm-linux-gnueabi-ld: drivers/video/fbdev/omap/omapfb_main.o: in function `omapfb_do_probe': omapfb_main.c:(.text+0x41ec): undefined reference to `omap_set_dma_priority' Add back the inline stub, and in turn hide the definition when omapfb is disabled, like we do for the usb specific bits. Reported-by: kernel test robot Reviewed-by: Tony Lindgren Fixes: 52ef8efcb75e ("dma: omap: hide legacy interface") Signed-off-by: Arnd Bergmann --- include/linux/omap-dma.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 254b4e10511b..6f6c31e3fb93 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -294,7 +294,14 @@ struct omap_system_dma_plat_info { extern struct omap_system_dma_plat_info *omap_get_plat_info(void); +#if defined(CONFIG_ARCH_OMAP1) extern void omap_set_dma_priority(int lch, int dst_port, int priority); +#else +static inline void omap_set_dma_priority(int lch, int dst_port, int priority) +{ +} +#endif + extern int omap_request_dma(int dev_id, const char *dev_name, void (*callback)(int lch, u16 ch_status, void *data), void *data, int *dma_ch); -- cgit v1.2.3 From 50e7b416d2ab10b9771bd00a4d85df90ad2e4b37 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Thu, 28 Apr 2022 15:43:37 +0100 Subject: sched/fair: Remove sched_trace_*() helper functions We no longer need them as we can use DWARF debug info or BTF + pahole to re-generate the required structs to compile against them for a given kernel. This moves the burden of maintaining these helper functions to the module. https://github.com/qais-yousef/sched_tp Note that pahole v1.15 is required at least for using DWARF. And for BTF v1.23 which is not yet released will be required. There's alignment problem that will lead to crashes in earlier versions when used with BTF. We should have enough infrastructure to make these helper functions now obsolete, so remove them. [Rewrote commit message to reflect the new alternative] Signed-off-by: Dietmar Eggemann Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220428144338.479094-2-qais.yousef@arm.com --- include/linux/sched.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 67f06f72c50e..fc74ea2578b7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2378,20 +2378,6 @@ static inline void rseq_syscall(struct pt_regs *regs) #endif -const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq); -char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len); -int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq); - -const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq); -const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); -const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); - -int sched_trace_rq_cpu(struct rq *rq); -int sched_trace_rq_cpu_capacity(struct rq *rq); -int sched_trace_rq_nr_running(struct rq *rq); - -const struct cpumask *sched_trace_rd_span(struct root_domain *rd); - #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); -- cgit v1.2.3 From 498af8d1678ae2351218337b47bbf3cb0fc16821 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 29 Apr 2022 12:39:45 +0100 Subject: firmware: arm_ffa: Add ffa_dev_get_drvdata helper function Add a helper function to fetch ffa_dev's driver_data using dev_get_drvdata. At the same time move existing ffa_dev_set_drvdata to use dev_set_drvdata. Link: https://lore.kernel.org/r/20220429113946.2087145-3-sudeep.holla@arm.com Suggested-by: Arunachalam Ganapathy Signed-off-by: Sudeep Holla --- include/linux/arm_ffa.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 85651e41ded8..e5c76c1ef9ed 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -38,7 +38,12 @@ struct ffa_driver { static inline void ffa_dev_set_drvdata(struct ffa_device *fdev, void *data) { - fdev->dev.driver_data = data; + dev_set_drvdata(&fdev->dev, data); +} + +static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev) +{ + return dev_get_drvdata(&fdev->dev); } #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT) -- cgit v1.2.3 From 892de36fd4a98fab3298d417c051d9099af5448d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 29 Apr 2022 12:22:10 -0400 Subject: SUNRPC: Ensure gss-proxy connects on setup For reasons best known to the author, gss-proxy does not implement a NULL procedure, and returns RPC_PROC_UNAVAIL. However we still want to ensure that we connect to the service at setup time. So add a quirk-flag specially for this case. Fixes: 1d658336b05f ("SUNRPC: Add RPC based upcall mechanism for RPCGSS auth") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 267b7aeaf1a6..db5149567305 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,6 +160,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) +#define RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, -- cgit v1.2.3 From 991b4de3275728fd746ce15e00087fdbd51c29a1 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Wed, 27 Apr 2022 21:19:23 -0700 Subject: drm/i915/uapi: Add kerneldoc for engine class enum We'll be adding a new type of engine soon. Let's document the existing engine classes first to help make it clear what each type of engine is used for. Cc: Andi Shyti Signed-off-by: Matt Roper Reviewed-by: Andi Shyti Reviewed-by: Jordan Justen Link: https://patchwork.freedesktop.org/patch/msgid/20220428041926.1483683-2-matthew.d.roper@intel.com --- include/uapi/drm/i915_drm.h | 53 ++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 47 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 35ca528803fd..ec000fc6c879 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -154,21 +154,62 @@ enum i915_mocs_table_index { I915_MOCS_CACHED, }; -/* +/** + * enum drm_i915_gem_engine_class - uapi engine type enumeration + * * Different engines serve different roles, and there may be more than one - * engine serving each role. enum drm_i915_gem_engine_class provides a - * classification of the role of the engine, which may be used when requesting - * operations to be performed on a certain subset of engines, or for providing - * information about that group. + * engine serving each role. This enum provides a classification of the role + * of the engine, which may be used when requesting operations to be performed + * on a certain subset of engines, or for providing information about that + * group. */ enum drm_i915_gem_engine_class { + /** + * @I915_ENGINE_CLASS_RENDER: + * + * Render engines support instructions used for 3D, Compute (GPGPU), + * and programmable media workloads. These instructions fetch data and + * dispatch individual work items to threads that operate in parallel. + * The threads run small programs (called "kernels" or "shaders") on + * the GPU's execution units (EUs). + */ I915_ENGINE_CLASS_RENDER = 0, + + /** + * @I915_ENGINE_CLASS_COPY: + * + * Copy engines (also referred to as "blitters") support instructions + * that move blocks of data from one location in memory to another, + * or that fill a specified location of memory with fixed data. + * Copy engines can perform pre-defined logical or bitwise operations + * on the source, destination, or pattern data. + */ I915_ENGINE_CLASS_COPY = 1, + + /** + * @I915_ENGINE_CLASS_VIDEO: + * + * Video engines (also referred to as "bit stream decode" (BSD) or + * "vdbox") support instructions that perform fixed-function media + * decode and encode. + */ I915_ENGINE_CLASS_VIDEO = 2, + + /** + * @I915_ENGINE_CLASS_VIDEO_ENHANCE: + * + * Video enhancement engines (also referred to as "vebox") support + * instructions related to image enhancement. + */ I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, - /* should be kept compact */ + /* Values in this enum should be kept compact. */ + /** + * @I915_ENGINE_CLASS_INVALID: + * + * Placeholder value to represent an invalid engine class assignment. + */ I915_ENGINE_CLASS_INVALID = -1 }; -- cgit v1.2.3 From ecf8eca51f33dbfddcc23902bdee65c17587247c Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Wed, 27 Apr 2022 21:19:25 -0700 Subject: drm/i915/xehp: Add compute engine ABI We're now ready to start exposing compute engines to userspace. v2: - Move kerneldoc for other engine classes to a separate patch. (Andi) Cc: Daniele Ceraolo Spurio Cc: Tvrtko Ursulin Cc: Vinay Belgaumkar Cc: Jordan Justen Cc: Szymon Morek UMD (mesa): https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14395 Signed-off-by: Matt Roper Acked-by: Tvrtko Ursulin Reviewed-by: Andi Shyti Reviewed-by: Jordan Justen Tested-by: Jordan Justen # mesa anvil & iris Link: https://patchwork.freedesktop.org/patch/msgid/20220428041926.1483683-4-matthew.d.roper@intel.com --- include/uapi/drm/i915_drm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index ec000fc6c879..a2def7b27009 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -203,6 +203,15 @@ enum drm_i915_gem_engine_class { */ I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, + /** + * @I915_ENGINE_CLASS_COMPUTE: + * + * Compute engines support a subset of the instructions available + * on render engines: compute engines support Compute (GPGPU) and + * programmable media workloads, but do not support the 3D pipeline. + */ + I915_ENGINE_CLASS_COMPUTE = 4, + /* Values in this enum should be kept compact. */ /** -- cgit v1.2.3 From ec2a0f9c8b50865a11720651c9c536f20c578def Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Fri, 29 Apr 2022 14:36:58 -0700 Subject: kasan: mark KASAN_VMALLOC flags as kasan_vmalloc_flags_t Fix sparse warning: mm/kasan/shadow.c:496:15: warning: restricted kasan_vmalloc_flags_t degrades to integer Link: https://lkml.kernel.org/r/52d8fccdd3a48d4bdfd0ff522553bac2a13f1579.1649351254.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reported-by: kernel test robot Cc: Andrey Konovalov Cc: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Andrey Ryabinin Signed-off-by: Andrew Morton --- include/linux/kasan.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index ceebcb9de7bf..b092277bf48d 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -23,10 +23,10 @@ struct task_struct; typedef unsigned int __bitwise kasan_vmalloc_flags_t; -#define KASAN_VMALLOC_NONE 0x00u -#define KASAN_VMALLOC_INIT 0x01u -#define KASAN_VMALLOC_VM_ALLOC 0x02u -#define KASAN_VMALLOC_PROT_NORMAL 0x04u +#define KASAN_VMALLOC_NONE ((__force kasan_vmalloc_flags_t)0x00u) +#define KASAN_VMALLOC_INIT ((__force kasan_vmalloc_flags_t)0x01u) +#define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) +#define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -- cgit v1.2.3 From 5d8de293c224896a4da99763fce4f9794308caf4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 14:37:59 -0700 Subject: vmcore: convert copy_oldmem_page() to take an iov_iter Patch series "Convert vmcore to use an iov_iter", v5. For some reason several people have been sending bad patches to fix compiler warnings in vmcore recently. Here's how it should be done. Compile-tested only on x86. As noted in the first patch, s390 should take this conversion a bit further, but I'm not inclined to do that work myself. This patch (of 3): Instead of passing in a 'buf' and 'userbuf' argument, pass in an iov_iter. s390 needs more work to pass the iov_iter down further, or refactor, but I'd be more comfortable if someone who can test on s390 did that work. It's more convenient to convert the whole of read_from_oldmem() to take an iov_iter at the same time, so rename it to read_from_oldmem_iter() and add a temporary read_from_oldmem() wrapper that creates an iov_iter. Link: https://lkml.kernel.org/r/20220408090636.560886-1-bhe@redhat.com Link: https://lkml.kernel.org/r/20220408090636.560886-2-bhe@redhat.com Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Baoquan He Reviewed-by: Christoph Hellwig Cc: Heiko Carstens Signed-off-by: Andrew Morton --- include/linux/crash_dump.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 620821549b23..a1cf7d5c03c7 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -24,11 +24,10 @@ extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot); -extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, - unsigned long, int); -extern ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, - size_t csize, unsigned long offset, - int userbuf); +ssize_t copy_oldmem_page(struct iov_iter *i, unsigned long pfn, size_t csize, + unsigned long offset); +ssize_t copy_oldmem_page_encrypted(struct iov_iter *iter, unsigned long pfn, + size_t csize, unsigned long offset); void vmcore_cleanup(void); -- cgit v1.2.3 From e0690479917cbce740eef51fa3de92c69647a5ad Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 14:37:59 -0700 Subject: vmcore: convert read_from_oldmem() to take an iov_iter Remove the read_from_oldmem() wrapper introduced earlier and convert all the remaining callers to pass an iov_iter. Link: https://lkml.kernel.org/r/20220408090636.560886-4-bhe@redhat.com Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Baoquan He Reviewed-by: Christoph Hellwig Cc: Tiezhu Yang Cc: Amit Daniel Kachhap Cc: Al Viro Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/crash_dump.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index a1cf7d5c03c7..0f3a656293b0 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -134,13 +134,11 @@ static inline int vmcore_add_device_dump(struct vmcoredd_data *data) #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ #ifdef CONFIG_PROC_VMCORE -ssize_t read_from_oldmem(char *buf, size_t count, - u64 *ppos, int userbuf, - bool encrypted); +ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, + u64 *ppos, bool encrypted); #else -static inline ssize_t read_from_oldmem(char *buf, size_t count, - u64 *ppos, int userbuf, - bool encrypted) +static inline ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, + u64 *ppos, bool encrypted) { return -EOPNOTSUPP; } -- cgit v1.2.3 From f485922d8fe4e44f6d52a5bb95a603b7c65554bb Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 29 Apr 2022 14:38:01 -0700 Subject: pipe: make poll_usage boolean and annotate its access Patch series "Fix data-races around epoll reported by KCSAN." This series suppresses a false positive KCSAN's message and fixes a real data-race. This patch (of 2): pipe_poll() runs locklessly and assigns 1 to poll_usage. Once poll_usage is set to 1, it never changes in other places. However, concurrent writes of a value trigger KCSAN, so let's make KCSAN happy. BUG: KCSAN: data-race in pipe_poll / pipe_poll write to 0xffff8880042f6678 of 4 bytes by task 174 on cpu 3: pipe_poll (fs/pipe.c:656) ep_item_poll.isra.0 (./include/linux/poll.h:88 fs/eventpoll.c:853) do_epoll_wait (fs/eventpoll.c:1692 fs/eventpoll.c:1806 fs/eventpoll.c:2234) __x64_sys_epoll_wait (fs/eventpoll.c:2246 fs/eventpoll.c:2241 fs/eventpoll.c:2241) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:113) write to 0xffff8880042f6678 of 4 bytes by task 177 on cpu 1: pipe_poll (fs/pipe.c:656) ep_item_poll.isra.0 (./include/linux/poll.h:88 fs/eventpoll.c:853) do_epoll_wait (fs/eventpoll.c:1692 fs/eventpoll.c:1806 fs/eventpoll.c:2234) __x64_sys_epoll_wait (fs/eventpoll.c:2246 fs/eventpoll.c:2241 fs/eventpoll.c:2241) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:113) Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 177 Comm: epoll_race Not tainted 5.17.0-58927-gf443e374ae13 #6 Hardware name: Red Hat KVM, BIOS 1.11.0-2.amzn2 04/01/2014 Link: https://lkml.kernel.org/r/20220322002653.33865-1-kuniyu@amazon.co.jp Link: https://lkml.kernel.org/r/20220322002653.33865-2-kuniyu@amazon.co.jp Fixes: 3b844826b6c6 ("pipe: avoid unnecessary EPOLLET wakeups under normal loads") Signed-off-by: Kuniyuki Iwashima Cc: Alexander Duyck Cc: Al Viro Cc: Davidlohr Bueso Cc: Kuniyuki Iwashima Cc: "Soheil Hassas Yeganeh" Cc: "Sridhar Samudrala" Signed-off-by: Andrew Morton --- include/linux/pipe_fs_i.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index c00c618ef290..cb0fd633a610 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -71,7 +71,7 @@ struct pipe_inode_info { unsigned int files; unsigned int r_counter; unsigned int w_counter; - unsigned int poll_usage; + bool poll_usage; struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; -- cgit v1.2.3 From d679ae94fdd5d3ab00c35078f5af5f37e068b03d Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 29 Apr 2022 14:38:01 -0700 Subject: list: fix a data-race around ep->rdllist ep_poll() first calls ep_events_available() with no lock held and checks if ep->rdllist is empty by list_empty_careful(), which reads rdllist->prev. Thus all accesses to it need some protection to avoid store/load-tearing. Note INIT_LIST_HEAD_RCU() already has the annotation for both prev and next. Commit bf3b9f6372c4 ("epoll: Add busy poll support to epoll with socket fds.") added the first lockless ep_events_available(), and commit c5a282e9635e ("fs/epoll: reduce the scope of wq lock in epoll_wait()") made some ep_events_available() calls lockless and added single call under a lock, finally commit e59d3c64cba6 ("epoll: eliminate unnecessary lock for zero timeout") made the last ep_events_available() lockless. BUG: KCSAN: data-race in do_epoll_wait / do_epoll_wait write to 0xffff88810480c7d8 of 8 bytes by task 1802 on cpu 0: INIT_LIST_HEAD include/linux/list.h:38 [inline] list_splice_init include/linux/list.h:492 [inline] ep_start_scan fs/eventpoll.c:622 [inline] ep_send_events fs/eventpoll.c:1656 [inline] ep_poll fs/eventpoll.c:1806 [inline] do_epoll_wait+0x4eb/0xf40 fs/eventpoll.c:2234 do_epoll_pwait fs/eventpoll.c:2268 [inline] __do_sys_epoll_pwait fs/eventpoll.c:2281 [inline] __se_sys_epoll_pwait+0x12b/0x240 fs/eventpoll.c:2275 __x64_sys_epoll_pwait+0x74/0x80 fs/eventpoll.c:2275 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88810480c7d8 of 8 bytes by task 1799 on cpu 1: list_empty_careful include/linux/list.h:329 [inline] ep_events_available fs/eventpoll.c:381 [inline] ep_poll fs/eventpoll.c:1797 [inline] do_epoll_wait+0x279/0xf40 fs/eventpoll.c:2234 do_epoll_pwait fs/eventpoll.c:2268 [inline] __do_sys_epoll_pwait fs/eventpoll.c:2281 [inline] __se_sys_epoll_pwait+0x12b/0x240 fs/eventpoll.c:2275 __x64_sys_epoll_pwait+0x74/0x80 fs/eventpoll.c:2275 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffff88810480c7d0 -> 0xffff888103c15098 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 1799 Comm: syz-fuzzer Tainted: G W 5.17.0-rc7-syzkaller-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Link: https://lkml.kernel.org/r/20220322002653.33865-3-kuniyu@amazon.co.jp Fixes: e59d3c64cba6 ("epoll: eliminate unnecessary lock for zero timeout") Fixes: c5a282e9635e ("fs/epoll: reduce the scope of wq lock in epoll_wait()") Fixes: bf3b9f6372c4 ("epoll: Add busy poll support to epoll with socket fds.") Signed-off-by: Kuniyuki Iwashima Reported-by: syzbot+bdd6e38a1ed5ee58d8bd@syzkaller.appspotmail.com Cc: Al Viro , Andrew Morton Cc: Kuniyuki Iwashima Cc: Kuniyuki Iwashima Cc: "Soheil Hassas Yeganeh" Cc: Davidlohr Bueso Cc: "Sridhar Samudrala" Cc: Alexander Duyck Signed-off-by: Andrew Morton --- include/linux/list.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index dd6c2041d09c..d7d2bfa1a365 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -35,7 +35,7 @@ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); - list->prev = list; + WRITE_ONCE(list->prev, list); } #ifdef CONFIG_DEBUG_LIST @@ -306,7 +306,7 @@ static inline int list_empty(const struct list_head *head) static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); - entry->prev = entry; + WRITE_ONCE(entry->prev, entry); smp_store_release(&entry->next, entry); } @@ -326,7 +326,7 @@ static inline void list_del_init_careful(struct list_head *entry) static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); - return list_is_head(next, head) && (next == head->prev); + return list_is_head(next, head) && (next == READ_ONCE(head->prev)); } /** -- cgit v1.2.3 From a9866bef5171c859cfabc1155c594d28f194aa23 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 29 Apr 2022 14:38:02 -0700 Subject: ptrace: fix wrong comment of PT_DTRACE PT_DTRACE is only used on um now, fix the wrong comment. Link: https://lkml.kernel.org/r/1649240981-11024-3-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Tiezhu Yang Cc: Oleg Nesterov Signed-off-by: Andrew Morton --- include/linux/ptrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 15b3d176b6b4..db4509587d2c 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -30,7 +30,7 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, #define PT_SEIZED 0x00010000 /* SEIZE used, enable new behavior */ #define PT_PTRACED 0x00000001 -#define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */ +#define PT_DTRACE 0x00000002 /* delayed trace (used on um) */ #define PT_OPT_FLAG_SHIFT 3 /* PT_TRACE_* event enable flags */ -- cgit v1.2.3 From 0e0af57e0e91b304f36b7d1dba859e3c04094273 Mon Sep 17 00:00:00 2001 From: "Dr. Thomas Orgis" Date: Fri, 29 Apr 2022 14:38:03 -0700 Subject: taskstats: version 12 with thread group and exe info The task exit struct needs some crucial information to be able to provide an enhanced version of process and thread accounting. This change provides: 1. ac_tgid in additon to ac_pid 2. thread group execution walltime in ac_tgetime 3. flag AGROUP in ac_flag to indicate the last task in a thread group / process 4. device ID and inode of task's /proc/self/exe in ac_exe_dev and ac_exe_inode 5. tools/accounting/procacct as demonstrator When a task exits, taskstats are reported to userspace including the task's pid and ppid, but without the id of the thread group this task is part of. Without the tgid, the stats of single tasks cannot be correlated to each other as a thread group (process). The taskstats documentation suggests that on process exit a data set consisting of accumulated stats for the whole group is produced. But such an additional set of stats is only produced for actually multithreaded processes, not groups that had only one thread, and also those stats only contain data about delay accounting and not the more basic information about CPU and memory resource usage. Adding the AGROUP flag to be set when the last task of a group exited enables determination of process end also for single-threaded processes. My applicaton basically does enhanced process accounting with summed cputime, biggest maxrss, tasks per process. The data is not available with the traditional BSD process accounting (which is not designed to be extensible) and the taskstats interface allows more efficient on-the-fly grouping and summing of the stats, anyway, without intermediate disk writes. Furthermore, I do carry statistics on which exact program binary is used how often with associated resources, getting a picture on how important which parts of a collection of installed scientific software in different versions are, and how well they put load on the machine. This is enabled by providing information on /proc/self/exe for each task. I assume the two 64-bit fields for device ID and inode are more appropriate than the possibly large resolved path to keep the data volume down. Add the tgid to the stats to complete task identification, the flag AGROUP to mark the last task of a group, the group wallclock time, and inode-based identification of the associated executable file. Add tools/accounting/procacct.c as a simplified fork of getdelays.c to demonstrate process and thread accounting. [thomas.orgis@uni-hamburg.de: fix version number in comment] Link: https://lkml.kernel.org/r/20220405003601.7a5f6008@plasteblaster Link: https://lkml.kernel.org/r/20220331004106.64e5616b@plasteblaster Signed-off-by: Dr. Thomas Orgis Reviewed-by: Ismael Luceno Cc: Balbir Singh Cc: Eric W. Biederman Cc: xu xin Cc: Yang Yang Signed-off-by: Andrew Morton --- include/uapi/linux/acct.h | 3 ++- include/uapi/linux/taskstats.h | 24 +++++++++++++++++++++--- 2 files changed, 23 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/acct.h b/include/uapi/linux/acct.h index 985b89068591..0e591152aa8a 100644 --- a/include/uapi/linux/acct.h +++ b/include/uapi/linux/acct.h @@ -103,12 +103,13 @@ struct acct_v3 /* * accounting flags */ - /* bit set when the process ... */ + /* bit set when the process/task ... */ #define AFORK 0x01 /* ... executed fork, but did not exec */ #define ASU 0x02 /* ... used super-user privileges */ #define ACOMPAT 0x04 /* ... used compatibility mode (VAX only not used) */ #define ACORE 0x08 /* ... dumped core */ #define AXSIG 0x10 /* ... was killed by a signal */ +#define AGROUP 0x20 /* ... was the last task of the process (task group) */ #if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN) #define ACCT_BYTEORDER 0x80 /* accounting file is big endian */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 12327d32378f..736154171489 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 11 +#define TASKSTATS_VERSION 12 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -48,7 +48,8 @@ struct taskstats { __u32 ac_exitcode; /* Exit status */ /* The accounting flags of a task as defined in - * Defined values are AFORK, ASU, ACOMPAT, ACORE, and AXSIG. + * Defined values are AFORK, ASU, ACOMPAT, ACORE, AXSIG, and AGROUP. + * (AGROUP since version 12). */ __u8 ac_flag; /* Record flags */ __u8 ac_nice; /* task_nice */ @@ -173,9 +174,26 @@ struct taskstats { /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ - /* Delay waiting for memory compact */ + /* v11: Delay waiting for memory compact */ __u64 compact_count; __u64 compact_delay_total; + + /* v12 begin */ + __u32 ac_tgid; /* thread group ID */ + /* Thread group walltime up to now. This is total process walltime if + * AGROUP flag is set. + */ + __u64 ac_tgetime __attribute__((aligned(8))); + /* Lightweight information to identify process binary files. + * This leaves userspace to match this to a file system path, using + * MAJOR() and MINOR() macros to identify a device and mount point, + * the inode to identify the executable file. This is /proc/self/exe + * at the end, so matching the most recent exec(). Values are zero + * for kernel threads. + */ + __u64 ac_exe_dev; /* program binary device ID */ + __u64 ac_exe_inode; /* program binary inode number */ + /* v12 end */ }; -- cgit v1.2.3 From f94fd25cb0aaf77fd7453f31c5d394a1a68ecf60 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 28 Apr 2022 18:45:06 -0600 Subject: tcp: pass back data left in socket after receive This is currently done for CMSG_INQ, add an ability to do so via struct msghdr as well and have CMSG_INQ use that too. If the caller sets msghdr->msg_get_inq, then we'll pass back the hint in msghdr->msg_inq. Rearrange struct msghdr a bit so we can add this member while shrinking it at the same time. On a 64-bit build, it was 96 bytes before this change and 88 bytes afterwards. Reviewed-by: Eric Dumazet Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/650c22ca-cffc-0255-9a05-2413a1e20826@kernel.dk Signed-off-by: Jakub Kicinski --- include/linux/socket.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index 6f85f5d957ef..12085c9a8544 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -50,6 +50,9 @@ struct linger { struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ + + int msg_inq; /* output, data left in socket */ + struct iov_iter msg_iter; /* data */ /* @@ -62,8 +65,9 @@ struct msghdr { void __user *msg_control_user; }; bool msg_control_is_user : 1; - __kernel_size_t msg_controllen; /* ancillary data buffer length */ + bool msg_get_inq : 1;/* return INQ after receive */ unsigned int msg_flags; /* flags on received message */ + __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ }; -- cgit v1.2.3 From f548a12efd5ab97e6b1fb332e5634ce44b3d9328 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 26 Apr 2022 17:39:50 -0600 Subject: io_uring: return hint on whether more data is available after receive For now just use a CQE flag for this, with big CQE support we could return the actual number of bytes left. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 49d1f3994f8d..92d1799892b2 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -220,9 +220,11 @@ struct io_uring_cqe { * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries + * IORING_CQE_F_SOCK_NONEMPTY If set, more data to read after socket recv */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) +#define IORING_CQE_F_SOCK_NONEMPTY (1U << 2) enum { IORING_CQE_BUFFER_SHIFT = 16, -- cgit v1.2.3 From de32bc6aad09131a30b4a9a738e2bf2ba5a9a5aa Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 28 Apr 2022 11:58:44 +0100 Subject: net: inline sock_alloc_send_skb sock_alloc_send_skb() is simple and just proxying to another function, so we can inline it and cut associated overhead. Signed-off-by: Pavel Begunkov Signed-off-by: David S. Miller --- include/net/sock.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 663041b92c21..73063c88a249 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1823,11 +1823,17 @@ int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, int __user *optlen); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32); -struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, - int noblock, int *errcode); struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order); + +static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk, + unsigned long size, + int noblock, int *errcode) +{ + return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); +} + void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); -- cgit v1.2.3 From 657dd5f97b2ed16cdaa6339f42f9130240af1c04 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 28 Apr 2022 11:58:45 +0100 Subject: net: inline skb_zerocopy_iter_dgram skb_zerocopy_iter_dgram() is a small proxy function, inline it. For that, move __zerocopy_sg_from_iter into linux/skbuff.h Signed-off-by: Pavel Begunkov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 36 ++++++++++++++++++++++-------------- 1 file changed, 22 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dc4b3e1cf21b..3270cb72e4d8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -684,20 +684,6 @@ struct ubuf_info { int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); -struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); -struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, - struct ubuf_info *uarg); - -void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); - -void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success); - -int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); -int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, - struct msghdr *msg, int len, - struct ubuf_info *uarg); - /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -1679,6 +1665,28 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); +struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg); + +void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); + +void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, + bool success); + +int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length); + +static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, + struct msghdr *msg, int len) +{ + return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len); +} + +int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, + struct msghdr *msg, int len, + struct ubuf_info *uarg); + /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) -- cgit v1.2.3 From c526fd8f9f4f21cb83c0b1c9a1ee9c0ac9be9e2e Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 28 Apr 2022 11:58:46 +0100 Subject: net: inline dev_queue_xmit() Inline dev_queue_xmit() and dev_queue_xmit_accel(), they both are small proxy functions doing nothing but redirecting the control flow to __dev_queue_xmit(). Signed-off-by: Pavel Begunkov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b75ca2d095ae..4aba92a4042a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2940,10 +2940,20 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); -int dev_queue_xmit(struct sk_buff *skb); -int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); +int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); +static inline int dev_queue_xmit(struct sk_buff *skb) +{ + return __dev_queue_xmit(skb, NULL); +} + +static inline int dev_queue_xmit_accel(struct sk_buff *skb, + struct net_device *sb_dev) +{ + return __dev_queue_xmit(skb, sb_dev); +} + static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { int ret; -- cgit v1.2.3 From 2f187bfa6f35cc8bf1626bfc09449a09a6063ea1 Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Fri, 29 Apr 2022 14:30:36 -0700 Subject: net: ethernet: ocelot: remove the need for num_stats initializer There is a desire to share the oclot_stats_layout struct outside of the current vsc7514 driver. In order to do so, the length of the array needs to be known at compile time, and defined in the struct ocelot and struct felix_info. Since the array is defined in a .c file and would be declared in the header file via: extern struct ocelot_stat_layout[]; the size of the array will not be known at compile time to outside modules. To fix this, remove the need for defining the number of stats at compile time and allow this number to be determined at initialization. Signed-off-by: Colin Foster Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 9b4e6c78d0f4..5c4f57cfa785 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -105,6 +105,13 @@ #define REG_RESERVED_ADDR 0xffffffff #define REG_RESERVED(reg) REG(reg, REG_RESERVED_ADDR) +#define OCELOT_STAT_FLAG_END BIT(0) + +#define for_each_stat(ocelot, stat) \ + for ((stat) = ocelot->stats_layout; \ + !((stat)->flags & OCELOT_STAT_FLAG_END); \ + (stat)++) + enum ocelot_target { ANA = 1, QS, @@ -535,9 +542,12 @@ enum ocelot_ptp_pins { struct ocelot_stat_layout { u32 offset; + u32 flags; char name[ETH_GSTRING_LEN]; }; +#define OCELOT_STAT_END { .flags = OCELOT_STAT_FLAG_END } + struct ocelot_stats_region { struct list_head node; u32 offset; -- cgit v1.2.3 From 48cec73a891cca087fbc7791c4753784180991a9 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Fri, 29 Apr 2022 09:19:53 +0200 Subject: net: lan966x: Fix compilation error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Starting from the blamed commit, the lan966x build fails with the following compilation error: drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c:342:9: error: implicit declaration of function ‘ptp_find_pin_unlocked’ [-Werror=implicit-function-declaration] 342 | pin = ptp_find_pin_unlocked(phc->clock, PTP_PF_EXTTS, 0); The issue is that there is no stub function for ptp_find_pin_unlocked in case CONFIG_PTP_1588_CLOCK is not selected. Therefore add one. Reported-by: kernel test robot Fixes: f3d8e0a9c28ba0 ("net: lan966x: Add support for PTP_PF_EXTTS") Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 554454cb8693..e8cc8b6bbf50 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -321,6 +321,10 @@ static inline int ptp_clock_index(struct ptp_clock *ptp) static inline int ptp_find_pin(struct ptp_clock *ptp, enum ptp_pin_function func, unsigned int chan) { return -1; } +static inline int ptp_find_pin_unlocked(struct ptp_clock *ptp, + enum ptp_pin_function func, + unsigned int chan) +{ return -1; } static inline int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay) { return -EOPNOTSUPP; } -- cgit v1.2.3 From e788be95a57a9bebe446878ce9bf2750f6fe4974 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 28 Apr 2022 17:25:16 -0600 Subject: task_work: allow TWA_SIGNAL without a rescheduling IPI Some use cases don't always need an IPI when sending a TWA_SIGNAL notification. Add TWA_SIGNAL_NO_IPI, which is just like TWA_SIGNAL, except it doesn't send an IPI to the target task. It merely sets TIF_NOTIFY_SIGNAL and wakes up the task. This can be useful in avoiding a forceful transition to the kernel if the task is running in userspace. Depending on the task_work in question, it may be quite fine waiting for the next reschedule or kernel enter anyway, or the use case may even have other mechanisms for hinting to the task that a transition may be useful. This can drive more cooperative scheduling of task_work. Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/821f42b6-7d91-8074-8212-d34998097de4@kernel.dk Signed-off-by: Jens Axboe --- include/linux/sched/signal.h | 13 +++++++++++-- include/linux/task_work.h | 1 + 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..66b689f6cfcb 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -355,14 +355,23 @@ static inline void clear_notify_signal(void) smp_mb__after_atomic(); } +/* + * Returns 'true' if kick_process() is needed to force a transition from + * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. + */ +static inline bool __set_notify_signal(struct task_struct *task) +{ + return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE); +} + /* * Called to break out of interruptible wait loops, and enter the * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && - !wake_up_state(task, TASK_INTERRUPTIBLE)) + if (__set_notify_signal(task)) kick_process(task); } diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 897494b597ba..795ef5a68429 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -17,6 +17,7 @@ enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, + TWA_SIGNAL_NO_IPI, }; static inline bool task_work_pending(struct task_struct *task) -- cgit v1.2.3 From e1169f06d5bbdbc2b22ae4e3083a4bf75ae5ecee Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 25 Apr 2022 19:49:03 -0600 Subject: io_uring: use TWA_SIGNAL_NO_IPI if IORING_SETUP_COOP_TASKRUN is used If this is set, io_uring will never use an IPI to deliver a task_work notification. This can be used in the common case where a single task or thread communicates with the ring, and doesn't rely on io_uring_cqe_peek(). This provides a noticeable win in performance, both from eliminating the IPI itself, but also from avoiding interrupting the submitting task unnecessarily. Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/20220426014904.60384-6-axboe@kernel.dk Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 980d82eb196e..a84f29d657c3 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -102,6 +102,14 @@ enum { #define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */ #define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ #define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ +/* + * Cooperative task running. When requests complete, they often require + * forcing the submitter to transition to the kernel to complete. If this + * flag is set, work will be done when the task transitions anyway, rather + * than force an inter-processor interrupt reschedule. This avoids interrupting + * a task running in userspace, and saves an IPI. + */ +#define IORING_SETUP_COOP_TASKRUN (1U << 8) enum { IORING_OP_NOP, -- cgit v1.2.3 From ef060ea9e4fd3b763e7060a3af0a258d2d5d7c0d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 25 Apr 2022 19:49:04 -0600 Subject: io_uring: add IORING_SETUP_TASKRUN_FLAG If IORING_SETUP_COOP_TASKRUN is set to use cooperative scheduling for running task_work, then IORING_SETUP_TASKRUN_FLAG can be set so the application can tell if task_work is pending in the kernel for this ring. This allows use cases like io_uring_peek_cqe() to still function appropriately, or for the task to know when it would be useful to call io_uring_wait_cqe() to run pending events. Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/20220426014904.60384-7-axboe@kernel.dk Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index a84f29d657c3..fad63564678a 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -110,6 +110,12 @@ enum { * a task running in userspace, and saves an IPI. */ #define IORING_SETUP_COOP_TASKRUN (1U << 8) +/* + * If COOP_TASKRUN is set, get notified if task work is available for + * running and a kernel transition would be needed to run it. This sets + * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. + */ +#define IORING_SETUP_TASKRUN_FLAG (1U << 9) enum { IORING_OP_NOP, @@ -256,6 +262,7 @@ struct io_sqring_offsets { */ #define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */ #define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */ +#define IORING_SQ_TASKRUN (1U << 2) /* task should enter the kernel */ struct io_cqring_offsets { __u32 head; -- cgit v1.2.3 From d664e399128bd78b905ff480917e2c2d4949e101 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Apr 2022 15:31:02 +0200 Subject: sched: Fix missing prototype warnings A W=1 build emits more than a dozen missing prototype warnings related to scheduler and scheduler specific includes. Reported-by: kernel test robot Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220413133024.249118058@linutronix.de --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index fc74ea2578b7..a27316f5f737 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2388,4 +2388,6 @@ static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } #endif +extern void sched_set_stop_task(int cpu, struct task_struct *stop); + #endif -- cgit v1.2.3 From 1a90bfd220201fbe050dfc15deaac20ca5f15638 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Apr 2022 15:31:05 +0200 Subject: smp: Make softirq handling RT safe in flush_smp_call_function_queue() flush_smp_call_function_queue() invokes do_softirq() which is not available on PREEMPT_RT. flush_smp_call_function_queue() is invoked from the idle task and the migration task with preemption or interrupts disabled. So RT kernels cannot process soft interrupts in that context as that has to acquire 'sleeping spinlocks' which is not possible with preemption or interrupts disabled and forbidden from the idle task anyway. The currently known SMP function call which raises a soft interrupt is in the block layer, but this functionality is not enabled on RT kernels due to latency and performance reasons. RT could wake up ksoftirqd unconditionally, but this wants to be avoided if there were soft interrupts pending already when this is invoked in the context of the migration task. The migration task might have preempted a threaded interrupt handler which raised a soft interrupt, but did not reach the local_bh_enable() to process it. The "running" ksoftirqd might prevent the handling in the interrupt thread context which is causing latency issues. Add a new function which handles this case explicitely for RT and falls back to do_softirq() on !RT kernels. In the RT case this warns when one of the flushed SMP function calls raised a soft interrupt so this can be investigated. [ tglx: Moved the RT part out of SMP code ] Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/YgKgL6aPj8aBES6G@linutronix.de Link: https://lore.kernel.org/r/20220413133024.356509586@linutronix.de --- include/linux/interrupt.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index f40754caaefa..a49fe8d88676 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -607,6 +607,15 @@ struct softirq_action asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); +#ifdef CONFIG_PREEMPT_RT +extern void do_softirq_post_smp_call_flush(unsigned int was_pending); +#else +static inline void do_softirq_post_smp_call_flush(unsigned int unused) +{ + do_softirq(); +} +#endif + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); -- cgit v1.2.3 From 47f753c1108e287edb3e27fad8a7511a9d55578e Mon Sep 17 00:00:00 2001 From: Tan Tee Min Date: Fri, 29 Apr 2022 19:58:07 +0800 Subject: net: stmmac: disable Split Header (SPH) for Intel platforms Based on DesignWare Ethernet QoS datasheet, we are seeing the limitation of Split Header (SPH) feature is not supported for Ipv4 fragmented packet. This SPH limitation will cause ping failure when the packets size exceed the MTU size. For example, the issue happens once the basic ping packet size is larger than the configured MTU size and the data is lost inside the fragmented packet, replaced by zeros/corrupted values, and leads to ping fail. So, disable the Split Header for Intel platforms. v2: Add fixes tag in commit message. Fixes: 67afd6d1cfdf("net: stmmac: Add Split Header support and enable it in XGMAC cores") Cc: # 5.10.x Suggested-by: Ong, Boon Leong Signed-off-by: Mohammad Athari Bin Ismail Signed-off-by: Wong Vee Khee Signed-off-by: Tan Tee Min Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 24eea1b05ca2..29917850f079 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -270,5 +270,6 @@ struct plat_stmmacenet_data { int msi_rx_base_vec; int msi_tx_base_vec; bool use_phy_wol; + bool sph_disable; }; #endif -- cgit v1.2.3 From 9bd1d9a0d8bb1a549831fd98fcc3105960f7068b Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Sun, 1 May 2022 16:55:06 +0200 Subject: soc: apple: Add RTKit IPC library Apple SoCs such as the M1 come with multiple embedded co-processors running proprietary firmware. Communication with those is established over a simple mailbox using the RTKit IPC protocol. This cannot be implemented inside the mailbox subsystem since on top of communication over channels we also need support for starting, hibernating and resetting these co-processors. We also need to handle shared memory allocations differently depending on the co-processor and don't want to split that across multiple drivers. Reviewed-by: Arnd Bergmann Signed-off-by: Sven Peter --- include/linux/soc/apple/rtkit.h | 155 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 155 insertions(+) create mode 100644 include/linux/soc/apple/rtkit.h (limited to 'include') diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h new file mode 100644 index 000000000000..88eb832eac7b --- /dev/null +++ b/include/linux/soc/apple/rtkit.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ +/* + * Apple RTKit IPC Library + * Copyright (C) The Asahi Linux Contributors + * + * Apple's SoCs come with various co-processors running their RTKit operating + * system. This protocol library is used by client drivers to use the + * features provided by them. + */ +#ifndef _LINUX_APPLE_RTKIT_H_ +#define _LINUX_APPLE_RTKIT_H_ + +#include +#include +#include + +/* + * Struct to represent implementation-specific RTKit operations. + * + * @buffer: Shared memory buffer allocated inside normal RAM. + * @iomem: Shared memory buffer controlled by the co-processors. + * @size: Size of the shared memory buffer. + * @iova: Device VA of shared memory buffer. + * @is_mapped: Shared memory buffer is managed by the co-processor. + */ + +struct apple_rtkit_shmem { + void *buffer; + void __iomem *iomem; + size_t size; + dma_addr_t iova; + bool is_mapped; +}; + +/* + * Struct to represent implementation-specific RTKit operations. + * + * @crashed: Called when the co-processor has crashed. Runs in process + * context. + * @recv_message: Function called when a message from RTKit is received + * on a non-system endpoint. Called from a worker thread. + * @recv_message_early: + * Like recv_message, but called from atomic context. It + * should return true if it handled the message. If it + * returns false, the message will be passed on to the + * worker thread. + * @shmem_setup: Setup shared memory buffer. If bfr.is_iomem is true the + * buffer is managed by the co-processor and needs to be mapped. + * Otherwise the buffer is managed by Linux and needs to be + * allocated. If not specified dma_alloc_coherent is used. + * Called in process context. + * @shmem_destroy: Undo the shared memory buffer setup in shmem_setup. If not + * specified dma_free_coherent is used. Called in process + * context. + */ +struct apple_rtkit_ops { + void (*crashed)(void *cookie); + void (*recv_message)(void *cookie, u8 endpoint, u64 message); + bool (*recv_message_early)(void *cookie, u8 endpoint, u64 message); + int (*shmem_setup)(void *cookie, struct apple_rtkit_shmem *bfr); + void (*shmem_destroy)(void *cookie, struct apple_rtkit_shmem *bfr); +}; + +struct apple_rtkit; + +/* + * Initializes the internal state required to handle RTKit. This + * should usually be called within _probe. + * + * @dev: Pointer to the device node this coprocessor is assocated with + * @cookie: opaque cookie passed to all functions defined in rtkit_ops + * @mbox_name: mailbox name used to communicate with the co-processor + * @mbox_idx: mailbox index to be used if mbox_name is NULL + * @ops: pointer to rtkit_ops to be used for this co-processor + */ +struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie, + const char *mbox_name, int mbox_idx, + const struct apple_rtkit_ops *ops); + +/* + * Reinitialize internal structures. Must only be called with the co-processor + * is held in reset. + */ +int apple_rtkit_reinit(struct apple_rtkit *rtk); + +/* + * Handle RTKit's boot process. Should be called after the CPU of the + * co-processor has been started. + */ +int apple_rtkit_boot(struct apple_rtkit *rtk); + +/* + * Quiesce the co-processor. + */ +int apple_rtkit_quiesce(struct apple_rtkit *rtk); + +/* + * Wake the co-processor up from hibernation mode. + */ +int apple_rtkit_wake(struct apple_rtkit *rtk); + +/* + * Shutdown the co-processor + */ +int apple_rtkit_shutdown(struct apple_rtkit *rtk); + +/* + * Checks if RTKit is running and ready to handle messages. + */ +bool apple_rtkit_is_running(struct apple_rtkit *rtk); + +/* + * Checks if RTKit has crashed. + */ +bool apple_rtkit_is_crashed(struct apple_rtkit *rtk); + +/* + * Starts an endpoint. Must be called after boot but before any messages can be + * sent or received from that endpoint. + */ +int apple_rtkit_start_ep(struct apple_rtkit *rtk, u8 endpoint); + +/* + * Send a message to the given endpoint. + * + * @rtk: RTKit reference + * @ep: target endpoint + * @message: message to be sent + * @completeion: will be completed once the message has been submitted + * to the hardware FIFO. Can be NULL. + * @atomic: if set to true this function can be called from atomic + * context. + */ +int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message, + struct completion *completion, bool atomic); + +/* + * Send a message to the given endpoint and wait until it has been submitted + * to the hardware FIFO. + * Will return zero on success and a negative error code on failure + * (e.g. -ETIME when the message couldn't be written within the given + * timeout) + * + * @rtk: RTKit reference + * @ep: target endpoint + * @message: message to be sent + * @timeout: timeout in milliseconds to allow the message transmission + * to be completed + * @atomic: if set to true this function can be called from atomic + * context. + */ +int apple_rtkit_send_message_wait(struct apple_rtkit *rtk, u8 ep, u64 message, + unsigned long timeout, bool atomic); + +#endif /* _LINUX_APPLE_RTKIT_H_ */ -- cgit v1.2.3 From 3254e0b9eb5649ffaa48717ebc9c593adc4ee6a9 Mon Sep 17 00:00:00 2001 From: Alexandru Tachici Date: Fri, 29 Apr 2022 18:34:31 +0300 Subject: ethtool: Add 10base-T1L link mode entry Add entry for the 10base-T1L full duplex mode. Reviewed-by: Andrew Lunn Reviewed-by: Oleksij Rempel Signed-off-by: Alexandru Tachici Signed-off-by: David S. Miller --- include/linux/phy.h | 2 +- include/uapi/linux/ethtool.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 36ca2b5c2253..b12af9e2f389 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -65,7 +65,7 @@ extern const int phy_basic_ports_array[3]; extern const int phy_fibre_port_array[1]; extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; -extern const int phy_basic_t1_features_array[2]; +extern const int phy_basic_t1_features_array[3]; extern const int phy_gbit_features_array[2]; extern const int phy_10gbit_features_array[1]; diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 7bc4b8def12c..e0f0ee9bc89e 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1691,6 +1691,7 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT = 89, ETHTOOL_LINK_MODE_100baseFX_Half_BIT = 90, ETHTOOL_LINK_MODE_100baseFX_Full_BIT = 91, + ETHTOOL_LINK_MODE_10baseT1L_Full_BIT = 92, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS }; -- cgit v1.2.3 From 909b4f2bf764a903e9183111368f1509f9b40e6d Mon Sep 17 00:00:00 2001 From: Alexandru Tachici Date: Fri, 29 Apr 2022 18:34:32 +0300 Subject: net: phy: Add 10-BaseT1L registers The 802.3gc specification defines the 10-BaseT1L link mode for ethernet trafic on twisted wire pair. PMA status register can be used to detect if the phy supports 2.4 V TX level and PCS control register can be used to enable/disable PCS level loopback. Reviewed-by: Andrew Lunn Signed-off-by: Alexandru Tachici Signed-off-by: David S. Miller --- include/uapi/linux/mdio.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index c54e6eae5366..0b2eba36dd7c 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -67,6 +67,9 @@ #define MDIO_PCS_10GBRT_STAT2 33 /* 10GBASE-R/-T PCS status 2 */ #define MDIO_AN_10GBT_CTRL 32 /* 10GBASE-T auto-negotiation control */ #define MDIO_AN_10GBT_STAT 33 /* 10GBASE-T auto-negotiation status */ +#define MDIO_B10L_PMA_CTRL 2294 /* 10BASE-T1L PMA control */ +#define MDIO_PMA_10T1L_STAT 2295 /* 10BASE-T1L PMA status */ +#define MDIO_PCS_10T1L_CTRL 2278 /* 10BASE-T1L PCS control */ /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */ #define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */ @@ -268,6 +271,28 @@ #define MDIO_AN_10GBT_STAT_MS 0x4000 /* Master/slave config */ #define MDIO_AN_10GBT_STAT_MSFLT 0x8000 /* Master/slave config fault */ +/* 10BASE-T1L PMA control */ +#define MDIO_PMA_10T1L_CTRL_LB_EN 0x0001 /* Enable loopback mode */ +#define MDIO_PMA_10T1L_CTRL_EEE_EN 0x0400 /* Enable EEE mode */ +#define MDIO_PMA_10T1L_CTRL_LOW_POWER 0x0800 /* Low-power mode */ +#define MDIO_PMA_10T1L_CTRL_2V4_EN 0x1000 /* Enable 2.4 Vpp operating mode */ +#define MDIO_PMA_10T1L_CTRL_TX_DIS 0x4000 /* Transmit disable */ +#define MDIO_PMA_10T1L_CTRL_PMA_RST 0x8000 /* MA reset */ + +/* 10BASE-T1L PMA status register. */ +#define MDIO_PMA_10T1L_STAT_LINK 0x0001 /* PMA receive link up */ +#define MDIO_PMA_10T1L_STAT_FAULT 0x0002 /* Fault condition detected */ +#define MDIO_PMA_10T1L_STAT_POLARITY 0x0004 /* Receive polarity is reversed */ +#define MDIO_PMA_10T1L_STAT_RECV_FAULT 0x0200 /* Able to detect fault on receive path */ +#define MDIO_PMA_10T1L_STAT_EEE 0x0400 /* PHY has EEE ability */ +#define MDIO_PMA_10T1L_STAT_LOW_POWER 0x0800 /* PMA has low-power ability */ +#define MDIO_PMA_10T1L_STAT_2V4_ABLE 0x1000 /* PHY has 2.4 Vpp operating mode ability */ +#define MDIO_PMA_10T1L_STAT_LB_ABLE 0x2000 /* PHY has loopback ability */ + +/* 10BASE-T1L PCS control register. */ +#define MDIO_PCS_10T1L_CTRL_LB 0x4000 /* Enable PCS level loopback mode */ +#define MDIO_PCS_10T1L_CTRL_RESET 0x8000 /* PCS reset */ + /* EEE Supported/Advertisement/LP Advertisement registers. * * EEE capability Register (3.20), Advertisement (7.60) and -- cgit v1.2.3 From 1b020e448e0fb67bcb04ee0f778d413045f965d3 Mon Sep 17 00:00:00 2001 From: Alexandru Tachici Date: Fri, 29 Apr 2022 18:34:33 +0300 Subject: net: phy: Add BaseT1 auto-negotiation registers Added BASE-T1 AN advertisement register (Registers 7.514, 7.515, and 7.516) and BASE-T1 AN LP Base Page ability register (Registers 7.517, 7.518, and 7.519). Reviewed-by: Andrew Lunn Signed-off-by: Alexandru Tachici Signed-off-by: David S. Miller --- include/uapi/linux/mdio.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 0b2eba36dd7c..fa3515257f54 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -70,6 +70,14 @@ #define MDIO_B10L_PMA_CTRL 2294 /* 10BASE-T1L PMA control */ #define MDIO_PMA_10T1L_STAT 2295 /* 10BASE-T1L PMA status */ #define MDIO_PCS_10T1L_CTRL 2278 /* 10BASE-T1L PCS control */ +#define MDIO_AN_T1_CTRL 512 /* BASE-T1 AN control */ +#define MDIO_AN_T1_STAT 513 /* BASE-T1 AN status */ +#define MDIO_AN_T1_ADV_L 514 /* BASE-T1 AN advertisement register [15:0] */ +#define MDIO_AN_T1_ADV_M 515 /* BASE-T1 AN advertisement register [31:16] */ +#define MDIO_AN_T1_ADV_H 516 /* BASE-T1 AN advertisement register [47:32] */ +#define MDIO_AN_T1_LP_L 517 /* BASE-T1 AN LP Base Page ability register [15:0] */ +#define MDIO_AN_T1_LP_M 518 /* BASE-T1 AN LP Base Page ability register [31:16] */ +#define MDIO_AN_T1_LP_H 519 /* BASE-T1 AN LP Base Page ability register [47:32] */ /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */ #define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */ @@ -293,6 +301,38 @@ #define MDIO_PCS_10T1L_CTRL_LB 0x4000 /* Enable PCS level loopback mode */ #define MDIO_PCS_10T1L_CTRL_RESET 0x8000 /* PCS reset */ +/* BASE-T1 auto-negotiation advertisement register [15:0] */ +#define MDIO_AN_T1_ADV_L_PAUSE_CAP ADVERTISE_PAUSE_CAP +#define MDIO_AN_T1_ADV_L_PAUSE_ASYM ADVERTISE_PAUSE_ASYM +#define MDIO_AN_T1_ADV_L_FORCE_MS 0x1000 /* Force Master/slave Configuration */ +#define MDIO_AN_T1_ADV_L_REMOTE_FAULT ADVERTISE_RFAULT +#define MDIO_AN_T1_ADV_L_ACK ADVERTISE_LPACK +#define MDIO_AN_T1_ADV_L_NEXT_PAGE_REQ ADVERTISE_NPAGE + +/* BASE-T1 auto-negotiation advertisement register [31:16] */ +#define MDIO_AN_T1_ADV_M_B10L 0x4000 /* device is compatible with 10BASE-T1L */ +#define MDIO_AN_T1_ADV_M_MST 0x0010 /* advertise master preference */ + +/* BASE-T1 auto-negotiation advertisement register [47:32] */ +#define MDIO_AN_T1_ADV_H_10L_TX_HI_REQ 0x1000 /* 10BASE-T1L High Level Transmit Request */ +#define MDIO_AN_T1_ADV_H_10L_TX_HI 0x2000 /* 10BASE-T1L High Level Transmit Ability */ + +/* BASE-T1 AN LP Base Page ability register [15:0] */ +#define MDIO_AN_T1_LP_L_PAUSE_CAP LPA_PAUSE_CAP +#define MDIO_AN_T1_LP_L_PAUSE_ASYM LPA_PAUSE_ASYM +#define MDIO_AN_T1_LP_L_FORCE_MS 0x1000 /* LP Force Master/slave Configuration */ +#define MDIO_AN_T1_LP_L_REMOTE_FAULT LPA_RFAULT +#define MDIO_AN_T1_LP_L_ACK LPA_LPACK +#define MDIO_AN_T1_LP_L_NEXT_PAGE_REQ LPA_NPAGE + +/* BASE-T1 AN LP Base Page ability register [31:16] */ +#define MDIO_AN_T1_LP_M_MST 0x0010 /* LP master preference */ +#define MDIO_AN_T1_LP_M_B10L 0x4000 /* LP is compatible with 10BASE-T1L */ + +/* BASE-T1 AN LP Base Page ability register [47:32] */ +#define MDIO_AN_T1_LP_H_10L_TX_HI_REQ 0x1000 /* 10BASE-T1L High Level LP Transmit Request */ +#define MDIO_AN_T1_LP_H_10L_TX_HI 0x2000 /* 10BASE-T1L High Level LP Transmit Ability */ + /* EEE Supported/Advertisement/LP Advertisement registers. * * EEE capability Register (3.20), Advertisement (7.60) and -- cgit v1.2.3 From 3da8ffd8545f62fec85a48a3c637b2f427974f11 Mon Sep 17 00:00:00 2001 From: Alexandru Tachici Date: Fri, 29 Apr 2022 18:34:34 +0300 Subject: net: phy: Add 10BASE-T1L support in phy-c45 This patch is needed because the BASE-T1 uses different registers for status, control and advertisement to those already employed in the existing phy-c45 functions. Where required, genphy_c45 functions will now check whether the device supports BASE-T1 and use the specific registers instead: 45.2.7.19 BASE-T1 AN control register, 45.2.7.20 BASE-T1 AN status, 45.2.7.21 BASE-T1 AN advertisement register, 45.2.7.22 BASE-T1 AN LP Base Page ability register, 45.2.1.185 BASE-T1 PMA/PMD control register. Tested-by: Oleksij Rempel Signed-off-by: Alexandru Tachici Signed-off-by: David S. Miller --- include/linux/mdio.h | 70 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 3 ++ include/uapi/linux/mdio.h | 10 +++++++ 3 files changed, 83 insertions(+) (limited to 'include') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index ecac96d52e01..00177567cfef 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -340,6 +340,76 @@ static inline void mii_10gbt_stat_mod_linkmode_lpa_t(unsigned long *advertising, advertising, lpa & MDIO_AN_10GBT_STAT_LP10G); } +/** + * mii_t1_adv_l_mod_linkmode_t + * @advertising: target the linkmode advertisement settings + * @lpa: value of the BASE-T1 Autonegotiation Advertisement [15:0] Register + * + * A small helper function that translates BASE-T1 Autonegotiation + * Advertisement [15:0] Register bits to linkmode advertisement settings. + * Other bits in advertising aren't changed. + */ +static inline void mii_t1_adv_l_mod_linkmode_t(unsigned long *advertising, u32 lpa) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising, + lpa & MDIO_AN_T1_ADV_L_PAUSE_CAP); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising, + lpa & MDIO_AN_T1_ADV_L_PAUSE_ASYM); +} + +/** + * mii_t1_adv_m_mod_linkmode_t + * @advertising: target the linkmode advertisement settings + * @lpa: value of the BASE-T1 Autonegotiation Advertisement [31:16] Register + * + * A small helper function that translates BASE-T1 Autonegotiation + * Advertisement [31:16] Register bits to linkmode advertisement settings. + * Other bits in advertising aren't changed. + */ +static inline void mii_t1_adv_m_mod_linkmode_t(unsigned long *advertising, u32 lpa) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, + advertising, lpa & MDIO_AN_T1_ADV_M_B10L); +} + +/** + * linkmode_adv_to_mii_t1_adv_l_t + * @advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * BASE-T1 Autonegotiation Advertisement [15:0] Register. + */ +static inline u32 linkmode_adv_to_mii_t1_adv_l_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising)) + result |= MDIO_AN_T1_ADV_L_PAUSE_CAP; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising)) + result |= MDIO_AN_T1_ADV_L_PAUSE_ASYM; + + return result; +} + +/** + * linkmode_adv_to_mii_t1_adv_m_t + * @advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * BASE-T1 Autonegotiation Advertisement [31:16] Register. + */ +static inline u32 linkmode_adv_to_mii_t1_adv_m_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, advertising)) + result |= MDIO_AN_T1_ADV_M_B10L; + + return result; +} + int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, diff --git a/include/linux/phy.h b/include/linux/phy.h index b12af9e2f389..2d12054932ba 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -570,6 +570,7 @@ struct macsec_ops; * @autoneg_complete: Flag auto negotiation of the link has completed * @mdix: Current crossover * @mdix_ctrl: User setting of crossover + * @pma_extable: Cached value of PMA/PMD Extended Abilities Register * @interrupts: Flag interrupts have been enabled * @interface: enum phy_interface_t value * @skb: Netlink message for cable diagnostics @@ -698,6 +699,8 @@ struct phy_device { u8 mdix; u8 mdix_ctrl; + int pma_extable; + void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index fa3515257f54..75b7257a51e1 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -70,6 +70,7 @@ #define MDIO_B10L_PMA_CTRL 2294 /* 10BASE-T1L PMA control */ #define MDIO_PMA_10T1L_STAT 2295 /* 10BASE-T1L PMA status */ #define MDIO_PCS_10T1L_CTRL 2278 /* 10BASE-T1L PCS control */ +#define MDIO_PMA_PMD_BT1 18 /* BASE-T1 PMA/PMD extended ability */ #define MDIO_AN_T1_CTRL 512 /* BASE-T1 AN control */ #define MDIO_AN_T1_STAT 513 /* BASE-T1 AN status */ #define MDIO_AN_T1_ADV_L 514 /* BASE-T1 AN advertisement register [15:0] */ @@ -78,6 +79,7 @@ #define MDIO_AN_T1_LP_L 517 /* BASE-T1 AN LP Base Page ability register [15:0] */ #define MDIO_AN_T1_LP_M 518 /* BASE-T1 AN LP Base Page ability register [31:16] */ #define MDIO_AN_T1_LP_H 519 /* BASE-T1 AN LP Base Page ability register [47:32] */ +#define MDIO_PMA_PMD_BT1_CTRL 2100 /* BASE-T1 PMA/PMD control register */ /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */ #define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */ @@ -170,6 +172,7 @@ #define MDIO_PMA_CTRL2_10BT 0x000f /* 10BASE-T type */ #define MDIO_PMA_CTRL2_2_5GBT 0x0030 /* 2.5GBaseT type */ #define MDIO_PMA_CTRL2_5GBT 0x0031 /* 5GBaseT type */ +#define MDIO_PMA_CTRL2_BASET1 0x003D /* BASE-T1 type */ #define MDIO_PCS_CTRL2_TYPE 0x0003 /* PCS type selection */ #define MDIO_PCS_CTRL2_10GBR 0x0000 /* 10GBASE-R type */ #define MDIO_PCS_CTRL2_10GBX 0x0001 /* 10GBASE-X type */ @@ -223,6 +226,7 @@ #define MDIO_PMA_EXTABLE_1000BKX 0x0040 /* 1000BASE-KX ability */ #define MDIO_PMA_EXTABLE_100BTX 0x0080 /* 100BASE-TX ability */ #define MDIO_PMA_EXTABLE_10BT 0x0100 /* 10BASE-T ability */ +#define MDIO_PMA_EXTABLE_BT1 0x0800 /* BASE-T1 ability */ #define MDIO_PMA_EXTABLE_NBT 0x4000 /* 2.5/5GBASE-T ability */ /* PHY XGXS lane state register. */ @@ -301,6 +305,9 @@ #define MDIO_PCS_10T1L_CTRL_LB 0x4000 /* Enable PCS level loopback mode */ #define MDIO_PCS_10T1L_CTRL_RESET 0x8000 /* PCS reset */ +/* BASE-T1 PMA/PMD extended ability register. */ +#define MDIO_PMA_PMD_BT1_B10L_ABLE 0x0004 /* 10BASE-T1L Ability */ + /* BASE-T1 auto-negotiation advertisement register [15:0] */ #define MDIO_AN_T1_ADV_L_PAUSE_CAP ADVERTISE_PAUSE_CAP #define MDIO_AN_T1_ADV_L_PAUSE_ASYM ADVERTISE_PAUSE_ASYM @@ -333,6 +340,9 @@ #define MDIO_AN_T1_LP_H_10L_TX_HI_REQ 0x1000 /* 10BASE-T1L High Level LP Transmit Request */ #define MDIO_AN_T1_LP_H_10L_TX_HI 0x2000 /* 10BASE-T1L High Level LP Transmit Ability */ +/* BASE-T1 PMA/PMD control register */ +#define MDIO_PMA_PMD_BT1_CTRL_CFG_MST 0x4000 /* MASTER-SLAVE config value */ + /* EEE Supported/Advertisement/LP Advertisement registers. * * EEE capability Register (3.20), Advertisement (7.60) and -- cgit v1.2.3 From 246d921646c071b878480997c294db6c83215b06 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 23 Nov 2021 13:37:52 -0500 Subject: fs-verity: define a function to return the integrity protected file digest Define a function named fsverity_get_digest() to return the verity file digest and the associated hash algorithm (enum hash_algo). This assumes that before calling fsverity_get_digest() the file must have been opened, which is even true for the IMA measure/appraise on file open policy rule use case (func=FILE_CHECK). do_open() calls vfs_open() immediately prior to ima_file_check(). Acked-by: Eric Biggers Signed-off-by: Mimi Zohar --- include/linux/fsverity.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index a7afc800bd8d..7af030fa3c36 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -12,8 +12,16 @@ #define _LINUX_FSVERITY_H #include +#include +#include #include +/* + * Largest digest size among all hash algorithms supported by fs-verity. + * Currently assumed to be <= size of fsverity_descriptor::root_hash. + */ +#define FS_VERITY_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE + /* Verity operations for filesystems */ struct fsverity_operations { @@ -131,6 +139,9 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *arg); /* measure.c */ int fsverity_ioctl_measure(struct file *filp, void __user *arg); +int fsverity_get_digest(struct inode *inode, + u8 digest[FS_VERITY_MAX_DIGEST_SIZE], + enum hash_algo *alg); /* open.c */ @@ -170,6 +181,13 @@ static inline int fsverity_ioctl_measure(struct file *filp, void __user *arg) return -EOPNOTSUPP; } +static inline int fsverity_get_digest(struct inode *inode, + u8 digest[FS_VERITY_MAX_DIGEST_SIZE], + enum hash_algo *alg) +{ + return -EOPNOTSUPP; +} + /* open.c */ static inline int fsverity_file_open(struct inode *inode, struct file *filp) -- cgit v1.2.3 From 57b8280a0a4163545b532ae516c2dd5c9b295ea3 Mon Sep 17 00:00:00 2001 From: Abhinav Kumar Date: Tue, 26 Apr 2022 07:41:18 -0700 Subject: drm: allow passing possible_crtcs to drm_writeback_connector_init() Clients of drm_writeback_connector_init() initialize the possible_crtcs and then invoke the call to this API. To simplify things, allow passing possible_crtcs as a parameter to drm_writeback_connector_init() and make changes to the other drm drivers to make them compatible with this change. changes in v2: - split the changes according to their functionality changes in v3: - allow passing possible_crtcs for existing users of drm_writeback_connector_init() - squash the vendor changes into the same commit so that each patch in the series can compile individually changes in v4: - keep only changes related to possible_crtcs - add line breaks after ARRAY_SIZE - stop using temporary variables for possible_crtcs changes in v5: - None changes in v6: - None changes in v7: - wrap long lines to match the coding style of existing drivers - Fix indentation and remove parenthesis where not needed - use u32 instead of uint32_t for possible_crtcs Signed-off-by: Abhinav Kumar Acked-by: Liviu Dudau Reviewed-by: Dmitry Baryshkov Reviewed-by: Laurent Pinchart Patchwork: https://patchwork.freedesktop.org/patch/483501/ Link: https://lore.kernel.org/r/1650984096-9964-2-git-send-email-quic_abhinavk@quicinc.com Signed-off-by: Dmitry Baryshkov --- include/drm/drm_writeback.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h index 9697d2714d2a..5d9263fdbd84 100644 --- a/include/drm/drm_writeback.h +++ b/include/drm/drm_writeback.h @@ -150,7 +150,8 @@ int drm_writeback_connector_init(struct drm_device *dev, struct drm_writeback_connector *wb_connector, const struct drm_connector_funcs *con_funcs, const struct drm_encoder_helper_funcs *enc_helper_funcs, - const u32 *formats, int n_formats); + const u32 *formats, int n_formats, + u32 possible_crtcs); int drm_writeback_set_fb(struct drm_connector_state *conn_state, struct drm_framebuffer *fb); -- cgit v1.2.3 From 7933aecffa28a1746997436426b5df767b2df925 Mon Sep 17 00:00:00 2001 From: Abhinav Kumar Date: Tue, 26 Apr 2022 07:41:19 -0700 Subject: drm: introduce drm_writeback_connector_init_with_encoder() API For vendors drivers which pass an already allocated and initialized encoder especially for cases where the encoder hardware is shared OR the writeback encoder shares the resources with the rest of the display pipeline introduce a new API, drm_writeback_connector_init_with_encoder() which expects an initialized encoder as a parameter and only sets up the writeback connector. changes in v5: - fix the encoder doc to indicate that its not valid for users of drm_writeback_connector_init_with_encoder() Reviewed-by: Liviu Dudau Signed-off-by: Abhinav Kumar Reviewed-by: Dmitry Baryshkov Reviewed-by: Laurent Pinchart Patchwork: https://patchwork.freedesktop.org/patch/483500/ Link: https://lore.kernel.org/r/1650984096-9964-3-git-send-email-quic_abhinavk@quicinc.com Signed-off-by: Dmitry Baryshkov --- include/drm/drm_writeback.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h index 5d9263fdbd84..17e576c80169 100644 --- a/include/drm/drm_writeback.h +++ b/include/drm/drm_writeback.h @@ -30,6 +30,8 @@ struct drm_writeback_connector { * @drm_writeback_connector control the behaviour of the @encoder * by passing the @enc_funcs parameter to drm_writeback_connector_init() * function. + * For users of drm_writeback_connector_init_with_encoder(), this field + * is not valid as the encoder is managed within their drivers. */ struct drm_encoder encoder; @@ -153,6 +155,12 @@ int drm_writeback_connector_init(struct drm_device *dev, const u32 *formats, int n_formats, u32 possible_crtcs); +int drm_writeback_connector_init_with_encoder(struct drm_device *dev, + struct drm_writeback_connector *wb_connector, + struct drm_encoder *enc, + const struct drm_connector_funcs *con_funcs, const u32 *formats, + int n_formats); + int drm_writeback_set_fb(struct drm_connector_state *conn_state, struct drm_framebuffer *fb); -- cgit v1.2.3 From 8cf9e1210adf49cd83d11e2b1984540cf0e0be71 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 28 Apr 2022 17:59:39 +0200 Subject: mm: slab: fix comment for ARCH_KMALLOC_MINALIGN The comment next to the ARCH_KMALLOC_MINALIGN definition says that ARCH_KMALLOC_MINALIGN can be defined in arch headers. This is incorrect: it's actually ARCH_DMA_MINALIGN that can be defined there. Fix the comment. Signed-off-by: Andrey Konovalov Acked-by: David Rientjes Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/fe1ca7a25a054b61d1038686d07569416e287e7b.1651161548.git.andreyknvl@google.com --- include/linux/slab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 11ceddcae9f4..8c090599fc21 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -197,7 +197,7 @@ void kmem_dump_obj(void *object); /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. - * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. + * Setting ARCH_DMA_MINALIGN in arch headers allows that. */ #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -- cgit v1.2.3 From 154036a3b3f39cb17fc65511011f4c4024846e91 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 28 Apr 2022 17:59:40 +0200 Subject: mm: slab: fix comment for __assume_kmalloc_alignment The comment next to the __assume_kmalloc_alignment definition is not precise: kmalloc relies on kmem_cache_alloc, so kmalloc technically returns pointers aligned to both ARCH_KMALLOC_MINALIGN and ARCH_SLAB_MINALIGN, not only to ARCH_KMALLOC_MINALIGN. (See create_kmalloc_cache()->create_boot_cache()->calculate_alignment() for SLAB and SLUB and __do_kmalloc_node() for SLOB.) Clarify the comment. The assumption specified by __assume_kmalloc_alignment is still correct, although it can be made stronger. I'll leave this to a separate patch. Signed-off-by: Andrey Konovalov Acked-by: David Rientjes Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/84d8142747230f2015eaf9705ee7c2e1a9f56596.1651161548.git.andreyknvl@google.com --- include/linux/slab.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 8c090599fc21..58bb9392775d 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -217,9 +217,9 @@ void kmem_dump_obj(void *object); #endif /* - * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned - * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN - * aligned pointers. + * kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN. + * kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN + * and ARCH_SLAB_MINALIGN, but here we only assume the former alignment. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) -- cgit v1.2.3 From 23587f7c5daa936524ede26201253a089666b5d9 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 29 Apr 2022 17:05:45 +0800 Subject: mm/slub: remove unused kmem_cache_order_objects max max field holds the largest slab order that was ever used for a slab cache. But it's unused now. Remove it. Signed-off-by: Miaohe Lin Reviewed-by: Muchun Song Acked-by: David Rientjes Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/20220429090545.33413-1-linmiaohe@huawei.com --- include/linux/slub_def.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 33c5c0e3bd8d..f9c68a9dac04 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -105,7 +105,6 @@ struct kmem_cache { struct kmem_cache_order_objects oo; /* Allocation and freeing of slabs */ - struct kmem_cache_order_objects max; struct kmem_cache_order_objects min; gfp_t allocflags; /* gfp flags to use on each alloc */ int refcount; /* Refcount for slab cache destroy */ -- cgit v1.2.3 From 94f697c5384bd7f9632acca483ba1ef9dd99ea97 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Fri, 29 Apr 2022 12:01:53 +0200 Subject: mtd: spi-nor: move spi_nor_write_ear() to winbond module The "Extended Address Register" is winbond specific. If the flash is larger than 16MiB and is used in 3 byte address mode, it is used to set the remaining address bits. Move the write_ear() function, the opcode macros and the spimem op template into the winbond module and rename them accordingly. Signed-off-by: Michael Walle Signed-off-by: Pratyush Yadav Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/r/20220429100153.2338501-1-michael@walle.cc --- include/linux/mtd/spi-nor.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 5e25a7b75ae2..e505c4a5c530 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -47,8 +47,6 @@ #define SPINOR_OP_RDID 0x9f /* Read JEDEC ID */ #define SPINOR_OP_RDSFDP 0x5a /* Read SFDP */ #define SPINOR_OP_RDCR 0x35 /* Read configuration register */ -#define SPINOR_OP_RDEAR 0xc8 /* Read Extended Address Register */ -#define SPINOR_OP_WREAR 0xc5 /* Write Extended Address Register */ #define SPINOR_OP_SRSTEN 0x66 /* Software Reset Enable */ #define SPINOR_OP_SRST 0x99 /* Software Reset */ #define SPINOR_OP_GBULK 0x98 /* Global Block Unlock */ -- cgit v1.2.3 From 43896f56b59eeaf08687fa976257ae7083d01b41 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Wed, 27 Apr 2022 18:21:31 +0200 Subject: clk: imx8mp: add clkout1/2 support clkout1 and clkout2 allow to supply clocks from the SoC to the board, which is used by some board designs to provide reference clocks. Signed-off-by: Lucas Stach Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20220427162131.3127303-1-l.stach@pengutronix.de Signed-off-by: Abel Vesa --- include/dt-bindings/clock/imx8mp-clock.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/imx8mp-clock.h b/include/dt-bindings/clock/imx8mp-clock.h index e05d21bf7813..9d5cc2ddde89 100644 --- a/include/dt-bindings/clock/imx8mp-clock.h +++ b/include/dt-bindings/clock/imx8mp-clock.h @@ -317,10 +317,15 @@ #define IMX8MP_CLK_AUDIO_AXI 310 #define IMX8MP_CLK_HSIO_AXI 311 #define IMX8MP_CLK_MEDIA_ISP 312 - #define IMX8MP_CLK_MEDIA_DISP2_PIX 313 +#define IMX8MP_CLK_CLKOUT1_SEL 314 +#define IMX8MP_CLK_CLKOUT1_DIV 315 +#define IMX8MP_CLK_CLKOUT1 316 +#define IMX8MP_CLK_CLKOUT2_SEL 317 +#define IMX8MP_CLK_CLKOUT2_DIV 318 +#define IMX8MP_CLK_CLKOUT2 319 -#define IMX8MP_CLK_END 314 +#define IMX8MP_CLK_END 320 #define IMX8MP_CLK_AUDIOMIX_SAI1_IPG 0 #define IMX8MP_CLK_AUDIOMIX_SAI1_MCLK1 1 -- cgit v1.2.3 From b170143ae1113882731666aec9b9105356f1fc17 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Sun, 1 May 2022 16:55:08 +0200 Subject: soc: apple: Add SART driver The NVMe co-processor on the Apple M1 uses a DMA address filter called SART for some DMA transactions. This adds a simple driver used to configure the memory regions from which DMA transactions are allowed. Unlike a real IOMMU, SART does not support any pagetables and can't be implemented inside the IOMMU subsystem using iommu_ops. It also can't be implemented using dma_map_ops since not all DMA transactions of the NVMe controller are filtered by SART. Instead, most buffers have to be registered using the integrated NVMe IOMMU and we can't have two separate dma_map_ops implementations for a single device. Co-developed-by: Hector Martin Reviewed-by: Arnd Bergmann Signed-off-by: Hector Martin Signed-off-by: Sven Peter --- include/linux/soc/apple/sart.h | 53 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) create mode 100644 include/linux/soc/apple/sart.h (limited to 'include') diff --git a/include/linux/soc/apple/sart.h b/include/linux/soc/apple/sart.h new file mode 100644 index 000000000000..2249bf6cde09 --- /dev/null +++ b/include/linux/soc/apple/sart.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ +/* + * Apple SART device driver + * Copyright (C) The Asahi Linux Contributors + * + * Apple SART is a simple address filter for DMA transactions. + * Regions of physical memory must be added to the SART's allow + * list before any DMA can target these. Unlike a proper + * IOMMU no remapping can be done. + */ + +#ifndef _LINUX_SOC_APPLE_SART_H_ +#define _LINUX_SOC_APPLE_SART_H_ + +#include +#include +#include + +struct apple_sart; + +/* + * Get a reference to the SART attached to dev. + * + * Looks for the phandle reference in apple,sart and returns a pointer + * to the corresponding apple_sart struct to be used with + * apple_sart_add_allowed_region and apple_sart_remove_allowed_region. + */ +struct apple_sart *devm_apple_sart_get(struct device *dev); + +/* + * Adds the region [paddr, paddr+size] to the DMA allow list. + * + * @sart: SART reference + * @paddr: Start address of the region to be used for DMA + * @size: Size of the region to be used for DMA. + */ +int apple_sart_add_allowed_region(struct apple_sart *sart, phys_addr_t paddr, + size_t size); + +/* + * Removes the region [paddr, paddr+size] from the DMA allow list. + * + * Note that exact same paddr and size used for apple_sart_add_allowed_region + * have to be passed. + * + * @sart: SART reference + * @paddr: Start address of the region no longer used for DMA + * @size: Size of the region no longer used for DMA. + */ +int apple_sart_remove_allowed_region(struct apple_sart *sart, phys_addr_t paddr, + size_t size); + +#endif /* _LINUX_SOC_APPLE_SART_H_ */ -- cgit v1.2.3 From f502cc568de95e5ed9cc9e6133fa454fbe0c5c01 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 4 Mar 2022 11:48:38 -0800 Subject: KVM: Add max_vcpus field in common 'struct kvm' For TDX guests, the maximum number of vcpus needs to be specified when the TDX guest VM is initialized (creating the TDX data corresponding to TDX guest) before creating vcpu. It needs to record the maximum number of vcpus on VM creation (KVM_CREATE_VM) and return error if the number of vcpus exceeds it Because there is already max_vcpu member in arm64 struct kvm_arch, move it to common struct kvm and initialize it to KVM_MAX_VCPUS before kvm_arch_init_vm() instead of adding it to x86 struct kvm_arch. Signed-off-by: Sean Christopherson Signed-off-by: Isaku Yamahata Message-Id: Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 252ee4a61b58..f94f72bbd2d3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -725,6 +725,7 @@ struct kvm { * and is accessed atomically. */ atomic_t online_vcpus; + int max_vcpus; int created_vcpus; int last_boosted_vcpu; struct list_head vm_list; -- cgit v1.2.3 From 1cdba21db2ca31514c60b9732fc3963ae24c59e0 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Fri, 29 Apr 2022 11:12:57 -0700 Subject: kunit: add ability to specify suite-level init and exit functions KUnit has support for setup/cleanup logic for each test case in a suite. But it lacks the ability to specify setup/cleanup for the entire suite itself. This can be used to do setup that is too expensive or cumbersome to do for each test. Or it can be used to do simpler things like log debug information after the suite completes. It's a fairly common feature, so the lack of it is noticeable. Some examples in other frameworks and languages: * https://docs.python.org/3/library/unittest.html#setupclass-and-teardownclass * https://google.github.io/googletest/reference/testing.html#Test::SetUpTestSuite Meta: This is very similar to this patch here: https://lore.kernel.org/linux-kselftest/20210805043503.20252-3-bvanassche@acm.org/ The changes from that patch: * pass in `struct kunit *` so users can do stuff like `kunit_info(suite, "debug message")` * makes sure the init failure is bubbled up as a failure * updates kunit-example-test.c to use a suite init * Updates kunit/usage.rst to mention the new support * some minor cosmetic things * use `suite_{init,exit}` instead of `{init/exit}_suite` * make suite init error message more consistent w/ test init * etc. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/test.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 17749b4467ad..607e02b8e167 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -153,6 +153,8 @@ static inline char *kunit_status_to_ok_not_ok(enum kunit_status status) * struct kunit_suite - describes a related collection of &struct kunit_case * * @name: the name of the test. Purely informational. + * @suite_init: called once per test suite before the test cases. + * @suite_exit: called once per test suite after all test cases. * @init: called before every test case. * @exit: called after every test case. * @test_cases: a null terminated array of test cases. @@ -167,6 +169,8 @@ static inline char *kunit_status_to_ok_not_ok(enum kunit_status status) */ struct kunit_suite { const char name[256]; + int (*suite_init)(struct kunit_suite *suite); + void (*suite_exit)(struct kunit_suite *suite); int (*init)(struct kunit *test); void (*exit)(struct kunit *test); struct kunit_case *test_cases; @@ -175,6 +179,7 @@ struct kunit_suite { char status_comment[KUNIT_STATUS_COMMENT_SIZE]; struct dentry *debugfs; char *log; + int suite_init_err; }; /** -- cgit v1.2.3 From db05628435aa761d30b4eae481a82befe7a8492a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:12 +0200 Subject: blk-cgroup: move blkcg_{get,set}_fc_appid out of line No need to have these helpers inline. Also remove the stubs and just use an IS_ENABLED for the get side (the set side already is only built conditionlly). Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-5-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 58 ++-------------------------------------------- 1 file changed, 2 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 652cd05b0924..7a2f7de30173 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -218,61 +218,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } #endif /* CONFIG_BLK_CGROUP */ -#ifdef CONFIG_BLK_CGROUP_FC_APPID -/* - * Sets the fc_app_id field associted to blkcg - * @app_id: application identifier - * @cgrp_id: cgroup id - * @app_id_len: size of application identifier - */ -static inline int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) -{ - struct cgroup *cgrp; - struct cgroup_subsys_state *css; - struct blkcg *blkcg; - int ret = 0; - - if (app_id_len > FC_APPID_LEN) - return -EINVAL; - - cgrp = cgroup_get_from_id(cgrp_id); - if (!cgrp) - return -ENOENT; - css = cgroup_get_e_css(cgrp, &io_cgrp_subsys); - if (!css) { - ret = -ENOENT; - goto out_cgrp_put; - } - blkcg = css_to_blkcg(css); - /* - * There is a slight race condition on setting the appid. - * Worst case an I/O may not find the right id. - * This is no different from the I/O we let pass while obtaining - * the vmid from the fabric. - * Adding the overhead of a lock is not necessary. - */ - strlcpy(blkcg->fc_app_id, app_id, app_id_len); - css_put(css); -out_cgrp_put: - cgroup_put(cgrp); - return ret; -} +int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len); +char *blkcg_get_fc_appid(struct bio *bio); -/** - * blkcg_get_fc_appid - get the fc app identifier associated with a bio - * @bio: target bio - * - * On success return the fc_app_id, on failure return NULL - */ -static inline char *blkcg_get_fc_appid(struct bio *bio) -{ - if (bio && bio->bi_blkg && - (bio->bi_blkg->blkcg->fc_app_id[0] != '\0')) - return bio->bi_blkg->blkcg->fc_app_id; - return NULL; -} -#else -static inline int blkcg_set_fc_appid(char *buf, u64 id, size_t len) { return -EINVAL; } -static inline char *blkcg_get_fc_appid(struct bio *bio) { return NULL; } -#endif /*CONFIG_BLK_CGROUP_FC_APPID*/ #endif /* _BLK_CGROUP_H */ -- cgit v1.2.3 From 216889aad362b5b7e998a5371348b5e95d485dd1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:13 +0200 Subject: blk-cgroup: move blk_cgroup_congested out line There is no urgent need to inline this function, so move it out of line. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-6-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 7a2f7de30173..988965c1c27b 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -135,25 +135,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) return NULL; } -static inline bool blk_cgroup_congested(void) -{ - struct cgroup_subsys_state *css; - bool ret = false; - - rcu_read_lock(); - css = kthread_blkcg(); - if (!css) - css = task_css(current, io_cgrp_id); - while (css) { - if (atomic_read(&css->cgroup->congestion_count)) { - ret = true; - break; - } - css = css->parent; - } - rcu_read_unlock(); - return ret; -} +bool blk_cgroup_congested(void); /** * blkcg_parent - get the parent of a blkcg -- cgit v1.2.3 From 397c9f46ee4d99024c64954b007c1b5762d01cb4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:14 +0200 Subject: blk-cgroup: move blkcg_{pin,unpin}_online out of line Move these two functions out of line as there is no good reason to inline them. Also switch to passing a cgroup_subsys_state instead of doing the conversion in the caller to prepare for making the blkcg structure private to blk-cgroup. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-7-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 46 ++-------------------------------------------- 1 file changed, 2 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 988965c1c27b..0fb7459096e9 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -111,7 +111,6 @@ struct blkcg_gq { extern struct cgroup_subsys_state * const blkcg_root_css; -void blkcg_destroy_blkgs(struct blkcg *blkcg); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); @@ -136,49 +135,8 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) } bool blk_cgroup_congested(void); - -/** - * blkcg_parent - get the parent of a blkcg - * @blkcg: blkcg of interest - * - * Return the parent blkcg of @blkcg. Can be called anytime. - */ -static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) -{ - return css_to_blkcg(blkcg->css.parent); -} - -/** - * blkcg_pin_online - pin online state - * @blkcg: blkcg of interest - * - * While pinned, a blkcg is kept online. This is primarily used to - * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline - * while an associated cgwb is still active. - */ -static inline void blkcg_pin_online(struct blkcg *blkcg) -{ - refcount_inc(&blkcg->online_pin); -} - -/** - * blkcg_unpin_online - unpin online state - * @blkcg: blkcg of interest - * - * This is primarily used to impedance-match blkg and cgwb lifetimes so - * that blkg doesn't go offline while an associated cgwb is still active. - * When this count goes to zero, all active cgwbs have finished so the - * blkcg can continue destruction by calling blkcg_destroy_blkgs(). - */ -static inline void blkcg_unpin_online(struct blkcg *blkcg) -{ - do { - if (!refcount_dec_and_test(&blkcg->online_pin)) - break; - blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); - } while (blkcg); -} +void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); +void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css); #else /* CONFIG_BLK_CGROUP */ -- cgit v1.2.3 From dec223c92a4688f6c9642d640cfe15a99d289dd4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:15 +0200 Subject: blk-cgroup: move struct blkcg to block/blk-cgroup.h There is no real need to expose the blkcg structure to the whole kernel. Move it to the private header an expose a helper to let the writeback code access the cgwb_list member. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-8-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 6 ++---- include/linux/blk-cgroup.h | 32 +------------------------------- 2 files changed, 3 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 87ce24d238f3..2bd073fa6bb5 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -17,8 +17,6 @@ #include #include -struct blkcg; - static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); @@ -154,7 +152,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); -void wb_blkcg_offline(struct blkcg *blkcg); +void wb_blkcg_offline(struct cgroup_subsys_state *css); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode @@ -378,7 +376,7 @@ static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } -static inline void wb_blkcg_offline(struct blkcg *blkcg) +static inline void wb_blkcg_offline(struct cgroup_subsys_state *css) { } diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 0fb7459096e9..d7b188095040 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -37,29 +37,6 @@ enum blkg_iostat_type { BLKG_IOSTAT_NR, }; -struct blkcg_gq; -struct blkg_policy_data; - -struct blkcg { - struct cgroup_subsys_state css; - spinlock_t lock; - refcount_t online_pin; - - struct radix_tree_root blkg_tree; - struct blkcg_gq __rcu *blkg_hint; - struct hlist_head blkg_list; - - struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; - - struct list_head all_blkcgs_node; -#ifdef CONFIG_BLK_CGROUP_FC_APPID - char fc_app_id[FC_APPID_LEN]; -#endif -#ifdef CONFIG_CGROUP_WRITEBACK - struct list_head cgwb_list; -#endif -}; - struct blkg_iostat { u64 bytes[BLKG_IOSTAT_NR]; u64 ios[BLKG_IOSTAT_NR]; @@ -114,11 +91,6 @@ extern struct cgroup_subsys_state * const blkcg_root_css; void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); -static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct blkcg, css) : NULL; -} - /** * bio_blkcg - grab the blkcg associated with a bio * @bio: target bio @@ -137,12 +109,10 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) bool blk_cgroup_congested(void); void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css); +struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css); #else /* CONFIG_BLK_CGROUP */ -struct blkcg { -}; - struct blkcg_gq { }; -- cgit v1.2.3 From f4a6a61cb6d40d9ae63e47743d33200f3efe3fe7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:16 +0200 Subject: blktrace: cleanup the __trace_note_message interface Pass the cgroup_subsys_state instead of a the blkg so that blktrace doesn't need to poke into blk-cgroup internals, and give the name a blk prefix as the current name is way too generic for a public interface. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-9-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 22501a293fa5..623e22492afa 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -27,12 +27,10 @@ struct blk_trace { atomic_t dropped; }; -struct blkcg; - extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); -extern __printf(3, 4) -void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...); +__printf(3, 4) void __blk_trace_note_message(struct blk_trace *bt, + struct cgroup_subsys_state *css, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream @@ -47,14 +45,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f * NOTE: Can not use 'static inline' due to presence of var args... * **/ -#define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ +#define blk_add_cgroup_trace_msg(q, css, fmt, ...) \ do { \ struct blk_trace *bt; \ \ rcu_read_lock(); \ bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ - __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + __blk_trace_note_message(bt, css, fmt, ##__VA_ARGS__);\ rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ -- cgit v1.2.3 From bbb1ebe7a909db4de49777fb7676d5bf293f34c9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:17 +0200 Subject: blk-cgroup: replace bio_blkcg with bio_blkcg_css All callers of bio_blkcg actually want the CSS, so replace it with an interface that does return the CSS. This now allows to move struct blkcg_gq to block/blk-cgroup.h instead of exposing it in a public header. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-10-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 83 +++------------------------------------------- 1 file changed, 5 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index d7b188095040..97c7968e3204 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -28,94 +28,18 @@ #define FC_APPID_LEN 129 #ifdef CONFIG_BLK_CGROUP - -enum blkg_iostat_type { - BLKG_IOSTAT_READ, - BLKG_IOSTAT_WRITE, - BLKG_IOSTAT_DISCARD, - - BLKG_IOSTAT_NR, -}; - -struct blkg_iostat { - u64 bytes[BLKG_IOSTAT_NR]; - u64 ios[BLKG_IOSTAT_NR]; -}; - -struct blkg_iostat_set { - struct u64_stats_sync sync; - struct blkg_iostat cur; - struct blkg_iostat last; -}; - -/* association between a blk cgroup and a request queue */ -struct blkcg_gq { - /* Pointer to the associated request_queue */ - struct request_queue *q; - struct list_head q_node; - struct hlist_node blkcg_node; - struct blkcg *blkcg; - - /* all non-root blkcg_gq's are guaranteed to have access to parent */ - struct blkcg_gq *parent; - - /* reference count */ - struct percpu_ref refcnt; - - /* is this blkg online? protected by both blkcg and q locks */ - bool online; - - struct blkg_iostat_set __percpu *iostat_cpu; - struct blkg_iostat_set iostat; - - struct blkg_policy_data *pd[BLKCG_MAX_POLS]; - - spinlock_t async_bio_lock; - struct bio_list async_bios; - union { - struct work_struct async_bio_work; - struct work_struct free_work; - }; - - atomic_t use_delay; - atomic64_t delay_nsec; - atomic64_t delay_start; - u64 last_delay; - int last_use; - - struct rcu_head rcu_head; -}; - extern struct cgroup_subsys_state * const blkcg_root_css; void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); - -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, %NULL if not associated. - * Callers are expected to either handle %NULL or know association has been - * done prior to calling this. - */ -static inline struct blkcg *bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; -} - bool blk_cgroup_congested(void); void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css); struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ -struct blkcg_gq { -}; - #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) static inline void blkcg_maybe_throttle_current(void) { } @@ -123,7 +47,10 @@ static inline bool blk_cgroup_congested(void) { return false; } #ifdef CONFIG_BLOCK static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } -static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } +static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) +{ + return NULL; +} #endif /* CONFIG_BLOCK */ #endif /* CONFIG_BLK_CGROUP */ -- cgit v1.2.3 From 7f20ba7c42fd899557cef7d001f48711c3066ba5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:18 +0200 Subject: blk-cgroup: remove pointless CONFIG_BLOCK ifdefs No need to make BLK_CGROUP stubs conditional on CONFIG_BLOCK as they can't be used without that. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-11-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 97c7968e3204..abbfa97d6d46 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -44,15 +44,11 @@ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio); static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } - -#ifdef CONFIG_BLOCK static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { return NULL; } -#endif /* CONFIG_BLOCK */ - #endif /* CONFIG_BLK_CGROUP */ int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len); -- cgit v1.2.3 From c97ab271576dec2170e7b804cb05f7617b30fed9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:19 +0200 Subject: blk-cgroup: remove unneeded includes from Remove all the includes that aren't actually needed from and push them to the actual source files where needed. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-12-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index abbfa97d6d46..9f40dbc65f82 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -14,16 +14,11 @@ * Nauman Rafique */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include +#include + +struct bio; +struct cgroup_subsys_state; +struct request_queue; #define FC_APPID_LEN 129 -- cgit v1.2.3 From f624506f98b198e65b44da303f44974590fb16c0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:23 +0200 Subject: kthread: unexport kthread_blkcg kthread_blkcg is only used by the built-in blk-cgroup code. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-16-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/kthread.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index de5d75bafd66..30e5bec81d2b 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -222,9 +222,5 @@ void kthread_associate_blkcg(struct cgroup_subsys_state *css); struct cgroup_subsys_state *kthread_blkcg(void); #else static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } -static inline struct cgroup_subsys_state *kthread_blkcg(void) -{ - return NULL; -} #endif #endif /* _LINUX_KTHREAD_H */ -- cgit v1.2.3 From c92a6b5d63359dd6d2ce6ea88ecd8e31dd769f6b Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 2 Mar 2022 00:35:47 -0500 Subject: scsi: core: Query VPD size before getting full page We currently default to 255 bytes when fetching VPD pages during discovery. However, we have had a few devices that are known to wedge if the requested buffer exceeds a certain size. See commit af73623f5f10 ("[SCSI] sd: Reduce buffer size for vpd request") which works around one example of this problem in the SCSI disk driver. With commit d188b0675b21 ("scsi: core: Add sysfs attributes for VPD pages 0h and 89h") we now risk triggering the same issue in the generic midlayer code. The problem with the ATA VPD page in particular is that the SCSI portion of the page is trailed by 512 bytes of verbatim ATA Identify Device information. However, not all controllers actually provide the additional 512 bytes and will lock up if one asks for more than the 64 bytes containing the SCSI protocol fields. Instead of picking a new, somewhat arbitrary, number of bytes for the VPD buffer size, start fetching the 4-byte header for each page. The header contains the size of the page as far as the device is concerned. We can use the reported size to specify the correct allocation length when subsequently fetching the full page. The header validation is done by a new helper function scsi_get_vpd_size() and both scsi_get_vpd_page() and scsi_get_vpd_buf() now rely on this to query the page size. In addition, scsi_get_vpd_page() is simplified to mirror the logic in scsi_get_vpd_page(). This involves removing the Supported VPD Pages lookup prior to attempting to query a page. There does not appear any evidence, even in the oldest SCSI specs, that this step is required. We already rely on scsi_get_vpd_page() throughout the stack and this function never consulted the Supported VPD Pages. Since this has not caused any problems it should be safe to remove the precondition from scsi_get_vpd_page(). Instrumented runs also revealed that the Supported VPD Pages lookup had little effect since the device page index often was larger than the supplied buffer size. As a result, inquiries frequently bypassed the index check and went through the "If we ran off the end of the buffer, give us the benefit of the doubt" code path which assumed the page was present despite not being listed. The revised code takes both the page size reported by the device as well as the size of the buffer provided by the scsi_get_vpd_page() caller into account. Link: https://lore.kernel.org/r/20220302053559.32147-3-martin.petersen@oracle.com Fixes: d188b0675b21 ("scsi: core: Add sysfs attributes for VPD pages 0h and 89h") Reported-by: Maciej W. Rozycki Tested-by: Maciej W. Rozycki Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/scsi/scsi_device.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 57e3e239a1fc..c37cc5b3ebeb 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -100,6 +100,10 @@ struct scsi_vpd { unsigned char data[]; }; +enum scsi_vpd_parameters { + SCSI_VPD_HEADER_SIZE = 4, +}; + struct scsi_device { struct Scsi_Host *host; struct request_queue *request_queue; @@ -141,7 +145,6 @@ struct scsi_device { const char * model; /* ... after scan; point to static string */ const char * rev; /* ... "nullnullnullnull" before scan */ -#define SCSI_VPD_PG_LEN 255 struct scsi_vpd __rcu *vpd_pg0; struct scsi_vpd __rcu *vpd_pg83; struct scsi_vpd __rcu *vpd_pg80; -- cgit v1.2.3 From e60ac0b9e445822e60230c00e68d8cdb7748701b Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 2 Mar 2022 00:35:50 -0500 Subject: scsi: core: Cache VPD pages b0, b1, b2 The SCSI disk driver consults VPD pages b0 (Block Limits), b1 (Block Device Characteristics), and b2 (Logical Block Provisioning). Instead of having sd.c request these pages every revalidate cycle, cache them along with the other commonly used VPDs. Link: https://lore.kernel.org/r/20220302053559.32147-6-martin.petersen@oracle.com Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/scsi/scsi_device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index c37cc5b3ebeb..7cf5f3b7589f 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -149,6 +149,10 @@ struct scsi_device { struct scsi_vpd __rcu *vpd_pg83; struct scsi_vpd __rcu *vpd_pg80; struct scsi_vpd __rcu *vpd_pg89; + struct scsi_vpd __rcu *vpd_pgb0; + struct scsi_vpd __rcu *vpd_pgb1; + struct scsi_vpd __rcu *vpd_pgb2; + struct scsi_target *sdev_target; blist_flags_t sdev_bflags; /* black/white flags as also found in -- cgit v1.2.3 From f5e6d5a343761081317c89d23489c93fbafc69ff Mon Sep 17 00:00:00 2001 From: Sumit Saxena Date: Fri, 29 Apr 2022 17:16:35 -0400 Subject: scsi: mpi3mr: Add support for driver commands There are certain bsg commands which need to be completed by the driver without involving firmware. These requests are termed driver commands. Add support for these. Link: https://lore.kernel.org/r/20220429211641.642010-3-sumit.saxena@broadcom.com Reported by: Stephen Rothwell Reported-by: kernel test robot Reviewed-by: Himanshu Madhani Signed-off-by: Sumit Saxena Signed-off-by: Martin K. Petersen --- include/uapi/scsi/scsi_bsg_mpi3mr.h | 457 ++++++++++++++++++++++++++++++++++++ 1 file changed, 457 insertions(+) create mode 100644 include/uapi/scsi/scsi_bsg_mpi3mr.h (limited to 'include') diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h new file mode 100644 index 000000000000..66697d963f64 --- /dev/null +++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h @@ -0,0 +1,457 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH Linux-syscall-note */ +/* + * Driver for Broadcom MPI3 Storage Controllers + * + * Copyright (C) 2017-2022 Broadcom Inc. + * (mailto: mpi3mr-linuxdrv.pdl@broadcom.com) + * + */ + +#ifndef SCSI_BSG_MPI3MR_H_INCLUDED +#define SCSI_BSG_MPI3MR_H_INCLUDED + +#include + +/* Definitions for BSG commands */ +#define MPI3MR_IOCTL_VERSION 0x06 + +#define MPI3MR_APP_DEFAULT_TIMEOUT (60) /*seconds*/ + +#define MPI3MR_BSG_ADPTYPE_UNKNOWN 0 +#define MPI3MR_BSG_ADPTYPE_AVGFAMILY 1 + +#define MPI3MR_BSG_ADPSTATE_UNKNOWN 0 +#define MPI3MR_BSG_ADPSTATE_OPERATIONAL 1 +#define MPI3MR_BSG_ADPSTATE_FAULT 2 +#define MPI3MR_BSG_ADPSTATE_IN_RESET 3 +#define MPI3MR_BSG_ADPSTATE_UNRECOVERABLE 4 + +#define MPI3MR_BSG_ADPRESET_UNKNOWN 0 +#define MPI3MR_BSG_ADPRESET_SOFT 1 +#define MPI3MR_BSG_ADPRESET_DIAG_FAULT 2 + +#define MPI3MR_BSG_LOGDATA_MAX_ENTRIES 400 +#define MPI3MR_BSG_LOGDATA_ENTRY_HEADER_SZ 4 + +#define MPI3MR_DRVBSG_OPCODE_UNKNOWN 0 +#define MPI3MR_DRVBSG_OPCODE_ADPINFO 1 +#define MPI3MR_DRVBSG_OPCODE_ADPRESET 2 +#define MPI3MR_DRVBSG_OPCODE_ALLTGTDEVINFO 4 +#define MPI3MR_DRVBSG_OPCODE_GETCHGCNT 5 +#define MPI3MR_DRVBSG_OPCODE_LOGDATAENABLE 6 +#define MPI3MR_DRVBSG_OPCODE_PELENABLE 7 +#define MPI3MR_DRVBSG_OPCODE_GETLOGDATA 8 +#define MPI3MR_DRVBSG_OPCODE_QUERY_HDB 9 +#define MPI3MR_DRVBSG_OPCODE_REPOST_HDB 10 +#define MPI3MR_DRVBSG_OPCODE_UPLOAD_HDB 11 +#define MPI3MR_DRVBSG_OPCODE_REFRESH_HDB_TRIGGERS 12 + + +#define MPI3MR_BSG_BUFTYPE_UNKNOWN 0 +#define MPI3MR_BSG_BUFTYPE_RAIDMGMT_CMD 1 +#define MPI3MR_BSG_BUFTYPE_RAIDMGMT_RESP 2 +#define MPI3MR_BSG_BUFTYPE_DATA_IN 3 +#define MPI3MR_BSG_BUFTYPE_DATA_OUT 4 +#define MPI3MR_BSG_BUFTYPE_MPI_REPLY 5 +#define MPI3MR_BSG_BUFTYPE_ERR_RESPONSE 6 +#define MPI3MR_BSG_BUFTYPE_MPI_REQUEST 0xFE + +#define MPI3MR_BSG_MPI_REPLY_BUFTYPE_UNKNOWN 0 +#define MPI3MR_BSG_MPI_REPLY_BUFTYPE_STATUS 1 +#define MPI3MR_BSG_MPI_REPLY_BUFTYPE_ADDRESS 2 + +#define MPI3MR_HDB_BUFTYPE_UNKNOWN 0 +#define MPI3MR_HDB_BUFTYPE_TRACE 1 +#define MPI3MR_HDB_BUFTYPE_FIRMWARE 2 +#define MPI3MR_HDB_BUFTYPE_RESERVED 3 + +#define MPI3MR_HDB_BUFSTATUS_UNKNOWN 0 +#define MPI3MR_HDB_BUFSTATUS_NOT_ALLOCATED 1 +#define MPI3MR_HDB_BUFSTATUS_POSTED_UNPAUSED 2 +#define MPI3MR_HDB_BUFSTATUS_POSTED_PAUSED 3 +#define MPI3MR_HDB_BUFSTATUS_RELEASED 4 + +#define MPI3MR_HDB_TRIGGER_TYPE_UNKNOWN 0 +#define MPI3MR_HDB_TRIGGER_TYPE_DIAGFAULT 1 +#define MPI3MR_HDB_TRIGGER_TYPE_ELEMENT 2 +#define MPI3MR_HDB_TRIGGER_TYPE_MASTER 3 + + +/* Supported BSG commands */ +enum command { + MPI3MR_DRV_CMD = 1, + MPI3MR_MPT_CMD = 2, +}; + +/** + * struct mpi3_driver_info_layout - Information about driver + * + * @information_length: Length of this structure in bytes + * @driver_signature: Driver Vendor name + * @os_name: Operating System Name + * @driver_name: Driver name + * @driver_version: Driver version + * @driver_release_date: Driver release date + * @driver_capabilities: Driver capabilities + */ +struct mpi3_driver_info_layout { + __le32 information_length; + __u8 driver_signature[12]; + __u8 os_name[16]; + __u8 os_version[12]; + __u8 driver_name[20]; + __u8 driver_version[32]; + __u8 driver_release_date[20]; + __le32 driver_capabilities; +}; + +/** + * struct mpi3mr_bsg_in_adpinfo - Adapter information request + * data returned by the driver. + * + * @adp_type: Adapter type + * @rsvd1: Reserved + * @pci_dev_id: PCI device ID of the adapter + * @pci_dev_hw_rev: PCI revision of the adapter + * @pci_subsys_dev_id: PCI subsystem device ID of the adapter + * @pci_subsys_ven_id: PCI subsystem vendor ID of the adapter + * @pci_dev: PCI device + * @pci_func: PCI function + * @pci_bus: PCI bus + * @rsvd2: Reserved + * @pci_seg_id: PCI segment ID + * @app_intfc_ver: version of the application interface definition + * @rsvd3: Reserved + * @rsvd4: Reserved + * @rsvd5: Reserved + * @driver_info: Driver Information (Version/Name) + */ +struct mpi3mr_bsg_in_adpinfo { + __u32 adp_type; + __u32 rsvd1; + __u32 pci_dev_id; + __u32 pci_dev_hw_rev; + __u32 pci_subsys_dev_id; + __u32 pci_subsys_ven_id; + __u32 pci_dev:5; + __u32 pci_func:3; + __u32 pci_bus:8; + __u16 rsvd2; + __u32 pci_seg_id; + __u32 app_intfc_ver; + __u8 adp_state; + __u8 rsvd3; + __u16 rsvd4; + __u32 rsvd5[2]; + struct mpi3_driver_info_layout driver_info; +}; + +/** + * struct mpi3mr_bsg_adp_reset - Adapter reset request + * payload data to the driver. + * + * @reset_type: Reset type + * @rsvd1: Reserved + * @rsvd2: Reserved + */ +struct mpi3mr_bsg_adp_reset { + __u8 reset_type; + __u8 rsvd1; + __u16 rsvd2; +}; + +/** + * struct mpi3mr_change_count - Topology change count + * returned by the driver. + * + * @change_count: Topology change count + * @rsvd: Reserved + */ +struct mpi3mr_change_count { + __u16 change_count; + __u16 rsvd; +}; + +/** + * struct mpi3mr_device_map_info - Target device mapping + * information + * + * @handle: Firmware device handle + * @perst_id: Persistent ID assigned by the firmware + * @target_id: Target ID assigned by the driver + * @bus_id: Bus ID assigned by the driver + * @rsvd1: Reserved + * @rsvd2: Reserved + */ +struct mpi3mr_device_map_info { + __u16 handle; + __u16 perst_id; + __u32 target_id; + __u8 bus_id; + __u8 rsvd1; + __u16 rsvd2; +}; + +/** + * struct mpi3mr_all_tgt_info - Target device mapping + * information returned by the driver + * + * @num_devices: The number of devices in driver's inventory + * @rsvd1: Reserved + * @rsvd2: Reserved + * @dmi: Variable length array of mapping information of targets + */ +struct mpi3mr_all_tgt_info { + __u16 num_devices; + __u16 rsvd1; + __u32 rsvd2; + struct mpi3mr_device_map_info dmi[1]; +}; + +/** + * struct mpi3mr_logdata_enable - Number of log data + * entries saved by the driver returned as payload data for + * enable logdata BSG request by the driver. + * + * @max_entries: Number of log data entries cached by the driver + * @rsvd: Reserved + */ +struct mpi3mr_logdata_enable { + __u16 max_entries; + __u16 rsvd; +}; + +/** + * struct mpi3mr_bsg_out_pel_enable - PEL enable request payload + * data to the driver. + * + * @pel_locale: PEL locale to the firmware + * @pel_class: PEL class to the firmware + * @rsvd: Reserved + */ +struct mpi3mr_bsg_out_pel_enable { + __u16 pel_locale; + __u8 pel_class; + __u8 rsvd; +}; + +/** + * struct mpi3mr_logdata_entry - Log data entry cached by the + * driver. + * + * @valid_entry: Is the entry valid + * @rsvd1: Reserved + * @rsvd2: Reserved + * @data: Variable length Log entry data + */ +struct mpi3mr_logdata_entry { + __u8 valid_entry; + __u8 rsvd1; + __u16 rsvd2; + __u8 data[1]; /* Variable length Array */ +}; + +/** + * struct mpi3mr_bsg_in_log_data - Log data entries saved by + * the driver returned as payload data for Get logdata request + * by the driver. + * + * @entry: Variable length Log data entry array + */ +struct mpi3mr_bsg_in_log_data { + struct mpi3mr_logdata_entry entry[1]; +}; + +/** + * struct mpi3mr_hdb_entry - host diag buffer entry. + * + * @buf_type: Buffer type + * @status: Buffer status + * @trigger_type: Trigger type + * @rsvd1: Reserved + * @size: Buffer size + * @rsvd2: Reserved + * @trigger_data: Trigger specific data + * @rsvd3: Reserved + * @rsvd4: Reserved + */ +struct mpi3mr_hdb_entry { + __u8 buf_type; + __u8 status; + __u8 trigger_type; + __u8 rsvd1; + __u16 size; + __u16 rsvd2; + __u64 trigger_data; + __u32 rsvd3; + __u32 rsvd4; +}; + + +/** + * struct mpi3mr_bsg_in_hdb_status - This structure contains + * return data for the BSG request to retrieve the number of host + * diagnostic buffers supported by the driver and their current + * status and additional status specific data if any in forms of + * multiple hdb entries. + * + * @num_hdb_types: Number of host diag buffer types supported + * @rsvd1: Reserved + * @rsvd2: Reserved + * @rsvd3: Reserved + * @entry: Variable length Diag buffer status entry array + */ +struct mpi3mr_bsg_in_hdb_status { + __u8 num_hdb_types; + __u8 rsvd1; + __u16 rsvd2; + __u32 rsvd3; + struct mpi3mr_hdb_entry entry[1]; +}; + +/** + * struct mpi3mr_bsg_out_repost_hdb - Repost host diagnostic + * buffer request payload data to the driver. + * + * @buf_type: Buffer type + * @rsvd1: Reserved + * @rsvd2: Reserved + */ +struct mpi3mr_bsg_out_repost_hdb { + __u8 buf_type; + __u8 rsvd1; + __u16 rsvd2; +}; + +/** + * struct mpi3mr_bsg_out_upload_hdb - Upload host diagnostic + * buffer request payload data to the driver. + * + * @buf_type: Buffer type + * @rsvd1: Reserved + * @rsvd2: Reserved + * @start_offset: Start offset of the buffer from where to copy + * @length: Length of the buffer to copy + */ +struct mpi3mr_bsg_out_upload_hdb { + __u8 buf_type; + __u8 rsvd1; + __u16 rsvd2; + __u32 start_offset; + __u32 length; +}; + +/** + * struct mpi3mr_bsg_out_refresh_hdb_triggers - Refresh host + * diagnostic buffer triggers request payload data to the driver. + * + * @page_type: Page type + * @rsvd1: Reserved + * @rsvd2: Reserved + */ +struct mpi3mr_bsg_out_refresh_hdb_triggers { + __u8 page_type; + __u8 rsvd1; + __u16 rsvd2; +}; +/** + * struct mpi3mr_bsg_drv_cmd - Generic bsg data + * structure for all driver specific requests. + * + * @mrioc_id: Controller ID + * @opcode: Driver specific opcode + * @rsvd1: Reserved + * @rsvd2: Reserved + */ +struct mpi3mr_bsg_drv_cmd { + __u8 mrioc_id; + __u8 opcode; + __u16 rsvd1; + __u32 rsvd2[4]; +}; +/** + * struct mpi3mr_bsg_in_reply_buf - MPI reply buffer returned + * for MPI Passthrough request . + * + * @mpi_reply_type: Type of MPI reply + * @rsvd1: Reserved + * @rsvd2: Reserved + * @reply_buf: Variable Length buffer based on mpirep type + */ +struct mpi3mr_bsg_in_reply_buf { + __u8 mpi_reply_type; + __u8 rsvd1; + __u16 rsvd2; + __u8 reply_buf[1]; +}; + +/** + * struct mpi3mr_buf_entry - User buffer descriptor for MPI + * Passthrough requests. + * + * @buf_type: Buffer type + * @rsvd1: Reserved + * @rsvd2: Reserved + * @buf_len: Buffer length + */ +struct mpi3mr_buf_entry { + __u8 buf_type; + __u8 rsvd1; + __u16 rsvd2; + __u32 buf_len; +}; +/** + * struct mpi3mr_bsg_buf_entry_list - list of user buffer + * descriptor for MPI Passthrough requests. + * + * @num_of_entries: Number of buffer descriptors + * @rsvd1: Reserved + * @rsvd2: Reserved + * @rsvd3: Reserved + * @buf_entry: Variable length array of buffer descriptors + */ +struct mpi3mr_buf_entry_list { + __u8 num_of_entries; + __u8 rsvd1; + __u16 rsvd2; + __u32 rsvd3; + struct mpi3mr_buf_entry buf_entry[1]; +}; +/** + * struct mpi3mr_bsg_mptcmd - Generic bsg data + * structure for all MPI Passthrough requests . + * + * @mrioc_id: Controller ID + * @rsvd1: Reserved + * @timeout: MPI request timeout + * @buf_entry_list: Buffer descriptor list + */ +struct mpi3mr_bsg_mptcmd { + __u8 mrioc_id; + __u8 rsvd1; + __u16 timeout; + __u32 rsvd2; + struct mpi3mr_buf_entry_list buf_entry_list; +}; + +/** + * struct mpi3mr_bsg_packet - Generic bsg data + * structure for all supported requests . + * + * @cmd_type: represents drvrcmd or mptcmd + * @rsvd1: Reserved + * @rsvd2: Reserved + * @drvrcmd: driver request structure + * @mptcmd: mpt request structure + */ +struct mpi3mr_bsg_packet { + __u8 cmd_type; + __u8 rsvd1; + __u16 rsvd2; + __u32 rsvd3; + union { + struct mpi3mr_bsg_drv_cmd drvrcmd; + struct mpi3mr_bsg_mptcmd mptcmd; + } cmd; +}; +#endif -- cgit v1.2.3 From f3de4706c1e0c3b9fa39ec24a30c1996a33bc9e4 Mon Sep 17 00:00:00 2001 From: Sumit Saxena Date: Fri, 29 Apr 2022 17:16:36 -0400 Subject: scsi: mpi3mr: Move data structures/definitions from MPI headers to uapi header This patch moves the data structures/definitions which are used by userspace applications from MPI headers to uapi/scsi/scsi_bsg_mpi3mr.h Link: https://lore.kernel.org/r/20220429211641.642010-4-sumit.saxena@broadcom.com Reported by: Stephen Rothwell Reviewed-by: Himanshu Madhani Signed-off-by: Sumit Saxena Signed-off-by: Martin K. Petersen --- include/uapi/scsi/scsi_bsg_mpi3mr.h | 117 ++++++++++++++++++++++++++++++++++++ 1 file changed, 117 insertions(+) (limited to 'include') diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h index 66697d963f64..b2c88d5d9c4c 100644 --- a/include/uapi/scsi/scsi_bsg_mpi3mr.h +++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h @@ -454,4 +454,121 @@ struct mpi3mr_bsg_packet { struct mpi3mr_bsg_mptcmd mptcmd; } cmd; }; + + +/* MPI3: NVMe Encasulation related definitions */ +#ifndef MPI3_NVME_ENCAP_CMD_MAX +#define MPI3_NVME_ENCAP_CMD_MAX (1) +#endif + +struct mpi3_nvme_encapsulated_request { + __le16 host_tag; + __u8 ioc_use_only02; + __u8 function; + __le16 ioc_use_only04; + __u8 ioc_use_only06; + __u8 msg_flags; + __le16 change_count; + __le16 dev_handle; + __le16 encapsulated_command_length; + __le16 flags; + __le32 data_length; + __le32 reserved14[3]; + __le32 command[MPI3_NVME_ENCAP_CMD_MAX]; +}; + +struct mpi3_nvme_encapsulated_error_reply { + __le16 host_tag; + __u8 ioc_use_only02; + __u8 function; + __le16 ioc_use_only04; + __u8 ioc_use_only06; + __u8 msg_flags; + __le16 ioc_use_only08; + __le16 ioc_status; + __le32 ioc_log_info; + __le32 nvme_completion_entry[4]; +}; + +/* MPI3: task management related definitions */ +struct mpi3_scsi_task_mgmt_request { + __le16 host_tag; + __u8 ioc_use_only02; + __u8 function; + __le16 ioc_use_only04; + __u8 ioc_use_only06; + __u8 msg_flags; + __le16 change_count; + __le16 dev_handle; + __le16 task_host_tag; + __u8 task_type; + __u8 reserved0f; + __le16 task_request_queue_id; + __le16 reserved12; + __le32 reserved14; + __u8 lun[8]; +}; + +#define MPI3_SCSITASKMGMT_MSGFLAGS_DO_NOT_SEND_TASK_IU (0x08) +#define MPI3_SCSITASKMGMT_TASKTYPE_ABORT_TASK (0x01) +#define MPI3_SCSITASKMGMT_TASKTYPE_ABORT_TASK_SET (0x02) +#define MPI3_SCSITASKMGMT_TASKTYPE_TARGET_RESET (0x03) +#define MPI3_SCSITASKMGMT_TASKTYPE_LOGICAL_UNIT_RESET (0x05) +#define MPI3_SCSITASKMGMT_TASKTYPE_CLEAR_TASK_SET (0x06) +#define MPI3_SCSITASKMGMT_TASKTYPE_QUERY_TASK (0x07) +#define MPI3_SCSITASKMGMT_TASKTYPE_CLEAR_ACA (0x08) +#define MPI3_SCSITASKMGMT_TASKTYPE_QUERY_TASK_SET (0x09) +#define MPI3_SCSITASKMGMT_TASKTYPE_QUERY_ASYNC_EVENT (0x0a) +#define MPI3_SCSITASKMGMT_TASKTYPE_I_T_NEXUS_RESET (0x0b) +struct mpi3_scsi_task_mgmt_reply { + __le16 host_tag; + __u8 ioc_use_only02; + __u8 function; + __le16 ioc_use_only04; + __u8 ioc_use_only06; + __u8 msg_flags; + __le16 ioc_use_only08; + __le16 ioc_status; + __le32 ioc_log_info; + __le32 termination_count; + __le32 response_data; + __le32 reserved18; +}; + +#define MPI3_SCSITASKMGMT_RSPCODE_TM_COMPLETE (0x00) +#define MPI3_SCSITASKMGMT_RSPCODE_INVALID_FRAME (0x02) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_FUNCTION_NOT_SUPPORTED (0x04) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_FAILED (0x05) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_SUCCEEDED (0x08) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_INVALID_LUN (0x09) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_OVERLAPPED_TAG (0x0a) +#define MPI3_SCSITASKMGMT_RSPCODE_IO_QUEUED_ON_IOC (0x80) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_NVME_DENIED (0x81) + +/* MPI3: PEL related definitions */ +#define MPI3_PEL_LOCALE_FLAGS_NON_BLOCKING_BOOT_EVENT (0x0200) +#define MPI3_PEL_LOCALE_FLAGS_BLOCKING_BOOT_EVENT (0x0100) +#define MPI3_PEL_LOCALE_FLAGS_PCIE (0x0080) +#define MPI3_PEL_LOCALE_FLAGS_CONFIGURATION (0x0040) +#define MPI3_PEL_LOCALE_FLAGS_CONTROLER (0x0020) +#define MPI3_PEL_LOCALE_FLAGS_SAS (0x0010) +#define MPI3_PEL_LOCALE_FLAGS_EPACK (0x0008) +#define MPI3_PEL_LOCALE_FLAGS_ENCLOSURE (0x0004) +#define MPI3_PEL_LOCALE_FLAGS_PD (0x0002) +#define MPI3_PEL_LOCALE_FLAGS_VD (0x0001) +#define MPI3_PEL_CLASS_DEBUG (0x00) +#define MPI3_PEL_CLASS_PROGRESS (0x01) +#define MPI3_PEL_CLASS_INFORMATIONAL (0x02) +#define MPI3_PEL_CLASS_WARNING (0x03) +#define MPI3_PEL_CLASS_CRITICAL (0x04) +#define MPI3_PEL_CLASS_FATAL (0x05) +#define MPI3_PEL_CLASS_FAULT (0x06) + +/* MPI3: Function definitions */ +#define MPI3_BSG_FUNCTION_MGMT_PASSTHROUGH (0x0a) +#define MPI3_BSG_FUNCTION_SCSI_IO (0x20) +#define MPI3_BSG_FUNCTION_SCSI_TASK_MGMT (0x21) +#define MPI3_BSG_FUNCTION_SMP_PASSTHROUGH (0x22) +#define MPI3_BSG_FUNCTION_NVME_ENCAPSULATED (0x24) + #endif -- cgit v1.2.3 From 7dbd0dd8cde356d2a747d5c87dad7c2233dad8a4 Mon Sep 17 00:00:00 2001 From: Sumit Saxena Date: Fri, 29 Apr 2022 17:16:40 -0400 Subject: scsi: mpi3mr: Add support for NVMe passthrough Add support for management applications to send an MPI3 Encapsulated NVMe passthru command to the NVMe devices attached to an Avenger controller. Since the NVMe drives are exposed as SCSI devices by the controller, the standard NVMe applications cannot be used to interact with the drives and the command sets supported are also limited by the controller firmware. Special handling is required for MPI3 Encapsulated NVMe passthru commands for PRP/SGL setup in the commands. Link: https://lore.kernel.org/r/20220429211641.642010-8-sumit.saxena@broadcom.com Reviewed-by: Himanshu Madhani Signed-off-by: Sumit Saxena Signed-off-by: Martin K. Petersen --- include/uapi/scsi/scsi_bsg_mpi3mr.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h index b2c88d5d9c4c..fdc3517f9e19 100644 --- a/include/uapi/scsi/scsi_bsg_mpi3mr.h +++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h @@ -490,6 +490,14 @@ struct mpi3_nvme_encapsulated_error_reply { __le32 nvme_completion_entry[4]; }; +#define MPI3MR_NVME_PRP_SIZE 8 /* PRP size */ +#define MPI3MR_NVME_CMD_PRP1_OFFSET 24 /* PRP1 offset in NVMe cmd */ +#define MPI3MR_NVME_CMD_PRP2_OFFSET 32 /* PRP2 offset in NVMe cmd */ +#define MPI3MR_NVME_CMD_SGL_OFFSET 24 /* SGL offset in NVMe cmd */ +#define MPI3MR_NVME_DATA_FORMAT_PRP 0 +#define MPI3MR_NVME_DATA_FORMAT_SGL1 1 +#define MPI3MR_NVME_DATA_FORMAT_SGL2 2 + /* MPI3: task management related definitions */ struct mpi3_scsi_task_mgmt_request { __le16 host_tag; -- cgit v1.2.3 From 05e4ed1ce585637958c8ad6121999dc3109633ad Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sat, 30 Apr 2022 16:23:26 -0700 Subject: net: mscc: ocelot: remove unnecessary variable Commit 2f187bfa6f35 ("net: ethernet: ocelot: remove the need for num_stats initializer") added a flags field to the ocelot stats structure. The same behavior can be achieved without this additional field taking up extra memory. Remove this structure element to free up RAM Suggested-by: Vladimir Oltean Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 5c4f57cfa785..75739766244b 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -105,11 +105,9 @@ #define REG_RESERVED_ADDR 0xffffffff #define REG_RESERVED(reg) REG(reg, REG_RESERVED_ADDR) -#define OCELOT_STAT_FLAG_END BIT(0) - #define for_each_stat(ocelot, stat) \ for ((stat) = ocelot->stats_layout; \ - !((stat)->flags & OCELOT_STAT_FLAG_END); \ + ((stat)->name[0] != '\0'); \ (stat)++) enum ocelot_target { @@ -542,11 +540,10 @@ enum ocelot_ptp_pins { struct ocelot_stat_layout { u32 offset; - u32 flags; char name[ETH_GSTRING_LEN]; }; -#define OCELOT_STAT_END { .flags = OCELOT_STAT_FLAG_END } +#define OCELOT_STAT_END { .name = "" } struct ocelot_stats_region { struct list_head node; -- cgit v1.2.3 From 8c5b07da9bc8c056a3ddca00b4e268358f643343 Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sat, 30 Apr 2022 16:23:27 -0700 Subject: net: mscc: ocelot: add missed parentheses around macro argument Commit 2f187bfa6f35 ("net: ethernet: ocelot: remove the need for num_stats initializer") added a macro that patchwork warned it lacked parentheses around an argument. Correct this mistake. Fixes: 2f187bfa6f35 ("net: ethernet: ocelot: remove the need for num_stats initializer") Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 75739766244b..8d8d46778f7e 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -106,7 +106,7 @@ #define REG_RESERVED(reg) REG(reg, REG_RESERVED_ADDR) #define for_each_stat(ocelot, stat) \ - for ((stat) = ocelot->stats_layout; \ + for ((stat) = (ocelot)->stats_layout; \ ((stat)->name[0] != '\0'); \ (stat)++) -- cgit v1.2.3 From d639af621600dc52dd9ed0dcf62b22595f2f5b52 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 22 Mar 2022 09:16:39 +0000 Subject: net/mlx5: fs, split software and IFC flow destination definitions Separate flow destinations between software and IFC. Flow destination type passed by callers was used as the input in firmware commands and over the years software only types were added which resulted in mixing between the two. Create an IFC enum that contains only the flow destinations defined when talking to the firmware. Now that there is a proper software only enum for flow destinations the hardcoded values can be removed as the values are no longer used in firmware commands. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 11 +++++++++++ include/linux/mlx5/mlx5_ifc.h | 16 ++++++---------- 2 files changed, 17 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index e3bfed68b08a..9da9df9ae751 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -40,6 +40,17 @@ #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) +enum mlx5_flow_destination_type { + MLX5_FLOW_DESTINATION_TYPE_VPORT, + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE, + MLX5_FLOW_DESTINATION_TYPE_TIR, + MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER, + MLX5_FLOW_DESTINATION_TYPE_UPLINK, + MLX5_FLOW_DESTINATION_TYPE_PORT, + MLX5_FLOW_DESTINATION_TYPE_COUNTER, + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM, +}; + enum { MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16, MLX5_FLOW_CONTEXT_ACTION_ENCRYPT = 1 << 17, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 7d2d0ba82144..7f4ec9faa180 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1806,16 +1806,12 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_c0[0x740]; }; -enum mlx5_flow_destination_type { - MLX5_FLOW_DESTINATION_TYPE_VPORT = 0x0, - MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, - MLX5_FLOW_DESTINATION_TYPE_TIR = 0x2, - MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6, - MLX5_FLOW_DESTINATION_TYPE_UPLINK = 0x8, - - MLX5_FLOW_DESTINATION_TYPE_PORT = 0x99, - MLX5_FLOW_DESTINATION_TYPE_COUNTER = 0x100, - MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM = 0x101, +enum mlx5_ifc_flow_destination_type { + MLX5_IFC_FLOW_DESTINATION_TYPE_VPORT = 0x0, + MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, + MLX5_IFC_FLOW_DESTINATION_TYPE_TIR = 0x2, + MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6, + MLX5_IFC_FLOW_DESTINATION_TYPE_UPLINK = 0x8, }; enum mlx5_flow_table_miss_action { -- cgit v1.2.3 From 6510bc0d7cb4119ebe10f9ab43aca6fd0e5f3e73 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 15 Mar 2022 14:08:23 +0000 Subject: net/mlx5: fs, add unused destination type When the caller doesn't pass a destination fs_core will create a unused rule just so a context can be returned. This unused rule is zeroed out and its type is 0 which can be mixed up with MLX5_FLOW_DESTINATION_TYPE_VPORT. Create a dedicated type to differentiate between the two named MLX5_FLOW_DESTINATION_TYPE_NONE. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 9da9df9ae751..8135713b0d2d 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -41,6 +41,7 @@ #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) enum mlx5_flow_destination_type { + MLX5_FLOW_DESTINATION_TYPE_NONE, MLX5_FLOW_DESTINATION_TYPE_VPORT, MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE, MLX5_FLOW_DESTINATION_TYPE_TIR, -- cgit v1.2.3 From c9bc1a0ef9f613a7bc1adfff4c67dc5e5d7d1709 Mon Sep 17 00:00:00 2001 From: "Dustin L. Howett" Date: Thu, 17 Feb 2022 10:59:30 -0600 Subject: platform/chrome: cros_ec_lpcs: reserve the MEC LPC I/O ports first Some ChromeOS EC devices (such as the Framework Laptop) only map I/O ports 0x800-0x807. Making the larger reservation required by the non-MEC LPC (the 0xFF ports for the memory map, and the 0xFF ports for the parameter region) is non-viable on these devices. Since we probe the MEC EC first, we can get away with a smaller reservation that covers the MEC EC ports. If we fall back to classic LPC, we can grow the reservation to cover the memory map and the parameter region. cros_ec_lpc_probe also interacted with I/O ports 0x800-0x807 without a reservation. Restructuring the code to request the MEC LPC region first obviates the need to do so. Signed-off-by: Dustin L. Howett Signed-off-by: Tzung-Bi Shih Link: https://lore.kernel.org/r/20220217165930.15081-3-dustin@howett.net --- include/linux/platform_data/cros_ec_commands.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index c23554531961..8cfa8cfca77e 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -51,10 +51,14 @@ /* * The actual block is 0x800-0x8ff, but some BIOSes think it's 0x880-0x8ff * and they tell the kernel that so we have to think of it as two parts. + * + * Other BIOSes report only the I/O port region spanned by the Microchip + * MEC series EC; an attempt to address a larger region may fail. */ -#define EC_HOST_CMD_REGION0 0x800 -#define EC_HOST_CMD_REGION1 0x880 -#define EC_HOST_CMD_REGION_SIZE 0x80 +#define EC_HOST_CMD_REGION0 0x800 +#define EC_HOST_CMD_REGION1 0x880 +#define EC_HOST_CMD_REGION_SIZE 0x80 +#define EC_HOST_CMD_MEC_REGION_SIZE 0x8 /* EC command register bit functions */ #define EC_LPC_CMDR_DATA BIT(0) /* Data ready for host to read */ -- cgit v1.2.3 From 4c7f24f857c7cd0381dd92495db476066d1c6aec Mon Sep 17 00:00:00 2001 From: Tonghao Zhang Date: Sun, 1 May 2022 11:55:23 +0800 Subject: net: sysctl: introduce sysctl SYSCTL_THREE This patch introdues the SYSCTL_THREE. KUnit: [00:10:14] ================ sysctl_test (10 subtests) ================= [00:10:14] [PASSED] sysctl_test_api_dointvec_null_tbl_data [00:10:14] [PASSED] sysctl_test_api_dointvec_table_maxlen_unset [00:10:14] [PASSED] sysctl_test_api_dointvec_table_len_is_zero [00:10:14] [PASSED] sysctl_test_api_dointvec_table_read_but_position_set [00:10:14] [PASSED] sysctl_test_dointvec_read_happy_single_positive [00:10:14] [PASSED] sysctl_test_dointvec_read_happy_single_negative [00:10:14] [PASSED] sysctl_test_dointvec_write_happy_single_positive [00:10:14] [PASSED] sysctl_test_dointvec_write_happy_single_negative [00:10:14] [PASSED] sysctl_test_api_dointvec_write_single_less_int_min [00:10:14] [PASSED] sysctl_test_api_dointvec_write_single_greater_int_max [00:10:14] =================== [PASSED] sysctl_test =================== ./run_kselftest.sh -c sysctl ... ok 1 selftests: sysctl: sysctl.sh Cc: Luis Chamberlain Cc: Kees Cook Cc: Iurii Zaikin Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Hideaki YOSHIFUJI Cc: David Ahern Cc: Simon Horman Cc: Julian Anastasov Cc: Pablo Neira Ayuso Cc: Jozsef Kadlecsik Cc: Florian Westphal Cc: Shuah Khan Cc: Andrew Morton Cc: Alexei Starovoitov Cc: Eric Dumazet Cc: Lorenz Bauer Cc: Akhmat Karakotov Signed-off-by: Tonghao Zhang Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni --- include/linux/sysctl.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 6353d6db69b2..80263f7cdb77 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -38,10 +38,10 @@ struct ctl_table_header; struct ctl_dir; /* Keep the same order as in fs/proc/proc_sysctl.c */ -#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[0]) -#define SYSCTL_ZERO ((void *)&sysctl_vals[1]) -#define SYSCTL_ONE ((void *)&sysctl_vals[2]) -#define SYSCTL_TWO ((void *)&sysctl_vals[3]) +#define SYSCTL_ZERO ((void *)&sysctl_vals[0]) +#define SYSCTL_ONE ((void *)&sysctl_vals[1]) +#define SYSCTL_TWO ((void *)&sysctl_vals[2]) +#define SYSCTL_THREE ((void *)&sysctl_vals[3]) #define SYSCTL_FOUR ((void *)&sysctl_vals[4]) #define SYSCTL_ONE_HUNDRED ((void *)&sysctl_vals[5]) #define SYSCTL_TWO_HUNDRED ((void *)&sysctl_vals[6]) @@ -51,6 +51,7 @@ struct ctl_dir; /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ #define SYSCTL_MAXOLDUID ((void *)&sysctl_vals[10]) +#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[11]) extern const int sysctl_vals[]; -- cgit v1.2.3 From 62139f52b7e588d565aa9df81ea0a0548a68b823 Mon Sep 17 00:00:00 2001 From: Per-Daniel Olsson Date: Fri, 29 Apr 2022 09:22:08 +0200 Subject: regulator: pca9450: Make I2C Level Translator configurable Make the I2C Level Translator included in PCA9450 configurable from devicetree. The reset state is off. By setting nxp,i2c-lt-enable, the I2C Level Translator will be enabled while in STANDBY or RUN state. Signed-off-by: Per-Daniel Olsson Signed-off-by: Rickard x Andersson Link: https://lore.kernel.org/r/20220429072211.24957-2-rickaran@axis.com Signed-off-by: Mark Brown --- include/linux/regulator/pca9450.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 71902f41c919..3c01c2bf84f5 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -226,4 +226,11 @@ enum { #define WDOG_B_CFG_COLD_LDO12 0x80 #define WDOG_B_CFG_COLD 0xC0 +/* PCA9450_REG_CONFIG2 bits */ +#define I2C_LT_MASK 0x03 +#define I2C_LT_FORCE_DISABLE 0x00 +#define I2C_LT_ON_STANDBY_RUN 0x01 +#define I2C_LT_ON_RUN 0x02 +#define I2C_LT_FORCE_ENABLE 0x03 + #endif /* __LINUX_REG_PCA9450_H__ */ -- cgit v1.2.3 From 1dcbae86ee669bdb0338954cd0136863f5c96c0a Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Thu, 14 Apr 2022 12:27:24 -0700 Subject: soc: ti: wkup_m3_ipc: Add support for IO Isolation AM43xx support isolation of the IOs so that control is taken from the peripheral they are connected to and overridden by values present in the CTRL_CONF_* registers for the pad in the control module. The actual toggling happens from the wkup_m3, so use a DT property from the wkup_m3_ipc node to allow the PM code to communicate the necessity for placing the IOs into isolation to the firmware. Signed-off-by: Dave Gerlach Signed-off-by: Keerthy Signed-off-by: Drew Fustini Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20220414192722.2978837-3-dfustini@baylibre.com --- include/linux/wkup_m3_ipc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index 2bc52c6381d5..b706eac58f92 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -34,6 +34,7 @@ struct wkup_m3_ipc { int mem_type; unsigned long resume_addr; int vtt_conf; + int isolation_conf; int state; struct completion sync_complete; -- cgit v1.2.3 From ea082040fe071d2ba1f8f73792743d7ca9fb218e Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Tue, 26 Apr 2022 13:07:44 -0700 Subject: soc: ti: wkup_m3_ipc: Add support for i2c voltage scaling Allow loading of a binary containing i2c scaling sequences to be provided to the wkup_m3 firmware in order to properly scale voltage rails on the PMIC during low power modes like DeepSleep0. Proper binary format is determined by the FW in use. Code expects firmware to have 0x0C57 present as the first two bytes followed by one byte defining offset to sleep sequence followed by one byte defining offset to wake sequence and then lastly both sequences. Each sequence is a series of I2C transfers in the form: u8 length | u8 chip address | u8 byte0/reg address | u8 byte1 | u8 byteN .. The length indicates the number of bytes to transfer, including the register address. The length of each transfer is limited by the I2C buffer size of 32 bytes. Based on previous work by Russ Dill. [dfustini: replace FW_ACTION_HOTPLUG with FW_ACTION_UEVENT] Signed-off-by: Dave Gerlach Signed-off-by: Keerthy [dfustini: add NULL argument to rproc_da_to_va() call] Signed-off-by: Drew Fustini Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20220426200741.712842-3-dfustini@baylibre.com --- include/linux/wkup_m3_ipc.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index b706eac58f92..fef0fac60f8c 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -37,6 +37,9 @@ struct wkup_m3_ipc { int isolation_conf; int state; + unsigned long volt_scale_offsets; + const char *sd_fw_name; + struct completion sync_complete; struct mbox_client mbox_client; struct mbox_chan *mbox; @@ -50,6 +53,12 @@ struct wkup_m3_wakeup_src { char src[10]; }; +struct wkup_m3_scale_data_header { + u16 magic; + u8 sleep_offset; + u8 wake_offset; +} __packed; + struct wkup_m3_ipc_ops { void (*set_mem_type)(struct wkup_m3_ipc *m3_ipc, int mem_type); void (*set_resume_address)(struct wkup_m3_ipc *m3_ipc, void *addr); -- cgit v1.2.3 From 2a21f9e6d9a408dbd09a01caf5fff42c2f70fa82 Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Sun, 1 May 2022 20:32:12 -0700 Subject: soc: ti: wkup_m3_ipc: Add debug option to halt m3 in suspend Add a debugfs option to allow configurable halting of the wkup_m3 during suspend at the last possible point before low power mode entry. This condition can only be resolved through JTAG and advancing beyond the while loop in a8_lp_ds0_handler [1]. Although this hangs the system it forces the system to remain active once it has been entirely configured for low power mode entry, allowing for register inspection through JTAG to help in debugging transition errors. Halt mode can be set using the enable_off_mode entry under wkup_m3_ipc in the debugfs. [1] https://git.ti.com/cgit/processor-firmware/ti-amx3-cm3-pm-firmware/tree/src/pm_services/pm_handlers.c?h=08.02.00.006#n141 Suggested-by: Brad Griffis Signed-off-by: Dave Gerlach [dfustini: add link for a8_lp_ds0_handler() in ti-amx3-cm3-pm-firmware] Signed-off-by: Drew Fustini Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20220502033211.1383158-1-dfustini@baylibre.com --- include/linux/wkup_m3_ipc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index fef0fac60f8c..26d1eb058fa3 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -36,6 +36,7 @@ struct wkup_m3_ipc { int vtt_conf; int isolation_conf; int state; + u32 halt; unsigned long volt_scale_offsets; const char *sd_fw_name; @@ -46,6 +47,7 @@ struct wkup_m3_ipc { struct wkup_m3_ipc_ops *ops; int is_rtc_only; + struct dentry *dbg_path; }; struct wkup_m3_wakeup_src { -- cgit v1.2.3 From 3ba75c1316390b2bc39c19cb8f0f85922ab3f9ed Mon Sep 17 00:00:00 2001 From: Baskov Evgeniy Date: Thu, 3 Mar 2022 17:21:19 +0300 Subject: efi: libstub: declare DXE services table UEFI DXE services are not yet used in kernel code but are required to manipulate page table memory protection flags. Add required declarations to use DXE services functions. Signed-off-by: Baskov Evgeniy Link: https://lore.kernel.org/r/20220303142120.1975-2-baskov@ispras.ru [ardb: ignore absent DXE table but warn if the signature check fails] Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index fd266198f9d8..b1f7c6a3e5bf 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -385,6 +385,7 @@ void efi_native_runtime_setup(void); #define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d) #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) +#define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) @@ -438,6 +439,7 @@ typedef struct { } efi_config_table_type_t; #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL) +#define EFI_DXE_SERVICES_TABLE_SIGNATURE ((u64)0x565245535f455844ULL) #define EFI_2_30_SYSTEM_TABLE_REVISION ((2 << 16) | (30)) #define EFI_2_20_SYSTEM_TABLE_REVISION ((2 << 16) | (20)) -- cgit v1.2.3 From 07768c55f9c2ad64ccae3ed82447a87d8af8a687 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 19 Mar 2022 19:00:20 +0100 Subject: efi/arm64: libstub: run image in place if randomized by the loader If the loader has already placed the EFI kernel image randomly in physical memory, and indicates having done so by installing the 'fixed placement' protocol onto the image handle, don't bother randomizing the placement again in the EFI stub. Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index b1f7c6a3e5bf..580ce607d6f5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -410,6 +410,17 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) #define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) +/* + * This GUID may be installed onto the kernel image's handle as a NULL protocol + * to signal to the stub that the placement of the image should be respected, + * and moving the image in physical memory is undesirable. To ensure + * compatibility with 64k pages kernels with virtually mapped stacks, and to + * avoid defeating physical randomization, this protocol should only be + * installed if the image was placed at a randomized 128k aligned address in + * memory. + */ +#define LINUX_EFI_LOADED_IMAGE_FIXED_GUID EFI_GUID(0xf5a37b6d, 0x3344, 0x42a5, 0xb6, 0xbb, 0x97, 0x86, 0x48, 0xc1, 0x89, 0x0a) + /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) #define AMD_SEV_MEM_ENCRYPT_GUID EFI_GUID(0x0cf29b71, 0x9e51, 0x433a, 0xa3, 0xb7, 0x81, 0xf3, 0xab, 0x16, 0xb8, 0x75) -- cgit v1.2.3 From 85fbe08e4da862dc64fc10071c4a03e51b6361d0 Mon Sep 17 00:00:00 2001 From: Raghavendra Rao Ananta Date: Mon, 2 May 2022 23:38:45 +0000 Subject: KVM: arm64: Factor out firmware register handling from psci.c Common hypercall firmware register handing is currently employed by psci.c. Since the upcoming patches add more of these registers, it's better to move the generic handling to hypercall.c for a cleaner presentation. While we are at it, collect all the firmware registers under fw_reg_ids[] to help implement kvm_arm_get_fw_num_regs() and kvm_arm_copy_fw_reg_indices() in a generic way. Also, define KVM_REG_FEATURE_LEVEL_MASK using a GENMASK instead. No functional change intended. Signed-off-by: Raghavendra Rao Ananta Reviewed-by: Oliver Upton Reviewed-by: Gavin Shan [maz: fixed KVM_REG_FEATURE_LEVEL_MASK] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220502233853.1233742-2-rananta@google.com --- include/kvm/arm_hypercalls.h | 7 +++++++ include/kvm/arm_psci.h | 7 ------- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h index 0e2509d27910..5d38628a8d04 100644 --- a/include/kvm/arm_hypercalls.h +++ b/include/kvm/arm_hypercalls.h @@ -40,4 +40,11 @@ static inline void smccc_set_retval(struct kvm_vcpu *vcpu, vcpu_set_reg(vcpu, 3, a3); } +struct kvm_one_reg; + +int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); +int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); +int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); +int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); + #endif diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h index 68b96c3826c3..6e55b9283789 100644 --- a/include/kvm/arm_psci.h +++ b/include/kvm/arm_psci.h @@ -39,11 +39,4 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu) int kvm_psci_call(struct kvm_vcpu *vcpu); -struct kvm_one_reg; - -int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); -int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); -int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); -int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); - #endif /* __KVM_ARM_PSCI_H__ */ -- cgit v1.2.3 From f2b6e79c7378542e03e42fd47c0c8bf00a2fcf6b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 3 May 2022 16:44:02 +0200 Subject: Revert "usb: core: hcd: Create platform devices for onboard hubs in probe()" This reverts commit c40b62216c1aecc0dc00faf33d71bd71cb440337. The series still has built errors as reported in linux-next, so revert it for now. Reported-by: Stephen Rothwell Link: https://lore.kernel.org/r/20220502210728.0b36f3cd@canb.auug.org.au Cc: Stephen Boyd Cc: Douglas Anderson Cc: Matthias Kaehlcke Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 4ebc91c09182..548a028f2dab 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -198,7 +198,6 @@ struct usb_hcd { struct usb_hcd *shared_hcd; struct usb_hcd *primary_hcd; - struct list_head onboard_hub_devs; #define HCD_BUFFER_POOLS 4 struct dma_pool *pool[HCD_BUFFER_POOLS]; -- cgit v1.2.3 From 67a7570ad31f2a7f02550153e774bf4c630f0fef Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 3 May 2022 16:44:11 +0200 Subject: Revert "usb: misc: Add onboard_usb_hub driver" This reverts commit 0298b4b95cb373c21e6323c905589f8dac42c5b4. The series still has built errors as reported in linux-next, so revert it for now. Reported-by: Stephen Rothwell Link: https://lore.kernel.org/r/20220502210728.0b36f3cd@canb.auug.org.au Cc: Alan Stern Cc: Douglas Anderson Cc: Matthias Kaehlcke Cc: Ravi Chandra Sadineni Cc: Stephen Boyd Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/onboard_hub.h | 18 ------------------ 1 file changed, 18 deletions(-) delete mode 100644 include/linux/usb/onboard_hub.h (limited to 'include') diff --git a/include/linux/usb/onboard_hub.h b/include/linux/usb/onboard_hub.h deleted file mode 100644 index d9373230556e..000000000000 --- a/include/linux/usb/onboard_hub.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef __LINUX_USB_ONBOARD_HUB_H -#define __LINUX_USB_ONBOARD_HUB_H - -struct usb_device; -struct list_head; - -#if IS_ENABLED(CONFIG_USB_ONBOARD_HUB) -void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list); -void onboard_hub_destroy_pdevs(struct list_head *pdev_list); -#else -static inline void onboard_hub_create_pdevs(struct usb_device *parent_hub, - struct list_head *pdev_list) {} -static inline void onboard_hub_destroy_pdevs(struct list_head *pdev_list) {} -#endif - -#endif /* __LINUX_USB_ONBOARD_HUB_H */ -- cgit v1.2.3 From 1a9517a0a43040b77b5ef64d9053df214ba33d17 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 3 May 2022 16:44:24 +0200 Subject: Revert "of/platform: Add stubs for of_platform_device_create/destroy()" This reverts commit 8e8b11956486e3fe8cacf54a1d492ebdd8cc1fb2. The series still has built errors as reported in linux-next, so revert it for now. Reported-by: Stephen Rothwell Link: https://lore.kernel.org/r/20220502210728.0b36f3cd@canb.auug.org.au Cc: Stephen Boyd Cc: Douglas Anderson Cc: Rob Herring Cc: Matthias Kaehlcke Signed-off-by: Greg Kroah-Hartman --- include/linux/of_platform.h | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index d15b6cd5e1c3..84a966623e78 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -61,18 +61,16 @@ static inline struct platform_device *of_find_device_by_node(struct device_node } #endif -extern int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent); - -#ifdef CONFIG_OF_ADDRESS /* Platform devices and busses creation */ extern struct platform_device *of_platform_device_create(struct device_node *np, const char *bus_id, struct device *parent); extern int of_platform_device_destroy(struct device *dev, void *data); - +extern int of_platform_bus_probe(struct device_node *root, + const struct of_device_id *matches, + struct device *parent); +#ifdef CONFIG_OF_ADDRESS extern int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, @@ -86,18 +84,6 @@ extern int devm_of_platform_populate(struct device *dev); extern void devm_of_platform_depopulate(struct device *dev); #else -/* Platform devices and busses creation */ -static inline struct platform_device *of_platform_device_create(struct device_node *np, - const char *bus_id, - struct device *parent) -{ - return NULL; -} -static inline int of_platform_device_destroy(struct device *dev, void *data) -{ - return -ENODEV; -} - static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, -- cgit v1.2.3 From 52f988d757c78cea06b1d5c75791a7fe1638ef86 Mon Sep 17 00:00:00 2001 From: Zelong Dong Date: Fri, 7 Jan 2022 10:39:30 +0800 Subject: dt-bindings: reset: add bindings for the Meson-S4 SoC Reset Controller Add DT bindings for the Meson-S4 SoC Reset Controller include file. Signed-off-by: Zelong Dong Reviewed-by: Martin Blumenstingl Signed-off-by: Philipp Zabel Link: https://lore.kernel.org/r/20220107023931.13251-3-zelong.dong@amlogic.com --- include/dt-bindings/reset/amlogic,meson-s4-reset.h | 125 +++++++++++++++++++++ 1 file changed, 125 insertions(+) create mode 100644 include/dt-bindings/reset/amlogic,meson-s4-reset.h (limited to 'include') diff --git a/include/dt-bindings/reset/amlogic,meson-s4-reset.h b/include/dt-bindings/reset/amlogic,meson-s4-reset.h new file mode 100644 index 000000000000..eab428eb8ad6 --- /dev/null +++ b/include/dt-bindings/reset/amlogic,meson-s4-reset.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */ +/* + * Copyright (c) 2021 Amlogic, Inc. All rights reserved. + * Author: Zelong Dong + * + */ + +#ifndef _DT_BINDINGS_AMLOGIC_MESON_S4_RESET_H +#define _DT_BINDINGS_AMLOGIC_MESON_S4_RESET_H + +/* RESET0 */ +#define RESET_USB_DDR0 0 +#define RESET_USB_DDR1 1 +#define RESET_USB_DDR2 2 +#define RESET_USB_DDR3 3 +#define RESET_USBCTRL 4 +/* 5-7 */ +#define RESET_USBPHY20 8 +#define RESET_USBPHY21 9 +/* 10-15 */ +#define RESET_HDMITX_APB 16 +#define RESET_BRG_VCBUS_DEC 17 +#define RESET_VCBUS 18 +#define RESET_VID_PLL_DIV 19 +#define RESET_VDI6 20 +#define RESET_GE2D 21 +#define RESET_HDMITXPHY 22 +#define RESET_VID_LOCK 23 +#define RESET_VENCL 24 +#define RESET_VDAC 25 +#define RESET_VENCP 26 +#define RESET_VENCI 27 +#define RESET_RDMA 28 +#define RESET_HDMI_TX 29 +#define RESET_VIU 30 +#define RESET_VENC 31 + +/* RESET1 */ +#define RESET_AUDIO 32 +#define RESET_MALI_APB 33 +#define RESET_MALI 34 +#define RESET_DDR_APB 35 +#define RESET_DDR 36 +#define RESET_DOS_APB 37 +#define RESET_DOS 38 +/* 39-47 */ +#define RESET_ETH 48 +/* 49-51 */ +#define RESET_DEMOD 52 +/* 53-63 */ + +/* RESET2 */ +#define RESET_ABUS_ARB 64 +#define RESET_IR_CTRL 65 +#define RESET_TEMPSENSOR_DDR 66 +#define RESET_TEMPSENSOR_PLL 67 +/* 68-71 */ +#define RESET_SMART_CARD 72 +#define RESET_SPICC0 73 +/* 74 */ +#define RESET_RSA 75 +/* 76-79 */ +#define RESET_MSR_CLK 80 +#define RESET_SPIFC 81 +#define RESET_SARADC 82 +/* 83-87 */ +#define RESET_ACODEC 88 +#define RESET_CEC 89 +#define RESET_AFIFO 90 +#define RESET_WATCHDOG 91 +/* 92-95 */ + +/* RESET3 */ +/* 96-127 */ + +/* RESET4 */ +/* 128-131 */ +#define RESET_PWM_AB 132 +#define RESET_PWM_CD 133 +#define RESET_PWM_EF 134 +#define RESET_PWM_GH 135 +#define RESET_PWM_IJ 136 +/* 137 */ +#define RESET_UART_A 138 +#define RESET_UART_B 139 +#define RESET_UART_C 140 +#define RESET_UART_D 141 +#define RESET_UART_E 142 +/* 143 */ +#define RESET_I2C_S_A 144 +#define RESET_I2C_M_A 145 +#define RESET_I2C_M_B 146 +#define RESET_I2C_M_C 147 +#define RESET_I2C_M_D 148 +#define RESET_I2C_M_E 149 +/* 150-151 */ +#define RESET_SD_EMMC_A 152 +#define RESET_SD_EMMC_B 153 +#define RESET_NAND_EMMC 154 +/* 155-159 */ + +/* RESET5 */ +#define RESET_BRG_VDEC_PIPL0 160 +#define RESET_BRG_HEVCF_PIPL0 161 +/* 162 */ +#define RESET_BRG_HCODEC_PIPL0 163 +#define RESET_BRG_GE2D_PIPL0 164 +#define RESET_BRG_VPU_PIPL0 165 +#define RESET_BRG_CPU_PIPL0 166 +#define RESET_BRG_MALI_PIPL0 167 +/* 168 */ +#define RESET_BRG_MALI_PIPL1 169 +/* 170-171 */ +#define RESET_BRG_HEVCF_PIPL1 172 +#define RESET_BRG_HEVCB_PIPL1 173 +/* 174-183 */ +#define RESET_RAMA 184 +/* 185-186 */ +#define RESET_BRG_NIC_VAPB 187 +#define RESET_BRG_NIC_DSU 188 +#define RESET_BRG_NIC_SYSCLK 189 +#define RESET_BRG_NIC_MAIN 190 +#define RESET_BRG_NIC_ALL 191 + +#endif -- cgit v1.2.3 From 1ac17586c950a2c129393f8a92901a2b357acf24 Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Mon, 2 May 2022 13:17:40 -0500 Subject: of: overlay: add entry to of_overlay_action_name[] The values of enum of_overlay_notify_action are used to index into array of_overlay_action_name. Add an entry to of_overlay_action_name for the value recently added to of_overlay_notify_action. Array of_overlay_action_name[] is moved into include/linux/of.h adjacent to enum of_overlay_notify_action to make the connection between the two more obvious if either is modified in the future. The only use of of_overlay_action_name is for error reporting in overlay_notify(). All callers of overlay_notify() report the same error, but with fewer details. Remove the redundant error reports in the callers. Fixes: 067c098766c6 ("of: overlay: rework overlay apply and remove kfree()s") Reported-by: Dan Carpenter Signed-off-by: Frank Rowand Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20220502181742.1402826-2-frowand.list@gmail.com --- include/linux/of.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index 17741eee0ca4..f0a5d6b10c5a 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1550,6 +1550,19 @@ enum of_overlay_notify_action { OF_OVERLAY_POST_REMOVE, }; +static inline char *of_overlay_action_name(enum of_overlay_notify_action action) +{ + static char *of_overlay_action_name[] = { + "init", + "pre-apply", + "post-apply", + "pre-remove", + "post-remove", + }; + + return of_overlay_action_name[action]; +} + struct of_overlay_notify_data { struct device_node *overlay; struct device_node *target; -- cgit v1.2.3 From 282d8998e9979c2186af7f7d22366f2fc3149838 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 8 Mar 2022 15:45:33 -0800 Subject: srcu: Prevent expedited GPs and blocking readers from consuming CPU If an SRCU reader blocks while a synchronize_srcu_expedited() waits for that same reader, then that grace period will spawn an endless series of workqueue handlers, consuming a full CPU. This quickly gets pointless because consuming more CPU isn't going to make that reader get done faster, especially if it is blocked waiting for an external event. This commit therefore spawns at most one pair of back-to-back workqueue handlers per expedited grace period phase, instead inserting increasing delays as that grace period phase grows older, but capped at 10 jiffies. In any case, if there have been at least 100 back-to-back workqueue handlers within a single jiffy, regardless of grace period or grace-period phase, then a one-jiffy delay is inserted. [ paulmck: Apply feedback from kernel test robot. ] Cc: Neeraj Upadhyay Reported-by: Song Liu Tested-by: kernel test robot Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 1b9ff4ed37e4..e3014319d1ad 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -71,9 +71,11 @@ struct srcu_struct { unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + unsigned long srcu_gp_start; /* Last GP start timestamp (jiffies) */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ + unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ @@ -83,6 +85,8 @@ struct srcu_struct { atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ /* callback for the barrier */ /* operation. */ + unsigned long reschedule_jiffies; + unsigned long reschedule_count; struct delayed_work work; struct lockdep_map dep_map; }; -- cgit v1.2.3 From c29722fad4aabbf6bb841b8f058f858ec911df56 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20G=C3=B6ttsche?= Date: Tue, 8 Mar 2022 18:09:26 +0100 Subject: selinux: log anon inode class name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Log the anonymous inode class name in the security hook inode_init_security_anon. This name is the key for name based type transitions on the anon_inode security class on creation. Example: type=AVC msg=audit(02/16/22 22:02:50.585:216) : avc: granted \ { create } for pid=2136 comm=mariadbd anonclass=[io_uring] \ scontext=system_u:system_r:mysqld_t:s0 \ tcontext=system_u:system_r:mysqld_iouring_t:s0 tclass=anon_inode Add a new LSM audit data type holding the inode and the class name. Signed-off-by: Christian Göttsche [PM: adjusted 'anonclass' to be a trusted string, cgzones approved] Signed-off-by: Paul Moore --- include/linux/lsm_audit.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index 17d02eda9538..97a8b21eb033 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -76,6 +76,7 @@ struct common_audit_data { #define LSM_AUDIT_DATA_IBENDPORT 14 #define LSM_AUDIT_DATA_LOCKDOWN 15 #define LSM_AUDIT_DATA_NOTIFICATION 16 +#define LSM_AUDIT_DATA_ANONINODE 17 union { struct path path; struct dentry *dentry; @@ -96,6 +97,7 @@ struct common_audit_data { struct lsm_ibpkey_audit *ibpkey; struct lsm_ibendport_audit *ibendport; int reason; + const char *anonclass; } u; /* this union contains LSM specific data */ union { -- cgit v1.2.3 From 05714cab7d63b189894235cf310fae7d6ffc2e9b Mon Sep 17 00:00:00 2001 From: Raghavendra Rao Ananta Date: Mon, 2 May 2022 23:38:46 +0000 Subject: KVM: arm64: Setup a framework for hypercall bitmap firmware registers KVM regularly introduces new hypercall services to the guests without any consent from the userspace. This means, the guests can observe hypercall services in and out as they migrate across various host kernel versions. This could be a major problem if the guest discovered a hypercall, started using it, and after getting migrated to an older kernel realizes that it's no longer available. Depending on how the guest handles the change, there's a potential chance that the guest would just panic. As a result, there's a need for the userspace to elect the services that it wishes the guest to discover. It can elect these services based on the kernels spread across its (migration) fleet. To remedy this, extend the existing firmware pseudo-registers, such as KVM_REG_ARM_PSCI_VERSION, but by creating a new COPROC register space for all the hypercall services available. These firmware registers are categorized based on the service call owners, but unlike the existing firmware pseudo-registers, they hold the features supported in the form of a bitmap. During the VM initialization, the registers are set to upper-limit of the features supported by the corresponding registers. It's expected that the VMMs discover the features provided by each register via GET_ONE_REG, and write back the desired values using SET_ONE_REG. KVM allows this modification only until the VM has started. Some of the standard features are not mapped to any bits of the registers. But since they can recreate the original problem of making it available without userspace's consent, they need to be explicitly added to the case-list in kvm_hvc_call_default_allowed(). Any function-id that's not enabled via the bitmap, or not listed in kvm_hvc_call_default_allowed, will be returned as SMCCC_RET_NOT_SUPPORTED to the guest. Older userspace code can simply ignore the feature and the hypercall services will be exposed unconditionally to the guests, thus ensuring backward compatibility. In this patch, the framework adds the register only for ARM's standard secure services (owner value 4). Currently, this includes support only for ARM True Random Number Generator (TRNG) service, with bit-0 of the register representing mandatory features of v1.0. Other services are momentarily added in the upcoming patches. Signed-off-by: Raghavendra Rao Ananta Reviewed-by: Gavin Shan [maz: reduced the scope of some helpers, tidy-up bitmap max values, dropped error-only fast path] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220502233853.1233742-3-rananta@google.com --- include/kvm/arm_hypercalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h index 5d38628a8d04..1188f116cf4e 100644 --- a/include/kvm/arm_hypercalls.h +++ b/include/kvm/arm_hypercalls.h @@ -42,6 +42,7 @@ static inline void smccc_set_retval(struct kvm_vcpu *vcpu, struct kvm_one_reg; +void kvm_arm_init_hypercalls(struct kvm *kvm); int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); -- cgit v1.2.3 From c2aa2dfef243efe213a480a1ee8566507a5152f4 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Tue, 3 May 2022 01:09:56 -0700 Subject: seccomp: Add wait_killable semantic to seccomp user notifier This introduces a per-filter flag (SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) that makes it so that when notifications are received by the supervisor the notifying process will transition to wait killable semantics. Although wait killable isn't a set of semantics formally exposed to userspace, the concept is searchable. If the notifying process is signaled prior to the notification being received by the userspace agent, it will be handled as normal. One quirk about how this is handled is that the notifying process only switches to TASK_KILLABLE if it receives a wakeup from either an addfd or a signal. This is to avoid an unnecessary wakeup of the notifying task. The reasons behind switching into wait_killable only after userspace receives the notification are: * Avoiding unncessary work - Often, workloads will perform work that they may abort (request racing comes to mind). This allows for syscalls to be aborted safely prior to the notification being received by the supervisor. In this, the supervisor doesn't end up doing work that the workload does not want to complete anyways. * Avoiding side effects - We don't want the syscall to be interruptible once the supervisor starts doing work because it may not be trivial to reverse the operation. For example, unmounting a file system may take a long time, and it's hard to rollback, or treat that as reentrant. * Avoid breaking runtimes - Various runtimes do not GC when they are during a syscall (or while running native code that subsequently calls a syscall). If many notifications are blocked, and not picked up by the supervisor, this can get the application into a bad state. Signed-off-by: Sargun Dhillon Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220503080958.20220-2-sargun@sargun.me --- include/linux/seccomp.h | 3 ++- include/uapi/linux/seccomp.h | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 0c564e5d40ff..d31d76be4982 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -8,7 +8,8 @@ SECCOMP_FILTER_FLAG_LOG | \ SECCOMP_FILTER_FLAG_SPEC_ALLOW | \ SECCOMP_FILTER_FLAG_NEW_LISTENER | \ - SECCOMP_FILTER_FLAG_TSYNC_ESRCH) + SECCOMP_FILTER_FLAG_TSYNC_ESRCH | \ + SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) /* sizeof() the first published struct seccomp_notif_addfd */ #define SECCOMP_NOTIFY_ADDFD_SIZE_VER0 24 diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 78074254ab98..0fdc6ef02b94 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -23,6 +23,8 @@ #define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) #define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) #define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4) +/* Received notifications wait in killable state (only respond to fatal signals) */ +#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5) /* * All BPF programs must return a 32-bit value. -- cgit v1.2.3 From 41b3c69bf9414375319290c59f198ff5c71d273f Mon Sep 17 00:00:00 2001 From: Kishen Maloor Date: Mon, 2 May 2022 13:52:36 -0700 Subject: mptcp: expose server_side attribute in MPTCP netlink events This change records the 'server_side' attribute of MPTCP_EVENT_CREATED and MPTCP_EVENT_ESTABLISHED events to inform their recipient about the Client/Server role of the running MPTCP application. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/246 Acked-by: Paolo Abeni Signed-off-by: Kishen Maloor Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 9690efedb5fa..e41ea01a94bb 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -188,6 +188,7 @@ enum mptcp_event_attr { MPTCP_ATTR_IF_IDX, /* s32 */ MPTCP_ATTR_RESET_REASON,/* u32 */ MPTCP_ATTR_RESET_FLAGS, /* u32 */ + MPTCP_ATTR_SERVER_SIDE, /* u8 */ __MPTCP_ATTR_AFTER_LAST }; -- cgit v1.2.3 From 58caed3dacb4354a25a1aa8d2febc3e9648ba1f4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 May 2022 16:27:03 -0700 Subject: netdev: reshuffle netif_napi_add() APIs to allow dropping weight Most drivers should not have to worry about selecting the right weight for their NAPI instances and pass NAPI_POLL_WEIGHT. It'd be best if we didn't require the argument at all and selected the default internally. This change prepares the ground for such reshuffling, allowing for a smooth transition. The following API should remain after the next release cycle: netif_napi_add() netif_napi_add_weight() netif_napi_add_tx() netif_napi_add_tx_weight() Where the _weight() variants take an explicit weight argument. I opted for a _weight() suffix rather than a __ prefix, because we use __ in places to mean that caller needs to also issue a synchronize_net() call. Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20220502232703.396351-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 50 +++++++++++++++++++++++++++++++---------------- 1 file changed, 33 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4aba92a4042a..eaf66e57d891 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2499,37 +2499,53 @@ static inline void *netdev_priv(const struct net_device *dev) */ #define NAPI_POLL_WEIGHT 64 +void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight); + /** - * netif_napi_add - initialize a NAPI context - * @dev: network device - * @napi: NAPI context - * @poll: polling function - * @weight: default weight + * netif_napi_add() - initialize a NAPI context + * @dev: network device + * @napi: NAPI context + * @poll: polling function + * @weight: default weight * * netif_napi_add() must be used to initialize a NAPI context prior to calling * *any* of the other NAPI-related functions. */ -void netif_napi_add(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight); +static inline void +netif_napi_add(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight) +{ + netif_napi_add_weight(dev, napi, poll, weight); +} + +static inline void +netif_napi_add_tx_weight(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight) +{ + set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); + netif_napi_add_weight(dev, napi, poll, weight); +} + +#define netif_tx_napi_add netif_napi_add_tx_weight /** - * netif_tx_napi_add - initialize a NAPI context - * @dev: network device - * @napi: NAPI context - * @poll: polling function - * @weight: default weight + * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only + * @dev: network device + * @napi: NAPI context + * @poll: polling function * * This variant of netif_napi_add() should be used from drivers using NAPI * to exclusively poll a TX queue. * This will avoid we add it into napi_hash[], thus polluting this hash table. */ -static inline void netif_tx_napi_add(struct net_device *dev, +static inline void netif_napi_add_tx(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), - int weight) + int (*poll)(struct napi_struct *, int)) { - set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); - netif_napi_add(dev, napi, poll, weight); + netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } /** -- cgit v1.2.3 From c674df973ad8af2074c834788e167332d81309fa Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 8 Mar 2022 20:36:15 +0200 Subject: net/mlx5: Store IPsec ESN update work in XFRM state mlx5 IPsec code updated ESN through workqueue with allocation calls in the data path, which can be saved easily if the work is created during XFRM state initialization routine. The locking used later in the work didn't protect from anything because change of HW context is possible during XFRM state add or delete only, which can cancel work and make sure that it is not running. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 0f2596297f6a..a2720ebbb9fd 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -127,8 +127,8 @@ struct mlx5_accel_esp_xfrm * mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, const struct mlx5_accel_esp_xfrm_attrs *attrs); void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm); -int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, - const struct mlx5_accel_esp_xfrm_attrs *attrs); +void mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, + const struct mlx5_accel_esp_xfrm_attrs *attrs); #else @@ -145,9 +145,11 @@ mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, } static inline void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm) {} -static inline int +static inline void mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, - const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; } + const struct mlx5_accel_esp_xfrm_attrs *attrs) +{ +} #endif /* CONFIG_MLX5_EN_IPSEC */ #endif /* __MLX5_ACCEL_H__ */ -- cgit v1.2.3 From 2ea36e2e4ad2b77bd5d45142a529b72eb5ca9156 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 8 Mar 2022 20:55:00 +0200 Subject: net/mlx5: Remove useless validity check All callers build xfrm attributes with help of mlx5e_ipsec_build_accel_xfrm_attrs() function that ensure validity of attributes. There is no need to recheck them again. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index a2720ebbb9fd..9c511d466e55 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -36,10 +36,6 @@ #include -enum mlx5_accel_esp_aes_gcm_keymat_iv_algo { - MLX5_ACCEL_ESP_AES_GCM_IV_ALGO_SEQ, -}; - enum mlx5_accel_esp_flags { MLX5_ACCEL_ESP_FLAGS_TUNNEL = 0, /* Default */ MLX5_ACCEL_ESP_FLAGS_TRANSPORT = 1UL << 0, @@ -57,14 +53,9 @@ enum mlx5_accel_esp_keymats { MLX5_ACCEL_ESP_KEYMAT_AES_GCM, }; -enum mlx5_accel_esp_replay { - MLX5_ACCEL_ESP_REPLAY_NONE, - MLX5_ACCEL_ESP_REPLAY_BMP, -}; struct aes_gcm_keymat { u64 seq_iv; - enum mlx5_accel_esp_aes_gcm_keymat_iv_algo iv_algo; u32 salt; u32 icv_len; @@ -81,7 +72,6 @@ struct mlx5_accel_esp_xfrm_attrs { u32 tfc_pad; u32 flags; u32 sa_handle; - enum mlx5_accel_esp_replay replay_type; union { struct { u32 size; -- cgit v1.2.3 From c6e3b421c7079af67201351c9faff62613e06f40 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 9 Mar 2022 10:35:05 +0200 Subject: net/mlx5: Merge various control path IPsec headers into one file The mlx5 IPsec code has logical separation between code that operates with XFRM objects (ipsec.c), HW objects (ipsec_offload.c), flow steering logic (ipsec_fs.c) and data path (ipsec_rxtx.c). Such separation makes sense for C-files, but isn't needed at all for H-files as they are included in batch anyway. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 145 --------------------------------------------- 1 file changed, 145 deletions(-) delete mode 100644 include/linux/mlx5/accel.h (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h deleted file mode 100644 index 9c511d466e55..000000000000 --- a/include/linux/mlx5/accel.h +++ /dev/null @@ -1,145 +0,0 @@ -/* - * Copyright (c) 2018 Mellanox Technologies. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - * - */ - -#ifndef __MLX5_ACCEL_H__ -#define __MLX5_ACCEL_H__ - -#include - -enum mlx5_accel_esp_flags { - MLX5_ACCEL_ESP_FLAGS_TUNNEL = 0, /* Default */ - MLX5_ACCEL_ESP_FLAGS_TRANSPORT = 1UL << 0, - MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED = 1UL << 1, - MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP = 1UL << 2, -}; - -enum mlx5_accel_esp_action { - MLX5_ACCEL_ESP_ACTION_DECRYPT, - MLX5_ACCEL_ESP_ACTION_ENCRYPT, -}; - -enum mlx5_accel_esp_keymats { - MLX5_ACCEL_ESP_KEYMAT_AES_NONE, - MLX5_ACCEL_ESP_KEYMAT_AES_GCM, -}; - - -struct aes_gcm_keymat { - u64 seq_iv; - - u32 salt; - u32 icv_len; - - u32 key_len; - u32 aes_key[256 / 32]; -}; - -struct mlx5_accel_esp_xfrm_attrs { - enum mlx5_accel_esp_action action; - u32 esn; - __be32 spi; - u32 seq; - u32 tfc_pad; - u32 flags; - u32 sa_handle; - union { - struct { - u32 size; - - } bmp; - } replay; - enum mlx5_accel_esp_keymats keymat_type; - union { - struct aes_gcm_keymat aes_gcm; - } keymat; - - union { - __be32 a4; - __be32 a6[4]; - } saddr; - - union { - __be32 a4; - __be32 a6[4]; - } daddr; - - u8 is_ipv6; -}; - -struct mlx5_accel_esp_xfrm { - struct mlx5_core_dev *mdev; - struct mlx5_accel_esp_xfrm_attrs attrs; -}; - -enum mlx5_accel_ipsec_cap { - MLX5_ACCEL_IPSEC_CAP_DEVICE = 1 << 0, - MLX5_ACCEL_IPSEC_CAP_ESP = 1 << 1, - MLX5_ACCEL_IPSEC_CAP_IPV6 = 1 << 2, - MLX5_ACCEL_IPSEC_CAP_LSO = 1 << 3, - MLX5_ACCEL_IPSEC_CAP_ESN = 1 << 4, -}; - -#ifdef CONFIG_MLX5_EN_IPSEC - -u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev); - -struct mlx5_accel_esp_xfrm * -mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, - const struct mlx5_accel_esp_xfrm_attrs *attrs); -void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm); -void mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, - const struct mlx5_accel_esp_xfrm_attrs *attrs); - -#else - -static inline u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) -{ - return 0; -} - -static inline struct mlx5_accel_esp_xfrm * -mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, - const struct mlx5_accel_esp_xfrm_attrs *attrs) -{ - return ERR_PTR(-EOPNOTSUPP); -} -static inline void -mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm) {} -static inline void -mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, - const struct mlx5_accel_esp_xfrm_attrs *attrs) -{ -} - -#endif /* CONFIG_MLX5_EN_IPSEC */ -#endif /* __MLX5_ACCEL_H__ */ -- cgit v1.2.3 From 1c4a59b9fa98c222bd6a8fa82bff942312165c1a Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 27 Mar 2022 19:23:19 +0300 Subject: net/mlx5: Remove not-supported ICV length mlx5 doesn't allow to configure any AEAD ICV length other than 128, so remove the logic that configures other unsupported values. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 7f4ec9faa180..7bab3e51c61e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -11379,8 +11379,6 @@ enum { enum { MLX5_IPSEC_OBJECT_ICV_LEN_16B, - MLX5_IPSEC_OBJECT_ICV_LEN_12B, - MLX5_IPSEC_OBJECT_ICV_LEN_8B, }; struct mlx5_ifc_ipsec_obj_bits { -- cgit v1.2.3 From 7b33a09d036ffd9a04506122840629c7e870cf08 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Wed, 4 May 2022 03:24:40 +0000 Subject: KVM: arm64: Add support for userspace to suspend a vCPU Introduce a new MP state, KVM_MP_STATE_SUSPENDED, which indicates a vCPU is in a suspended state. In the suspended state the vCPU will block until a wakeup event (pending interrupt) is recognized. Add a new system event type, KVM_SYSTEM_EVENT_WAKEUP, to indicate to userspace that KVM has recognized one such wakeup event. It is the responsibility of userspace to then make the vCPU runnable, or leave it suspended until the next wakeup event. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220504032446.4133305-7-oupton@google.com --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 6a184d260c7f..7f72fb7b05f2 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -444,6 +444,7 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_SHUTDOWN 1 #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 +#define KVM_SYSTEM_EVENT_WAKEUP 4 __u32 type; __u32 ndata; union { @@ -646,6 +647,7 @@ struct kvm_vapic_addr { #define KVM_MP_STATE_OPERATING 7 #define KVM_MP_STATE_LOAD 8 #define KVM_MP_STATE_AP_RESET_HOLD 9 +#define KVM_MP_STATE_SUSPENDED 10 struct kvm_mp_state { __u32 mp_state; -- cgit v1.2.3 From bfbab44568779e1682bc6f63688bb9c965f0e74a Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Wed, 4 May 2022 03:24:41 +0000 Subject: KVM: arm64: Implement PSCI SYSTEM_SUSPEND ARM DEN0022D.b 5.19 "SYSTEM_SUSPEND" describes a PSCI call that allows software to request that a system be placed in the deepest possible low-power state. Effectively, software can use this to suspend itself to RAM. Unfortunately, there really is no good way to implement a system-wide PSCI call in KVM. Any precondition checks done in the kernel will need to be repeated by userspace since there is no good way to protect a critical section that spans an exit to userspace. SYSTEM_RESET and SYSTEM_OFF are equally plagued by this issue, although no users have seemingly cared for the relatively long time these calls have been supported. The solution is to just make the whole implementation userspace's problem. Introduce a new system event, KVM_SYSTEM_EVENT_SUSPEND, that indicates to userspace a calling vCPU has invoked PSCI SYSTEM_SUSPEND. Additionally, add a CAP to get buy-in from userspace for this new exit type. Only advertise the SYSTEM_SUSPEND PSCI call if userspace has opted in. If a vCPU calls SYSTEM_SUSPEND, punt straight to userspace. Provide explicit documentation of userspace's responsibilites for the exit and point to the PSCI specification to describe the actual PSCI call. Reviewed-by: Reiji Watanabe Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220504032446.4133305-8-oupton@google.com --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 7f72fb7b05f2..32c56384fd08 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -445,6 +445,7 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 #define KVM_SYSTEM_EVENT_WAKEUP 4 +#define KVM_SYSTEM_EVENT_SUSPEND 5 __u32 type; __u32 ndata; union { @@ -1154,6 +1155,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DISABLE_QUIRKS2 213 /* #define KVM_CAP_VM_TSC_CONTROL 214 */ #define KVM_CAP_SYSTEM_EVENT_DATA 215 +#define KVM_CAP_ARM_SYSTEM_SUSPEND 216 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 6625ffb90f44efc28a3fe1432191a4eacb08c915 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 3 May 2022 15:13:52 +0800 Subject: dt-bindings: mediatek: mt8195: Add binding for MM IOMMU This patch adds descriptions for mt8195 IOMMU which also use ARM Short-Descriptor translation table format. In mt8195, there are two smi-common HW and IOMMU, one is for vdo(video output), the other is for vpp(video processing pipe). They connects with different smi-larbs, then some setting(larbid_remap) is different. Differentiate them with the compatible string. Something like this: IOMMU(VDO) IOMMU(VPP) | | SMI_COMMON_VDO SMI_COMMON_VPP --------------- ---------------- | | ... | | ... larb0 larb2 ... larb1 larb3 ... Another change is that we have a new IOMMU that is for infra master like PCIe and USB. The infra master don't have the larb and ports, thus we rename the port header file to mt8195-memory-port.h rather than mt8195-larb-port.h. Also, the IOMMU is not only for MM, thus, we don't call it "m4u" which means "MultiMedia Memory Management UNIT". thus, use the "iommu" as the compatiable string. Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20220503071427.2285-2-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- include/dt-bindings/memory/mt8195-memory-port.h | 390 ++++++++++++++++++++++++ 1 file changed, 390 insertions(+) create mode 100644 include/dt-bindings/memory/mt8195-memory-port.h (limited to 'include') diff --git a/include/dt-bindings/memory/mt8195-memory-port.h b/include/dt-bindings/memory/mt8195-memory-port.h new file mode 100644 index 000000000000..c10e8b61f1e8 --- /dev/null +++ b/include/dt-bindings/memory/mt8195-memory-port.h @@ -0,0 +1,390 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Yong Wu + */ +#ifndef _DT_BINDINGS_MEMORY_MT8195_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT8195_LARB_PORT_H_ + +#include + +/* + * MM IOMMU supports 16GB dma address. We separate it to four ranges: + * 0 ~ 4G; 4G ~ 8G; 8G ~ 12G; 12G ~ 16G, we could adjust these masters + * locate in anyone region. BUT: + * a) Make sure all the ports inside a larb are in one range. + * b) The iova of any master can NOT cross the 4G/8G/12G boundary. + * + * This is the suggested mapping in this SoC: + * + * modules dma-address-region larbs-ports + * disp 0 ~ 4G larb0/1/2/3 + * vcodec 4G ~ 8G larb19/20/21/22/23/24 + * cam/mdp 8G ~ 12G the other larbs. + * N/A 12G ~ 16G + * CCU0 0x24000_0000 ~ 0x243ff_ffff larb18: port 0/1 + * CCU1 0x24400_0000 ~ 0x247ff_ffff larb18: port 2/3 + * + * This SoC have two IOMMU HWs, this is the detailed connected information: + * iommu-vdo: larb0/2/5/7/9/10/11/13/17/19/21/24/25/28 + * iommu-vpp: larb1/3/4/6/8/12/14/16/18/20/22/23/26/27 + */ + +/* MM IOMMU ports */ +/* larb0 */ +#define M4U_PORT_L0_DISP_RDMA0 MTK_M4U_ID(0, 0) +#define M4U_PORT_L0_DISP_WDMA0 MTK_M4U_ID(0, 1) +#define M4U_PORT_L0_DISP_OVL0_RDMA0 MTK_M4U_ID(0, 2) +#define M4U_PORT_L0_DISP_OVL0_RDMA1 MTK_M4U_ID(0, 3) +#define M4U_PORT_L0_DISP_OVL0_HDR MTK_M4U_ID(0, 4) +#define M4U_PORT_L0_DISP_FAKE0 MTK_M4U_ID(0, 5) + +/* larb1 */ +#define M4U_PORT_L1_DISP_RDMA0 MTK_M4U_ID(1, 0) +#define M4U_PORT_L1_DISP_WDMA0 MTK_M4U_ID(1, 1) +#define M4U_PORT_L1_DISP_OVL0_RDMA0 MTK_M4U_ID(1, 2) +#define M4U_PORT_L1_DISP_OVL0_RDMA1 MTK_M4U_ID(1, 3) +#define M4U_PORT_L1_DISP_OVL0_HDR MTK_M4U_ID(1, 4) +#define M4U_PORT_L1_DISP_FAKE0 MTK_M4U_ID(1, 5) + +/* larb2 */ +#define M4U_PORT_L2_MDP_RDMA0 MTK_M4U_ID(2, 0) +#define M4U_PORT_L2_MDP_RDMA2 MTK_M4U_ID(2, 1) +#define M4U_PORT_L2_MDP_RDMA4 MTK_M4U_ID(2, 2) +#define M4U_PORT_L2_MDP_RDMA6 MTK_M4U_ID(2, 3) +#define M4U_PORT_L2_DISP_FAKE1 MTK_M4U_ID(2, 4) + +/* larb3 */ +#define M4U_PORT_L3_MDP_RDMA1 MTK_M4U_ID(3, 0) +#define M4U_PORT_L3_MDP_RDMA3 MTK_M4U_ID(3, 1) +#define M4U_PORT_L3_MDP_RDMA5 MTK_M4U_ID(3, 2) +#define M4U_PORT_L3_MDP_RDMA7 MTK_M4U_ID(3, 3) +#define M4U_PORT_L3_HDR_DS MTK_M4U_ID(3, 4) +#define M4U_PORT_L3_HDR_ADL MTK_M4U_ID(3, 5) +#define M4U_PORT_L3_DISP_FAKE1 MTK_M4U_ID(3, 6) + +/* larb4 */ +#define M4U_PORT_L4_MDP_RDMA MTK_M4U_ID(4, 0) +#define M4U_PORT_L4_MDP_FG MTK_M4U_ID(4, 1) +#define M4U_PORT_L4_MDP_OVL MTK_M4U_ID(4, 2) +#define M4U_PORT_L4_MDP_WROT MTK_M4U_ID(4, 3) +#define M4U_PORT_L4_FAKE MTK_M4U_ID(4, 4) + +/* larb5 */ +#define M4U_PORT_L5_SVPP1_MDP_RDMA MTK_M4U_ID(5, 0) +#define M4U_PORT_L5_SVPP1_MDP_FG MTK_M4U_ID(5, 1) +#define M4U_PORT_L5_SVPP1_MDP_OVL MTK_M4U_ID(5, 2) +#define M4U_PORT_L5_SVPP1_MDP_WROT MTK_M4U_ID(5, 3) +#define M4U_PORT_L5_SVPP2_MDP_RDMA MTK_M4U_ID(5, 4) +#define M4U_PORT_L5_SVPP2_MDP_FG MTK_M4U_ID(5, 5) +#define M4U_PORT_L5_SVPP2_MDP_WROT MTK_M4U_ID(5, 6) +#define M4U_PORT_L5_FAKE MTK_M4U_ID(5, 7) + +/* larb6 */ +#define M4U_PORT_L6_SVPP3_MDP_RDMA MTK_M4U_ID(6, 0) +#define M4U_PORT_L6_SVPP3_MDP_FG MTK_M4U_ID(6, 1) +#define M4U_PORT_L6_SVPP3_MDP_WROT MTK_M4U_ID(6, 2) +#define M4U_PORT_L6_FAKE MTK_M4U_ID(6, 3) + +/* larb7 */ +#define M4U_PORT_L7_IMG_WPE_RDMA0 MTK_M4U_ID(7, 0) +#define M4U_PORT_L7_IMG_WPE_RDMA1 MTK_M4U_ID(7, 1) +#define M4U_PORT_L7_IMG_WPE_WDMA0 MTK_M4U_ID(7, 2) + +/* larb8 */ +#define M4U_PORT_L8_IMG_WPE_RDMA0 MTK_M4U_ID(8, 0) +#define M4U_PORT_L8_IMG_WPE_RDMA1 MTK_M4U_ID(8, 1) +#define M4U_PORT_L8_IMG_WPE_WDMA0 MTK_M4U_ID(8, 2) + +/* larb9 */ +#define M4U_PORT_L9_IMG_IMGI_T1_A MTK_M4U_ID(9, 0) +#define M4U_PORT_L9_IMG_IMGBI_T1_A MTK_M4U_ID(9, 1) +#define M4U_PORT_L9_IMG_IMGCI_T1_A MTK_M4U_ID(9, 2) +#define M4U_PORT_L9_IMG_SMTI_T1_A MTK_M4U_ID(9, 3) +#define M4U_PORT_L9_IMG_TNCSTI_T1_A MTK_M4U_ID(9, 4) +#define M4U_PORT_L9_IMG_TNCSTI_T4_A MTK_M4U_ID(9, 5) +#define M4U_PORT_L9_IMG_YUVO_T1_A MTK_M4U_ID(9, 6) +#define M4U_PORT_L9_IMG_TIMGO_T1_A MTK_M4U_ID(9, 7) +#define M4U_PORT_L9_IMG_YUVO_T2_A MTK_M4U_ID(9, 8) +#define M4U_PORT_L9_IMG_IMGI_T1_B MTK_M4U_ID(9, 9) +#define M4U_PORT_L9_IMG_IMGBI_T1_B MTK_M4U_ID(9, 10) +#define M4U_PORT_L9_IMG_IMGCI_T1_B MTK_M4U_ID(9, 11) +#define M4U_PORT_L9_IMG_YUVO_T5_A MTK_M4U_ID(9, 12) +#define M4U_PORT_L9_IMG_SMTI_T1_B MTK_M4U_ID(9, 13) +#define M4U_PORT_L9_IMG_TNCSO_T1_A MTK_M4U_ID(9, 14) +#define M4U_PORT_L9_IMG_SMTO_T1_A MTK_M4U_ID(9, 15) +#define M4U_PORT_L9_IMG_TNCSTO_T1_A MTK_M4U_ID(9, 16) +#define M4U_PORT_L9_IMG_YUVO_T2_B MTK_M4U_ID(9, 17) +#define M4U_PORT_L9_IMG_YUVO_T5_B MTK_M4U_ID(9, 18) +#define M4U_PORT_L9_IMG_SMTO_T1_B MTK_M4U_ID(9, 19) + +/* larb10 */ +#define M4U_PORT_L10_IMG_IMGI_D1_A MTK_M4U_ID(10, 0) +#define M4U_PORT_L10_IMG_IMGCI_D1_A MTK_M4U_ID(10, 1) +#define M4U_PORT_L10_IMG_DEPI_D1_A MTK_M4U_ID(10, 2) +#define M4U_PORT_L10_IMG_DMGI_D1_A MTK_M4U_ID(10, 3) +#define M4U_PORT_L10_IMG_VIPI_D1_A MTK_M4U_ID(10, 4) +#define M4U_PORT_L10_IMG_TNRWI_D1_A MTK_M4U_ID(10, 5) +#define M4U_PORT_L10_IMG_RECI_D1_A MTK_M4U_ID(10, 6) +#define M4U_PORT_L10_IMG_SMTI_D1_A MTK_M4U_ID(10, 7) +#define M4U_PORT_L10_IMG_SMTI_D6_A MTK_M4U_ID(10, 8) +#define M4U_PORT_L10_IMG_PIMGI_P1_A MTK_M4U_ID(10, 9) +#define M4U_PORT_L10_IMG_PIMGBI_P1_A MTK_M4U_ID(10, 10) +#define M4U_PORT_L10_IMG_PIMGCI_P1_A MTK_M4U_ID(10, 11) +#define M4U_PORT_L10_IMG_PIMGI_P1_B MTK_M4U_ID(10, 12) +#define M4U_PORT_L10_IMG_PIMGBI_P1_B MTK_M4U_ID(10, 13) +#define M4U_PORT_L10_IMG_PIMGCI_P1_B MTK_M4U_ID(10, 14) +#define M4U_PORT_L10_IMG_IMG3O_D1_A MTK_M4U_ID(10, 15) +#define M4U_PORT_L10_IMG_IMG4O_D1_A MTK_M4U_ID(10, 16) +#define M4U_PORT_L10_IMG_IMG3CO_D1_A MTK_M4U_ID(10, 17) +#define M4U_PORT_L10_IMG_FEO_D1_A MTK_M4U_ID(10, 18) +#define M4U_PORT_L10_IMG_IMG2O_D1_A MTK_M4U_ID(10, 19) +#define M4U_PORT_L10_IMG_TNRWO_D1_A MTK_M4U_ID(10, 20) +#define M4U_PORT_L10_IMG_SMTO_D1_A MTK_M4U_ID(10, 21) +#define M4U_PORT_L10_IMG_WROT_P1_A MTK_M4U_ID(10, 22) +#define M4U_PORT_L10_IMG_WROT_P1_B MTK_M4U_ID(10, 23) + +/* larb11 */ +#define M4U_PORT_L11_IMG_WPE_EIS_RDMA0_A MTK_M4U_ID(11, 0) +#define M4U_PORT_L11_IMG_WPE_EIS_RDMA1_A MTK_M4U_ID(11, 1) +#define M4U_PORT_L11_IMG_WPE_EIS_WDMA0_A MTK_M4U_ID(11, 2) +#define M4U_PORT_L11_IMG_WPE_TNR_RDMA0_A MTK_M4U_ID(11, 3) +#define M4U_PORT_L11_IMG_WPE_TNR_RDMA1_A MTK_M4U_ID(11, 4) +#define M4U_PORT_L11_IMG_WPE_TNR_WDMA0_A MTK_M4U_ID(11, 5) +#define M4U_PORT_L11_IMG_WPE_EIS_CQ0_A MTK_M4U_ID(11, 6) +#define M4U_PORT_L11_IMG_WPE_EIS_CQ1_A MTK_M4U_ID(11, 7) +#define M4U_PORT_L11_IMG_WPE_TNR_CQ0_A MTK_M4U_ID(11, 8) +#define M4U_PORT_L11_IMG_WPE_TNR_CQ1_A MTK_M4U_ID(11, 9) + +/* larb12 */ +#define M4U_PORT_L12_IMG_FDVT_RDA MTK_M4U_ID(12, 0) +#define M4U_PORT_L12_IMG_FDVT_RDB MTK_M4U_ID(12, 1) +#define M4U_PORT_L12_IMG_FDVT_WRA MTK_M4U_ID(12, 2) +#define M4U_PORT_L12_IMG_FDVT_WRB MTK_M4U_ID(12, 3) +#define M4U_PORT_L12_IMG_ME_RDMA MTK_M4U_ID(12, 4) +#define M4U_PORT_L12_IMG_ME_WDMA MTK_M4U_ID(12, 5) +#define M4U_PORT_L12_IMG_DVS_RDMA MTK_M4U_ID(12, 6) +#define M4U_PORT_L12_IMG_DVS_WDMA MTK_M4U_ID(12, 7) +#define M4U_PORT_L12_IMG_DVP_RDMA MTK_M4U_ID(12, 8) +#define M4U_PORT_L12_IMG_DVP_WDMA MTK_M4U_ID(12, 9) + +/* larb13 */ +#define M4U_PORT_L13_CAM_CAMSV_CQI_E1 MTK_M4U_ID(13, 0) +#define M4U_PORT_L13_CAM_CAMSV_CQI_E2 MTK_M4U_ID(13, 1) +#define M4U_PORT_L13_CAM_GCAMSV_A_IMGO_0 MTK_M4U_ID(13, 2) +#define M4U_PORT_L13_CAM_SCAMSV_A_IMGO_0 MTK_M4U_ID(13, 3) +#define M4U_PORT_L13_CAM_GCAMSV_B_IMGO_0 MTK_M4U_ID(13, 4) +#define M4U_PORT_L13_CAM_GCAMSV_B_IMGO_1 MTK_M4U_ID(13, 5) +#define M4U_PORT_L13_CAM_GCAMSV_A_UFEO_0 MTK_M4U_ID(13, 6) +#define M4U_PORT_L13_CAM_GCAMSV_B_UFEO_0 MTK_M4U_ID(13, 7) +#define M4U_PORT_L13_CAM_PDAI_0 MTK_M4U_ID(13, 8) +#define M4U_PORT_L13_CAM_FAKE MTK_M4U_ID(13, 9) + +/* larb14 */ +#define M4U_PORT_L14_CAM_GCAMSV_A_IMGO_1 MTK_M4U_ID(14, 0) +#define M4U_PORT_L14_CAM_SCAMSV_A_IMGO_1 MTK_M4U_ID(14, 1) +#define M4U_PORT_L14_CAM_GCAMSV_B_IMGO_0 MTK_M4U_ID(14, 2) +#define M4U_PORT_L14_CAM_GCAMSV_B_IMGO_1 MTK_M4U_ID(14, 3) +#define M4U_PORT_L14_CAM_SCAMSV_B_IMGO_0 MTK_M4U_ID(14, 4) +#define M4U_PORT_L14_CAM_SCAMSV_B_IMGO_1 MTK_M4U_ID(14, 5) +#define M4U_PORT_L14_CAM_IPUI MTK_M4U_ID(14, 6) +#define M4U_PORT_L14_CAM_IPU2I MTK_M4U_ID(14, 7) +#define M4U_PORT_L14_CAM_IPUO MTK_M4U_ID(14, 8) +#define M4U_PORT_L14_CAM_IPU2O MTK_M4U_ID(14, 9) +#define M4U_PORT_L14_CAM_IPU3O MTK_M4U_ID(14, 10) +#define M4U_PORT_L14_CAM_GCAMSV_A_UFEO_1 MTK_M4U_ID(14, 11) +#define M4U_PORT_L14_CAM_GCAMSV_B_UFEO_1 MTK_M4U_ID(14, 12) +#define M4U_PORT_L14_CAM_PDAI_1 MTK_M4U_ID(14, 13) +#define M4U_PORT_L14_CAM_PDAO MTK_M4U_ID(14, 14) + +/* larb15: null */ + +/* larb16 */ +#define M4U_PORT_L16_CAM_IMGO_R1 MTK_M4U_ID(16, 0) +#define M4U_PORT_L16_CAM_CQI_R1 MTK_M4U_ID(16, 1) +#define M4U_PORT_L16_CAM_CQI_R2 MTK_M4U_ID(16, 2) +#define M4U_PORT_L16_CAM_BPCI_R1 MTK_M4U_ID(16, 3) +#define M4U_PORT_L16_CAM_LSCI_R1 MTK_M4U_ID(16, 4) +#define M4U_PORT_L16_CAM_RAWI_R2 MTK_M4U_ID(16, 5) +#define M4U_PORT_L16_CAM_RAWI_R3 MTK_M4U_ID(16, 6) +#define M4U_PORT_L16_CAM_UFDI_R2 MTK_M4U_ID(16, 7) +#define M4U_PORT_L16_CAM_UFDI_R3 MTK_M4U_ID(16, 8) +#define M4U_PORT_L16_CAM_RAWI_R4 MTK_M4U_ID(16, 9) +#define M4U_PORT_L16_CAM_RAWI_R5 MTK_M4U_ID(16, 10) +#define M4U_PORT_L16_CAM_AAI_R1 MTK_M4U_ID(16, 11) +#define M4U_PORT_L16_CAM_FHO_R1 MTK_M4U_ID(16, 12) +#define M4U_PORT_L16_CAM_AAO_R1 MTK_M4U_ID(16, 13) +#define M4U_PORT_L16_CAM_TSFSO_R1 MTK_M4U_ID(16, 14) +#define M4U_PORT_L16_CAM_FLKO_R1 MTK_M4U_ID(16, 15) + +/* larb17 */ +#define M4U_PORT_L17_CAM_YUVO_R1 MTK_M4U_ID(17, 0) +#define M4U_PORT_L17_CAM_YUVO_R3 MTK_M4U_ID(17, 1) +#define M4U_PORT_L17_CAM_YUVCO_R1 MTK_M4U_ID(17, 2) +#define M4U_PORT_L17_CAM_YUVO_R2 MTK_M4U_ID(17, 3) +#define M4U_PORT_L17_CAM_RZH1N2TO_R1 MTK_M4U_ID(17, 4) +#define M4U_PORT_L17_CAM_DRZS4NO_R1 MTK_M4U_ID(17, 5) +#define M4U_PORT_L17_CAM_TNCSO_R1 MTK_M4U_ID(17, 6) + +/* larb18 */ +#define M4U_PORT_L18_CAM_CCUI MTK_M4U_ID(18, 0) +#define M4U_PORT_L18_CAM_CCUO MTK_M4U_ID(18, 1) +#define M4U_PORT_L18_CAM_CCUI2 MTK_M4U_ID(18, 2) +#define M4U_PORT_L18_CAM_CCUO2 MTK_M4U_ID(18, 3) + +/* larb19 */ +#define M4U_PORT_L19_VENC_RCPU MTK_M4U_ID(19, 0) +#define M4U_PORT_L19_VENC_REC MTK_M4U_ID(19, 1) +#define M4U_PORT_L19_VENC_BSDMA MTK_M4U_ID(19, 2) +#define M4U_PORT_L19_VENC_SV_COMV MTK_M4U_ID(19, 3) +#define M4U_PORT_L19_VENC_RD_COMV MTK_M4U_ID(19, 4) +#define M4U_PORT_L19_VENC_NBM_RDMA MTK_M4U_ID(19, 5) +#define M4U_PORT_L19_VENC_NBM_RDMA_LITE MTK_M4U_ID(19, 6) +#define M4U_PORT_L19_JPGENC_Y_RDMA MTK_M4U_ID(19, 7) +#define M4U_PORT_L19_JPGENC_C_RDMA MTK_M4U_ID(19, 8) +#define M4U_PORT_L19_JPGENC_Q_TABLE MTK_M4U_ID(19, 9) +#define M4U_PORT_L19_VENC_SUB_W_LUMA MTK_M4U_ID(19, 10) +#define M4U_PORT_L19_VENC_FCS_NBM_RDMA MTK_M4U_ID(19, 11) +#define M4U_PORT_L19_JPGENC_BSDMA MTK_M4U_ID(19, 12) +#define M4U_PORT_L19_JPGDEC_WDMA0 MTK_M4U_ID(19, 13) +#define M4U_PORT_L19_JPGDEC_BSDMA0 MTK_M4U_ID(19, 14) +#define M4U_PORT_L19_VENC_NBM_WDMA MTK_M4U_ID(19, 15) +#define M4U_PORT_L19_VENC_NBM_WDMA_LITE MTK_M4U_ID(19, 16) +#define M4U_PORT_L19_VENC_FCS_NBM_WDMA MTK_M4U_ID(19, 17) +#define M4U_PORT_L19_JPGDEC_WDMA1 MTK_M4U_ID(19, 18) +#define M4U_PORT_L19_JPGDEC_BSDMA1 MTK_M4U_ID(19, 19) +#define M4U_PORT_L19_JPGDEC_BUFF_OFFSET1 MTK_M4U_ID(19, 20) +#define M4U_PORT_L19_JPGDEC_BUFF_OFFSET0 MTK_M4U_ID(19, 21) +#define M4U_PORT_L19_VENC_CUR_LUMA MTK_M4U_ID(19, 22) +#define M4U_PORT_L19_VENC_CUR_CHROMA MTK_M4U_ID(19, 23) +#define M4U_PORT_L19_VENC_REF_LUMA MTK_M4U_ID(19, 24) +#define M4U_PORT_L19_VENC_REF_CHROMA MTK_M4U_ID(19, 25) +#define M4U_PORT_L19_VENC_SUB_R_CHROMA MTK_M4U_ID(19, 26) + +/* larb20 */ +#define M4U_PORT_L20_VENC_RCPU MTK_M4U_ID(20, 0) +#define M4U_PORT_L20_VENC_REC MTK_M4U_ID(20, 1) +#define M4U_PORT_L20_VENC_BSDMA MTK_M4U_ID(20, 2) +#define M4U_PORT_L20_VENC_SV_COMV MTK_M4U_ID(20, 3) +#define M4U_PORT_L20_VENC_RD_COMV MTK_M4U_ID(20, 4) +#define M4U_PORT_L20_VENC_NBM_RDMA MTK_M4U_ID(20, 5) +#define M4U_PORT_L20_VENC_NBM_RDMA_LITE MTK_M4U_ID(20, 6) +#define M4U_PORT_L20_JPGENC_Y_RDMA MTK_M4U_ID(20, 7) +#define M4U_PORT_L20_JPGENC_C_RDMA MTK_M4U_ID(20, 8) +#define M4U_PORT_L20_JPGENC_Q_TABLE MTK_M4U_ID(20, 9) +#define M4U_PORT_L20_VENC_SUB_W_LUMA MTK_M4U_ID(20, 10) +#define M4U_PORT_L20_VENC_FCS_NBM_RDMA MTK_M4U_ID(20, 11) +#define M4U_PORT_L20_JPGENC_BSDMA MTK_M4U_ID(20, 12) +#define M4U_PORT_L20_JPGDEC_WDMA0 MTK_M4U_ID(20, 13) +#define M4U_PORT_L20_JPGDEC_BSDMA0 MTK_M4U_ID(20, 14) +#define M4U_PORT_L20_VENC_NBM_WDMA MTK_M4U_ID(20, 15) +#define M4U_PORT_L20_VENC_NBM_WDMA_LITE MTK_M4U_ID(20, 16) +#define M4U_PORT_L20_VENC_FCS_NBM_WDMA MTK_M4U_ID(20, 17) +#define M4U_PORT_L20_JPGDEC_WDMA1 MTK_M4U_ID(20, 18) +#define M4U_PORT_L20_JPGDEC_BSDMA1 MTK_M4U_ID(20, 19) +#define M4U_PORT_L20_JPGDEC_BUFF_OFFSET1 MTK_M4U_ID(20, 20) +#define M4U_PORT_L20_JPGDEC_BUFF_OFFSET0 MTK_M4U_ID(20, 21) +#define M4U_PORT_L20_VENC_CUR_LUMA MTK_M4U_ID(20, 22) +#define M4U_PORT_L20_VENC_CUR_CHROMA MTK_M4U_ID(20, 23) +#define M4U_PORT_L20_VENC_REF_LUMA MTK_M4U_ID(20, 24) +#define M4U_PORT_L20_VENC_REF_CHROMA MTK_M4U_ID(20, 25) +#define M4U_PORT_L20_VENC_SUB_R_CHROMA MTK_M4U_ID(20, 26) + +/* larb21 */ +#define M4U_PORT_L21_VDEC_MC_EXT MTK_M4U_ID(21, 0) +#define M4U_PORT_L21_VDEC_UFO_EXT MTK_M4U_ID(21, 1) +#define M4U_PORT_L21_VDEC_PP_EXT MTK_M4U_ID(21, 2) +#define M4U_PORT_L21_VDEC_PRED_RD_EXT MTK_M4U_ID(21, 3) +#define M4U_PORT_L21_VDEC_PRED_WR_EXT MTK_M4U_ID(21, 4) +#define M4U_PORT_L21_VDEC_PPWRAP_EXT MTK_M4U_ID(21, 5) +#define M4U_PORT_L21_VDEC_TILE_EXT MTK_M4U_ID(21, 6) +#define M4U_PORT_L21_VDEC_VLD_EXT MTK_M4U_ID(21, 7) +#define M4U_PORT_L21_VDEC_VLD2_EXT MTK_M4U_ID(21, 8) +#define M4U_PORT_L21_VDEC_AVC_MV_EXT MTK_M4U_ID(21, 9) + +/* larb22 */ +#define M4U_PORT_L22_VDEC_MC_EXT MTK_M4U_ID(22, 0) +#define M4U_PORT_L22_VDEC_UFO_EXT MTK_M4U_ID(22, 1) +#define M4U_PORT_L22_VDEC_PP_EXT MTK_M4U_ID(22, 2) +#define M4U_PORT_L22_VDEC_PRED_RD_EXT MTK_M4U_ID(22, 3) +#define M4U_PORT_L22_VDEC_PRED_WR_EXT MTK_M4U_ID(22, 4) +#define M4U_PORT_L22_VDEC_PPWRAP_EXT MTK_M4U_ID(22, 5) +#define M4U_PORT_L22_VDEC_TILE_EXT MTK_M4U_ID(22, 6) +#define M4U_PORT_L22_VDEC_VLD_EXT MTK_M4U_ID(22, 7) +#define M4U_PORT_L22_VDEC_VLD2_EXT MTK_M4U_ID(22, 8) +#define M4U_PORT_L22_VDEC_AVC_MV_EXT MTK_M4U_ID(22, 9) + +/* larb23 */ +#define M4U_PORT_L23_VDEC_UFO_ENC_EXT MTK_M4U_ID(23, 0) +#define M4U_PORT_L23_VDEC_RDMA_EXT MTK_M4U_ID(23, 1) + +/* larb24 */ +#define M4U_PORT_L24_VDEC_LAT0_VLD_EXT MTK_M4U_ID(24, 0) +#define M4U_PORT_L24_VDEC_LAT0_VLD2_EXT MTK_M4U_ID(24, 1) +#define M4U_PORT_L24_VDEC_LAT0_AVC_MC_EXT MTK_M4U_ID(24, 2) +#define M4U_PORT_L24_VDEC_LAT0_PRED_RD_EXT MTK_M4U_ID(24, 3) +#define M4U_PORT_L24_VDEC_LAT0_TILE_EXT MTK_M4U_ID(24, 4) +#define M4U_PORT_L24_VDEC_LAT0_WDMA_EXT MTK_M4U_ID(24, 5) +#define M4U_PORT_L24_VDEC_LAT1_VLD_EXT MTK_M4U_ID(24, 6) +#define M4U_PORT_L24_VDEC_LAT1_VLD2_EXT MTK_M4U_ID(24, 7) +#define M4U_PORT_L24_VDEC_LAT1_AVC_MC_EXT MTK_M4U_ID(24, 8) +#define M4U_PORT_L24_VDEC_LAT1_PRED_RD_EXT MTK_M4U_ID(24, 9) +#define M4U_PORT_L24_VDEC_LAT1_TILE_EXT MTK_M4U_ID(24, 10) +#define M4U_PORT_L24_VDEC_LAT1_WDMA_EXT MTK_M4U_ID(24, 11) + +/* larb25 */ +#define M4U_PORT_L25_CAM_MRAW0_LSCI_M1 MTK_M4U_ID(25, 0) +#define M4U_PORT_L25_CAM_MRAW0_CQI_M1 MTK_M4U_ID(25, 1) +#define M4U_PORT_L25_CAM_MRAW0_CQI_M2 MTK_M4U_ID(25, 2) +#define M4U_PORT_L25_CAM_MRAW0_IMGO_M1 MTK_M4U_ID(25, 3) +#define M4U_PORT_L25_CAM_MRAW0_IMGBO_M1 MTK_M4U_ID(25, 4) +#define M4U_PORT_L25_CAM_MRAW2_LSCI_M1 MTK_M4U_ID(25, 5) +#define M4U_PORT_L25_CAM_MRAW2_CQI_M1 MTK_M4U_ID(25, 6) +#define M4U_PORT_L25_CAM_MRAW2_CQI_M2 MTK_M4U_ID(25, 7) +#define M4U_PORT_L25_CAM_MRAW2_IMGO_M1 MTK_M4U_ID(25, 8) +#define M4U_PORT_L25_CAM_MRAW2_IMGBO_M1 MTK_M4U_ID(25, 9) +#define M4U_PORT_L25_CAM_MRAW0_AFO_M1 MTK_M4U_ID(25, 10) +#define M4U_PORT_L25_CAM_MRAW2_AFO_M1 MTK_M4U_ID(25, 11) + +/* larb26 */ +#define M4U_PORT_L26_CAM_MRAW1_LSCI_M1 MTK_M4U_ID(26, 0) +#define M4U_PORT_L26_CAM_MRAW1_CQI_M1 MTK_M4U_ID(26, 1) +#define M4U_PORT_L26_CAM_MRAW1_CQI_M2 MTK_M4U_ID(26, 2) +#define M4U_PORT_L26_CAM_MRAW1_IMGO_M1 MTK_M4U_ID(26, 3) +#define M4U_PORT_L26_CAM_MRAW1_IMGBO_M1 MTK_M4U_ID(26, 4) +#define M4U_PORT_L26_CAM_MRAW3_LSCI_M1 MTK_M4U_ID(26, 5) +#define M4U_PORT_L26_CAM_MRAW3_CQI_M1 MTK_M4U_ID(26, 6) +#define M4U_PORT_L26_CAM_MRAW3_CQI_M2 MTK_M4U_ID(26, 7) +#define M4U_PORT_L26_CAM_MRAW3_IMGO_M1 MTK_M4U_ID(26, 8) +#define M4U_PORT_L26_CAM_MRAW3_IMGBO_M1 MTK_M4U_ID(26, 9) +#define M4U_PORT_L26_CAM_MRAW1_AFO_M1 MTK_M4U_ID(26, 10) +#define M4U_PORT_L26_CAM_MRAW3_AFO_M1 MTK_M4U_ID(26, 11) + +/* larb27 */ +#define M4U_PORT_L27_CAM_IMGO_R1 MTK_M4U_ID(27, 0) +#define M4U_PORT_L27_CAM_CQI_R1 MTK_M4U_ID(27, 1) +#define M4U_PORT_L27_CAM_CQI_R2 MTK_M4U_ID(27, 2) +#define M4U_PORT_L27_CAM_BPCI_R1 MTK_M4U_ID(27, 3) +#define M4U_PORT_L27_CAM_LSCI_R1 MTK_M4U_ID(27, 4) +#define M4U_PORT_L27_CAM_RAWI_R2 MTK_M4U_ID(27, 5) +#define M4U_PORT_L27_CAM_RAWI_R3 MTK_M4U_ID(27, 6) +#define M4U_PORT_L27_CAM_UFDI_R2 MTK_M4U_ID(27, 7) +#define M4U_PORT_L27_CAM_UFDI_R3 MTK_M4U_ID(27, 8) +#define M4U_PORT_L27_CAM_RAWI_R4 MTK_M4U_ID(27, 9) +#define M4U_PORT_L27_CAM_RAWI_R5 MTK_M4U_ID(27, 10) +#define M4U_PORT_L27_CAM_AAI_R1 MTK_M4U_ID(27, 11) +#define M4U_PORT_L27_CAM_FHO_R1 MTK_M4U_ID(27, 12) +#define M4U_PORT_L27_CAM_AAO_R1 MTK_M4U_ID(27, 13) +#define M4U_PORT_L27_CAM_TSFSO_R1 MTK_M4U_ID(27, 14) +#define M4U_PORT_L27_CAM_FLKO_R1 MTK_M4U_ID(27, 15) + +/* larb28 */ +#define M4U_PORT_L28_CAM_YUVO_R1 MTK_M4U_ID(28, 0) +#define M4U_PORT_L28_CAM_YUVO_R3 MTK_M4U_ID(28, 1) +#define M4U_PORT_L28_CAM_YUVCO_R1 MTK_M4U_ID(28, 2) +#define M4U_PORT_L28_CAM_YUVO_R2 MTK_M4U_ID(28, 3) +#define M4U_PORT_L28_CAM_RZH1N2TO_R1 MTK_M4U_ID(28, 4) +#define M4U_PORT_L28_CAM_DRZS4NO_R1 MTK_M4U_ID(28, 5) +#define M4U_PORT_L28_CAM_TNCSO_R1 MTK_M4U_ID(28, 6) + +#endif -- cgit v1.2.3 From dc1d99342db705efbeec517f9c6187f3b93ab423 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 3 May 2022 15:13:53 +0800 Subject: dt-bindings: mediatek: mt8195: Add binding for infra IOMMU In mt8195, we have a new IOMMU that is for INFRA IOMMU. its masters mainly are PCIe and USB. Different with MM IOMMU, all these masters connect with IOMMU directly, there is no mediatek,larbs property for infra IOMMU. Another thing is about PCIe ports. currently the function "of_iommu_configure_dev_id" only support the id number is 1, But our PCIe have two ports, one is for reading and the other is for writing. see more about the PCIe patch in this patchset. Thus, I only list the reading id here and add the other id in our driver. Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20220503071427.2285-3-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- include/dt-bindings/memory/mt8195-memory-port.h | 18 ++++++++++++++++++ include/dt-bindings/memory/mtk-memory-port.h | 2 ++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/memory/mt8195-memory-port.h b/include/dt-bindings/memory/mt8195-memory-port.h index c10e8b61f1e8..70ba9f498eeb 100644 --- a/include/dt-bindings/memory/mt8195-memory-port.h +++ b/include/dt-bindings/memory/mt8195-memory-port.h @@ -387,4 +387,22 @@ #define M4U_PORT_L28_CAM_DRZS4NO_R1 MTK_M4U_ID(28, 5) #define M4U_PORT_L28_CAM_TNCSO_R1 MTK_M4U_ID(28, 6) +/* Infra iommu ports */ +/* PCIe1: read: BIT16; write BIT17. */ +#define IOMMU_PORT_INFRA_PCIE1 MTK_IFAIOMMU_PERI_ID(16) +/* PCIe0: read: BIT18; write BIT19. */ +#define IOMMU_PORT_INFRA_PCIE0 MTK_IFAIOMMU_PERI_ID(18) +#define IOMMU_PORT_INFRA_SSUSB_P3_R MTK_IFAIOMMU_PERI_ID(20) +#define IOMMU_PORT_INFRA_SSUSB_P3_W MTK_IFAIOMMU_PERI_ID(21) +#define IOMMU_PORT_INFRA_SSUSB_P2_R MTK_IFAIOMMU_PERI_ID(22) +#define IOMMU_PORT_INFRA_SSUSB_P2_W MTK_IFAIOMMU_PERI_ID(23) +#define IOMMU_PORT_INFRA_SSUSB_P1_1_R MTK_IFAIOMMU_PERI_ID(24) +#define IOMMU_PORT_INFRA_SSUSB_P1_1_W MTK_IFAIOMMU_PERI_ID(25) +#define IOMMU_PORT_INFRA_SSUSB_P1_0_R MTK_IFAIOMMU_PERI_ID(26) +#define IOMMU_PORT_INFRA_SSUSB_P1_0_W MTK_IFAIOMMU_PERI_ID(27) +#define IOMMU_PORT_INFRA_SSUSB2_R MTK_IFAIOMMU_PERI_ID(28) +#define IOMMU_PORT_INFRA_SSUSB2_W MTK_IFAIOMMU_PERI_ID(29) +#define IOMMU_PORT_INFRA_SSUSB_R MTK_IFAIOMMU_PERI_ID(30) +#define IOMMU_PORT_INFRA_SSUSB_W MTK_IFAIOMMU_PERI_ID(31) + #endif diff --git a/include/dt-bindings/memory/mtk-memory-port.h b/include/dt-bindings/memory/mtk-memory-port.h index 7d64103209af..2f68a0511a25 100644 --- a/include/dt-bindings/memory/mtk-memory-port.h +++ b/include/dt-bindings/memory/mtk-memory-port.h @@ -12,4 +12,6 @@ #define MTK_M4U_TO_LARB(id) (((id) >> 5) & 0x1f) #define MTK_M4U_TO_PORT(id) ((id) & 0x1f) +#define MTK_IFAIOMMU_PERI_ID(port) MTK_M4U_ID(0, port) + #endif -- cgit v1.2.3 From 2d555a3844142b9e0f876925a8475cc830cd472a Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 3 May 2022 15:13:54 +0800 Subject: dt-bindings: mediatek: mt8186: Add binding for MM iommu Add mt8186 iommu binding. "-mm" means the iommu is for Multimedia. Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Reviewed-by: Matthias Brugger Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20220503071427.2285-4-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- include/dt-bindings/memory/mt8186-memory-port.h | 217 ++++++++++++++++++++++++ 1 file changed, 217 insertions(+) create mode 100644 include/dt-bindings/memory/mt8186-memory-port.h (limited to 'include') diff --git a/include/dt-bindings/memory/mt8186-memory-port.h b/include/dt-bindings/memory/mt8186-memory-port.h new file mode 100644 index 000000000000..2bc6e4433048 --- /dev/null +++ b/include/dt-bindings/memory/mt8186-memory-port.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 MediaTek Inc. + * + * Author: Anan Sun + * Author: Yong Wu + */ +#ifndef _DT_BINDINGS_MEMORY_MT8186_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT8186_LARB_PORT_H_ + +#include + +/* + * MM IOMMU supports 16GB dma address. We separate it to four ranges: + * 0 ~ 4G; 4G ~ 8G; 8G ~ 12G; 12G ~ 16G, we could adjust these masters + * locate in anyone region. BUT: + * a) Make sure all the ports inside a larb are in one range. + * b) The iova of any master can NOT cross the 4G/8G/12G boundary. + * + * This is the suggested mapping in this SoC: + * + * modules dma-address-region larbs-ports + * disp 0 ~ 4G larb0/1/2 + * vcodec 4G ~ 8G larb4/7 + * cam/mdp 8G ~ 12G the other larbs. + * N/A 12G ~ 16G + * CCU0 0x24000_0000 ~ 0x243ff_ffff larb13: port 9/10 + * CCU1 0x24400_0000 ~ 0x247ff_ffff larb14: port 4/5 + */ + +/* MM IOMMU ports */ +/* LARB 0 -- MMSYS */ +#define IOMMU_PORT_L0_DISP_POSTMASK0 MTK_M4U_ID(0, 0) +#define IOMMU_PORT_L0_REVERSED MTK_M4U_ID(0, 1) +#define IOMMU_PORT_L0_OVL_RDMA0 MTK_M4U_ID(0, 2) +#define IOMMU_PORT_L0_DISP_FAKE0 MTK_M4U_ID(0, 3) + +/* LARB 1 -- MMSYS */ +#define IOMMU_PORT_L1_DISP_RDMA1 MTK_M4U_ID(1, 0) +#define IOMMU_PORT_L1_OVL_2L_RDMA0 MTK_M4U_ID(1, 1) +#define IOMMU_PORT_L1_DISP_RDMA0 MTK_M4U_ID(1, 2) +#define IOMMU_PORT_L1_DISP_WDMA0 MTK_M4U_ID(1, 3) +#define IOMMU_PORT_L1_DISP_FAKE1 MTK_M4U_ID(1, 4) + +/* LARB 2 -- MMSYS */ +#define IOMMU_PORT_L2_MDP_RDMA0 MTK_M4U_ID(2, 0) +#define IOMMU_PORT_L2_MDP_RDMA1 MTK_M4U_ID(2, 1) +#define IOMMU_PORT_L2_MDP_WROT0 MTK_M4U_ID(2, 2) +#define IOMMU_PORT_L2_MDP_WROT1 MTK_M4U_ID(2, 3) +#define IOMMU_PORT_L2_DISP_FAKE0 MTK_M4U_ID(2, 4) + +/* LARB 4 -- VDEC */ +#define IOMMU_PORT_L4_HW_VDEC_MC_EXT MTK_M4U_ID(4, 0) +#define IOMMU_PORT_L4_HW_VDEC_UFO_EXT MTK_M4U_ID(4, 1) +#define IOMMU_PORT_L4_HW_VDEC_PP_EXT MTK_M4U_ID(4, 2) +#define IOMMU_PORT_L4_HW_VDEC_PRED_RD_EXT MTK_M4U_ID(4, 3) +#define IOMMU_PORT_L4_HW_VDEC_PRED_WR_EXT MTK_M4U_ID(4, 4) +#define IOMMU_PORT_L4_HW_VDEC_PPWRAP_EXT MTK_M4U_ID(4, 5) +#define IOMMU_PORT_L4_HW_VDEC_TILE_EXT MTK_M4U_ID(4, 6) +#define IOMMU_PORT_L4_HW_VDEC_VLD_EXT MTK_M4U_ID(4, 7) +#define IOMMU_PORT_L4_HW_VDEC_VLD2_EXT MTK_M4U_ID(4, 8) +#define IOMMU_PORT_L4_HW_VDEC_AVC_MV_EXT MTK_M4U_ID(4, 9) +#define IOMMU_PORT_L4_HW_VDEC_UFO_ENC_EXT MTK_M4U_ID(4, 10) +#define IOMMU_PORT_L4_HW_VDEC_RG_CTRL_DMA_EXT MTK_M4U_ID(4, 11) +#define IOMMU_PORT_L4_HW_MINI_MDP_R0_EXT MTK_M4U_ID(4, 12) +#define IOMMU_PORT_L4_HW_MINI_MDP_W0_EXT MTK_M4U_ID(4, 13) + +/* LARB 7 -- VENC */ +#define IOMMU_PORT_L7_VENC_RCPU MTK_M4U_ID(7, 0) +#define IOMMU_PORT_L7_VENC_REC MTK_M4U_ID(7, 1) +#define IOMMU_PORT_L7_VENC_BSDMA MTK_M4U_ID(7, 2) +#define IOMMU_PORT_L7_VENC_SV_COMV MTK_M4U_ID(7, 3) +#define IOMMU_PORT_L7_VENC_RD_COMV MTK_M4U_ID(7, 4) +#define IOMMU_PORT_L7_VENC_CUR_LUMA MTK_M4U_ID(7, 5) +#define IOMMU_PORT_L7_VENC_CUR_CHROMA MTK_M4U_ID(7, 6) +#define IOMMU_PORT_L7_VENC_REF_LUMA MTK_M4U_ID(7, 7) +#define IOMMU_PORT_L7_VENC_REF_CHROMA MTK_M4U_ID(7, 8) +#define IOMMU_PORT_L7_JPGENC_Y_RDMA MTK_M4U_ID(7, 9) +#define IOMMU_PORT_L7_JPGENC_C_RDMA MTK_M4U_ID(7, 10) +#define IOMMU_PORT_L7_JPGENC_Q_TABLE MTK_M4U_ID(7, 11) +#define IOMMU_PORT_L7_JPGENC_BSDMA MTK_M4U_ID(7, 12) + +/* LARB 8 -- WPE */ +#define IOMMU_PORT_L8_WPE_RDMA_0 MTK_M4U_ID(8, 0) +#define IOMMU_PORT_L8_WPE_RDMA_1 MTK_M4U_ID(8, 1) +#define IOMMU_PORT_L8_WPE_WDMA_0 MTK_M4U_ID(8, 2) + +/* LARB 9 -- IMG-1 */ +#define IOMMU_PORT_L9_IMG_IMGI_D1 MTK_M4U_ID(9, 0) +#define IOMMU_PORT_L9_IMG_IMGBI_D1 MTK_M4U_ID(9, 1) +#define IOMMU_PORT_L9_IMG_DMGI_D1 MTK_M4U_ID(9, 2) +#define IOMMU_PORT_L9_IMG_DEPI_D1 MTK_M4U_ID(9, 3) +#define IOMMU_PORT_L9_IMG_LCE_D1 MTK_M4U_ID(9, 4) +#define IOMMU_PORT_L9_IMG_SMTI_D1 MTK_M4U_ID(9, 5) +#define IOMMU_PORT_L9_IMG_SMTO_D2 MTK_M4U_ID(9, 6) +#define IOMMU_PORT_L9_IMG_SMTO_D1 MTK_M4U_ID(9, 7) +#define IOMMU_PORT_L9_IMG_CRZO_D1 MTK_M4U_ID(9, 8) +#define IOMMU_PORT_L9_IMG_IMG3O_D1 MTK_M4U_ID(9, 9) +#define IOMMU_PORT_L9_IMG_VIPI_D1 MTK_M4U_ID(9, 10) +#define IOMMU_PORT_L9_IMG_SMTI_D5 MTK_M4U_ID(9, 11) +#define IOMMU_PORT_L9_IMG_TIMGO_D1 MTK_M4U_ID(9, 12) +#define IOMMU_PORT_L9_IMG_UFBC_W0 MTK_M4U_ID(9, 13) +#define IOMMU_PORT_L9_IMG_UFBC_R0 MTK_M4U_ID(9, 14) +#define IOMMU_PORT_L9_IMG_WPE_RDMA1 MTK_M4U_ID(9, 15) +#define IOMMU_PORT_L9_IMG_WPE_RDMA0 MTK_M4U_ID(9, 16) +#define IOMMU_PORT_L9_IMG_WPE_WDMA MTK_M4U_ID(9, 17) +#define IOMMU_PORT_L9_IMG_MFB_RDMA0 MTK_M4U_ID(9, 18) +#define IOMMU_PORT_L9_IMG_MFB_RDMA1 MTK_M4U_ID(9, 19) +#define IOMMU_PORT_L9_IMG_MFB_RDMA2 MTK_M4U_ID(9, 20) +#define IOMMU_PORT_L9_IMG_MFB_RDMA3 MTK_M4U_ID(9, 21) +#define IOMMU_PORT_L9_IMG_MFB_RDMA4 MTK_M4U_ID(9, 22) +#define IOMMU_PORT_L9_IMG_MFB_RDMA5 MTK_M4U_ID(9, 23) +#define IOMMU_PORT_L9_IMG_MFB_WDMA0 MTK_M4U_ID(9, 24) +#define IOMMU_PORT_L9_IMG_MFB_WDMA1 MTK_M4U_ID(9, 25) +#define IOMMU_PORT_L9_IMG_RESERVE6 MTK_M4U_ID(9, 26) +#define IOMMU_PORT_L9_IMG_RESERVE7 MTK_M4U_ID(9, 27) +#define IOMMU_PORT_L9_IMG_RESERVE8 MTK_M4U_ID(9, 28) + +/* LARB 11 -- IMG-2 */ +#define IOMMU_PORT_L11_IMG_IMGI_D1 MTK_M4U_ID(11, 0) +#define IOMMU_PORT_L11_IMG_IMGBI_D1 MTK_M4U_ID(11, 1) +#define IOMMU_PORT_L11_IMG_DMGI_D1 MTK_M4U_ID(11, 2) +#define IOMMU_PORT_L11_IMG_DEPI_D1 MTK_M4U_ID(11, 3) +#define IOMMU_PORT_L11_IMG_LCE_D1 MTK_M4U_ID(11, 4) +#define IOMMU_PORT_L11_IMG_SMTI_D1 MTK_M4U_ID(11, 5) +#define IOMMU_PORT_L11_IMG_SMTO_D2 MTK_M4U_ID(11, 6) +#define IOMMU_PORT_L11_IMG_SMTO_D1 MTK_M4U_ID(11, 7) +#define IOMMU_PORT_L11_IMG_CRZO_D1 MTK_M4U_ID(11, 8) +#define IOMMU_PORT_L11_IMG_IMG3O_D1 MTK_M4U_ID(11, 9) +#define IOMMU_PORT_L11_IMG_VIPI_D1 MTK_M4U_ID(11, 10) +#define IOMMU_PORT_L11_IMG_SMTI_D5 MTK_M4U_ID(11, 11) +#define IOMMU_PORT_L11_IMG_TIMGO_D1 MTK_M4U_ID(11, 12) +#define IOMMU_PORT_L11_IMG_UFBC_W0 MTK_M4U_ID(11, 13) +#define IOMMU_PORT_L11_IMG_UFBC_R0 MTK_M4U_ID(11, 14) +#define IOMMU_PORT_L11_IMG_WPE_RDMA1 MTK_M4U_ID(11, 15) +#define IOMMU_PORT_L11_IMG_WPE_RDMA0 MTK_M4U_ID(11, 16) +#define IOMMU_PORT_L11_IMG_WPE_WDMA MTK_M4U_ID(11, 17) +#define IOMMU_PORT_L11_IMG_MFB_RDMA0 MTK_M4U_ID(11, 18) +#define IOMMU_PORT_L11_IMG_MFB_RDMA1 MTK_M4U_ID(11, 19) +#define IOMMU_PORT_L11_IMG_MFB_RDMA2 MTK_M4U_ID(11, 20) +#define IOMMU_PORT_L11_IMG_MFB_RDMA3 MTK_M4U_ID(11, 21) +#define IOMMU_PORT_L11_IMG_MFB_RDMA4 MTK_M4U_ID(11, 22) +#define IOMMU_PORT_L11_IMG_MFB_RDMA5 MTK_M4U_ID(11, 23) +#define IOMMU_PORT_L11_IMG_MFB_WDMA0 MTK_M4U_ID(11, 24) +#define IOMMU_PORT_L11_IMG_MFB_WDMA1 MTK_M4U_ID(11, 25) +#define IOMMU_PORT_L11_IMG_RESERVE6 MTK_M4U_ID(11, 26) +#define IOMMU_PORT_L11_IMG_RESERVE7 MTK_M4U_ID(11, 27) +#define IOMMU_PORT_L11_IMG_RESERVE8 MTK_M4U_ID(11, 28) + +/* LARB 13 -- CAM */ +#define IOMMU_PORT_L13_CAM_MRAWI MTK_M4U_ID(13, 0) +#define IOMMU_PORT_L13_CAM_MRAWO_0 MTK_M4U_ID(13, 1) +#define IOMMU_PORT_L13_CAM_MRAWO_1 MTK_M4U_ID(13, 2) +#define IOMMU_PORT_L13_CAM_CAMSV_4 MTK_M4U_ID(13, 6) +#define IOMMU_PORT_L13_CAM_CAMSV_5 MTK_M4U_ID(13, 7) +#define IOMMU_PORT_L13_CAM_CAMSV_6 MTK_M4U_ID(13, 8) +#define IOMMU_PORT_L13_CAM_CCUI MTK_M4U_ID(13, 9) +#define IOMMU_PORT_L13_CAM_CCUO MTK_M4U_ID(13, 10) +#define IOMMU_PORT_L13_CAM_FAKE MTK_M4U_ID(13, 11) + +/* LARB 14 -- CAM */ +#define IOMMU_PORT_L14_CAM_CCUI MTK_M4U_ID(14, 4) +#define IOMMU_PORT_L14_CAM_CCUO MTK_M4U_ID(14, 5) + +/* LARB 16 -- RAW-A */ +#define IOMMU_PORT_L16_CAM_IMGO_R1_A MTK_M4U_ID(16, 0) +#define IOMMU_PORT_L16_CAM_RRZO_R1_A MTK_M4U_ID(16, 1) +#define IOMMU_PORT_L16_CAM_CQI_R1_A MTK_M4U_ID(16, 2) +#define IOMMU_PORT_L16_CAM_BPCI_R1_A MTK_M4U_ID(16, 3) +#define IOMMU_PORT_L16_CAM_YUVO_R1_A MTK_M4U_ID(16, 4) +#define IOMMU_PORT_L16_CAM_UFDI_R2_A MTK_M4U_ID(16, 5) +#define IOMMU_PORT_L16_CAM_RAWI_R2_A MTK_M4U_ID(16, 6) +#define IOMMU_PORT_L16_CAM_RAWI_R3_A MTK_M4U_ID(16, 7) +#define IOMMU_PORT_L16_CAM_AAO_R1_A MTK_M4U_ID(16, 8) +#define IOMMU_PORT_L16_CAM_AFO_R1_A MTK_M4U_ID(16, 9) +#define IOMMU_PORT_L16_CAM_FLKO_R1_A MTK_M4U_ID(16, 10) +#define IOMMU_PORT_L16_CAM_LCESO_R1_A MTK_M4U_ID(16, 11) +#define IOMMU_PORT_L16_CAM_CRZO_R1_A MTK_M4U_ID(16, 12) +#define IOMMU_PORT_L16_CAM_LTMSO_R1_A MTK_M4U_ID(16, 13) +#define IOMMU_PORT_L16_CAM_RSSO_R1_A MTK_M4U_ID(16, 14) +#define IOMMU_PORT_L16_CAM_AAHO_R1_A MTK_M4U_ID(16, 15) +#define IOMMU_PORT_L16_CAM_LSCI_R1_A MTK_M4U_ID(16, 16) + +/* LARB 17 -- RAW-B */ +#define IOMMU_PORT_L17_CAM_IMGO_R1_B MTK_M4U_ID(17, 0) +#define IOMMU_PORT_L17_CAM_RRZO_R1_B MTK_M4U_ID(17, 1) +#define IOMMU_PORT_L17_CAM_CQI_R1_B MTK_M4U_ID(17, 2) +#define IOMMU_PORT_L17_CAM_BPCI_R1_B MTK_M4U_ID(17, 3) +#define IOMMU_PORT_L17_CAM_YUVO_R1_B MTK_M4U_ID(17, 4) +#define IOMMU_PORT_L17_CAM_UFDI_R2_B MTK_M4U_ID(17, 5) +#define IOMMU_PORT_L17_CAM_RAWI_R2_B MTK_M4U_ID(17, 6) +#define IOMMU_PORT_L17_CAM_RAWI_R3_B MTK_M4U_ID(17, 7) +#define IOMMU_PORT_L17_CAM_AAO_R1_B MTK_M4U_ID(17, 8) +#define IOMMU_PORT_L17_CAM_AFO_R1_B MTK_M4U_ID(17, 9) +#define IOMMU_PORT_L17_CAM_FLKO_R1_B MTK_M4U_ID(17, 10) +#define IOMMU_PORT_L17_CAM_LCESO_R1_B MTK_M4U_ID(17, 11) +#define IOMMU_PORT_L17_CAM_CRZO_R1_B MTK_M4U_ID(17, 12) +#define IOMMU_PORT_L17_CAM_LTMSO_R1_B MTK_M4U_ID(17, 13) +#define IOMMU_PORT_L17_CAM_RSSO_R1_B MTK_M4U_ID(17, 14) +#define IOMMU_PORT_L17_CAM_AAHO_R1_B MTK_M4U_ID(17, 15) +#define IOMMU_PORT_L17_CAM_LSCI_R1_B MTK_M4U_ID(17, 16) + +/* LARB 19 -- IPE */ +#define IOMMU_PORT_L19_IPE_DVS_RDMA MTK_M4U_ID(19, 0) +#define IOMMU_PORT_L19_IPE_DVS_WDMA MTK_M4U_ID(19, 1) +#define IOMMU_PORT_L19_IPE_DVP_RDMA MTK_M4U_ID(19, 2) +#define IOMMU_PORT_L19_IPE_DVP_WDMA MTK_M4U_ID(19, 3) + +/* LARB 20 -- IPE */ +#define IOMMU_PORT_L20_IPE_FDVT_RDA MTK_M4U_ID(20, 0) +#define IOMMU_PORT_L20_IPE_FDVT_RDB MTK_M4U_ID(20, 1) +#define IOMMU_PORT_L20_IPE_FDVT_WRA MTK_M4U_ID(20, 2) +#define IOMMU_PORT_L20_IPE_FDVT_WRB MTK_M4U_ID(20, 3) +#define IOMMU_PORT_L20_IPE_RSC_RDMA0 MTK_M4U_ID(20, 4) +#define IOMMU_PORT_L20_IPE_RSC_WDMA MTK_M4U_ID(20, 5) + +#endif -- cgit v1.2.3 From 9b0df592522c6f86283679436f2eac49bd23cdce Mon Sep 17 00:00:00 2001 From: Alexandre Torgue Date: Fri, 22 Apr 2022 17:09:47 +0200 Subject: dt-bindings: clock: stm32mp15: rename CK_SCMI define As we only have one SCMI instance, it's not necessary to add an index to the name. Signed-off-by: Alexandre Torgue Acked-by: Rob Herring --- include/dt-bindings/clock/stm32mp1-clks.h | 46 ++++++++++++++----------------- 1 file changed, 21 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/stm32mp1-clks.h b/include/dt-bindings/clock/stm32mp1-clks.h index e02770b98e6c..25e8cfd43459 100644 --- a/include/dt-bindings/clock/stm32mp1-clks.h +++ b/include/dt-bindings/clock/stm32mp1-clks.h @@ -249,30 +249,26 @@ #define STM32MP1_LAST_CLK 232 /* SCMI clock identifiers */ -#define CK_SCMI0_HSE 0 -#define CK_SCMI0_HSI 1 -#define CK_SCMI0_CSI 2 -#define CK_SCMI0_LSE 3 -#define CK_SCMI0_LSI 4 -#define CK_SCMI0_PLL2_Q 5 -#define CK_SCMI0_PLL2_R 6 -#define CK_SCMI0_MPU 7 -#define CK_SCMI0_AXI 8 -#define CK_SCMI0_BSEC 9 -#define CK_SCMI0_CRYP1 10 -#define CK_SCMI0_GPIOZ 11 -#define CK_SCMI0_HASH1 12 -#define CK_SCMI0_I2C4 13 -#define CK_SCMI0_I2C6 14 -#define CK_SCMI0_IWDG1 15 -#define CK_SCMI0_RNG1 16 -#define CK_SCMI0_RTC 17 -#define CK_SCMI0_RTCAPB 18 -#define CK_SCMI0_SPI6 19 -#define CK_SCMI0_USART1 20 - -#define CK_SCMI1_PLL3_Q 0 -#define CK_SCMI1_PLL3_R 1 -#define CK_SCMI1_MCU 2 +#define CK_SCMI_HSE 0 +#define CK_SCMI_HSI 1 +#define CK_SCMI_CSI 2 +#define CK_SCMI_LSE 3 +#define CK_SCMI_LSI 4 +#define CK_SCMI_PLL2_Q 5 +#define CK_SCMI_PLL2_R 6 +#define CK_SCMI_MPU 7 +#define CK_SCMI_AXI 8 +#define CK_SCMI_BSEC 9 +#define CK_SCMI_CRYP1 10 +#define CK_SCMI_GPIOZ 11 +#define CK_SCMI_HASH1 12 +#define CK_SCMI_I2C4 13 +#define CK_SCMI_I2C6 14 +#define CK_SCMI_IWDG1 15 +#define CK_SCMI_RNG1 16 +#define CK_SCMI_RTC 17 +#define CK_SCMI_RTCAPB 18 +#define CK_SCMI_SPI6 19 +#define CK_SCMI_USART1 20 #endif /* _DT_BINDINGS_STM32MP1_CLKS_H_ */ -- cgit v1.2.3 From 5f5d7decf046557876794c5686ee0ccf5907bfde Mon Sep 17 00:00:00 2001 From: Alexandre Torgue Date: Fri, 22 Apr 2022 17:09:48 +0200 Subject: dt-bindings: reset: stm32mp15: rename RST_SCMI define As we only have one SCMI instance, it's not necessary to add an index to the name. Signed-off-by: Alexandre Torgue Acked-by: Rob Herring --- include/dt-bindings/reset/stm32mp1-resets.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/reset/stm32mp1-resets.h b/include/dt-bindings/reset/stm32mp1-resets.h index f3a0ed317835..4ffa7c3612e6 100644 --- a/include/dt-bindings/reset/stm32mp1-resets.h +++ b/include/dt-bindings/reset/stm32mp1-resets.h @@ -107,17 +107,17 @@ #define GPIOK_R 19786 /* SCMI reset domain identifiers */ -#define RST_SCMI0_SPI6 0 -#define RST_SCMI0_I2C4 1 -#define RST_SCMI0_I2C6 2 -#define RST_SCMI0_USART1 3 -#define RST_SCMI0_STGEN 4 -#define RST_SCMI0_GPIOZ 5 -#define RST_SCMI0_CRYP1 6 -#define RST_SCMI0_HASH1 7 -#define RST_SCMI0_RNG1 8 -#define RST_SCMI0_MDMA 9 -#define RST_SCMI0_MCU 10 -#define RST_SCMI0_MCU_HOLD_BOOT 11 +#define RST_SCMI_SPI6 0 +#define RST_SCMI_I2C4 1 +#define RST_SCMI_I2C6 2 +#define RST_SCMI_USART1 3 +#define RST_SCMI_STGEN 4 +#define RST_SCMI_GPIOZ 5 +#define RST_SCMI_CRYP1 6 +#define RST_SCMI_HASH1 7 +#define RST_SCMI_RNG1 8 +#define RST_SCMI_MDMA 9 +#define RST_SCMI_MCU 10 +#define RST_SCMI_MCU_HOLD_BOOT 11 #endif /* _DT_BINDINGS_STM32MP1_RESET_H_ */ -- cgit v1.2.3 From 31ab09b4218879bc394c9faa6da983a82a694600 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Fri, 22 Apr 2022 13:52:13 -0700 Subject: drivers: Add hardware timestamp engine (HTE) subsystem Some devices can timestamp system lines/signals/Buses in real-time using the hardware counter or other hardware means which can give finer granularity and help avoid jitter introduced by software timestamping. To utilize such functionality, this patchset creates HTE subsystem where devices can register themselves as providers so that the consumers devices can request specific line from the providers. The patch also adds compilation support in Makefile and menu options in Kconfig. The provider does following: - Registers chip with the framework. - Provides translation hook to convert logical line id. - Provides enable/disable, request/release callbacks. - Pushes timestamp data to HTE subsystem. The consumer does following: - Initializes line attribute. - Gets HTE timestamp descriptor. - Requests timestamp functionality. - Puts HTE timestamp descriptor. Signed-off-by: Dipen Patel Reported-by: kernel test robot Signed-off-by: Thierry Reding --- include/linux/hte.h | 271 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 271 insertions(+) create mode 100644 include/linux/hte.h (limited to 'include') diff --git a/include/linux/hte.h b/include/linux/hte.h new file mode 100644 index 000000000000..8289055061ab --- /dev/null +++ b/include/linux/hte.h @@ -0,0 +1,271 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_HTE_H +#define __LINUX_HTE_H + +#include + +struct hte_chip; +struct hte_device; +struct of_phandle_args; + +/** + * enum hte_edge - HTE line edge flags. + * + * @HTE_EDGE_NO_SETUP: No edge setup. In this case consumer will setup edges, + * for example during request irq call. + * @HTE_RISING_EDGE_TS: Rising edge. + * @HTE_FALLING_EDGE_TS: Falling edge. + * + */ +enum hte_edge { + HTE_EDGE_NO_SETUP = 1U << 0, + HTE_RISING_EDGE_TS = 1U << 1, + HTE_FALLING_EDGE_TS = 1U << 2, +}; + +/** + * enum hte_return - HTE subsystem return values used during callback. + * + * @HTE_CB_HANDLED: The consumer handled the data. + * @HTE_RUN_SECOND_CB: The consumer needs further processing, in that case + * HTE subsystem calls secondary callback provided by the consumer where it + * is allowed to sleep. + */ +enum hte_return { + HTE_CB_HANDLED, + HTE_RUN_SECOND_CB, +}; + +/** + * struct hte_ts_data - HTE timestamp data. + * + * @tsc: Timestamp value. + * @seq: Sequence counter of the timestamps. + * @raw_level: Level of the line at the timestamp if provider supports it, + * -1 otherwise. + */ +struct hte_ts_data { + u64 tsc; + u64 seq; + int raw_level; +}; + +/** + * struct hte_clk_info - Clock source info that HTE provider uses to timestamp. + * + * @hz: Supported clock rate in HZ, for example 1KHz clock = 1000. + * @type: Supported clock type. + */ +struct hte_clk_info { + u64 hz; + clockid_t type; +}; + +/** + * typedef hte_ts_cb_t - HTE timestamp data processing primary callback. + * + * The callback is used to push timestamp data to the client and it is + * not allowed to sleep. + * + * @ts: HW timestamp data. + * @data: Client supplied data. + */ +typedef enum hte_return (*hte_ts_cb_t)(struct hte_ts_data *ts, void *data); + +/** + * typedef hte_ts_sec_cb_t - HTE timestamp data processing secondary callback. + * + * This is used when the client needs further processing where it is + * allowed to sleep. + * + * @data: Client supplied data. + * + */ +typedef enum hte_return (*hte_ts_sec_cb_t)(void *data); + +/** + * struct hte_line_attr - Line attributes. + * + * @line_id: The logical ID understood by the consumers and providers. + * @line_data: Line data related to line_id. + * @edge_flags: Edge setup flags. + * @name: Descriptive name of the entity that is being monitored for the + * hardware timestamping. If null, HTE core will construct the name. + * + */ +struct hte_line_attr { + u32 line_id; + void *line_data; + unsigned long edge_flags; + const char *name; +}; + +/** + * struct hte_ts_desc - HTE timestamp descriptor. + * + * This structure is a communication token between consumers to subsystem + * and subsystem to providers. + * + * @attr: The line attributes. + * @hte_data: Subsystem's private data, set by HTE subsystem. + */ +struct hte_ts_desc { + struct hte_line_attr attr; + void *hte_data; +}; + +/** + * struct hte_ops - HTE operations set by providers. + * + * @request: Hook for requesting a HTE timestamp. Returns 0 on success, + * non-zero for failures. + * @release: Hook for releasing a HTE timestamp. Returns 0 on success, + * non-zero for failures. + * @enable: Hook to enable the specified timestamp. Returns 0 on success, + * non-zero for failures. + * @disable: Hook to disable specified timestamp. Returns 0 on success, + * non-zero for failures. + * @get_clk_src_info: Hook to get the clock information the provider uses + * to timestamp. Returns 0 for success and negative error code for failure. On + * success HTE subsystem fills up provided struct hte_clk_info. + * + * xlated_id parameter is used to communicate between HTE subsystem and the + * providers and is translated by the provider. + */ +struct hte_ops { + int (*request)(struct hte_chip *chip, struct hte_ts_desc *desc, + u32 xlated_id); + int (*release)(struct hte_chip *chip, struct hte_ts_desc *desc, + u32 xlated_id); + int (*enable)(struct hte_chip *chip, u32 xlated_id); + int (*disable)(struct hte_chip *chip, u32 xlated_id); + int (*get_clk_src_info)(struct hte_chip *chip, + struct hte_clk_info *ci); +}; + +/** + * struct hte_chip - Abstract HTE chip. + * + * @name: functional name of the HTE IP block. + * @dev: device providing the HTE. + * @ops: callbacks for this HTE. + * @nlines: number of lines/signals supported by this chip. + * @xlate_of: Callback which translates consumer supplied logical ids to + * physical ids, return 0 for the success and negative for the failures. + * It stores (between 0 to @nlines) in xlated_id parameter for the success. + * @xlate_plat: Same as above but for the consumers with no DT node. + * @match_from_linedata: Match HTE device using the line_data. + * @of_hte_n_cells: Number of cells used to form the HTE specifier. + * @gdev: HTE subsystem abstract device, internal to the HTE subsystem. + * @data: chip specific private data. + */ +struct hte_chip { + const char *name; + struct device *dev; + const struct hte_ops *ops; + u32 nlines; + int (*xlate_of)(struct hte_chip *gc, + const struct of_phandle_args *args, + struct hte_ts_desc *desc, u32 *xlated_id); + int (*xlate_plat)(struct hte_chip *gc, struct hte_ts_desc *desc, + u32 *xlated_id); + bool (*match_from_linedata)(const struct hte_chip *chip, + const struct hte_ts_desc *hdesc); + u8 of_hte_n_cells; + + struct hte_device *gdev; + void *data; +}; + +#if IS_ENABLED(CONFIG_HTE) +/* HTE APIs for the providers */ +int devm_hte_register_chip(struct hte_chip *chip); +int hte_push_ts_ns(const struct hte_chip *chip, u32 xlated_id, + struct hte_ts_data *data); + +/* HTE APIs for the consumers */ +int hte_init_line_attr(struct hte_ts_desc *desc, u32 line_id, + unsigned long edge_flags, const char *name, + void *data); +int hte_ts_get(struct device *dev, struct hte_ts_desc *desc, int index); +int hte_ts_put(struct hte_ts_desc *desc); +int hte_request_ts_ns(struct hte_ts_desc *desc, hte_ts_cb_t cb, + hte_ts_sec_cb_t tcb, void *data); +int devm_hte_request_ts_ns(struct device *dev, struct hte_ts_desc *desc, + hte_ts_cb_t cb, hte_ts_sec_cb_t tcb, void *data); +int of_hte_req_count(struct device *dev); +int hte_enable_ts(struct hte_ts_desc *desc); +int hte_disable_ts(struct hte_ts_desc *desc); +int hte_get_clk_src_info(const struct hte_ts_desc *desc, + struct hte_clk_info *ci); + +#else /* !CONFIG_HTE */ +static inline int devm_hte_register_chip(struct hte_chip *chip) +{ + return -EOPNOTSUPP; +} + +static inline int hte_push_ts_ns(const struct hte_chip *chip, + u32 xlated_id, + const struct hte_ts_data *data) +{ + return -EOPNOTSUPP; +} + +static inline int hte_init_line_attr(struct hte_ts_desc *desc, u32 line_id, + unsigned long edge_flags, + const char *name, void *data) +{ + return -EOPNOTSUPP; +} + +static inline int hte_ts_get(struct device *dev, struct hte_ts_desc *desc, + int index) +{ + return -EOPNOTSUPP; +} + +static inline int hte_ts_put(struct hte_ts_desc *desc) +{ + return -EOPNOTSUPP; +} + +static inline int hte_request_ts_ns(struct hte_ts_desc *desc, hte_ts_cb_t cb, + hte_ts_sec_cb_t tcb, void *data) +{ + return -EOPNOTSUPP; +} + +static inline int devm_hte_request_ts_ns(struct device *dev, + struct hte_ts_desc *desc, + hte_ts_cb_t cb, + hte_ts_sec_cb_t tcb, + void *data) +{ + return -EOPNOTSUPP; +} + +static inline int of_hte_req_count(struct device *dev) +{ + return -EOPNOTSUPP; +} + +static inline int hte_enable_ts(struct hte_ts_desc *desc) +{ + return -EOPNOTSUPP; +} + +static inline int hte_disable_ts(struct hte_ts_desc *desc) +{ + return -EOPNOTSUPP; +} + +static inline int hte_get_clk_src_info(const struct hte_ts_desc *desc, + struct hte_clk_info *ci) +{ + return -EOPNOTSUPP; +} +#endif /* !CONFIG_HTE */ + +#endif -- cgit v1.2.3 From 42112dd77b74220e6a1f4a71bb51ca3f583d3842 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Fri, 22 Apr 2022 13:52:16 -0700 Subject: gpiolib: Add HTE support Some GPIO chip can provide hardware timestamp support on its GPIO lines , in order to support that, additional API needs to be added which can talk to both GPIO chip and HTE (hardware timestamping engine) providers if there is any dependencies. This patch introduces optional hooks to enable and disable hardware timestamping related features in the GPIO controller chip. Signed-off-by: Dipen Patel Reviewed-by: Linus Walleij Reported-by: kernel test robot Signed-off-by: Thierry Reding --- include/linux/gpio/consumer.h | 16 ++++++++++++++-- include/linux/gpio/driver.h | 10 ++++++++++ 2 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index c3aa8b330e1c..7eaec081ae6c 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -109,6 +109,8 @@ int gpiod_get_direction(struct gpio_desc *desc); int gpiod_direction_input(struct gpio_desc *desc); int gpiod_direction_output(struct gpio_desc *desc, int value); int gpiod_direction_output_raw(struct gpio_desc *desc, int value); +int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags); +int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags); /* Value get/set from non-sleeping context */ int gpiod_get_value(const struct gpio_desc *desc); @@ -350,8 +352,18 @@ static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value) WARN_ON(desc); return -ENOSYS; } - - +static inline int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, + unsigned long flags) +{ + WARN_ON(desc); + return -ENOSYS; +} +static inline int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, + unsigned long flags) +{ + WARN_ON(desc); + return -ENOSYS; +} static inline int gpiod_get_value(const struct gpio_desc *desc) { /* GPIO can never have been requested */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..0ce96ebdaa36 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -323,6 +323,10 @@ struct gpio_irq_chip { * @add_pin_ranges: optional routine to initialize pin ranges, to be used when * requires special mapping of the pins that provides GPIO functionality. * It is called after adding GPIO chip and before adding IRQ chip. + * @en_hw_timestamp: Dependent on GPIO chip, an optional routine to + * enable hardware timestamp. + * @dis_hw_timestamp: Dependent on GPIO chip, an optional routine to + * disable hardware timestamp. * @base: identifies the first GPIO number handled by this chip; * or, if negative during registration, requests dynamic ID allocation. * DEPRECATION: providing anything non-negative and nailing the base @@ -419,6 +423,12 @@ struct gpio_chip { int (*add_pin_ranges)(struct gpio_chip *gc); + int (*en_hw_timestamp)(struct gpio_chip *gc, + u32 offset, + unsigned long flags); + int (*dis_hw_timestamp)(struct gpio_chip *gc, + u32 offset, + unsigned long flags); int base; u16 ngpio; u16 offset; -- cgit v1.2.3 From 2068339a6c35147847ba433fd0da67b313779059 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Fri, 22 Apr 2022 13:52:18 -0700 Subject: gpiolib: cdev: Add hardware timestamp clock type This patch adds new clock type for the GPIO controller which can timestamp gpio lines in using hardware means. To expose such functionalities to the userspace, code has been added where during line create or set config API calls, it checks for new clock type and if requested, calls HTE API. During line change event, the HTE subsystem pushes timestamp data to userspace through gpiolib-cdev. Signed-off-by: Dipen Patel Acked-by: Linus Walleij Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Thierry Reding --- include/uapi/linux/gpio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index eaaea3d8e6b4..cb9966d49a16 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -66,6 +66,8 @@ struct gpiochip_info { * @GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN: line has pull-down bias enabled * @GPIO_V2_LINE_FLAG_BIAS_DISABLED: line has bias disabled * @GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME: line events contain REALTIME timestamps + * @GPIO_V2_LINE_FLAG_EVENT_CLOCK_HTE: line events contain timestamps from + * hardware timestamp engine */ enum gpio_v2_line_flag { GPIO_V2_LINE_FLAG_USED = _BITULL(0), @@ -80,6 +82,7 @@ enum gpio_v2_line_flag { GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN = _BITULL(9), GPIO_V2_LINE_FLAG_BIAS_DISABLED = _BITULL(10), GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME = _BITULL(11), + GPIO_V2_LINE_FLAG_EVENT_CLOCK_HTE = _BITULL(12), }; /** -- cgit v1.2.3 From 9ab4807c84a4aacfc9b4f79cc81254035e0ec361 Mon Sep 17 00:00:00 2001 From: Kishen Maloor Date: Tue, 3 May 2022 19:38:52 -0700 Subject: mptcp: netlink: Add MPTCP_PM_CMD_ANNOUNCE This change adds a MPTCP netlink interface for issuing ADD_ADDR advertisements over the chosen MPTCP connection from a userspace path manager. The command requires the following parameters: { token, { loc_id, family, daddr4 | daddr6 [, dport] } [, if_idx], flags[signal] }. Acked-by: Paolo Abeni Signed-off-by: Kishen Maloor Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index e41ea01a94bb..ac66c1263f02 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -55,6 +55,7 @@ enum { MPTCP_PM_ATTR_ADDR, /* nested address */ MPTCP_PM_ATTR_RCV_ADD_ADDRS, /* u32 */ MPTCP_PM_ATTR_SUBFLOWS, /* u32 */ + MPTCP_PM_ATTR_TOKEN, /* u32 */ __MPTCP_PM_ATTR_MAX }; @@ -93,6 +94,7 @@ enum { MPTCP_PM_CMD_SET_LIMITS, MPTCP_PM_CMD_GET_LIMITS, MPTCP_PM_CMD_SET_FLAGS, + MPTCP_PM_CMD_ANNOUNCE, __MPTCP_PM_CMD_AFTER_LAST }; -- cgit v1.2.3 From d9a4594edabf125dc17dfd52acc722c3de1cb44c Mon Sep 17 00:00:00 2001 From: Kishen Maloor Date: Tue, 3 May 2022 19:38:54 -0700 Subject: mptcp: netlink: Add MPTCP_PM_CMD_REMOVE This change adds a MPTCP netlink command for issuing a REMOVE_ADDR signal for an address over the chosen MPTCP connection from a userspace path manager. The command requires the following parameters: {token, loc_id}. Acked-by: Paolo Abeni Signed-off-by: Kishen Maloor Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index ac66c1263f02..11f9fa001a3c 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -56,6 +56,7 @@ enum { MPTCP_PM_ATTR_RCV_ADD_ADDRS, /* u32 */ MPTCP_PM_ATTR_SUBFLOWS, /* u32 */ MPTCP_PM_ATTR_TOKEN, /* u32 */ + MPTCP_PM_ATTR_LOC_ID, /* u8 */ __MPTCP_PM_ATTR_MAX }; @@ -95,6 +96,7 @@ enum { MPTCP_PM_CMD_GET_LIMITS, MPTCP_PM_CMD_SET_FLAGS, MPTCP_PM_CMD_ANNOUNCE, + MPTCP_PM_CMD_REMOVE, __MPTCP_PM_CMD_AFTER_LAST }; -- cgit v1.2.3 From 702c2f646d42cfd9e31133d68a8283fea48fd810 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 3 May 2022 19:38:56 -0700 Subject: mptcp: netlink: allow userspace-driven subflow establishment This allows userspace to tell kernel to add a new subflow to an existing mptcp connection. Userspace provides the token to identify the mptcp-level connection that needs a change in active subflows and the local and remote addresses of the new or the to-be-removed subflow. MPTCP_PM_CMD_SUBFLOW_CREATE requires the following parameters: { token, { loc_id, family, loc_addr4 | loc_addr6 }, { family, rem_addr4 | rem_addr6, rem_port } MPTCP_PM_CMD_SUBFLOW_DESTROY requires the following parameters: { token, { family, loc_addr4 | loc_addr6, loc_port }, { family, rem_addr4 | rem_addr6, rem_port } Acked-by: Paolo Abeni Co-developed-by: Kishen Maloor Signed-off-by: Kishen Maloor Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 11f9fa001a3c..921963589904 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -57,6 +57,7 @@ enum { MPTCP_PM_ATTR_SUBFLOWS, /* u32 */ MPTCP_PM_ATTR_TOKEN, /* u32 */ MPTCP_PM_ATTR_LOC_ID, /* u8 */ + MPTCP_PM_ATTR_ADDR_REMOTE, /* nested address */ __MPTCP_PM_ATTR_MAX }; @@ -97,6 +98,8 @@ enum { MPTCP_PM_CMD_SET_FLAGS, MPTCP_PM_CMD_ANNOUNCE, MPTCP_PM_CMD_REMOVE, + MPTCP_PM_CMD_SUBFLOW_CREATE, + MPTCP_PM_CMD_SUBFLOW_DESTROY, __MPTCP_PM_CMD_AFTER_LAST }; -- cgit v1.2.3 From 3ae2722c93c916b47bfe47a4326e88cc4abb9bf4 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 27 Apr 2022 14:55:57 +0200 Subject: mmc: mmci: Remove custom ios handler The custom boardfile ios handler isn't used anywhere in the kernel. Delete it. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220427125557.1608825-1-linus.walleij@linaro.org Signed-off-by: Ulf Hansson --- include/linux/amba/mmci.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h index c92ebc39fc1f..6f96dc2209c0 100644 --- a/include/linux/amba/mmci.h +++ b/include/linux/amba/mmci.h @@ -13,17 +13,11 @@ * @ocr_mask: available voltages on the 4 pins from the block, this * is ignored if a regulator is used, see the MMC_VDD_* masks in * mmc/host.h - * @ios_handler: a callback function to act on specfic ios changes, - * used for example to control a levelshifter - * mask into a value to be binary (or set some other custom bits - * in MMCIPWR) or:ed and written into the MMCIPWR register of the - * block. May also control external power based on the power_mode. * @status: if no GPIO line was given to the block in this function will * be called to determine whether a card is present in the MMC slot or not */ struct mmci_platform_data { unsigned int ocr_mask; - int (*ios_handler)(struct device *, struct mmc_ios *); unsigned int (*status)(struct device *); }; -- cgit v1.2.3 From 00ce3873f730fb24c657854ec04374358e711838 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 4 May 2022 10:17:32 +0200 Subject: opp: Add apis to retrieve opps with interconnect bandwidth Add dev_pm_opp_find_bw_ceil and dev_pm_opp_find_bw_floor to retrieve opps based on interconnect associated with the opp and bandwidth. The index variable is the index of the interconnect as specified in the opp table in Devicetree. Co-developed-by: Thara Gopinath Signed-off-by: Thara Gopinath Signed-off-by: Krzysztof Kozlowski Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 0d85a63a1f78..dcea178868c9 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -129,6 +129,13 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev, struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq); + +struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, + unsigned int *bw, int index); + +struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, + unsigned int *bw, int index); + void dev_pm_opp_put(struct dev_pm_opp *opp); int dev_pm_opp_add(struct device *dev, unsigned long freq, @@ -279,6 +286,18 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } +static inline struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, + unsigned int *bw, int index) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, + unsigned int *bw, int index) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} static inline int dev_pm_opp_add(struct device *dev, unsigned long freq, -- cgit v1.2.3 From 22079af7df5a5dfef1c4d160abfd43035211759e Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 4 May 2022 15:40:22 +0530 Subject: opp: Reorder definition of ceil/floor helpers Reorder the helpers to keep all freq specific ones, followed by level and bw. No functional change. Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index dcea178868c9..6708b4ec244d 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -117,16 +117,16 @@ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available); -struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, - unsigned int level); -struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, - unsigned int *level); - struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq); struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev, unsigned long u_volt); +struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, + unsigned int level); +struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, + unsigned int *level); + struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq); @@ -250,12 +250,6 @@ static inline unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev) return 0; } -static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, - unsigned long freq, bool available) -{ - return ERR_PTR(-EOPNOTSUPP); -} - static inline struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, unsigned int level) { @@ -268,6 +262,12 @@ static inline struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } +static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, + unsigned long freq, bool available) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq) { -- cgit v1.2.3 From 34c9a0e71cbb316f360919353273b185c2780cd7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 12 Apr 2022 22:09:59 +0200 Subject: cfg80211: remove cfg80211_get_chan_state() We haven't used this function for years, since commit c781944b71f8 ("cfg80211: Remove unused cfg80211_can_use_iftype_chan()") which itself removed a function unused since commit 97dc94f1d933 ("cfg80211: remove channel_switch combination check"), almost eight years ago. Also remove the now unused enum cfg80211_chan_mode and some struct members that were only used for this function. Link: https://lore.kernel.org/r/20220412220958.1a191dca19d7.Ide4448f02d0e2f1ca2992971421ffc1933a5370a@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 68713388b617..cd1212113901 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5549,8 +5549,6 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * @conn_owner_nlportid: (private) connection owner socket port ID * @disconnect_wk: (private) auto-disconnect work * @disconnect_bssid: (private) the BSSID to use for auto-disconnect - * @ibss_fixed: (private) IBSS is using fixed BSSID - * @ibss_dfs_possible: (private) IBSS may change to a DFS channel * @event_list: (private) list for internal event processing * @event_lock: (private) lock for event list * @owner_nlportid: (private) owner socket port ID @@ -5599,9 +5597,6 @@ struct wireless_dev { struct cfg80211_chan_def preset_chandef; struct cfg80211_chan_def chandef; - bool ibss_fixed; - bool ibss_dfs_possible; - bool ps; int ps_timeout; -- cgit v1.2.3 From 34453c2e9f799d02f5f379519495208bbd96a935 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Apr 2022 19:23:24 +0100 Subject: irqchip/gic-v3: Exposes bit values for GICR_CTLR.{IR, CES} As we're about to expose GICR_CTLR.{IR,CES} to guests, populate the include file with the architectural values. Signed-off-by: Marc Zyngier Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20220405182327.205520-2-maz@kernel.org --- include/linux/irqchip/arm-gic-v3.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 12d91f0dedf9..728691365464 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -127,6 +127,8 @@ #define GICR_PIDR2 GICD_PIDR2 #define GICR_CTLR_ENABLE_LPIS (1UL << 0) +#define GICR_CTLR_CES (1UL << 1) +#define GICR_CTLR_IR (1UL << 2) #define GICR_CTLR_RWP (1UL << 3) #define GICR_TYPER_CPU_NUMBER(r) (((r) >> 8) & 0xffff) -- cgit v1.2.3 From 94828468a6085e6ae148986d300b634b87f86516 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Apr 2022 19:23:25 +0100 Subject: KVM: arm64: vgic-v3: Expose GICR_CTLR.RWP when disabling LPIs When disabling LPIs, a guest needs to poll GICR_CTLR.RWP in order to be sure that the write has taken effect. We so far reported it as 0, as we didn't advertise that LPIs could be turned off the first place. Start tracking this state during which LPIs are being disabled, and expose the 'in progress' state via the RWP bit. We also take this opportunity to disallow enabling LPIs and programming GICR_{PEND,PROP}BASER while LPI disabling is in progress, as allowed by the architecture (UNPRED behaviour). We don't advertise the feature to the guest yet (which is allowed by the architecture). Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220405182327.205520-3-maz@kernel.org --- include/kvm/arm_vgic.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index bb30a6803d9f..fdf1c2c322e5 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -347,8 +347,8 @@ struct vgic_cpu { /* Contains the attributes and gpa of the LPI pending tables. */ u64 pendbaser; - - bool lpis_enabled; + /* GICR_CTLR.{ENABLE_LPIS,RWP} */ + atomic_t ctlr; /* Cache guest priority bits */ u32 num_pri_bits; -- cgit v1.2.3 From 4645d11f4a5538ec1221f36e397cfb0115718ffe Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Apr 2022 19:23:26 +0100 Subject: KVM: arm64: vgic-v3: Implement MMIO-based LPI invalidation Since GICv4.1, it has become legal for an implementation to advertise GICR_{INVLPIR,INVALLR,SYNCR} while having an ITS, allowing for a more efficient invalidation scheme (no guest command queue contention when multiple CPUs are generating invalidations). Provide the invalidation registers as a primitive to their ITS counterpart. Note that we don't advertise them to the guest yet (the architecture allows an implementation to do this). Signed-off-by: Marc Zyngier Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20220405182327.205520-4-maz@kernel.org --- include/kvm/arm_vgic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index fdf1c2c322e5..401236f97cf2 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -344,6 +344,7 @@ struct vgic_cpu { struct vgic_io_device rd_iodev; struct vgic_redist_region *rdreg; u32 rdreg_index; + atomic_t syncr_busy; /* Contains the attributes and gpa of the LPI pending tables. */ u64 pendbaser; -- cgit v1.2.3 From 49a1a2c70a7fd820fe60a65a3e38ab9095082dc9 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Apr 2022 19:23:27 +0100 Subject: KVM: arm64: vgic-v3: Advertise GICR_CTLR.{IR, CES} as a new GICD_IIDR revision Since adversising GICR_CTLR.{IC,CES} is directly observable from a guest, we need to make it selectable from userspace. For that, bump the default GICD_IIDR revision and let userspace downgrade it to the previous default. For GICv2, the two distributor revisions are strictly equivalent. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220405182327.205520-5-maz@kernel.org --- include/kvm/arm_vgic.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 401236f97cf2..2d8f2e90edc2 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -231,6 +231,9 @@ struct vgic_dist { /* Implementation revision as reported in the GICD_IIDR */ u32 implementation_rev; +#define KVM_VGIC_IMP_REV_2 2 /* GICv2 restorable groups */ +#define KVM_VGIC_IMP_REV_3 3 /* GICv3 GICR_CTLR.{IW,CES,RWP} */ +#define KVM_VGIC_IMP_REV_LATEST KVM_VGIC_IMP_REV_3 /* Userspace can write to GICv2 IGROUPR */ bool v2_groups_user_writable; -- cgit v1.2.3 From 5eca8379c73d1bb8cd84e335b9529c263f699468 Mon Sep 17 00:00:00 2001 From: Hawking Zhang Date: Tue, 22 Feb 2022 13:38:51 +0800 Subject: drm/amdgpu: add GC v11_0_0 family id Add GC v11_0_0 family id Signed-off-by: Hawking Zhang Reviewed-by: Likun Gao Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 1d65c1fbc4ec..992851219441 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1150,6 +1150,7 @@ struct drm_amdgpu_info_video_caps { #define AMDGPU_FAMILY_RV 142 /* Raven */ #define AMDGPU_FAMILY_NV 143 /* Navi10 */ #define AMDGPU_FAMILY_VGH 144 /* Van Gogh */ +#define AMDGPU_FAMILY_GC_11_0_0 145 /* GC 11.0.0 */ #define AMDGPU_FAMILY_YC 146 /* Yellow Carp */ #define AMDGPU_FAMILY_GC_10_3_6 149 /* GC 10.3.6 */ #define AMDGPU_FAMILY_GC_10_3_7 151 /* GC 10.3.7 */ -- cgit v1.2.3 From ec69dfbdc426f22a9557e5c5408d7902fe0e0144 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 2 May 2022 14:54:06 -0700 Subject: soc: qcom: llcc: Add sc8180x and sc8280xp configurations Add LLCC configuration data for the SC8180X and SC8280XP platforms, based on the downstream tables. Signed-off-by: Bjorn Andersson Reviewed-by: Sai Prakash Ranjan Link: https://lore.kernel.org/r/20220502215406.612967-3-bjorn.andersson@linaro.org --- include/linux/soc/qcom/llcc-qcom.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 0bc21ee58fac..9ed5384c5ca1 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -29,6 +29,8 @@ #define LLCC_AUDHW 22 #define LLCC_NPU 23 #define LLCC_WLHW 24 +#define LLCC_PIMEM 25 +#define LLCC_DRE 26 #define LLCC_CVP 28 #define LLCC_MODPE 29 #define LLCC_APTCM 30 -- cgit v1.2.3 From 36f8423597000bd7d5e48b7b306e1d0958e72359 Mon Sep 17 00:00:00 2001 From: Muna Sinada Date: Wed, 23 Mar 2022 15:46:35 -0700 Subject: cfg80211: support disabling EHT mode Allow userspace to disable EHT mode during association. Signed-off-by: Muna Sinada Signed-off-by: Aloka Dixit Link: https://lore.kernel.org/r/20220323224636.20211-1-quic_alokad@quicinc.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cd1212113901..6a3e3f0a8615 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2735,6 +2735,7 @@ struct cfg80211_auth_request { * userspace if this flag is set. Only applicable for cfg80211_connect() * request (connect callback). * @ASSOC_REQ_DISABLE_HE: Disable HE + * @ASSOC_REQ_DISABLE_EHT: Disable EHT */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), @@ -2742,6 +2743,7 @@ enum cfg80211_assoc_req_flags { ASSOC_REQ_USE_RRM = BIT(2), CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3), ASSOC_REQ_DISABLE_HE = BIT(4), + ASSOC_REQ_DISABLE_EHT = BIT(5), }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 0568a79097b8..d9490e3062a7 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3175,6 +3175,8 @@ enum nl80211_attrs { NL80211_ATTR_EHT_CAPABILITY, + NL80211_ATTR_DISABLE_EHT, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 8b3dd27bfe47abe30450d01077983497aa1a159f Mon Sep 17 00:00:00 2001 From: Paul Elder Date: Wed, 6 Apr 2022 17:33:54 +0200 Subject: dt-bindings: soc: Add i.MX8MP media block control DT bindings The i.MX8MP Media Block Control (MEDIA BLK_CTRL) is a top-level peripheral providing access to the NoC and ensuring proper power sequencing of the peripherals within the MEDIAMIX domain. Add DT bindings for it. There is already a driver for block controls of other SoCs in the i.MX8M family, so these bindings will expand upon that. Signed-off-by: Paul Elder Reviewed-by: Rob Herring Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Reviewed-by: Marek Vasut Signed-off-by: Lucas Stach Signed-off-by: Shawn Guo --- include/dt-bindings/power/imx8mp-power.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/imx8mp-power.h b/include/dt-bindings/power/imx8mp-power.h index 9f90c40a2c6c..bc8458f1e725 100644 --- a/include/dt-bindings/power/imx8mp-power.h +++ b/include/dt-bindings/power/imx8mp-power.h @@ -32,4 +32,14 @@ #define IMX8MP_HSIOBLK_PD_PCIE 3 #define IMX8MP_HSIOBLK_PD_PCIE_PHY 4 +#define IMX8MP_MEDIABLK_PD_MIPI_DSI_1 0 +#define IMX8MP_MEDIABLK_PD_MIPI_CSI2_1 1 +#define IMX8MP_MEDIABLK_PD_LCDIF_1 2 +#define IMX8MP_MEDIABLK_PD_ISI 3 +#define IMX8MP_MEDIABLK_PD_MIPI_CSI2_2 4 +#define IMX8MP_MEDIABLK_PD_LCDIF_2 5 +#define IMX8MP_MEDIABLK_PD_ISP 6 +#define IMX8MP_MEDIABLK_PD_DWE 7 +#define IMX8MP_MEDIABLK_PD_MIPI_DSI_2 8 + #endif -- cgit v1.2.3 From f11cf9e35e7f740d158e298baf5764bcdd8a199e Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Wed, 6 Apr 2022 17:33:56 +0200 Subject: dt-bindings: power: imx8mp: add defines for HDMI blk-ctrl domains This adds the defines for the power domains provided by the HDMI blk-ctrl on the i.MX8MP. Signed-off-by: Lucas Stach Acked-by: Rob Herring Signed-off-by: Shawn Guo --- include/dt-bindings/power/imx8mp-power.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/imx8mp-power.h b/include/dt-bindings/power/imx8mp-power.h index bc8458f1e725..7789bcca3223 100644 --- a/include/dt-bindings/power/imx8mp-power.h +++ b/include/dt-bindings/power/imx8mp-power.h @@ -42,4 +42,12 @@ #define IMX8MP_MEDIABLK_PD_DWE 7 #define IMX8MP_MEDIABLK_PD_MIPI_DSI_2 8 +#define IMX8MP_HDMIBLK_PD_IRQSTEER 0 +#define IMX8MP_HDMIBLK_PD_LCDIF 1 +#define IMX8MP_HDMIBLK_PD_PAI 2 +#define IMX8MP_HDMIBLK_PD_PVI 3 +#define IMX8MP_HDMIBLK_PD_TRNG 4 +#define IMX8MP_HDMIBLK_PD_HDMI_TX 5 +#define IMX8MP_HDMIBLK_PD_HDMI_TX_PHY 6 + #endif -- cgit v1.2.3 From b2d057560b8107c633b39aabe517ff9d93f285e3 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 2 May 2022 10:46:08 +0200 Subject: secure_seq: use the 64 bits of the siphash for port offset calculation SipHash replaced MD5 in secure_ipv{4,6}_port_ephemeral() via commit 7cd23e5300c1 ("secure_seq: use SipHash in place of MD5"), but the output remained truncated to 32-bit only. In order to exploit more bits from the hash, let's make the functions return the full 64-bit of siphash_3u32(). We also make sure the port offset calculation in __inet_hash_connect() remains done on 32-bit to avoid the need for div_u64_rem() and an extra cost on 32-bit systems. Cc: Jason A. Donenfeld Cc: Moshe Kol Cc: Yossi Gilad Cc: Amit Klein Reviewed-by: Eric Dumazet Signed-off-by: Willy Tarreau Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 2 +- include/net/secure_seq.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index f72ec113ae56..98e1ec1a14f0 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -425,7 +425,7 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) } int __inet_hash_connect(struct inet_timewait_death_row *death_row, - struct sock *sk, u32 port_offset, + struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **)); diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index d7d2495f83c2..dac91aa38c5a 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -4,8 +4,8 @@ #include -u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); -u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, +u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); +u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); u32 secure_tcp_seq(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); -- cgit v1.2.3 From 170f37d6aa6ad4582eefd7459015de79e244536e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 3 May 2022 00:09:31 -0400 Subject: block: Do not call folio_next() on an unreferenced folio It is unsafe to call folio_next() on a folio unless you hold a reference on it that prevents it from being split or freed. After returning from the iterator, iomap calls folio_end_writeback() which may drop the last reference to the page, or allow the page to be split. If that happens, the iterator will not advance far enough through the bio_vec, leading to assertion failures like the BUG() in folio_end_writeback() that checks we're not trying to end writeback on a page not currently under writeback. Other assertion failures were also seen, but they're all explained by this one bug. Fix the bug by remembering where the next folio starts before returning from the iterator. There are other ways of fixing this bug, but this seems the simplest. Reported-by: Darrick J. Wong Tested-by: Darrick J. Wong Reported-by: Brian Foster Tested-by: Brian Foster Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/bio.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 278cc81cc1e7..00450fd86bb4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -269,6 +269,7 @@ struct folio_iter { size_t offset; size_t length; /* private: for use by the iterator */ + struct folio *_next; size_t _seg_count; int _i; }; @@ -283,6 +284,7 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, PAGE_SIZE * (bvec->bv_page - &fi->folio->page); fi->_seg_count = bvec->bv_len; fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count); + fi->_next = folio_next(fi->folio); fi->_i = i; } @@ -290,9 +292,10 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) { fi->_seg_count -= fi->length; if (fi->_seg_count) { - fi->folio = folio_next(fi->folio); + fi->folio = fi->_next; fi->offset = 0; fi->length = min(folio_size(fi->folio), fi->_seg_count); + fi->_next = folio_next(fi->folio); } else if (fi->_i + 1 < bio->bi_vcnt) { bio_first_folio(fi, bio, fi->_i + 1); } else { -- cgit v1.2.3 From 8e1de7042596abb7cb277ea751fc13a4c2b65aea Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 13 Feb 2022 16:44:45 +0200 Subject: thunderbolt: Add support for XDomain lane bonding The USB4 Inter-Domain Service specification defines a protocol that can be used to establish lane bonding between two USB4 domains (hosts). So far we have not implemented it because the host controller DMA was not fast enough to be able to go over 20 Gbits/s even if lanes were bonded. However, starting from Intel Alder Lake CPUs the DMA can go over 20 Gbits/s so now it makes more sense to add this support to the driver. Because both ends need to negotiate the bonding we add a simple state machine that tracks the connection state and does the necessary steps described by the USB4 Inter-Domain Service specification. We only establish lane bonding when both sides of the link support it. Otherwise we default to use the single lane. Also this is only done when software connection manager is used. On systems with firmware based connection manager, it handles the high-speed tunneling so bonding lanes is specific to the implementation (Intel firmware based connection manager does not support lane bonding). Signed-off-by: Mika Westerberg --- include/linux/thunderbolt.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 124e13cb1469..e13fe15e6a51 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -198,15 +198,15 @@ void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir); * @local_property_block_len: Length of the @local_property_block in dwords * @remote_properties: Properties exported by the remote domain * @remote_property_block_gen: Generation of @remote_properties - * @get_uuid_work: Work used to retrieve @remote_uuid - * @uuid_retries: Number of times left @remote_uuid is requested before - * giving up - * @get_properties_work: Work used to get remote domain properties - * @properties_retries: Number of times left to read properties + * @state: Next XDomain discovery state to run + * @state_work: Work used to run the next state + * @state_retries: Number of retries remain for the state * @properties_changed_work: Work used to notify the remote domain that * our properties have changed * @properties_changed_retries: Number of times left to send properties * changed notification + * @bonding_possible: True if lane bonding is possible on local side + * @target_link_width: Target link width from the remote host * @link: Root switch link the remote domain is connected (ICM only) * @depth: Depth in the chain the remote domain is connected (ICM only) * @@ -244,12 +244,13 @@ struct tb_xdomain { u32 local_property_block_len; struct tb_property_dir *remote_properties; u32 remote_property_block_gen; - struct delayed_work get_uuid_work; - int uuid_retries; - struct delayed_work get_properties_work; - int properties_retries; + int state; + struct delayed_work state_work; + int state_retries; struct delayed_work properties_changed_work; int properties_changed_retries; + bool bonding_possible; + u8 target_link_width; u8 link; u8 depth; }; -- cgit v1.2.3 From 680e1c8370a2ed7aff4f99ce3cebf79873d68f59 Mon Sep 17 00:00:00 2001 From: Chanho Park Date: Wed, 4 May 2022 16:51:43 +0900 Subject: dt-bindings: clock: add clock binding definitions for Exynos Auto v9 Add device tree clock binding definitions for below CMU blocks. - CMU_TOP - CMU_BUSMC - CMU_CORE - CMU_FYS2 - CMU_PERIC0 / C1 - CMU_PERIS Reviewed-by: Krzysztof Kozlowski Signed-off-by: Chanho Park Acked-by: Chanwoo Choi Link: https://lore.kernel.org/r/20220504075154.58819-2-chanho61.park@samsung.com Signed-off-by: Krzysztof Kozlowski --- include/dt-bindings/clock/samsung,exynosautov9.h | 299 +++++++++++++++++++++++ 1 file changed, 299 insertions(+) create mode 100644 include/dt-bindings/clock/samsung,exynosautov9.h (limited to 'include') diff --git a/include/dt-bindings/clock/samsung,exynosautov9.h b/include/dt-bindings/clock/samsung,exynosautov9.h new file mode 100644 index 000000000000..71ec0a955364 --- /dev/null +++ b/include/dt-bindings/clock/samsung,exynosautov9.h @@ -0,0 +1,299 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2022 Samsung Electronics Co., Ltd. + * Author: Chanho Park + * + * Device Tree binding constants for Exynos Auto V9 clock controller. + */ + +#ifndef _DT_BINDINGS_CLOCK_EXYNOSAUTOV9_H +#define _DT_BINDINGS_CLOCK_EXYNOSAUTOV9_H + +/* CMU_TOP */ +#define FOUT_SHARED0_PLL 1 +#define FOUT_SHARED1_PLL 2 +#define FOUT_SHARED2_PLL 3 +#define FOUT_SHARED3_PLL 4 +#define FOUT_SHARED4_PLL 5 + +/* MUX in CMU_TOP */ +#define MOUT_SHARED0_PLL 6 +#define MOUT_SHARED1_PLL 7 +#define MOUT_SHARED2_PLL 8 +#define MOUT_SHARED3_PLL 9 +#define MOUT_SHARED4_PLL 10 +#define MOUT_CLKCMU_CMU_BOOST 11 +#define MOUT_CLKCMU_CMU_CMUREF 12 +#define MOUT_CLKCMU_ACC_BUS 13 +#define MOUT_CLKCMU_APM_BUS 14 +#define MOUT_CLKCMU_AUD_CPU 15 +#define MOUT_CLKCMU_AUD_BUS 16 +#define MOUT_CLKCMU_BUSC_BUS 17 +#define MOUT_CLKCMU_BUSMC_BUS 19 +#define MOUT_CLKCMU_CORE_BUS 20 +#define MOUT_CLKCMU_CPUCL0_SWITCH 21 +#define MOUT_CLKCMU_CPUCL0_CLUSTER 22 +#define MOUT_CLKCMU_CPUCL1_SWITCH 24 +#define MOUT_CLKCMU_CPUCL1_CLUSTER 25 +#define MOUT_CLKCMU_DPTX_BUS 26 +#define MOUT_CLKCMU_DPTX_DPGTC 27 +#define MOUT_CLKCMU_DPUM_BUS 28 +#define MOUT_CLKCMU_DPUS0_BUS 29 +#define MOUT_CLKCMU_DPUS1_BUS 30 +#define MOUT_CLKCMU_FSYS0_BUS 31 +#define MOUT_CLKCMU_FSYS0_PCIE 32 +#define MOUT_CLKCMU_FSYS1_BUS 33 +#define MOUT_CLKCMU_FSYS1_USBDRD 34 +#define MOUT_CLKCMU_FSYS1_MMC_CARD 35 +#define MOUT_CLKCMU_FSYS2_BUS 36 +#define MOUT_CLKCMU_FSYS2_UFS_EMBD 37 +#define MOUT_CLKCMU_FSYS2_ETHERNET 38 +#define MOUT_CLKCMU_G2D_G2D 39 +#define MOUT_CLKCMU_G2D_MSCL 40 +#define MOUT_CLKCMU_G3D00_SWITCH 41 +#define MOUT_CLKCMU_G3D01_SWITCH 42 +#define MOUT_CLKCMU_G3D1_SWITCH 43 +#define MOUT_CLKCMU_ISPB_BUS 44 +#define MOUT_CLKCMU_MFC_MFC 45 +#define MOUT_CLKCMU_MFC_WFD 46 +#define MOUT_CLKCMU_MIF_SWITCH 47 +#define MOUT_CLKCMU_MIF_BUSP 48 +#define MOUT_CLKCMU_NPU_BUS 49 +#define MOUT_CLKCMU_PERIC0_BUS 50 +#define MOUT_CLKCMU_PERIC0_IP 51 +#define MOUT_CLKCMU_PERIC1_BUS 52 +#define MOUT_CLKCMU_PERIC1_IP 53 +#define MOUT_CLKCMU_PERIS_BUS 54 + +/* DIV in CMU_TOP */ +#define DOUT_SHARED0_DIV3 101 +#define DOUT_SHARED0_DIV2 102 +#define DOUT_SHARED1_DIV3 103 +#define DOUT_SHARED1_DIV2 104 +#define DOUT_SHARED1_DIV4 105 +#define DOUT_SHARED2_DIV3 106 +#define DOUT_SHARED2_DIV2 107 +#define DOUT_SHARED2_DIV4 108 +#define DOUT_SHARED4_DIV2 109 +#define DOUT_SHARED4_DIV4 110 +#define DOUT_CLKCMU_CMU_BOOST 111 +#define DOUT_CLKCMU_ACC_BUS 112 +#define DOUT_CLKCMU_APM_BUS 113 +#define DOUT_CLKCMU_AUD_CPU 114 +#define DOUT_CLKCMU_AUD_BUS 115 +#define DOUT_CLKCMU_BUSC_BUS 116 +#define DOUT_CLKCMU_BUSMC_BUS 118 +#define DOUT_CLKCMU_CORE_BUS 119 +#define DOUT_CLKCMU_CPUCL0_SWITCH 120 +#define DOUT_CLKCMU_CPUCL0_CLUSTER 121 +#define DOUT_CLKCMU_CPUCL1_SWITCH 123 +#define DOUT_CLKCMU_CPUCL1_CLUSTER 124 +#define DOUT_CLKCMU_DPTX_BUS 125 +#define DOUT_CLKCMU_DPTX_DPGTC 126 +#define DOUT_CLKCMU_DPUM_BUS 127 +#define DOUT_CLKCMU_DPUS0_BUS 128 +#define DOUT_CLKCMU_DPUS1_BUS 129 +#define DOUT_CLKCMU_FSYS0_BUS 130 +#define DOUT_CLKCMU_FSYS0_PCIE 131 +#define DOUT_CLKCMU_FSYS1_BUS 132 +#define DOUT_CLKCMU_FSYS1_USBDRD 133 +#define DOUT_CLKCMU_FSYS2_BUS 134 +#define DOUT_CLKCMU_FSYS2_UFS_EMBD 135 +#define DOUT_CLKCMU_FSYS2_ETHERNET 136 +#define DOUT_CLKCMU_G2D_G2D 137 +#define DOUT_CLKCMU_G2D_MSCL 138 +#define DOUT_CLKCMU_G3D00_SWITCH 139 +#define DOUT_CLKCMU_G3D01_SWITCH 140 +#define DOUT_CLKCMU_G3D1_SWITCH 141 +#define DOUT_CLKCMU_ISPB_BUS 142 +#define DOUT_CLKCMU_MFC_MFC 143 +#define DOUT_CLKCMU_MFC_WFD 144 +#define DOUT_CLKCMU_MIF_SWITCH 145 +#define DOUT_CLKCMU_MIF_BUSP 146 +#define DOUT_CLKCMU_NPU_BUS 147 +#define DOUT_CLKCMU_PERIC0_BUS 148 +#define DOUT_CLKCMU_PERIC0_IP 149 +#define DOUT_CLKCMU_PERIC1_BUS 150 +#define DOUT_CLKCMU_PERIC1_IP 151 +#define DOUT_CLKCMU_PERIS_BUS 152 + +/* GAT in CMU_TOP */ +#define GOUT_CLKCMU_CMU_BOOST 201 +#define GOUT_CLKCMU_CPUCL0_BOOST 202 +#define GOUT_CLKCMU_CPUCL1_BOOST 203 +#define GOUT_CLKCMU_CORE_BOOST 204 +#define GOUT_CLKCMU_BUSC_BOOST 205 +#define GOUT_CLKCMU_BUSMC_BOOST 206 +#define GOUT_CLKCMU_MIF_BOOST 207 +#define GOUT_CLKCMU_ACC_BUS 208 +#define GOUT_CLKCMU_APM_BUS 209 +#define GOUT_CLKCMU_AUD_CPU 210 +#define GOUT_CLKCMU_AUD_BUS 211 +#define GOUT_CLKCMU_BUSC_BUS 212 +#define GOUT_CLKCMU_BUSMC_BUS 214 +#define GOUT_CLKCMU_CORE_BUS 215 +#define GOUT_CLKCMU_CPUCL0_SWITCH 216 +#define GOUT_CLKCMU_CPUCL0_CLUSTER 217 +#define GOUT_CLKCMU_CPUCL1_SWITCH 219 +#define GOUT_CLKCMU_CPUCL1_CLUSTER 220 +#define GOUT_CLKCMU_DPTX_BUS 221 +#define GOUT_CLKCMU_DPTX_DPGTC 222 +#define GOUT_CLKCMU_DPUM_BUS 223 +#define GOUT_CLKCMU_DPUS0_BUS 224 +#define GOUT_CLKCMU_DPUS1_BUS 225 +#define GOUT_CLKCMU_FSYS0_BUS 226 +#define GOUT_CLKCMU_FSYS0_PCIE 227 +#define GOUT_CLKCMU_FSYS1_BUS 228 +#define GOUT_CLKCMU_FSYS1_USBDRD 229 +#define GOUT_CLKCMU_FSYS1_MMC_CARD 230 +#define GOUT_CLKCMU_FSYS2_BUS 231 +#define GOUT_CLKCMU_FSYS2_UFS_EMBD 232 +#define GOUT_CLKCMU_FSYS2_ETHERNET 233 +#define GOUT_CLKCMU_G2D_G2D 234 +#define GOUT_CLKCMU_G2D_MSCL 235 +#define GOUT_CLKCMU_G3D00_SWITCH 236 +#define GOUT_CLKCMU_G3D01_SWITCH 237 +#define GOUT_CLKCMU_G3D1_SWITCH 238 +#define GOUT_CLKCMU_ISPB_BUS 239 +#define GOUT_CLKCMU_MFC_MFC 240 +#define GOUT_CLKCMU_MFC_WFD 241 +#define GOUT_CLKCMU_MIF_SWITCH 242 +#define GOUT_CLKCMU_MIF_BUSP 243 +#define GOUT_CLKCMU_NPU_BUS 244 +#define GOUT_CLKCMU_PERIC0_BUS 245 +#define GOUT_CLKCMU_PERIC0_IP 246 +#define GOUT_CLKCMU_PERIC1_BUS 247 +#define GOUT_CLKCMU_PERIC1_IP 248 +#define GOUT_CLKCMU_PERIS_BUS 249 + +#define TOP_NR_CLK 249 + +/* CMU_BUSMC */ +#define CLK_MOUT_BUSMC_BUS_USER 1 +#define CLK_DOUT_BUSMC_BUSP 2 +#define CLK_GOUT_BUSMC_PDMA0_PCLK 3 +#define CLK_GOUT_BUSMC_SPDMA_PCLK 4 + +#define BUSMC_NR_CLK 4 + +/* CMU_CORE */ +#define CLK_MOUT_CORE_BUS_USER 1 +#define CLK_DOUT_CORE_BUSP 2 +#define CLK_GOUT_CORE_CCI_CLK 3 +#define CLK_GOUT_CORE_CCI_PCLK 4 +#define CLK_GOUT_CORE_CMU_CORE_PCLK 5 + +#define CORE_NR_CLK 5 + +/* CMU_FSYS2 */ +#define CLK_MOUT_FSYS2_BUS_USER 1 +#define CLK_MOUT_FSYS2_UFS_EMBD_USER 2 +#define CLK_MOUT_FSYS2_ETHERNET_USER 3 +#define CLK_GOUT_FSYS2_UFS_EMBD0_ACLK 4 +#define CLK_GOUT_FSYS2_UFS_EMBD0_UNIPRO 5 +#define CLK_GOUT_FSYS2_UFS_EMBD1_ACLK 6 +#define CLK_GOUT_FSYS2_UFS_EMBD1_UNIPRO 7 + +#define FSYS2_NR_CLK 7 + +/* CMU_PERIC0 */ +#define CLK_MOUT_PERIC0_BUS_USER 1 +#define CLK_MOUT_PERIC0_IP_USER 2 +#define CLK_MOUT_PERIC0_USI00_USI 3 +#define CLK_MOUT_PERIC0_USI01_USI 4 +#define CLK_MOUT_PERIC0_USI02_USI 5 +#define CLK_MOUT_PERIC0_USI03_USI 6 +#define CLK_MOUT_PERIC0_USI04_USI 7 +#define CLK_MOUT_PERIC0_USI05_USI 8 +#define CLK_MOUT_PERIC0_USI_I2C 9 + +#define CLK_DOUT_PERIC0_USI00_USI 10 +#define CLK_DOUT_PERIC0_USI01_USI 11 +#define CLK_DOUT_PERIC0_USI02_USI 12 +#define CLK_DOUT_PERIC0_USI03_USI 13 +#define CLK_DOUT_PERIC0_USI04_USI 14 +#define CLK_DOUT_PERIC0_USI05_USI 15 +#define CLK_DOUT_PERIC0_USI_I2C 16 + +#define CLK_GOUT_PERIC0_IPCLK_0 20 +#define CLK_GOUT_PERIC0_IPCLK_1 21 +#define CLK_GOUT_PERIC0_IPCLK_2 22 +#define CLK_GOUT_PERIC0_IPCLK_3 23 +#define CLK_GOUT_PERIC0_IPCLK_4 24 +#define CLK_GOUT_PERIC0_IPCLK_5 25 +#define CLK_GOUT_PERIC0_IPCLK_6 26 +#define CLK_GOUT_PERIC0_IPCLK_7 27 +#define CLK_GOUT_PERIC0_IPCLK_8 28 +#define CLK_GOUT_PERIC0_IPCLK_9 29 +#define CLK_GOUT_PERIC0_IPCLK_10 30 +#define CLK_GOUT_PERIC0_IPCLK_11 30 +#define CLK_GOUT_PERIC0_PCLK_0 31 +#define CLK_GOUT_PERIC0_PCLK_1 32 +#define CLK_GOUT_PERIC0_PCLK_2 33 +#define CLK_GOUT_PERIC0_PCLK_3 34 +#define CLK_GOUT_PERIC0_PCLK_4 35 +#define CLK_GOUT_PERIC0_PCLK_5 36 +#define CLK_GOUT_PERIC0_PCLK_6 37 +#define CLK_GOUT_PERIC0_PCLK_7 38 +#define CLK_GOUT_PERIC0_PCLK_8 39 +#define CLK_GOUT_PERIC0_PCLK_9 40 +#define CLK_GOUT_PERIC0_PCLK_10 41 +#define CLK_GOUT_PERIC0_PCLK_11 42 + +#define PERIC0_NR_CLK 42 + +/* CMU_PERIC1 */ +#define CLK_MOUT_PERIC1_BUS_USER 1 +#define CLK_MOUT_PERIC1_IP_USER 2 +#define CLK_MOUT_PERIC1_USI06_USI 3 +#define CLK_MOUT_PERIC1_USI07_USI 4 +#define CLK_MOUT_PERIC1_USI08_USI 5 +#define CLK_MOUT_PERIC1_USI09_USI 6 +#define CLK_MOUT_PERIC1_USI10_USI 7 +#define CLK_MOUT_PERIC1_USI11_USI 8 +#define CLK_MOUT_PERIC1_USI_I2C 9 + +#define CLK_DOUT_PERIC1_USI06_USI 10 +#define CLK_DOUT_PERIC1_USI07_USI 11 +#define CLK_DOUT_PERIC1_USI08_USI 12 +#define CLK_DOUT_PERIC1_USI09_USI 13 +#define CLK_DOUT_PERIC1_USI10_USI 14 +#define CLK_DOUT_PERIC1_USI11_USI 15 +#define CLK_DOUT_PERIC1_USI_I2C 16 + +#define CLK_GOUT_PERIC1_IPCLK_0 20 +#define CLK_GOUT_PERIC1_IPCLK_1 21 +#define CLK_GOUT_PERIC1_IPCLK_2 22 +#define CLK_GOUT_PERIC1_IPCLK_3 23 +#define CLK_GOUT_PERIC1_IPCLK_4 24 +#define CLK_GOUT_PERIC1_IPCLK_5 25 +#define CLK_GOUT_PERIC1_IPCLK_6 26 +#define CLK_GOUT_PERIC1_IPCLK_7 27 +#define CLK_GOUT_PERIC1_IPCLK_8 28 +#define CLK_GOUT_PERIC1_IPCLK_9 29 +#define CLK_GOUT_PERIC1_IPCLK_10 30 +#define CLK_GOUT_PERIC1_IPCLK_11 30 +#define CLK_GOUT_PERIC1_PCLK_0 31 +#define CLK_GOUT_PERIC1_PCLK_1 32 +#define CLK_GOUT_PERIC1_PCLK_2 33 +#define CLK_GOUT_PERIC1_PCLK_3 34 +#define CLK_GOUT_PERIC1_PCLK_4 35 +#define CLK_GOUT_PERIC1_PCLK_5 36 +#define CLK_GOUT_PERIC1_PCLK_6 37 +#define CLK_GOUT_PERIC1_PCLK_7 38 +#define CLK_GOUT_PERIC1_PCLK_8 39 +#define CLK_GOUT_PERIC1_PCLK_9 40 +#define CLK_GOUT_PERIC1_PCLK_10 41 +#define CLK_GOUT_PERIC1_PCLK_11 42 + +#define PERIC1_NR_CLK 42 + +/* CMU_PERIS */ +#define CLK_MOUT_PERIS_BUS_USER 1 +#define CLK_GOUT_SYSREG_PERIS_PCLK 2 +#define CLK_GOUT_WDT_CLUSTER0 3 +#define CLK_GOUT_WDT_CLUSTER1 4 + +#define PERIS_NR_CLK 4 + +#endif /* _DT_BINDINGS_CLOCK_EXYNOSAUTOV9_H */ -- cgit v1.2.3 From 96055bf71ab1629cdedff15bcbc04609cfa1f198 Mon Sep 17 00:00:00 2001 From: Phil Edworthy Date: Tue, 3 May 2022 12:55:47 +0100 Subject: dt-bindings: clock: Add r9a09g011 CPG Clock Definitions Define RZ/V2M (R9A09G011) Clock Pulse Generator module clock outputs (CPG_CLK_ON* registers), and reset definitions (CPG_RST_* registers) in Section 48.5 ("Register Description") of the RZ/V2M Hardware User's Manual (Rev. 1.10, Sep. 2021). Signed-off-by: Phil Edworthy Reviewed-by: Biju Das Link: https://lore.kernel.org/r/20220503115557.53370-3-phil.edworthy@renesas.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/clock/r9a09g011-cpg.h | 352 ++++++++++++++++++++++++++++++ 1 file changed, 352 insertions(+) create mode 100644 include/dt-bindings/clock/r9a09g011-cpg.h (limited to 'include') diff --git a/include/dt-bindings/clock/r9a09g011-cpg.h b/include/dt-bindings/clock/r9a09g011-cpg.h new file mode 100644 index 000000000000..41dd585d7115 --- /dev/null +++ b/include/dt-bindings/clock/r9a09g011-cpg.h @@ -0,0 +1,352 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + * + * Copyright (C) 2022 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_CLOCK_R9A09G011_CPG_H__ +#define __DT_BINDINGS_CLOCK_R9A09G011_CPG_H__ + +#include + +/* Module Clocks */ +#define R9A09G011_SYS_CLK 0 +#define R9A09G011_PFC_PCLK 1 +#define R9A09G011_PMC_CORE_CLOCK 2 +#define R9A09G011_GIC_CLK 3 +#define R9A09G011_RAMA_ACLK 4 +#define R9A09G011_ROMA_ACLK 5 +#define R9A09G011_SEC_ACLK 6 +#define R9A09G011_SEC_PCLK 7 +#define R9A09G011_SEC_TCLK 8 +#define R9A09G011_DMAA_ACLK 9 +#define R9A09G011_TSU0_PCLK 10 +#define R9A09G011_TSU1_PCLK 11 + +#define R9A09G011_CST_TRACECLK 12 +#define R9A09G011_CST_SB_CLK 13 +#define R9A09G011_CST_AHB_CLK 14 +#define R9A09G011_CST_ATB_SB_CLK 15 +#define R9A09G011_CST_TS_SB_CLK 16 + +#define R9A09G011_SDI0_ACLK 17 +#define R9A09G011_SDI0_IMCLK 18 +#define R9A09G011_SDI0_IMCLK2 19 +#define R9A09G011_SDI0_CLK_HS 20 +#define R9A09G011_SDI1_ACLK 21 +#define R9A09G011_SDI1_IMCLK 22 +#define R9A09G011_SDI1_IMCLK2 23 +#define R9A09G011_SDI1_CLK_HS 24 +#define R9A09G011_EMM_ACLK 25 +#define R9A09G011_EMM_IMCLK 26 +#define R9A09G011_EMM_IMCLK2 27 +#define R9A09G011_EMM_CLK_HS 28 +#define R9A09G011_NFI_ACLK 29 +#define R9A09G011_NFI_NF_CLK 30 + +#define R9A09G011_PCI_ACLK 31 +#define R9A09G011_PCI_CLK_PMU 32 +#define R9A09G011_PCI_APB_CLK 33 +#define R9A09G011_USB_ACLK_H 34 +#define R9A09G011_USB_ACLK_P 35 +#define R9A09G011_USB_PCLK 36 +#define R9A09G011_ETH0_CLK_AXI 37 +#define R9A09G011_ETH0_CLK_CHI 38 +#define R9A09G011_ETH0_GPTP_EXT 39 + +#define R9A09G011_SDT_CLK 40 +#define R9A09G011_SDT_CLKAPB 41 +#define R9A09G011_SDT_CLK48 42 +#define R9A09G011_GRP_CLK 43 +#define R9A09G011_CIF_P0_CLK 44 +#define R9A09G011_CIF_P1_CLK 45 +#define R9A09G011_CIF_APB_CLK 46 +#define R9A09G011_DCI_CLKAXI 47 +#define R9A09G011_DCI_CLKAPB 48 +#define R9A09G011_DCI_CLKDCI2 49 + +#define R9A09G011_HMI_PCLK 50 +#define R9A09G011_LCI_PCLK 51 +#define R9A09G011_LCI_ACLK 52 +#define R9A09G011_LCI_VCLK 53 +#define R9A09G011_LCI_LPCLK 54 + +#define R9A09G011_AUI_CLK 55 +#define R9A09G011_AUI_CLKAXI 56 +#define R9A09G011_AUI_CLKAPB 57 +#define R9A09G011_AUMCLK 58 +#define R9A09G011_GMCLK0 59 +#define R9A09G011_GMCLK1 60 +#define R9A09G011_MTR_CLK0 61 +#define R9A09G011_MTR_CLK1 62 +#define R9A09G011_MTR_CLKAPB 63 +#define R9A09G011_GFT_CLK 64 +#define R9A09G011_GFT_CLKAPB 65 +#define R9A09G011_GFT_MCLK 66 + +#define R9A09G011_ATGA_CLK 67 +#define R9A09G011_ATGA_CLKAPB 68 +#define R9A09G011_ATGB_CLK 69 +#define R9A09G011_ATGB_CLKAPB 70 +#define R9A09G011_SYC_CNT_CLK 71 + +#define R9A09G011_CPERI_GRPA_PCLK 72 +#define R9A09G011_TIM0_CLK 73 +#define R9A09G011_TIM1_CLK 74 +#define R9A09G011_TIM2_CLK 75 +#define R9A09G011_TIM3_CLK 76 +#define R9A09G011_TIM4_CLK 77 +#define R9A09G011_TIM5_CLK 78 +#define R9A09G011_TIM6_CLK 79 +#define R9A09G011_TIM7_CLK 80 +#define R9A09G011_IIC_PCLK0 81 + +#define R9A09G011_CPERI_GRPB_PCLK 82 +#define R9A09G011_TIM8_CLK 83 +#define R9A09G011_TIM9_CLK 84 +#define R9A09G011_TIM10_CLK 85 +#define R9A09G011_TIM11_CLK 86 +#define R9A09G011_TIM12_CLK 87 +#define R9A09G011_TIM13_CLK 88 +#define R9A09G011_TIM14_CLK 89 +#define R9A09G011_TIM15_CLK 90 +#define R9A09G011_IIC_PCLK1 91 + +#define R9A09G011_CPERI_GRPC_PCLK 92 +#define R9A09G011_TIM16_CLK 93 +#define R9A09G011_TIM17_CLK 94 +#define R9A09G011_TIM18_CLK 95 +#define R9A09G011_TIM19_CLK 96 +#define R9A09G011_TIM20_CLK 97 +#define R9A09G011_TIM21_CLK 98 +#define R9A09G011_TIM22_CLK 99 +#define R9A09G011_TIM23_CLK 100 +#define R9A09G011_WDT0_PCLK 101 +#define R9A09G011_WDT0_CLK 102 +#define R9A09G011_WDT1_PCLK 103 +#define R9A09G011_WDT1_CLK 104 + +#define R9A09G011_CPERI_GRPD_PCLK 105 +#define R9A09G011_TIM24_CLK 106 +#define R9A09G011_TIM25_CLK 107 +#define R9A09G011_TIM26_CLK 108 +#define R9A09G011_TIM27_CLK 109 +#define R9A09G011_TIM28_CLK 110 +#define R9A09G011_TIM29_CLK 111 +#define R9A09G011_TIM30_CLK 112 +#define R9A09G011_TIM31_CLK 113 + +#define R9A09G011_CPERI_GRPE_PCLK 114 +#define R9A09G011_PWM0_CLK 115 +#define R9A09G011_PWM1_CLK 116 +#define R9A09G011_PWM2_CLK 117 +#define R9A09G011_PWM3_CLK 118 +#define R9A09G011_PWM4_CLK 119 +#define R9A09G011_PWM5_CLK 120 +#define R9A09G011_PWM6_CLK 121 +#define R9A09G011_PWM7_CLK 122 + +#define R9A09G011_CPERI_GRPF_PCLK 123 +#define R9A09G011_PWM8_CLK 124 +#define R9A09G011_PWM9_CLK 125 +#define R9A09G011_PWM10_CLK 126 +#define R9A09G011_PWM11_CLK 127 +#define R9A09G011_PWM12_CLK 128 +#define R9A09G011_PWM13_CLK 129 +#define R9A09G011_PWM14_CLK 130 +#define R9A09G011_PWM15_CLK 131 + +#define R9A09G011_CPERI_GRPG_PCLK 132 +#define R9A09G011_CPERI_GRPH_PCLK 133 +#define R9A09G011_URT_PCLK 134 +#define R9A09G011_URT0_CLK 135 +#define R9A09G011_URT1_CLK 136 +#define R9A09G011_CSI0_CLK 137 +#define R9A09G011_CSI1_CLK 138 +#define R9A09G011_CSI2_CLK 139 +#define R9A09G011_CSI3_CLK 140 +#define R9A09G011_CSI4_CLK 141 +#define R9A09G011_CSI5_CLK 142 + +#define R9A09G011_ICB_ACLK1 143 +#define R9A09G011_ICB_GIC_CLK 144 +#define R9A09G011_ICB_MPCLK1 145 +#define R9A09G011_ICB_SPCLK1 146 +#define R9A09G011_ICB_CLK48 147 +#define R9A09G011_ICB_CLK48_2 148 +#define R9A09G011_ICB_CLK48_3 149 +#define R9A09G011_ICB_CLK48_4L 150 +#define R9A09G011_ICB_CLK48_4R 151 +#define R9A09G011_ICB_CLK48_5 152 +#define R9A09G011_ICB_CST_ATB_SB_CLK 153 +#define R9A09G011_ICB_CST_CS_CLK 154 +#define R9A09G011_ICB_CLK100_1 155 +#define R9A09G011_ICB_ETH0_CLK_AXI 156 +#define R9A09G011_ICB_DCI_CLKAXI 157 +#define R9A09G011_ICB_SYC_CNT_CLK 158 + +#define R9A09G011_ICB_DRPA_ACLK 159 +#define R9A09G011_ICB_RFX_ACLK 160 +#define R9A09G011_ICB_RFX_PCLK5 161 +#define R9A09G011_ICB_MMC_ACLK 162 + +#define R9A09G011_ICB_MPCLK3 163 +#define R9A09G011_ICB_CIMA_CLK 164 +#define R9A09G011_ICB_CIMB_CLK 165 +#define R9A09G011_ICB_BIMA_CLK 166 +#define R9A09G011_ICB_FCD_CLKAXI 167 +#define R9A09G011_ICB_VD_ACLK4 168 +#define R9A09G011_ICB_MPCLK4 169 +#define R9A09G011_ICB_VCD_PCLK4 170 + +#define R9A09G011_CA53_CLK 171 +#define R9A09G011_CA53_ACLK 172 +#define R9A09G011_CA53_APCLK_DBG 173 +#define R9A09G011_CST_APB_CA53_CLK 174 +#define R9A09G011_CA53_ATCLK 175 +#define R9A09G011_CST_CS_CLK 176 +#define R9A09G011_CA53_TSCLK 177 +#define R9A09G011_CST_TS_CLK 178 +#define R9A09G011_CA53_APCLK_REG 179 + +#define R9A09G011_DRPA_ACLK 180 +#define R9A09G011_DRPA_DCLK 181 +#define R9A09G011_DRPA_INITCLK 182 + +#define R9A09G011_RAMB0_ACLK 183 +#define R9A09G011_RAMB1_ACLK 184 +#define R9A09G011_RAMB2_ACLK 185 +#define R9A09G011_RAMB3_ACLK 186 + +#define R9A09G011_CIMA_CLKAPB 187 +#define R9A09G011_CIMA_CLK 188 +#define R9A09G011_CIMB_CLK 189 +#define R9A09G011_FAFA_CLK 190 +#define R9A09G011_STG_CLKAXI 191 +#define R9A09G011_STG_CLK0 192 + +#define R9A09G011_BIMA_CLKAPB 193 +#define R9A09G011_BIMA_CLK 194 +#define R9A09G011_FAFB_CLK 195 +#define R9A09G011_FCD_CLK 196 +#define R9A09G011_FCD_CLKAXI 197 + +#define R9A09G011_RIM_CLK 198 +#define R9A09G011_VCD_ACLK 199 +#define R9A09G011_VCD_PCLK 200 +#define R9A09G011_JPG0_CLK 201 +#define R9A09G011_JPG0_ACLK 202 + +#define R9A09G011_MMC_CORE_DDRC_CLK 203 +#define R9A09G011_MMC_ACLK 204 +#define R9A09G011_MMC_PCLK 205 +#define R9A09G011_DDI_APBCLK 206 + +/* Resets */ +#define R9A09G011_SYS_RST_N 0 +#define R9A09G011_PFC_PRESETN 1 +#define R9A09G011_RAMA_ARESETN 2 +#define R9A09G011_ROM_ARESETN 3 +#define R9A09G011_DMAA_ARESETN 4 +#define R9A09G011_SEC_ARESETN 5 +#define R9A09G011_SEC_PRESETN 6 +#define R9A09G011_SEC_RSTB 7 +#define R9A09G011_TSU0_RESETN 8 +#define R9A09G011_TSU1_RESETN 9 +#define R9A09G011_PMC_RESET_N 10 + +#define R9A09G011_CST_NTRST 11 +#define R9A09G011_CST_NPOTRST 12 +#define R9A09G011_CST_NTRST2 13 +#define R9A09G011_CST_CS_RESETN 14 +#define R9A09G011_CST_TS_RESETN 15 +#define R9A09G011_CST_TRESETN 16 +#define R9A09G011_CST_SB_RESETN 17 +#define R9A09G011_CST_AHB_RESETN 18 +#define R9A09G011_CST_TS_SB_RESETN 19 +#define R9A09G011_CST_APB_CA53_RESETN 20 +#define R9A09G011_CST_ATB_SB_RESETN 21 + +#define R9A09G011_SDI0_IXRST 22 +#define R9A09G011_SDI1_IXRST 23 +#define R9A09G011_EMM_IXRST 24 +#define R9A09G011_NFI_MARESETN 25 +#define R9A09G011_NFI_REG_RST_N 26 +#define R9A09G011_USB_PRESET_N 27 +#define R9A09G011_USB_DRD_RESET 28 +#define R9A09G011_USB_ARESETN_P 29 +#define R9A09G011_USB_ARESETN_H 30 +#define R9A09G011_ETH0_RST_HW_N 31 +#define R9A09G011_PCI_ARESETN 32 + +#define R9A09G011_SDT_RSTSYSAX 33 +#define R9A09G011_GRP_RESETN 34 +#define R9A09G011_CIF_RST_N 35 +#define R9A09G011_DCU_RSTSYSAX 36 +#define R9A09G011_HMI_RST_N 37 +#define R9A09G011_HMI_PRESETN 38 +#define R9A09G011_LCI_PRESETN 39 +#define R9A09G011_LCI_ARESETN 40 + +#define R9A09G011_AUI_RSTSYSAX 41 +#define R9A09G011_MTR_RSTSYSAX 42 +#define R9A09G011_GFT_RSTSYSAX 43 +#define R9A09G011_ATGA_RSTSYSAX 44 +#define R9A09G011_ATGB_RSTSYSAX 45 +#define R9A09G011_SYC_RST_N 46 + +#define R9A09G011_TIM_GPA_PRESETN 47 +#define R9A09G011_TIM_GPB_PRESETN 48 +#define R9A09G011_TIM_GPC_PRESETN 49 +#define R9A09G011_TIM_GPD_PRESETN 50 +#define R9A09G011_PWM_GPE_PRESETN 51 +#define R9A09G011_PWM_GPF_PRESETN 52 +#define R9A09G011_CSI_GPG_PRESETN 53 +#define R9A09G011_CSI_GPH_PRESETN 54 +#define R9A09G011_IIC_GPA_PRESETN 55 +#define R9A09G011_IIC_GPB_PRESETN 56 +#define R9A09G011_URT_PRESETN 57 +#define R9A09G011_WDT0_PRESETN 58 +#define R9A09G011_WDT1_PRESETN 59 + +#define R9A09G011_ICB_PD_AWO_RST_N 60 +#define R9A09G011_ICB_PD_MMC_RST_N 61 +#define R9A09G011_ICB_PD_VD0_RST_N 62 +#define R9A09G011_ICB_PD_VD1_RST_N 63 +#define R9A09G011_ICB_PD_RFX_RST_N 64 + +#define R9A09G011_CA53_NCPUPORESET0 65 +#define R9A09G011_CA53_NCPUPORESET1 66 +#define R9A09G011_CA53_NCORERESET0 67 +#define R9A09G011_CA53_NCORERESET1 68 +#define R9A09G011_CA53_NPRESETDBG 69 +#define R9A09G011_CA53_L2RESET 70 +#define R9A09G011_CA53_NMISCRESET_HM 71 +#define R9A09G011_CA53_NMISCRESET_SM 72 +#define R9A09G011_CA53_NARESET 73 + +#define R9A09G011_DRPA_ARESETN 74 + +#define R9A09G011_RAMB0_ARESETN 75 +#define R9A09G011_RAMB1_ARESETN 76 +#define R9A09G011_RAMB2_ARESETN 77 +#define R9A09G011_RAMB3_ARESETN 78 + +#define R9A09G011_CIMA_RSTSYSAX 79 +#define R9A09G011_CIMB_RSTSYSAX 80 +#define R9A09G011_FAFA_RSTSYSAX 81 +#define R9A09G011_STG_RSTSYSAX 82 + +#define R9A09G011_BIMA_RSTSYSAX 83 +#define R9A09G011_FAFB_RSTSYSAX 84 +#define R9A09G011_FCD_RSTSYSAX 85 +#define R9A09G011_RIM_RSTSYSAX 86 +#define R9A09G011_VCD_RESETN 87 +#define R9A09G011_JPG_XRESET 88 + +#define R9A09G011_MMC_CORE_DDRC_RSTN 89 +#define R9A09G011_MMC_ARESETN_N 90 +#define R9A09G011_MMC_PRESETN 91 +#define R9A09G011_DDI_PWROK 92 +#define R9A09G011_DDI_RESET 93 +#define R9A09G011_DDI_RESETN_APB 94 + +#endif /* __DT_BINDINGS_CLOCK_R9A09G011_CPG_H__ */ -- cgit v1.2.3 From 4b439e25e29ec336c0e71ef1d1b212c412526518 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 9 Apr 2022 19:17:27 +0200 Subject: mm, hugetlbfs: Allow an arch to always use generic versions of get_unmapped_area functions Unlike most architectures, powerpc can only define at runtime if it is going to use the generic arch_get_unmapped_area() or not. Today, powerpc has a copy of the generic arch_get_unmapped_area() because when selection HAVE_ARCH_UNMAPPED_AREA the generic arch_get_unmapped_area() is not available. Rename it generic_get_unmapped_area() and make it independent of HAVE_ARCH_UNMAPPED_AREA. Do the same for arch_get_unmapped_area_topdown() versus HAVE_ARCH_UNMAPPED_AREA_TOPDOWN. Do the same for hugetlb_get_unmapped_area() versus HAVE_ARCH_HUGETLB_UNMAPPED_AREA. Signed-off-by: Christophe Leroy Reviewed-by: Nicholas Piggin Acked-by: Andrew Morton Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/77f9d3e592f1c8511df9381aa1c4e754651da4d1.1649523076.git.christophe.leroy@csgroup.eu --- include/linux/hugetlb.h | 5 +++++ include/linux/sched/mm.h | 9 +++++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ac2a1d758a80..bc97c8458df6 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -519,6 +519,11 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ +unsigned long +generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); + /* * huegtlb page specific state flags. These flags are located in page.private * of the hugetlb head page. Functions created via the below macros should be diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 1ad1f4bfa025..da3a32d05b34 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -153,6 +153,15 @@ extern unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); + +unsigned long +generic_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); +unsigned long +generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} -- cgit v1.2.3 From 2cb4de085f383cb9289083d1bedbaad046f640eb Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 9 Apr 2022 19:17:28 +0200 Subject: mm: Add len and flags parameters to arch_get_mmap_end() Powerpc needs flags and len to make decision on arch_get_mmap_end(). So add them as parameters to arch_get_mmap_end(). Signed-off-by: Christophe Leroy Acked-by: Catalin Marinas Acked-by: Andrew Morton Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/b556daabe7d2bdb2361c4d6130280da7c1ba2c14.1649523076.git.christophe.leroy@csgroup.eu --- include/linux/sched/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index da3a32d05b34..8cd975a8bfeb 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -137,7 +137,7 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #ifdef CONFIG_MMU #ifndef arch_get_mmap_end -#define arch_get_mmap_end(addr) (TASK_SIZE) +#define arch_get_mmap_end(addr, len, flags) (TASK_SIZE) #endif #ifndef arch_get_mmap_base -- cgit v1.2.3 From d77e745613680c54708470402e2b623dcd769681 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 30 Apr 2022 04:51:44 +0200 Subject: regmap: Add bulk read/write callbacks into regmap_config Currently the regmap_config structure only allows the user to implement single element register read/write using .reg_read/.reg_write callbacks. The regmap_bus already implements bulk counterparts of both, and is being misused as a workaround for the missing bulk read/write callbacks in regmap_config by a couple of drivers. To stop this misuse, add the bulk read/write callbacks to regmap_config and call them from the regmap core code. Signed-off-by: Marek Vasut Cc: Jagan Teki Cc: Mark Brown Cc: Maxime Ripard Cc: Robert Foss Cc: Sam Ravnborg Cc: Thomas Zimmermann To: dri-devel@lists.freedesktop.org Link: https://lore.kernel.org/r/20220430025145.640305-1-marex@denx.de Signed-off-by: Mark Brown --- include/linux/regmap.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index de81a94d7b30..8952fa3d0d59 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -299,6 +299,12 @@ typedef void (*regmap_unlock)(void *); * if the function require special handling with lock and reg * handling and the operation cannot be represented as a simple * update_bits operation on a bus such as SPI, I2C, etc. + * @read: Optional callback that if filled will be used to perform all the + * bulk reads from the registers. Data is returned in the buffer used + * to transmit data. + * @write: Same as above for writing. + * @max_raw_read: Max raw read size that can be used on the device. + * @max_raw_write: Max raw write size that can be used on the device. * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock * functions are used (see fields lock/unlock of struct regmap_config). @@ -385,6 +391,12 @@ struct regmap_config { int (*reg_write)(void *context, unsigned int reg, unsigned int val); int (*reg_update_bits)(void *context, unsigned int reg, unsigned int mask, unsigned int val); + /* Bulk read/write */ + int (*read)(void *context, const void *reg_buf, size_t reg_size, + void *val_buf, size_t val_size); + int (*write)(void *context, const void *data, size_t count); + size_t max_raw_read; + size_t max_raw_write; bool fast_io; -- cgit v1.2.3 From ed85a6e6fe7c01faff4504af9d5569e8ba417999 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Thu, 5 May 2022 12:48:17 +0300 Subject: ASoC: SOF: Add initial header file for ipc4 The header file contains essential structure definitions, description of bit fields and bits in the ipc4 header and an internally used ipc4 message container definition. Signed-off-by: Peter Ujfalusi Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Link: https://lore.kernel.org/r/20220505094818.10346-3-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/ipc4/header.h | 460 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 460 insertions(+) create mode 100644 include/sound/sof/ipc4/header.h (limited to 'include') diff --git a/include/sound/sof/ipc4/header.h b/include/sound/sof/ipc4/header.h new file mode 100644 index 000000000000..b8b8e5b5e3e1 --- /dev/null +++ b/include/sound/sof/ipc4/header.h @@ -0,0 +1,460 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * Copyright(c) 2022 Intel Corporation. All rights reserved. + */ + +#ifndef __INCLUDE_SOUND_SOF_IPC4_HEADER_H__ +#define __INCLUDE_SOUND_SOF_IPC4_HEADER_H__ + +#include +#include + +/* maximum message size for mailbox Tx/Rx */ +#define SOF_IPC4_MSG_MAX_SIZE 4096 + +/** \addtogroup sof_uapi uAPI + * SOF uAPI specification. + * @{ + */ + +/** + * struct sof_ipc4_msg - Placeholder of an IPC4 message + * @header_u64: IPC4 header as single u64 number + * @primary: Primary, mandatory part of the header + * @extension: Extended part of the header, if not used it should be + * set to 0 + * @data_size: Size of data in bytes pointed by @data_ptr + * @data_ptr: Pointer to the optional payload of a message + */ +struct sof_ipc4_msg { + union { + u64 header_u64; + struct { + u32 primary; + u32 extension; + }; + }; + + size_t data_size; + void *data_ptr; +}; + +/** + * struct sof_ipc4_tuple - Generic type/ID and parameter tuple + * @type: type/ID + * @size: size of the @value array in bytes + * @value: value for the given type + */ +struct sof_ipc4_tuple { + uint32_t type; + uint32_t size; + uint32_t value[]; +} __packed; + +/* + * IPC4 messages have two 32 bit identifier made up as follows :- + * + * header - msg type, msg id, msg direction ... + * extension - extra params such as msg data size in mailbox + * + * These are sent at the start of the IPC message in the mailbox. Messages + * should not be sent in the doorbell (special exceptions for firmware). + */ + +/* + * IPC4 primary header bit allocation for messages + * bit 0-23: message type specific + * bit 24-28: type: enum sof_ipc4_global_msg if target is SOF_IPC4_FW_GEN_MSG + * enum sof_ipc4_module_type if target is SOF_IPC4_MODULE_MSG + * bit 29: response - sof_ipc4_msg_dir + * bit 30: target - enum sof_ipc4_msg_target + * bit 31: reserved, unused + */ + +/* Value of target field - must fit into 1 bit */ +enum sof_ipc4_msg_target { + /* Global FW message */ + SOF_IPC4_FW_GEN_MSG, + + /* Module message */ + SOF_IPC4_MODULE_MSG +}; + +/* Value of type field - must fit into 5 bits */ +enum sof_ipc4_global_msg { + SOF_IPC4_GLB_BOOT_CONFIG, + SOF_IPC4_GLB_ROM_CONTROL, + SOF_IPC4_GLB_IPCGATEWAY_CMD, + + /* 3 .. 12: RESERVED - do not use */ + + SOF_IPC4_GLB_PERF_MEASUREMENTS_CMD = 13, + SOF_IPC4_GLB_CHAIN_DMA, + + SOF_IPC4_GLB_LOAD_MULTIPLE_MODULES, + SOF_IPC4_GLB_UNLOAD_MULTIPLE_MODULES, + + /* pipeline settings */ + SOF_IPC4_GLB_CREATE_PIPELINE, + SOF_IPC4_GLB_DELETE_PIPELINE, + SOF_IPC4_GLB_SET_PIPELINE_STATE, + SOF_IPC4_GLB_GET_PIPELINE_STATE, + SOF_IPC4_GLB_GET_PIPELINE_CONTEXT_SIZE, + SOF_IPC4_GLB_SAVE_PIPELINE, + SOF_IPC4_GLB_RESTORE_PIPELINE, + + /* Loads library (using Code Load or HD/A Host Output DMA) */ + SOF_IPC4_GLB_LOAD_LIBRARY, + + /* 25: RESERVED - do not use */ + + SOF_IPC4_GLB_INTERNAL_MESSAGE = 26, + + /* Notification (FW to SW driver) */ + SOF_IPC4_GLB_NOTIFICATION, + + /* 28 .. 31: RESERVED - do not use */ + + SOF_IPC4_GLB_TYPE_LAST, +}; + +/* Value of response field - must fit into 1 bit */ +enum sof_ipc4_msg_dir { + SOF_IPC4_MSG_REQUEST, + SOF_IPC4_MSG_REPLY, +}; + +enum sof_ipc4_pipeline_state { + SOF_IPC4_PIPE_INVALID_STATE, + SOF_IPC4_PIPE_UNINITIALIZED, + SOF_IPC4_PIPE_RESET, + SOF_IPC4_PIPE_PAUSED, + SOF_IPC4_PIPE_RUNNING, + SOF_IPC4_PIPE_EOS +}; + +/* Generic message fields (bit 24-30) */ + +/* encoded to header's msg_tgt field */ +#define SOF_IPC4_MSG_TARGET_SHIFT 30 +#define SOF_IPC4_MSG_TARGET_MASK BIT(30) +#define SOF_IPC4_MSG_TARGET(x) ((x) << SOF_IPC4_MSG_TARGET_SHIFT) +#define SOF_IPC4_MSG_IS_MODULE_MSG(x) ((x) & SOF_IPC4_MSG_TARGET_MASK ? 1 : 0) + +/* encoded to header's rsp field */ +#define SOF_IPC4_MSG_DIR_SHIFT 29 +#define SOF_IPC4_MSG_DIR_MASK BIT(29) +#define SOF_IPC4_MSG_DIR(x) ((x) << SOF_IPC4_MSG_DIR_SHIFT) + +/* encoded to header's type field */ +#define SOF_IPC4_MSG_TYPE_SHIFT 24 +#define SOF_IPC4_MSG_TYPE_MASK GENMASK(28, 24) +#define SOF_IPC4_MSG_TYPE_SET(x) (((x) << SOF_IPC4_MSG_TYPE_SHIFT) & \ + SOF_IPC4_MSG_TYPE_MASK) +#define SOF_IPC4_MSG_TYPE_GET(x) (((x) & SOF_IPC4_MSG_TYPE_MASK) >> \ + SOF_IPC4_MSG_TYPE_SHIFT) + +/* Global message type specific field definitions */ + +/* pipeline creation ipc msg */ +#define SOF_IPC4_GLB_PIPE_INSTANCE_SHIFT 16 +#define SOF_IPC4_GLB_PIPE_INSTANCE_MASK GENMASK(23, 16) +#define SOF_IPC4_GLB_PIPE_INSTANCE_ID(x) ((x) << SOF_IPC4_GLB_PIPE_INSTANCE_SHIFT) + +#define SOF_IPC4_GLB_PIPE_PRIORITY_SHIFT 11 +#define SOF_IPC4_GLB_PIPE_PRIORITY_MASK GENMASK(15, 11) +#define SOF_IPC4_GLB_PIPE_PRIORITY(x) ((x) << SOF_IPC4_GLB_PIPE_PRIORITY_SHIFT) + +#define SOF_IPC4_GLB_PIPE_MEM_SIZE_SHIFT 0 +#define SOF_IPC4_GLB_PIPE_MEM_SIZE_MASK GENMASK(10, 0) +#define SOF_IPC4_GLB_PIPE_MEM_SIZE(x) ((x) << SOF_IPC4_GLB_PIPE_MEM_SIZE_SHIFT) + +#define SOF_IPC4_GLB_PIPE_EXT_LP_SHIFT 0 +#define SOF_IPC4_GLB_PIPE_EXT_LP_MASK BIT(0) +#define SOF_IPC4_GLB_PIPE_EXT_LP(x) ((x) << SOF_IPC4_GLB_PIPE_EXT_LP_SHIFT) + +/* pipeline set state ipc msg */ +#define SOF_IPC4_GLB_PIPE_STATE_ID_SHIFT 16 +#define SOF_IPC4_GLB_PIPE_STATE_ID_MASK GENMASK(23, 16) +#define SOF_IPC4_GLB_PIPE_STATE_ID(x) ((x) << SOF_IPC4_GLB_PIPE_STATE_ID_SHIFT) + +#define SOF_IPC4_GLB_PIPE_STATE_SHIFT 0 +#define SOF_IPC4_GLB_PIPE_STATE_MASK GENMASK(15, 0) +#define SOF_IPC4_GLB_PIPE_STATE(x) ((x) << SOF_IPC4_GLB_PIPE_STATE_SHIFT) + +enum sof_ipc4_channel_config { + /* one channel only. */ + SOF_IPC4_CHANNEL_CONFIG_MONO, + /* L & R. */ + SOF_IPC4_CHANNEL_CONFIG_STEREO, + /* L, R & LFE; PCM only. */ + SOF_IPC4_CHANNEL_CONFIG_2_POINT_1, + /* L, C & R; MP3 & AAC only. */ + SOF_IPC4_CHANNEL_CONFIG_3_POINT_0, + /* L, C, R & LFE; PCM only. */ + SOF_IPC4_CHANNEL_CONFIG_3_POINT_1, + /* L, R, Ls & Rs; PCM only. */ + SOF_IPC4_CHANNEL_CONFIG_QUATRO, + /* L, C, R & Cs; MP3 & AAC only. */ + SOF_IPC4_CHANNEL_CONFIG_4_POINT_0, + /* L, C, R, Ls & Rs. */ + SOF_IPC4_CHANNEL_CONFIG_5_POINT_0, + /* L, C, R, Ls, Rs & LFE. */ + SOF_IPC4_CHANNEL_CONFIG_5_POINT_1, + /* one channel replicated in two. */ + SOF_IPC4_CHANNEL_CONFIG_DUAL_MONO, + /* Stereo (L,R) in 4 slots, 1st stream: [ L, R, -, - ] */ + SOF_IPC4_CHANNEL_CONFIG_I2S_DUAL_STEREO_0, + /* Stereo (L,R) in 4 slots, 2nd stream: [ -, -, L, R ] */ + SOF_IPC4_CHANNEL_CONFIG_I2S_DUAL_STEREO_1, + /* L, C, R, Ls, Rs & LFE., LS, RS */ + SOF_IPC4_CHANNEL_CONFIG_7_POINT_1, +}; + +enum sof_ipc4_interleaved_style { + SOF_IPC4_CHANNELS_INTERLEAVED, + SOF_IPC4_CHANNELS_NONINTERLEAVED, +}; + +enum sof_ipc4_sample_type { + SOF_IPC4_MSB_INTEGER, /* integer with Most Significant Byte first */ + SOF_IPC4_LSB_INTEGER, /* integer with Least Significant Byte first */ +}; + +struct sof_ipc4_audio_format { + uint32_t sampling_frequency; + uint32_t bit_depth; + uint32_t ch_map; + uint32_t ch_cfg; /* sof_ipc4_channel_config */ + uint32_t interleaving_style; + uint32_t fmt_cfg; /* channels_count valid_bit_depth s_type */ +} __packed __aligned(4); + +#define SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT_SHIFT 0 +#define SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT_MASK GENMASK(7, 0) +#define SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT(x) \ + ((x) & SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT_MASK) +#define SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH_SHIFT 8 +#define SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH_MASK GENMASK(15, 8) +#define SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH(x) \ + (((x) & SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH_MASK) >> \ + SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH_SHIFT) +#define SOF_IPC4_AUDIO_FORMAT_CFG_SAMPLE_TYPE_SHIFT 16 +#define SOF_IPC4_AUDIO_FORMAT_CFG_SAMPLE_TYPE_MASK GENMASK(23, 16) +#define SOF_IPC4_AUDIO_FORMAT_CFG_SAMPLE_TYPE(x) \ + (((x) & SOF_IPC4_AUDIO_FORMAT_CFG_SAMPLE_TYPE_MASK) >> \ + SOF_IPC4_AUDIO_FORMAT_CFG_SAMPLE_TYPE_SHIFT) + +/* Module message type specific field definitions */ + +enum sof_ipc4_module_type { + SOF_IPC4_MOD_INIT_INSTANCE, + SOF_IPC4_MOD_CONFIG_GET, + SOF_IPC4_MOD_CONFIG_SET, + SOF_IPC4_MOD_LARGE_CONFIG_GET, + SOF_IPC4_MOD_LARGE_CONFIG_SET, + SOF_IPC4_MOD_BIND, + SOF_IPC4_MOD_UNBIND, + SOF_IPC4_MOD_SET_DX, + SOF_IPC4_MOD_SET_D0IX, + SOF_IPC4_MOD_ENTER_MODULE_RESTORE, + SOF_IPC4_MOD_EXIT_MODULE_RESTORE, + SOF_IPC4_MOD_DELETE_INSTANCE, + + SOF_IPC4_MOD_TYPE_LAST, +}; + +struct sof_ipc4_base_module_cfg { + uint32_t cpc; /* the max count of Cycles Per Chunk processing */ + uint32_t ibs; /* input Buffer Size (in bytes) */ + uint32_t obs; /* output Buffer Size (in bytes) */ + uint32_t is_pages; /* number of physical pages used */ + struct sof_ipc4_audio_format audio_fmt; +} __packed __aligned(4); + +/* common module ipc msg */ +#define SOF_IPC4_MOD_INSTANCE_SHIFT 16 +#define SOF_IPC4_MOD_INSTANCE_MASK GENMASK(23, 16) +#define SOF_IPC4_MOD_INSTANCE(x) ((x) << SOF_IPC4_MOD_INSTANCE_SHIFT) + +#define SOF_IPC4_MOD_ID_SHIFT 0 +#define SOF_IPC4_MOD_ID_MASK GENMASK(15, 0) +#define SOF_IPC4_MOD_ID(x) ((x) << SOF_IPC4_MOD_ID_SHIFT) + +/* init module ipc msg */ +#define SOF_IPC4_MOD_EXT_PARAM_SIZE_SHIFT 0 +#define SOF_IPC4_MOD_EXT_PARAM_SIZE_MASK GENMASK(15, 0) +#define SOF_IPC4_MOD_EXT_PARAM_SIZE(x) ((x) << SOF_IPC4_MOD_EXT_PARAM_SIZE_SHIFT) + +#define SOF_IPC4_MOD_EXT_PPL_ID_SHIFT 16 +#define SOF_IPC4_MOD_EXT_PPL_ID_MASK GENMASK(23, 16) +#define SOF_IPC4_MOD_EXT_PPL_ID(x) ((x) << SOF_IPC4_MOD_EXT_PPL_ID_SHIFT) + +#define SOF_IPC4_MOD_EXT_CORE_ID_SHIFT 24 +#define SOF_IPC4_MOD_EXT_CORE_ID_MASK GENMASK(27, 24) +#define SOF_IPC4_MOD_EXT_CORE_ID(x) ((x) << SOF_IPC4_MOD_EXT_CORE_ID_SHIFT) + +#define SOF_IPC4_MOD_EXT_DOMAIN_SHIFT 28 +#define SOF_IPC4_MOD_EXT_DOMAIN_MASK BIT(28) +#define SOF_IPC4_MOD_EXT_DOMAIN(x) ((x) << SOF_IPC4_MOD_EXT_DOMAIN_SHIFT) + +/* bind/unbind module ipc msg */ +#define SOF_IPC4_MOD_EXT_DST_MOD_ID_SHIFT 0 +#define SOF_IPC4_MOD_EXT_DST_MOD_ID_MASK GENMASK(15, 0) +#define SOF_IPC4_MOD_EXT_DST_MOD_ID(x) ((x) << SOF_IPC4_MOD_EXT_DST_MOD_ID_SHIFT) + +#define SOF_IPC4_MOD_EXT_DST_MOD_INSTANCE_SHIFT 16 +#define SOF_IPC4_MOD_EXT_DST_MOD_INSTANCE_MASK GENMASK(23, 16) +#define SOF_IPC4_MOD_EXT_DST_MOD_INSTANCE(x) ((x) << SOF_IPC4_MOD_EXT_DST_MOD_INSTANCE_SHIFT) + +#define SOF_IPC4_MOD_EXT_DST_MOD_QUEUE_ID_SHIFT 24 +#define SOF_IPC4_MOD_EXT_DST_MOD_QUEUE_ID_MASK GENMASK(26, 24) +#define SOF_IPC4_MOD_EXT_DST_MOD_QUEUE_ID(x) ((x) << SOF_IPC4_MOD_EXT_DST_MOD_QUEUE_ID_SHIFT) + +#define SOF_IPC4_MOD_EXT_SRC_MOD_QUEUE_ID_SHIFT 27 +#define SOF_IPC4_MOD_EXT_SRC_MOD_QUEUE_ID_MASK GENMASK(29, 27) +#define SOF_IPC4_MOD_EXT_SRC_MOD_QUEUE_ID(x) ((x) << SOF_IPC4_MOD_EXT_SRC_MOD_QUEUE_ID_SHIFT) + +#define MOD_ENABLE_LOG 6 +#define MOD_SYSTEM_TIME 20 + +/* set module large config */ +#define SOF_IPC4_MOD_EXT_MSG_SIZE_SHIFT 0 +#define SOF_IPC4_MOD_EXT_MSG_SIZE_MASK GENMASK(19, 0) +#define SOF_IPC4_MOD_EXT_MSG_SIZE(x) ((x) << SOF_IPC4_MOD_EXT_MSG_SIZE_SHIFT) + +#define SOF_IPC4_MOD_EXT_MSG_PARAM_ID_SHIFT 20 +#define SOF_IPC4_MOD_EXT_MSG_PARAM_ID_MASK GENMASK(27, 20) +#define SOF_IPC4_MOD_EXT_MSG_PARAM_ID(x) ((x) << SOF_IPC4_MOD_EXT_MSG_PARAM_ID_SHIFT) + +#define SOF_IPC4_MOD_EXT_MSG_LAST_BLOCK_SHIFT 28 +#define SOF_IPC4_MOD_EXT_MSG_LAST_BLOCK_MASK BIT(28) +#define SOF_IPC4_MOD_EXT_MSG_LAST_BLOCK(x) ((x) << SOF_IPC4_MOD_EXT_MSG_LAST_BLOCK_SHIFT) + +#define SOF_IPC4_MOD_EXT_MSG_FIRST_BLOCK_SHIFT 29 +#define SOF_IPC4_MOD_EXT_MSG_FIRST_BLOCK_MASK BIT(29) +#define SOF_IPC4_MOD_EXT_MSG_FIRST_BLOCK(x) ((x) << SOF_IPC4_MOD_EXT_MSG_FIRST_BLOCK_SHIFT) + +/* Init instance messagees */ +#define SOF_IPC4_MOD_INIT_BASEFW_MOD_ID 0 +#define SOF_IPC4_MOD_INIT_BASEFW_INSTANCE_ID 0 + +enum sof_ipc4_base_fw_params { + SOF_IPC4_FW_PARAM_ENABLE_LOGS = 6, + SOF_IPC4_FW_PARAM_FW_CONFIG, + SOF_IPC4_FW_PARAM_HW_CONFIG_GET, + SOF_IPC4_FW_PARAM_MODULES_INFO_GET, + SOF_IPC4_FW_PARAM_LIBRARIES_INFO_GET = 16, + SOF_IPC4_FW_PARAM_SYSTEM_TIME = 20, +}; + +enum sof_ipc4_fw_config_params { + SOF_IPC4_FW_CFG_FW_VERSION, + SOF_IPC4_FW_CFG_MEMORY_RECLAIMED, + SOF_IPC4_FW_CFG_SLOW_CLOCK_FREQ_HZ, + SOF_IPC4_FW_CFG_FAST_CLOCK_FREQ_HZ, + SOF_IPC4_FW_CFG_DMA_BUFFER_CONFIG, + SOF_IPC4_FW_CFG_ALH_SUPPORT_LEVEL, + SOF_IPC4_FW_CFG_DL_MAILBOX_BYTES, + SOF_IPC4_FW_CFG_UL_MAILBOX_BYTES, + SOF_IPC4_FW_CFG_TRACE_LOG_BYTES, + SOF_IPC4_FW_CFG_MAX_PPL_COUNT, + SOF_IPC4_FW_CFG_MAX_ASTATE_COUNT, + SOF_IPC4_FW_CFG_MAX_MODULE_PIN_COUNT, + SOF_IPC4_FW_CFG_MODULES_COUNT, + SOF_IPC4_FW_CFG_MAX_MOD_INST_COUNT, + SOF_IPC4_FW_CFG_MAX_LL_TASKS_PER_PRI_COUNT, + SOF_IPC4_FW_CFG_LL_PRI_COUNT, + SOF_IPC4_FW_CFG_MAX_DP_TASKS_COUNT, + SOF_IPC4_FW_CFG_MAX_LIBS_COUNT, + SOF_IPC4_FW_CFG_SCHEDULER_CONFIG, + SOF_IPC4_FW_CFG_XTAL_FREQ_HZ, + SOF_IPC4_FW_CFG_CLOCKS_CONFIG, + SOF_IPC4_FW_CFG_RESERVED, + SOF_IPC4_FW_CFG_POWER_GATING_POLICY, + SOF_IPC4_FW_CFG_ASSERT_MODE, +}; + +struct sof_ipc4_fw_version { + uint16_t major; + uint16_t minor; + uint16_t hotfix; + uint16_t build; +} __packed; + +/* Reply messages */ + +/* + * IPC4 primary header bit allocation for replies + * bit 0-23: status + * bit 24-28: type: enum sof_ipc4_global_msg if target is SOF_IPC4_FW_GEN_MSG + * enum sof_ipc4_module_type if target is SOF_IPC4_MODULE_MSG + * bit 29: response - sof_ipc4_msg_dir + * bit 30: target - enum sof_ipc4_msg_target + * bit 31: reserved, unused + */ + +#define SOF_IPC4_REPLY_STATUS GENMASK(23, 0) + +/* Notification messages */ + +/* + * IPC4 primary header bit allocation for notifications + * bit 0-15: notification type specific + * bit 16-23: enum sof_ipc4_notification_type + * bit 24-28: SOF_IPC4_GLB_NOTIFICATION + * bit 29: response - sof_ipc4_msg_dir + * bit 30: target - enum sof_ipc4_msg_target + * bit 31: reserved, unused + */ + +#define SOF_IPC4_MSG_IS_NOTIFICATION(x) (SOF_IPC4_MSG_TYPE_GET(x) == \ + SOF_IPC4_GLB_NOTIFICATION) + +#define SOF_IPC4_NOTIFICATION_TYPE_SHIFT 16 +#define SOF_IPC4_NOTIFICATION_TYPE_MASK GENMASK(23, 16) +#define SOF_IPC4_NOTIFICATION_TYPE_GET(x) (((x) & SOF_IPC4_NOTIFICATION_TYPE_MASK) >> \ + SOF_IPC4_NOTIFICATION_TYPE_SHIFT) + +/* Value of notification type field - must fit into 8 bits */ +enum sof_ipc4_notification_type { + /* Phrase detected (notification from WoV module) */ + SOF_IPC4_NOTIFY_PHRASE_DETECTED = 4, + /* Event from a resource (pipeline or module instance) */ + SOF_IPC4_NOTIFY_RESOURCE_EVENT, + /* Debug log buffer status changed */ + SOF_IPC4_NOTIFY_LOG_BUFFER_STATUS, + /* Timestamp captured at the link */ + SOF_IPC4_NOTIFY_TIMESTAMP_CAPTURED, + /* FW complete initialization */ + SOF_IPC4_NOTIFY_FW_READY, + /* Audio classifier result (ACA) */ + SOF_IPC4_NOTIFY_FW_AUD_CLASS_RESULT, + /* Exception caught by DSP FW */ + SOF_IPC4_NOTIFY_EXCEPTION_CAUGHT, + /* 11 is skipped by the existing cavs firmware */ + /* Custom module notification */ + SOF_IPC4_NOTIFY_MODULE_NOTIFICATION = 12, + /* 13 is reserved - do not use */ + /* Probe notify data available */ + SOF_IPC4_NOTIFY_PROBE_DATA_AVAILABLE = 14, + /* AM module notifications */ + SOF_IPC4_NOTIFY_ASYNC_MSG_SRVC_MESSAGE, + + SOF_IPC4_NOTIFY_TYPE_LAST, +}; + +struct sof_ipc4_notify_resource_data { + uint32_t resource_type; + uint32_t resource_id; + uint32_t event_type; + uint32_t reserved; + uint32_t data[6]; +} __packed __aligned(4); + +/** @}*/ + +#endif -- cgit v1.2.3 From 6d5f2207447b28dc73c25b3907e7ee32ee66bdbd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 2 May 2022 19:08:27 +0200 Subject: gpio: max732x: Drop unused support for irq and setup code via platform data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The only user of max732x_platform_data is arch/arm/mach-pxa/littleton.c and it only uses .gpio_base. So drop the other members from the data struct and simplify the driver accordingly. The motivating side effect of this change is that the .remove() callback cannot return a nonzero error code any more which prepares making i2c remove callbacks return void. Signed-off-by: Uwe Kleine-König Signed-off-by: Bartosz Golaszewski --- include/linux/platform_data/max732x.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/max732x.h b/include/linux/platform_data/max732x.h index f231c635faec..423999207cd5 100644 --- a/include/linux/platform_data/max732x.h +++ b/include/linux/platform_data/max732x.h @@ -7,17 +7,5 @@ struct max732x_platform_data { /* number of the first GPIO */ unsigned gpio_base; - - /* interrupt base */ - int irq_base; - - void *context; /* param to setup/teardown */ - - int (*setup)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - int (*teardown)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); }; #endif /* __LINUX_I2C_MAX732X_H */ -- cgit v1.2.3 From 8221ecd4e4620cf2f0e942cafcdecac1685f8f16 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 14 Apr 2022 15:04:27 +0200 Subject: PCI/PM: Drop the runtime_d3cold device flag The runtime_d3cold flag is not needed any more, so drop it. Link: https://lore.kernel.org/r/8077784.T7Z3S40VBb@kreacher Signed-off-by: Rafael J. Wysocki Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg --- include/linux/pci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 60adf42460ab..3266ac08f8ec 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -379,10 +379,6 @@ struct pci_dev { unsigned int mmio_always_on:1; /* Disallow turning off io/mem decoding during BAR sizing */ unsigned int wakeup_prepared:1; - unsigned int runtime_d3cold:1; /* Whether go through runtime - D3cold, not set for devices - powered on/off by the - corresponding bridge */ unsigned int skip_bus_pm:1; /* Internal: Skip bus-level PM */ unsigned int ignore_hotplug:1; /* Ignore hotplug events */ unsigned int hotplug_user_indicators:1; /* SlotCtl indicators -- cgit v1.2.3 From 6808b7f5c8255d07d79cb8eac40047f59e4154ad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Wed, 4 May 2022 10:20:46 +0300 Subject: termbits: Convert octal defines to hex MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Many archs have termbits.h as octal numbers. It makes hard for humans to parse the magnitude of large numbers correctly and to compare with hex ones of the same define. Convert octal values to hex. First step is an automated conversion with: for i in $(git ls-files | grep 'termbits\.h'); do awk --non-decimal-data '/^#define\s+[A-Z][A-Z0-9]*\s+0[0-9]/ { l=int(((length($3) - 1) * 3 + 3) / 4); repl = sprintf("0x%0" l "x", $3); print gensub(/[^[:blank:]]+/, repl, 3); next} {print}' $i > $i~; mv $i~ $i; done On top of that, some manual processing on alignment and number of zeros. In addition, small tweaks to formatting of a few comments on the same lines. Signed-off-by: Ilpo Järvinen Acked-by: Arnd Bergmann Acked-by: Michael Ellerman (powerpc) Link: https://lore.kernel.org/r/2c8c96f-a12f-aadc-18ac-34c1d371929c@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/asm-generic/termbits.h | 220 ++++++++++++++++++------------------ 1 file changed, 110 insertions(+), 110 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/termbits.h b/include/uapi/asm-generic/termbits.h index 2fbaf9ae89dd..470fd673ff84 100644 --- a/include/uapi/asm-generic/termbits.h +++ b/include/uapi/asm-generic/termbits.h @@ -60,126 +60,126 @@ struct ktermios { #define VEOL2 16 /* c_iflag bits */ -#define IGNBRK 0000001 -#define BRKINT 0000002 -#define IGNPAR 0000004 -#define PARMRK 0000010 -#define INPCK 0000020 -#define ISTRIP 0000040 -#define INLCR 0000100 -#define IGNCR 0000200 -#define ICRNL 0000400 -#define IUCLC 0001000 -#define IXON 0002000 -#define IXANY 0004000 -#define IXOFF 0010000 -#define IMAXBEL 0020000 -#define IUTF8 0040000 +#define IGNBRK 0x00001 +#define BRKINT 0x00002 +#define IGNPAR 0x00004 +#define PARMRK 0x00008 +#define INPCK 0x00010 +#define ISTRIP 0x00020 +#define INLCR 0x00040 +#define IGNCR 0x00080 +#define ICRNL 0x00100 +#define IUCLC 0x00200 +#define IXON 0x00400 +#define IXANY 0x00800 +#define IXOFF 0x01000 +#define IMAXBEL 0x02000 +#define IUTF8 0x04000 /* c_oflag bits */ -#define OPOST 0000001 -#define OLCUC 0000002 -#define ONLCR 0000004 -#define OCRNL 0000010 -#define ONOCR 0000020 -#define ONLRET 0000040 -#define OFILL 0000100 -#define OFDEL 0000200 -#define NLDLY 0000400 -#define NL0 0000000 -#define NL1 0000400 -#define CRDLY 0003000 -#define CR0 0000000 -#define CR1 0001000 -#define CR2 0002000 -#define CR3 0003000 -#define TABDLY 0014000 -#define TAB0 0000000 -#define TAB1 0004000 -#define TAB2 0010000 -#define TAB3 0014000 -#define XTABS 0014000 -#define BSDLY 0020000 -#define BS0 0000000 -#define BS1 0020000 -#define VTDLY 0040000 -#define VT0 0000000 -#define VT1 0040000 -#define FFDLY 0100000 -#define FF0 0000000 -#define FF1 0100000 +#define OPOST 0x00001 +#define OLCUC 0x00002 +#define ONLCR 0x00004 +#define OCRNL 0x00008 +#define ONOCR 0x00010 +#define ONLRET 0x00020 +#define OFILL 0x00040 +#define OFDEL 0x00080 +#define NLDLY 0x00100 +#define NL0 0x00000 +#define NL1 0x00100 +#define CRDLY 0x00600 +#define CR0 0x00000 +#define CR1 0x00200 +#define CR2 0x00400 +#define CR3 0x00600 +#define TABDLY 0x01800 +#define TAB0 0x00000 +#define TAB1 0x00800 +#define TAB2 0x01000 +#define TAB3 0x01800 +#define XTABS 0x01800 +#define BSDLY 0x02000 +#define BS0 0x00000 +#define BS1 0x02000 +#define VTDLY 0x04000 +#define VT0 0x00000 +#define VT1 0x04000 +#define FFDLY 0x08000 +#define FF0 0x00000 +#define FF1 0x08000 /* c_cflag bit meaning */ -#define CBAUD 0010017 -#define B0 0000000 /* hang up */ -#define B50 0000001 -#define B75 0000002 -#define B110 0000003 -#define B134 0000004 -#define B150 0000005 -#define B200 0000006 -#define B300 0000007 -#define B600 0000010 -#define B1200 0000011 -#define B1800 0000012 -#define B2400 0000013 -#define B4800 0000014 -#define B9600 0000015 -#define B19200 0000016 -#define B38400 0000017 +#define CBAUD 0x0000100f +#define B0 0x00000000 /* hang up */ +#define B50 0x00000001 +#define B75 0x00000002 +#define B110 0x00000003 +#define B134 0x00000004 +#define B150 0x00000005 +#define B200 0x00000006 +#define B300 0x00000007 +#define B600 0x00000008 +#define B1200 0x00000009 +#define B1800 0x0000000a +#define B2400 0x0000000b +#define B4800 0x0000000c +#define B9600 0x0000000d +#define B19200 0x0000000e +#define B38400 0x0000000f #define EXTA B19200 #define EXTB B38400 -#define CSIZE 0000060 -#define CS5 0000000 -#define CS6 0000020 -#define CS7 0000040 -#define CS8 0000060 -#define CSTOPB 0000100 -#define CREAD 0000200 -#define PARENB 0000400 -#define PARODD 0001000 -#define HUPCL 0002000 -#define CLOCAL 0004000 -#define CBAUDEX 0010000 -#define BOTHER 0010000 -#define B57600 0010001 -#define B115200 0010002 -#define B230400 0010003 -#define B460800 0010004 -#define B500000 0010005 -#define B576000 0010006 -#define B921600 0010007 -#define B1000000 0010010 -#define B1152000 0010011 -#define B1500000 0010012 -#define B2000000 0010013 -#define B2500000 0010014 -#define B3000000 0010015 -#define B3500000 0010016 -#define B4000000 0010017 -#define CIBAUD 002003600000 /* input baud rate */ -#define CMSPAR 010000000000 /* mark or space (stick) parity */ -#define CRTSCTS 020000000000 /* flow control */ +#define CSIZE 0x00000030 +#define CS5 0x00000000 +#define CS6 0x00000010 +#define CS7 0x00000020 +#define CS8 0x00000030 +#define CSTOPB 0x00000040 +#define CREAD 0x00000080 +#define PARENB 0x00000100 +#define PARODD 0x00000200 +#define HUPCL 0x00000400 +#define CLOCAL 0x00000800 +#define CBAUDEX 0x00001000 +#define BOTHER 0x00001000 +#define B57600 0x00001001 +#define B115200 0x00001002 +#define B230400 0x00001003 +#define B460800 0x00001004 +#define B500000 0x00001005 +#define B576000 0x00001006 +#define B921600 0x00001007 +#define B1000000 0x00001008 +#define B1152000 0x00001009 +#define B1500000 0x0000100a +#define B2000000 0x0000100b +#define B2500000 0x0000100c +#define B3000000 0x0000100d +#define B3500000 0x0000100e +#define B4000000 0x0000100f +#define CIBAUD 0x100f0000 /* input baud rate */ +#define CMSPAR 0x40000000 /* mark or space (stick) parity */ +#define CRTSCTS 0x80000000 /* flow control */ #define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */ /* c_lflag bits */ -#define ISIG 0000001 -#define ICANON 0000002 -#define XCASE 0000004 -#define ECHO 0000010 -#define ECHOE 0000020 -#define ECHOK 0000040 -#define ECHONL 0000100 -#define NOFLSH 0000200 -#define TOSTOP 0000400 -#define ECHOCTL 0001000 -#define ECHOPRT 0002000 -#define ECHOKE 0004000 -#define FLUSHO 0010000 -#define PENDIN 0040000 -#define IEXTEN 0100000 -#define EXTPROC 0200000 +#define ISIG 0x00001 +#define ICANON 0x00002 +#define XCASE 0x00004 +#define ECHO 0x00008 +#define ECHOE 0x00010 +#define ECHOK 0x00020 +#define ECHONL 0x00040 +#define NOFLSH 0x00080 +#define TOSTOP 0x00100 +#define ECHOCTL 0x00200 +#define ECHOPRT 0x00400 +#define ECHOKE 0x00800 +#define FLUSHO 0x01000 +#define PENDIN 0x04000 +#define IEXTEN 0x08000 +#define EXTPROC 0x10000 /* tcflow() and TCXONC use these */ #define TCOOFF 0 -- cgit v1.2.3 From 26817fb7b066b21c66cd41d75ed2137e046045be Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 4 May 2022 09:27:10 -0400 Subject: Revert "fbdev: fbmem: add a helper to determine if an aperture is used by a fw fb" This reverts commit 9a45ac2320d0a6ae01880a30d4b86025fce4061b. This was added a helper for amdgpu to workaround a runtime pm regression caused by a runtime pm fix in efifb. We now have a better workaround in amdgpu in commit f95af4a9236695 ("drm/amdgpu: don't runtime suspend if there are displays attached (v3)") so this workaround is no longer necessary. Since amdgpu was the only user of this interface, we can remove it. Reviewed-by: Javier Martinez Canillas Acked-by: Daniel Vetter Signed-off-by: Alex Deucher --- include/linux/fb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index 9a77ab615c36..147d582dab41 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -612,7 +612,6 @@ extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const char *name); extern int remove_conflicting_framebuffers(struct apertures_struct *a, const char *name, bool primary); -extern bool is_firmware_framebuffer(struct apertures_struct *a); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); extern int fb_show_logo(struct fb_info *fb_info, int rotate); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); -- cgit v1.2.3 From c4a67a21a6d255ddcbaa076c0412aad73c7e0c02 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 4 May 2022 08:40:37 -0700 Subject: Revert "Merge branch 'mlxsw-line-card-model'" This reverts commit 5e927a9f4b9f29d78a7c7d66ea717bb5c8bbad8e, reversing changes made to cfc1d91a7d78cf9de25b043d81efcc16966d55b3. The discussion is still ongoing so let's remove the uAPI until the discussion settles. Link: https://lore.kernel.org/all/20220425090021.32e9a98f@kernel.org/ Reviewed-by: Ido Schimmel Link: https://lore.kernel.org/r/20220504154037.539442-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 18 +----------------- include/uapi/linux/devlink.h | 5 ----- 2 files changed, 1 insertion(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 062895973656..2a2a2a0c93f7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -150,9 +150,6 @@ struct devlink_port_new_attrs { sfnum_valid:1; }; -struct devlink_info_req; -struct devlink_linecard_device; - /** * struct devlink_linecard_ops - Linecard operations * @provision: callback to provision the linecard slot with certain @@ -171,8 +168,6 @@ struct devlink_linecard_device; * provisioned. * @types_count: callback to get number of supported types * @types_get: callback to get next type in list - * @info_get: callback to get linecard info - * @device_info_get: callback to get linecard device info */ struct devlink_linecard_ops { int (*provision)(struct devlink_linecard *linecard, void *priv, @@ -187,12 +182,6 @@ struct devlink_linecard_ops { void (*types_get)(struct devlink_linecard *linecard, void *priv, unsigned int index, const char **type, const void **type_priv); - int (*info_get)(struct devlink_linecard *linecard, void *priv, - struct devlink_info_req *req, - struct netlink_ext_ack *extack); - int (*device_info_get)(struct devlink_linecard_device *device, - void *priv, struct devlink_info_req *req, - struct netlink_ext_ack *extack); }; struct devlink_sb_pool_info { @@ -639,6 +628,7 @@ struct devlink_flash_update_params { #define DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK BIT(1) struct devlink_region; +struct devlink_info_req; /** * struct devlink_region_ops - Region operations @@ -1588,12 +1578,6 @@ struct devlink_linecard * devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, const struct devlink_linecard_ops *ops, void *priv); void devlink_linecard_destroy(struct devlink_linecard *linecard); -struct devlink_linecard_device * -devlink_linecard_device_create(struct devlink_linecard *linecard, - unsigned int device_index, void *priv); -void -devlink_linecard_device_destroy(struct devlink_linecard *linecard, - struct devlink_linecard_device *linecard_device); void devlink_linecard_provision_set(struct devlink_linecard *linecard, const char *type); void devlink_linecard_provision_clear(struct devlink_linecard *linecard); diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index fb8c3864457f..b3d40a5d72ff 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -136,8 +136,6 @@ enum devlink_command { DEVLINK_CMD_LINECARD_NEW, DEVLINK_CMD_LINECARD_DEL, - DEVLINK_CMD_LINECARD_INFO_GET, /* can dump */ - /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -577,9 +575,6 @@ enum devlink_attr { DEVLINK_ATTR_LINECARD_STATE, /* u8 */ DEVLINK_ATTR_LINECARD_TYPE, /* string */ DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES, /* nested */ - DEVLINK_ATTR_LINECARD_DEVICE_LIST, /* nested */ - DEVLINK_ATTR_LINECARD_DEVICE, /* nested */ - DEVLINK_ATTR_LINECARD_DEVICE_INDEX, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From 0455d4ccec548b0fb51db39a4d3350a7a80a0222 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 26 Apr 2022 12:11:33 -0600 Subject: io_uring: add POLL_FIRST support for send/sendmsg and recv/recvmsg If IORING_RECVSEND_POLL_FIRST is set for recv/recvmsg or send/sendmsg, then we arm poll first rather than attempt a receive or send upfront. This can be useful if we expect there to be no data (or space) available for the request, as we can then avoid wasting time on the initial issue attempt. Reviewed-by: Hao Xu Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index fad63564678a..06621a278cb6 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -213,6 +213,16 @@ enum { #define IORING_ASYNC_CANCEL_FD (1U << 1) #define IORING_ASYNC_CANCEL_ANY (1U << 2) +/* + * send/sendmsg and recv/recvmsg flags (sqe->addr2) + * + * IORING_RECVSEND_POLL_FIRST If set, instead of first attempting to send + * or receive and arm poll if that yields an + * -EAGAIN result, arm poll upfront and skip + * the initial transfer attempt. + */ +#define IORING_RECVSEND_POLL_FIRST (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ -- cgit v1.2.3 From c67b627e99affe4865b13557d68152ad4c35515c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 May 2022 10:09:47 -0700 Subject: net: Make msg_zerocopy_alloc static msg_zerocopy_alloc is only used by msg_zerocopy_realloc; remove the export and make static in skbuff.c Signed-off-by: David Ahern Acked-by: Jonathan Lemon Link: https://lore.kernel.org/r/20220504170947.18773-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3270cb72e4d8..5c2599e3fe7d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1665,7 +1665,6 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif -struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); -- cgit v1.2.3 From 85db6352fc8a158a893151baa1716463d34a20d0 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 4 May 2022 11:09:14 +0300 Subject: net: Fix features skip in for_each_netdev_feature() The find_next_netdev_feature() macro gets the "remaining length", not bit index. Passing "bit - 1" for the following iteration is wrong as it skips the adjacent bit. Pass "bit" instead. Fixes: 3b89ea9c5902 ("net: Fix for_each_netdev_feature on Big endian") Signed-off-by: Tariq Toukan Reviewed-by: Gal Pressman Link: https://lore.kernel.org/r/20220504080914.1918-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- include/linux/netdev_features.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2c6b9e416225..7c2d77d75a88 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -169,7 +169,7 @@ enum { #define NETIF_F_HW_HSR_FWD __NETIF_F(HW_HSR_FWD) #define NETIF_F_HW_HSR_DUP __NETIF_F(HW_HSR_DUP) -/* Finds the next feature with the highest number of the range of start till 0. +/* Finds the next feature with the highest number of the range of start-1 till 0. */ static inline int find_next_netdev_feature(u64 feature, unsigned long start) { @@ -188,7 +188,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) for ((bit) = find_next_netdev_feature((mask_addr), \ NETDEV_FEATURE_COUNT); \ (bit) >= 0; \ - (bit) = find_next_netdev_feature((mask_addr), (bit) - 1)) + (bit) = find_next_netdev_feature((mask_addr), (bit))) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ -- cgit v1.2.3 From ea66758c1795cef81dc59cd5240e9d0f5c5207cf Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 4 May 2022 14:54:06 -0700 Subject: tcp: allow MPTCP to update the announced window The MPTCP RFC requires that the MPTCP-level receive window's right edge never moves backward. Currently the MPTCP code enforces such constraint while tracking the right edge, but it does not reflects it on the wire, as MPTCP lacks a suitable hook to update accordingly the TCP header. This change modifies the existing mptcp_write_options() hook, providing the current packet's TCP header to the MPTCP protocol, so that the next patch could implement the above mentioned constraint. No functional changes intended. Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/net/mptcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 8b1afd6f5cc4..d4ec894ce67b 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -125,7 +125,7 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, struct mptcp_out_options *opts); bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); -void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, +void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, struct mptcp_out_options *opts); void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info); -- cgit v1.2.3 From e1846cff2fe614d93a2f89461b5935678fd34bd9 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 5 May 2022 02:54:59 +0300 Subject: net: mscc: ocelot: mark traps with a bool instead of keeping them in a list Since the blamed commit, VCAP filters can appear on more than one list. If their action is "trap", they are chained on ocelot->traps via filter->trap_list. This is in addition to their normal placement on the VCAP block->rules list head. Therefore, when we free a VCAP filter, we must remove it from all lists it is a member of, including ocelot->traps. There are at least 2 bugs which are direct consequences of this design decision. First is the incorrect usage of list_empty(), meant to denote whether "filter" is chained into ocelot->traps via filter->trap_list. This does not do the correct thing, because list_empty() checks whether "head->next == head", but in our case, head->next == head->prev == NULL. So we dereference NULL pointers and die when we call list_del(). Second is the fact that not all places that should remove the filter from ocelot->traps do so. One example is ocelot_vcap_block_remove_filter(), which is where we have the main kfree(filter). By keeping freed filters in ocelot->traps we end up in a use-after-free in felix_update_trapping_destinations(). Attempting to fix all the buggy patterns is a whack-a-mole game which makes the driver unmaintainable. Actually this is what the previous patch version attempted to do: https://patchwork.kernel.org/project/netdevbpf/patch/20220503115728.834457-3-vladimir.oltean@nxp.com/ but it introduced another set of bugs, because there are other places in which create VCAP filters, not just ocelot_vcap_filter_create(): - ocelot_trap_add() - felix_tag_8021q_vlan_add_rx() - felix_tag_8021q_vlan_add_tx() Relying on the convention that all those code paths must call INIT_LIST_HEAD(&filter->trap_list) is not going to scale. So let's do what should have been done in the first place and keep a bool in struct ocelot_vcap_filter which denotes whether we are looking at a trapping rule or not. Iterating now happens over the main VCAP IS2 block->rules. The advantage is that we no longer risk having stale references to a freed filter, since it is only present in that list. Fixes: e42bd4ed09aa ("net: mscc: ocelot: keep traps in a list") Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot_vcap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 7b2bf9b1fe69..de26c992f821 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -681,7 +681,6 @@ struct ocelot_vcap_id { struct ocelot_vcap_filter { struct list_head list; - struct list_head trap_list; enum ocelot_vcap_filter_type type; int block_id; @@ -695,6 +694,7 @@ struct ocelot_vcap_filter { struct ocelot_vcap_stats stats; /* For VCAP IS1 and IS2 */ bool take_ts; + bool is_trap; unsigned long ingress_port_mask; /* For VCAP ES0 */ struct ocelot_vcap_port ingress_port; -- cgit v1.2.3 From 7e555e9975698924d7f3ead154847bcf8f5cd40c Mon Sep 17 00:00:00 2001 From: Adam Skladowski Date: Tue, 26 Apr 2022 09:30:47 +0200 Subject: dt-bindings: clk: qcom: gcc-msm8976: Add modem reset Add modem reset for MSM8976. Signed-off-by: Adam Skladowski Acked-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220426073048.11509-3-a39.skl@gmail.com --- include/dt-bindings/clock/qcom,gcc-msm8976.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-msm8976.h b/include/dt-bindings/clock/qcom,gcc-msm8976.h index 51955fd49426..5351f48b2068 100644 --- a/include/dt-bindings/clock/qcom,gcc-msm8976.h +++ b/include/dt-bindings/clock/qcom,gcc-msm8976.h @@ -224,6 +224,7 @@ #define RST_CAMSS_CSI_VFE1_BCR 7 #define RST_CAMSS_VFE1_BCR 8 #define RST_CAMSS_CPP_BCR 9 +#define RST_MSS_BCR 10 /* GDSCs */ #define VENUS_GDSC 0 -- cgit v1.2.3 From b01a277a0520edd5c815af346f05ef2c747919b6 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 5 May 2022 13:06:38 +0300 Subject: xfrm: free not used XFRM_ESP_NO_TRAILER flag After removal of Innova IPsec support from mlx5 driver, the last user of this XFRM_ESP_NO_TRAILER was gone too. This means that we can safely remove it as no other hardware is capable (or need) to remove ESP trailer. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Acked-by: David S. Miller Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6fb899ff5afc..b41278abeeaa 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1006,7 +1006,7 @@ struct xfrm_offload { #define CRYPTO_FALLBACK 8 #define XFRM_GSO_SEGMENT 16 #define XFRM_GRO 32 -#define XFRM_ESP_NO_TRAILER 64 +/* 64 is free */ #define XFRM_DEV_RESUME 128 #define XFRM_XMIT 256 -- cgit v1.2.3 From a36708e646586f74d073199828ed878b223e988d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 5 May 2022 13:06:39 +0300 Subject: xfrm: delete not used number of external headers num_exthdrs is set but never used, so delete it. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Acked-by: David S. Miller Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b41278abeeaa..4e097423116c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -131,7 +131,6 @@ struct xfrm_state_offload { netdevice_tracker dev_tracker; struct net_device *real_dev; unsigned long offload_handle; - unsigned int num_exthdrs; u8 flags; }; -- cgit v1.2.3 From 87e0a94e60ea2e29be9dec6bc146fbc9861a4055 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 5 May 2022 13:06:40 +0300 Subject: xfrm: rename xfrm_state_offload struct to allow reuse The struct xfrm_state_offload has all fields needed to hold information for offloaded policies too. In order to do not create new struct with same fields, let's rename existing one and reuse it later. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Acked-by: David S. Miller Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 4e097423116c..bb20278d689c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -126,7 +126,7 @@ struct xfrm_state_walk { struct xfrm_address_filter *filter; }; -struct xfrm_state_offload { +struct xfrm_dev_offload { struct net_device *dev; netdevice_tracker dev_tracker; struct net_device *real_dev; @@ -246,7 +246,7 @@ struct xfrm_state { struct xfrm_lifetime_cur curlft; struct hrtimer mtimer; - struct xfrm_state_offload xso; + struct xfrm_dev_offload xso; /* used to fix curlft->add_time when changing date */ long saved_tmo; @@ -1865,7 +1865,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x); static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) { - struct xfrm_state_offload *xso = &x->xso; + struct xfrm_dev_offload *xso = &x->xso; if (xso->dev && xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn) xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn(x); @@ -1891,7 +1891,7 @@ static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) static inline void xfrm_dev_state_delete(struct xfrm_state *x) { - struct xfrm_state_offload *xso = &x->xso; + struct xfrm_dev_offload *xso = &x->xso; if (xso->dev) xso->dev->xfrmdev_ops->xdo_dev_state_delete(x); @@ -1899,7 +1899,7 @@ static inline void xfrm_dev_state_delete(struct xfrm_state *x) static inline void xfrm_dev_state_free(struct xfrm_state *x) { - struct xfrm_state_offload *xso = &x->xso; + struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = xso->dev; if (dev && dev->xfrmdev_ops) { -- cgit v1.2.3 From 482db2f1dd211f73ad9d71e33ae15c1df6379982 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 5 May 2022 13:06:41 +0300 Subject: xfrm: store and rely on direction to construct offload flags XFRM state doesn't need anything from flags except to understand direction, so store it separately. For future patches, such change will allow us to reuse xfrm_dev_offload for policy offload too, which has three possible directions instead of two. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index bb20278d689c..45422f7be0c5 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -126,12 +126,18 @@ struct xfrm_state_walk { struct xfrm_address_filter *filter; }; +enum { + XFRM_DEV_OFFLOAD_IN = 1, + XFRM_DEV_OFFLOAD_OUT, +}; + struct xfrm_dev_offload { struct net_device *dev; netdevice_tracker dev_tracker; struct net_device *real_dev; unsigned long offload_handle; u8 flags; + u8 dir : 2; }; struct xfrm_mode { -- cgit v1.2.3 From 254c4a824c7c6a53360bc4974710e4213b8b7f5d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 5 May 2022 13:06:45 +0300 Subject: xfrm: drop not needed flags variable in XFRM offload struct After drivers were converted to rely on direction, the flags is not used anymore and can be removed. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 45422f7be0c5..736c349de8bf 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -136,7 +136,6 @@ struct xfrm_dev_offload { netdevice_tracker dev_tracker; struct net_device *real_dev; unsigned long offload_handle; - u8 flags; u8 dir : 2; }; -- cgit v1.2.3 From bb17d110cbf270d5247a6e261c5ad50e362d1675 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 29 Apr 2022 21:59:45 +0200 Subject: rpmsg: Fix calling device_lock() on non-initialized device driver_set_override() helper uses device_lock() so it should not be called before rpmsg_register_device() (which calls device_register()). Effect can be seen with CONFIG_DEBUG_MUTEXES: DEBUG_LOCKS_WARN_ON(lock->magic != lock) WARNING: CPU: 3 PID: 57 at kernel/locking/mutex.c:582 __mutex_lock+0x1ec/0x430 ... Call trace: __mutex_lock+0x1ec/0x430 mutex_lock_nested+0x44/0x50 driver_set_override+0x124/0x150 qcom_glink_native_probe+0x30c/0x3b0 glink_rpm_probe+0x274/0x350 platform_probe+0x6c/0xe0 really_probe+0x17c/0x3d0 __driver_probe_device+0x114/0x190 driver_probe_device+0x3c/0xf0 ... Refactor the rpmsg_register_device() function to use two-step device registering (initialization + add) and call driver_set_override() in proper moment. This moves the code around, so while at it also NULL-ify the rpdev->driver_override in error path to be sure it won't be kfree() second time. Fixes: 42cd402b8fd4 ("rpmsg: Fix kfree() of static memory on setting driver_override") Reported-by: Marek Szyprowski Signed-off-by: Krzysztof Kozlowski Tested-by: Marek Szyprowski Link: https://lore.kernel.org/r/20220429195946.1061725-2-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/rpmsg.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index 20c8cd1cde21..523c98b96cb4 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -165,6 +165,8 @@ static inline __rpmsg64 cpu_to_rpmsg64(struct rpmsg_device *rpdev, u64 val) #if IS_ENABLED(CONFIG_RPMSG) +int rpmsg_register_device_override(struct rpmsg_device *rpdev, + const char *driver_override); int rpmsg_register_device(struct rpmsg_device *rpdev); int rpmsg_unregister_device(struct device *parent, struct rpmsg_channel_info *chinfo); @@ -192,6 +194,12 @@ ssize_t rpmsg_get_mtu(struct rpmsg_endpoint *ept); #else +static inline int rpmsg_register_device_override(struct rpmsg_device *rpdev, + const char *driver_override) +{ + return -ENXIO; +} + static inline int rpmsg_register_device(struct rpmsg_device *rpdev) { return -ENXIO; -- cgit v1.2.3 From d143b9db8069f0e2a0fa34484e806a55a0dd4855 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 27 Apr 2022 11:04:42 +0200 Subject: export: fix string handling of namespace in EXPORT_SYMBOL_NS Commit c3a6cf19e695 ("export: avoid code duplication in include/linux/export.h") broke the ability for a defined string to be used as a namespace value. Fix this up by using stringify to properly encode the namespace name. Fixes: c3a6cf19e695 ("export: avoid code duplication in include/linux/export.h") Cc: Miroslav Benes Cc: Emil Velikov Cc: Jessica Yu Cc: Quentin Perret Cc: Matthias Maennich Reviewed-by: Masahiro Yamada Link: https://lore.kernel.org/r/20220427090442.2105905-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/export.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/export.h b/include/linux/export.h index 27d848712b90..5910ccb66ca2 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -2,6 +2,8 @@ #ifndef _LINUX_EXPORT_H #define _LINUX_EXPORT_H +#include + /* * Export symbols from the kernel to modules. Forked from module.h * to reduce the amount of pointless cruft we feed to gcc when only @@ -154,7 +156,6 @@ struct kernel_symbol { #endif /* CONFIG_MODULES */ #ifdef DEFAULT_SYMBOL_NAMESPACE -#include #define _EXPORT_SYMBOL(sym, sec) __EXPORT_SYMBOL(sym, sec, __stringify(DEFAULT_SYMBOL_NAMESPACE)) #else #define _EXPORT_SYMBOL(sym, sec) __EXPORT_SYMBOL(sym, sec, "") @@ -162,8 +163,8 @@ struct kernel_symbol { #define EXPORT_SYMBOL(sym) _EXPORT_SYMBOL(sym, "") #define EXPORT_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "_gpl") -#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", #ns) -#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", #ns) +#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", __stringify(ns)) +#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", __stringify(ns)) #endif /* !__ASSEMBLY__ */ -- cgit v1.2.3 From c3d438eeb5413111889edef10cb5fcc2c0fb8bc9 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 Apr 2022 09:08:06 +0100 Subject: arch_topology: Trace the update thermal pressure Add trace event to capture the moment of the call for updating the thermal pressure value. It's helpful to investigate how often those events occur in a system dealing with throttling. This trace event is needed since the old 'cdev_update' might not be used by some drivers. The old 'cdev_update' trace event only provides a cooling state value: [0, n]. That state value then needs additional tools to translate it: state -> freq -> capacity -> thermal pressure. This new trace event just stores proper thermal pressure value in the trace buffer, no need for additional logic. This is helpful for cooperation when someone can simply sends to the list the trace buffer output from the platform (no need from additional information from other subsystems). There are also platforms which due to some design reasons don't use cooling devices and thus don't trigger old 'cdev_update' trace event. They are also important and measuring latency for the thermal signal raising/decaying characteristics is in scope. This new trace event would cover them as well. We already have a trace point 'pelt_thermal_tp' which after a change to trace event can be paired with this new 'thermal_pressure_update' and derive more insight what is going on in the system under thermal pressure (and why). Signed-off-by: Lukasz Luba Acked-by: Sudeep Holla Link: https://lore.kernel.org/r/20220427080806.1906-1-lukasz.luba@arm.com Signed-off-by: Greg Kroah-Hartman --- include/trace/events/thermal_pressure.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/trace/events/thermal_pressure.h (limited to 'include') diff --git a/include/trace/events/thermal_pressure.h b/include/trace/events/thermal_pressure.h new file mode 100644 index 000000000000..b68680201360 --- /dev/null +++ b/include/trace/events/thermal_pressure.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM thermal_pressure + +#if !defined(_TRACE_THERMAL_PRESSURE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_THERMAL_PRESSURE_H + +#include + +TRACE_EVENT(thermal_pressure_update, + TP_PROTO(int cpu, unsigned long thermal_pressure), + TP_ARGS(cpu, thermal_pressure), + + TP_STRUCT__entry( + __field(unsigned long, thermal_pressure) + __field(int, cpu) + ), + + TP_fast_assign( + __entry->thermal_pressure = thermal_pressure; + __entry->cpu = cpu; + ), + + TP_printk("cpu=%d thermal_pressure=%lu", __entry->cpu, __entry->thermal_pressure) +); +#endif /* _TRACE_THERMAL_PRESSURE_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 6de4d4eca9a2d0195f802bc97b0e9aeeaff05900 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Thu, 28 Apr 2022 02:24:27 -0400 Subject: platform/x86: pmc_atom: remove unused pmc_atom_write() This function isn't used anywhere in the driver or anywhere in tree. So remove it. It can always be re-added if/when a use arises. Cc: Andy Shevchenko Cc: Aubrey Li Cc: Hans de Goede Cc: Mark Gross Cc: platform-driver-x86@vger.kernel.org Signed-off-by: Paul Gortmaker Link: https://lore.kernel.org/r/20220428062430.31010-2-paul.gortmaker@windriver.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- include/linux/platform_data/x86/pmc_atom.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/x86/pmc_atom.h b/include/linux/platform_data/x86/pmc_atom.h index 022bcea9edec..6807839c718b 100644 --- a/include/linux/platform_data/x86/pmc_atom.h +++ b/include/linux/platform_data/x86/pmc_atom.h @@ -144,6 +144,5 @@ #define SLEEP_ENABLE 0x2000 extern int pmc_atom_read(int offset, u32 *value); -extern int pmc_atom_write(int offset, u32 value); #endif /* PMC_ATOM_H */ -- cgit v1.2.3 From 6df6398f7c8b481ce83f28143bc08a5231616deb Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 5 May 2022 19:51:31 -0700 Subject: net: add netif_inherit_tso_max() To make later patches smaller create a helper for inheriting the TSO limitations of a lower device. The TSO in the name is not an accident, subsequent patches will replace GSO with TSO in more names. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eaf66e57d891..006bb5c0e413 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4895,6 +4895,9 @@ static inline void netif_set_gro_max_size(struct net_device *dev, WRITE_ONCE(dev->gro_max_size, size); } +void netif_inherit_tso_max(struct net_device *to, + const struct net_device *from); + static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, int pulled_hlen, u16 mac_offset, int mac_len) -- cgit v1.2.3 From 14d7b8122fd591693a2388b98563707ba72c6780 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 5 May 2022 19:51:32 -0700 Subject: net: don't allow user space to lift the device limits Up until commit 46e6b992c250 ("rtnetlink: allow GSO maximums to be set on device creation") the gso_max_segs and gso_max_size of a device were not controlled from user space. The quoted commit added the ability to control them because of the following setup: netns A | netns B veth<->veth eth0 If eth0 has TSO limitations and user wants to efficiently forward traffic between eth0 and the veths they should copy the TSO limitations of eth0 onto the veths. This would happen automatically for macvlans or ipvlan but veth users are not so lucky (given the loose coupling). Unfortunately the commit in question allowed users to also override the limits on real HW devices. It may be useful to control the max GSO size and someone may be using that ability (not that I know of any user), so create a separate set of knobs to reliably record the TSO limitations. Validate the user requests. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 006bb5c0e413..e12f7de6d6ae 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1917,8 +1917,10 @@ enum netdev_ml_priv_type { * @rtnl_link_ops: Rtnl_link_ops * * @gso_max_size: Maximum size of generic segmentation offload + * @tso_max_size: Device (as in HW) limit on the max TSO request size * @gso_max_segs: Maximum number of segments that can be passed to the * NIC for GSO + * @tso_max_segs: Device (as in HW) limit on the max TSO segment count * * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device @@ -2262,8 +2264,13 @@ struct net_device { /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; +#define TSO_LEGACY_MAX_SIZE 65536 +#define TSO_MAX_SIZE UINT_MAX + unsigned int tso_max_size; #define GSO_MAX_SEGS 65535 u16 gso_max_segs; +#define TSO_MAX_SEGS U16_MAX + u16 tso_max_segs; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; @@ -4895,6 +4902,8 @@ static inline void netif_set_gro_max_size(struct net_device *dev, WRITE_ONCE(dev->gro_max_size, size); } +void netif_set_tso_max_size(struct net_device *dev, unsigned int size); +void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs); void netif_inherit_tso_max(struct net_device *to, const struct net_device *from); -- cgit v1.2.3 From 744d49daf8bd3b17b345c836f2e6f97d49fa6ae8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 5 May 2022 19:51:34 -0700 Subject: net: move netif_set_gso_max helpers These are now internal to the core, no need to expose them. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e12f7de6d6ae..8cf0ac616cb9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4881,27 +4881,6 @@ static inline bool netif_needs_gso(struct sk_buff *skb, (skb->ip_summed != CHECKSUM_UNNECESSARY))); } -static inline void netif_set_gso_max_size(struct net_device *dev, - unsigned int size) -{ - /* dev->gso_max_size is read locklessly from sk_setup_caps() */ - WRITE_ONCE(dev->gso_max_size, size); -} - -static inline void netif_set_gso_max_segs(struct net_device *dev, - unsigned int segs) -{ - /* dev->gso_max_segs is read locklessly from sk_setup_caps() */ - WRITE_ONCE(dev->gso_max_segs, segs); -} - -static inline void netif_set_gro_max_size(struct net_device *dev, - unsigned int size) -{ - /* This pairs with the READ_ONCE() in skb_gro_receive() */ - WRITE_ONCE(dev->gro_max_size, size); -} - void netif_set_tso_max_size(struct net_device *dev, unsigned int size); void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs); void netif_inherit_tso_max(struct net_device *to, -- cgit v1.2.3 From 3ff5f7840979aa36d47a6a00694826c78d63bf3c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 6 May 2022 14:14:36 +0200 Subject: linkage: Fix issue with missing symbol size Occasionally, typically when a function doesn't end with 'ret', an alias on that function will have 0 size. The difference between what GCC generates and our linkage magic, is that GCC doesn't appear to provide .size for the alias'ed symbol at all. And indeed, removing this directive cures the issue. Additionally, GCC also doesn't emit .type for alias symbols either, so also omit that. Fixes: e0891269a8c2 ("linkage: add SYM_FUNC_ALIAS{,_LOCAL,_WEAK}()") Suggested-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Reviewed-by: Mark Rutland Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220506121631.437480085@infradead.org --- include/linux/linkage.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index acb1ad2356f1..1feab6136b5b 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -171,12 +171,9 @@ /* SYM_ALIAS -- use only if you have to */ #ifndef SYM_ALIAS -#define SYM_ALIAS(alias, name, sym_type, linkage) \ - linkage(alias) ASM_NL \ - .set alias, name ASM_NL \ - .type alias sym_type ASM_NL \ - .set .L__sym_size_##alias, .L__sym_size_##name ASM_NL \ - .size alias, .L__sym_size_##alias +#define SYM_ALIAS(alias, name, linkage) \ + linkage(alias) ASM_NL \ + .set alias, name ASM_NL #endif /* === code annotations === */ @@ -261,7 +258,7 @@ */ #ifndef SYM_FUNC_ALIAS #define SYM_FUNC_ALIAS(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_GLOBAL) + SYM_ALIAS(alias, name, SYM_L_GLOBAL) #endif /* @@ -269,7 +266,7 @@ */ #ifndef SYM_FUNC_ALIAS_LOCAL #define SYM_FUNC_ALIAS_LOCAL(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_LOCAL) + SYM_ALIAS(alias, name, SYM_L_LOCAL) #endif /* @@ -277,7 +274,7 @@ */ #ifndef SYM_FUNC_ALIAS_WEAK #define SYM_FUNC_ALIAS_WEAK(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) + SYM_ALIAS(alias, name, SYM_L_WEAK) #endif /* SYM_CODE_START -- use for non-C (special) functions */ -- cgit v1.2.3 From 6b79738b6ed91a2d0fe958819469eeedac3bca81 Mon Sep 17 00:00:00 2001 From: Qi Liu Date: Fri, 15 Apr 2022 18:23:52 +0800 Subject: drivers/perf: hisi: Add Support for CPA PMU On HiSilicon Hip09 platform, there is a CPA (Coherency Protocol Agent) on each SICL (Super IO Cluster) which implements packet format translation, route parsing and traffic statistics. CPA PMU has 8 PMU counters and interrupt is supported to handle counter overflow. Let's support its driver under the framework of HiSilicon PMU driver. Signed-off-by: Qi Liu Reviewed-by: John Garry Reviewed-by: Shaokun Zhang Link: https://lore.kernel.org/r/20220415102352.6665-3-liuqi115@huawei.com Signed-off-by: Will Deacon --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 82e33137f917..b66c5f389159 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -222,6 +222,7 @@ enum cpuhp_state { CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, + CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE, CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, -- cgit v1.2.3 From cbe757ecdb4b0c8ac4c62b03cda3fa58ba6d23fd Mon Sep 17 00:00:00 2001 From: Huang Rui Date: Mon, 2 Aug 2021 09:06:03 +0800 Subject: drm/amdgpu: add GC 11.0.1 family id Add a flag to define GC 11.0.1. Signed-off-by: Huang Rui Reviewed-by: Aaron Liu Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 992851219441..9a1d210d135d 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1152,6 +1152,7 @@ struct drm_amdgpu_info_video_caps { #define AMDGPU_FAMILY_VGH 144 /* Van Gogh */ #define AMDGPU_FAMILY_GC_11_0_0 145 /* GC 11.0.0 */ #define AMDGPU_FAMILY_YC 146 /* Yellow Carp */ +#define AMDGPU_FAMILY_GC_11_0_1 148 /* GC 11.0.1 */ #define AMDGPU_FAMILY_GC_10_3_6 149 /* GC 10.3.6 */ #define AMDGPU_FAMILY_GC_10_3_7 151 /* GC 10.3.7 */ -- cgit v1.2.3 From 38d321b61bda32624bde46f662faac039905e3db Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 29 Apr 2022 00:09:28 +0100 Subject: clk: sunxi-ng: h6-r: Add RTC gate clock The H6 and H616 feature an (undocumented) bus clock gate for accessing the RTC registers. This seems to be enabled at reset (or by the BootROM), so we got away without it so far, but exists regardless. Since the new RTC clock binding for the H616 requires this "bus" clock to be specified in the DT, add this to R_CCU clock driver and expose it on the DT side with a new number. We do this for both the H6 and H616, but mark it as IGNORE_UNUSED, as we cannot reference it in any H6 DTs. Signed-off-by: Andre Przywara Reviewed-by: Samuel Holland Signed-off-by: Jernej Skrabec Link: https://lore.kernel.org/r/20220428230933.15262-2-andre.przywara@arm.com --- include/dt-bindings/clock/sun50i-h6-r-ccu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/sun50i-h6-r-ccu.h b/include/dt-bindings/clock/sun50i-h6-r-ccu.h index 890368d252c4..a96087abc86f 100644 --- a/include/dt-bindings/clock/sun50i-h6-r-ccu.h +++ b/include/dt-bindings/clock/sun50i-h6-r-ccu.h @@ -22,5 +22,6 @@ #define CLK_W1 12 #define CLK_R_APB2_RSB 13 +#define CLK_R_APB1_RTC 14 #endif /* _DT_BINDINGS_CLK_SUN50I_H6_R_CCU_H_ */ -- cgit v1.2.3 From 31ab5169803ebc009e01d1ee4501ca9faf347161 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 29 Apr 2022 00:09:29 +0100 Subject: clk: sunxi-ng: h616: Add PLL derived 32KHz clock The RTC section of the H616 manual mentions in a half-sentence the existence of a clock "32K divided by PLL_PERI(2X)". This is used as one of the possible inputs for the mux that selects the clock for the 32 KHz fanout pad. On the H616 this is routed to pin PG10, and some boards use that clock output to compensate for a missing 32KHz crystal. On the OrangePi Zero2 this is for instance connected to the LPO pin of the WiFi/BT chip. The new RTC clock binding requires this clock to be named as one input clock, so we need to expose this to the DT. In contrast to the D1 SoC there does not seem to be a gate for this clock, so just use a fixed divider clock, using a newly assigned clock number. Signed-off-by: Andre Przywara Reviewed-by: Samuel Holland Signed-off-by: Jernej Skrabec Link: https://lore.kernel.org/r/20220428230933.15262-3-andre.przywara@arm.com --- include/dt-bindings/clock/sun50i-h616-ccu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/sun50i-h616-ccu.h b/include/dt-bindings/clock/sun50i-h616-ccu.h index 4fc08b0df2f3..1191aca53ac6 100644 --- a/include/dt-bindings/clock/sun50i-h616-ccu.h +++ b/include/dt-bindings/clock/sun50i-h616-ccu.h @@ -111,5 +111,6 @@ #define CLK_BUS_TVE0 125 #define CLK_HDCP 126 #define CLK_BUS_HDCP 127 +#define CLK_PLL_SYSTEM_32K 128 #endif /* _DT_BINDINGS_CLK_SUN50I_H616_H_ */ -- cgit v1.2.3 From 343f4c49f2438d8920f1f76fa823ee59b91f02e4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 11 Apr 2022 11:40:14 -0500 Subject: kthread: Don't allocate kthread_struct for init and umh MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If kthread_is_per_cpu runs concurrently with free_kthread_struct the kthread_struct that was just freed may be read from. This bug was introduced by commit 40966e316f86 ("kthread: Ensure struct kthread is present for all kthreads"). When kthread_struct started to be allocated for all tasks that have PF_KTHREAD set. This in turn required the kthread_struct to be freed in kernel_execve and violated the assumption that kthread_struct will have the same lifetime as the task. Looking a bit deeper this only applies to callers of kernel_execve which is just the init process and the user mode helper processes. These processes really don't want to be kernel threads but are for historical reasons. Mostly that copy_thread does not know how to take a kernel mode function to the process with for processes without PF_KTHREAD or PF_IO_WORKER set. Solve this by not allocating kthread_struct for the init process and the user mode helper processes. This is done by adding a kthread member to struct kernel_clone_args. Setting kthread in fork_idle and kernel_thread. Adding user_mode_thread that works like kernel_thread except it does not set kthread. In fork only allocating the kthread_struct if .kthread is set. I have looked at kernel/kthread.c and since commit 40966e316f86 ("kthread: Ensure struct kthread is present for all kthreads") there have been no assumptions added that to_kthread or __to_kthread will not return NULL. There are a few callers of to_kthread or __to_kthread that assume a non-NULL struct kthread pointer will be returned. These functions are kthread_data(), kthread_parmme(), kthread_exit(), kthread(), kthread_park(), kthread_unpark(), kthread_stop(). All of those functions can reasonably expected to be called when it is know that a task is a kthread so that assumption seems reasonable. Cc: stable@vger.kernel.org Fixes: 40966e316f86 ("kthread: Ensure struct kthread is present for all kthreads") Reported-by: Максим Кутявин Link: https://lkml.kernel.org/r/20220506141512.516114-1-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched/task.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 719c9a6cac8d..4492266935dd 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -32,6 +32,7 @@ struct kernel_clone_args { size_t set_tid_size; int cgroup; int io_thread; + int kthread; struct cgroup *cgrp; struct css_set *cset; }; @@ -89,6 +90,7 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); +extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); -- cgit v1.2.3 From e2ef115813c34ea5380ac5b4879f515070150210 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 6 May 2022 14:14:37 +0200 Subject: objtool: Fix STACK_FRAME_NON_STANDARD reloc type STACK_FRAME_NON_STANDARD results in inconsistent relocation types depending on .c or .S usage: Relocation section '.rela.discard.func_stack_frame_non_standard' at offset 0x3c01090 contains 5 entries: Offset Info Type Symbol's Value Symbol's Name + Addend 0000000000000000 00020c2200000002 R_X86_64_PC32 0000000000047b40 do_suspend_lowlevel + 0 0000000000000008 0002461e00000001 R_X86_64_64 00000000000480a0 machine_real_restart + 0 0000000000000010 0000001400000001 R_X86_64_64 0000000000000000 .rodata + b3d4 0000000000000018 0002444600000002 R_X86_64_PC32 00000000000678a0 __efi64_thunk + 0 0000000000000020 0002659d00000001 R_X86_64_64 0000000000113160 __crash_kexec + 0 Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220506121631.508692613@infradead.org --- include/linux/objtool.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 586d35720f13..b9c1474a571e 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -40,6 +40,8 @@ struct unwind_hint { #ifdef CONFIG_STACK_VALIDATION +#include + #ifndef __ASSEMBLY__ #define UNWIND_HINT(sp_reg, sp_offset, type, end) \ @@ -137,7 +139,7 @@ struct unwind_hint { .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - .long \func - . + _ASM_PTR \func .popsection .endm -- cgit v1.2.3 From 28de0f9fec5a84bd5b56d6364432a8730eac410a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 5 May 2022 19:22:12 +0300 Subject: net: dsa: felix: perform MDB migration based on ocelot->multicast list The felix driver is the only user of dsa_port_walk_mdbs(), and there isn't even a good reason for it, considering that the host MDB entries are already saved by the ocelot switch lib in the ocelot->multicast list. Rewrite the multicast entry migration procedure around the ocelot->multicast list so we can delete dsa_port_walk_mdbs(). Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 8d8d46778f7e..e88bcfe4b2cd 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -998,6 +998,9 @@ int ocelot_mact_learn_streamdata(struct ocelot *ocelot, int dst_idx, enum macaccess_entry_type type, int sfid, int ssid); +int ocelot_migrate_mdbs(struct ocelot *ocelot, unsigned long from_mask, + unsigned long to_mask); + int ocelot_vcap_policer_add(struct ocelot *ocelot, u32 pol_ix, struct ocelot_policer *pol); int ocelot_vcap_policer_del(struct ocelot *ocelot, u32 pol_ix); -- cgit v1.2.3 From fe5233b0ba0d2216d549f93e4540542b99b97642 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 5 May 2022 19:22:13 +0300 Subject: net: dsa: delete dsa_port_walk_{fdbs,mdbs} All the users of these functions are gone, delete them before they gain new ones. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 934958fda962..efd33956df37 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1239,12 +1239,6 @@ struct dsa_switch_driver { struct net_device *dsa_dev_to_net_device(struct device *dev); -typedef int dsa_fdb_walk_cb_t(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid, - struct dsa_db db); - -int dsa_port_walk_fdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb); -int dsa_port_walk_mdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb); bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); -- cgit v1.2.3 From c5febea0956fd3874e8fb59c6f84d68f128d68f8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 8 Apr 2022 18:07:50 -0500 Subject: fork: Pass struct kernel_clone_args into copy_thread With io_uring we have started supporting tasks that are for most purposes user space tasks that exclusively run code in kernel mode. The kernel task that exec's init and tasks that exec user mode helpers are also user mode tasks that just run kernel code until they call kernel execve. Pass kernel_clone_args into copy_thread so these oddball tasks can be supported more cleanly and easily. v2: Fix spelling of kenrel_clone_args on h8300 Link: https://lkml.kernel.org/r/20220506141512.516114-2-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched/task.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4492266935dd..fcdcba231aac 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -68,8 +68,7 @@ extern void fork_init(void); extern void release_task(struct task_struct * p); -extern int copy_thread(unsigned long, unsigned long, unsigned long, - struct task_struct *, unsigned long); +extern int copy_thread(struct task_struct *, const struct kernel_clone_args *); extern void flush_thread(void); -- cgit v1.2.3 From 36cb0e1cda645ee645b85a6ce652cb46a16e14e5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 11 Apr 2022 16:17:28 -0500 Subject: fork: Explicity test for idle tasks in copy_thread The architectures ia64 and parisc have special handling for the idle thread in copy_process. Add a flag named idle to kernel_clone_args and use it to explicity test if an idle process is being created. Fullfill the expectations of the rest of the copy_thread implemetations and pass a function pointer in .stack from fork_idle(). This makes what is happening in copy_thread better defined, and is useful to make idle threads less special. Link: https://lkml.kernel.org/r/20220506141512.516114-3-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched/task.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index fcdcba231aac..3d6b99ce5408 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -33,6 +33,7 @@ struct kernel_clone_args { int cgroup; int io_thread; int kthread; + int idle; struct cgroup *cgrp; struct css_set *cset; }; -- cgit v1.2.3 From 5bd2e97c868a8a44470950ed01846cab6328e540 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 12 Apr 2022 10:18:48 -0500 Subject: fork: Generalize PF_IO_WORKER handling Add fn and fn_arg members into struct kernel_clone_args and test for them in copy_thread (instead of testing for PF_KTHREAD | PF_IO_WORKER). This allows any task that wants to be a user space task that only runs in kernel mode to use this functionality. The code on x86 is an exception and still retains a PF_KTHREAD test because x86 unlikely everything else handles kthreads slightly differently than user space tasks that start with a function. The functions that created tasks that start with a function have been updated to set ".fn" and ".fn_arg" instead of ".stack" and ".stack_size". These functions are fork_idle(), create_io_thread(), kernel_thread(), and user_mode_thread(). Link: https://lkml.kernel.org/r/20220506141512.516114-4-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched/task.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 3d6b99ce5408..505aaf9fe477 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -34,6 +34,8 @@ struct kernel_clone_args { int io_thread; int kthread; int idle; + int (*fn)(void *); + void *fn_arg; struct cgroup *cgrp; struct css_set *cset; }; -- cgit v1.2.3 From 3d1b0d351441c2be7de082b92f43d0bfdc95a8f3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 7 May 2022 13:48:21 -0400 Subject: Revert "SUNRPC: Ensure gss-proxy connects on setup" This reverts commit 892de36fd4a98fab3298d417c051d9099af5448d. The gssproxy server is unresponsive when it calls into the kernel to start the upcall service, so it will not reply to our RPC ping at all. Reported-by: "J.Bruce Fields" Fixes: 892de36fd4a9 ("SUNRPC: Ensure gss-proxy connects on setup") Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index db5149567305..267b7aeaf1a6 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,7 +160,6 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) -#define RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, -- cgit v1.2.3 From fd13359f54ee854f00134abc6be32da94ec53dbf Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 7 May 2022 13:53:59 -0400 Subject: SUNRPC: Ensure that the gssproxy client can start in a connected state Ensure that the gssproxy client connects to the server from the gssproxy daemon process context so that the AF_LOCAL socket connection is done using the correct path and namespaces. Fixes: 1d658336b05f ("SUNRPC: Add RPC based upcall mechanism for RPCGSS auth") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 267b7aeaf1a6..90501404fa49 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,6 +160,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) +#define RPC_CLNT_CREATE_CONNECTED (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, -- cgit v1.2.3 From 813c2aee51dd7d7d9092251851e33f66719513cc Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 7 May 2022 14:33:31 +0200 Subject: ARM/pxa/mfd/power/sound: Switch Tosa to GPIO descriptors The Tosa device (Sharp SL-6000) has a mishmash driver set-up for the Toshiba TC6393xb MFD that includes a battery charger and touchscreen and has some kind of relationship to the SoC sound driver for the AC97 codec. Other devices define a chip like this but seem only half-implemented, not really handling battery charging etc. This patch switches the Toshiba MFD device to provide GPIO descriptors to the battery charger and SoC codec. As a result some descriptors need to be moved out of the Tosa boardfile and new one added: all SoC GPIO resources to these drivers now comes from the main boardfile, while the MFD provide GPIOs for its portions. As a result we can request one GPIO from our own GPIO chip and drop two hairy callbacks into the board file. This platform badly needs to have its drivers split up and converted to device tree probing to handle this quite complex relationship in an orderly manner. I just do my best in solving the GPIO descriptor part of the puzzle. Please don't ask me to fix everything that is wrong with these driver to todays standards, I am just trying to fix one aspect. I do try to use modern devres resource management and handle deferred probe using new functions where appropriate. Cc: Dmitry Eremin-Solenikov Cc: Dirk Opfer Cc: Robert Jarzmik Cc: Daniel Mack Cc: Haojian Zhuang Cc: Lee Jones Cc: Liam Girdwood Reviewed-by: Dmitry Baryshkov Acked-by: Mark Brown Acked-by: Sebastian Reichel Signed-off-by: Linus Walleij Signed-off-by: Arnd Bergmann --- include/linux/gpio/machine.h | 12 ++++++++++++ include/linux/mfd/tc6393xb.h | 3 --- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index 2647dd10b541..4d55da28e664 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -63,6 +63,18 @@ struct gpiod_hog { int dflags; }; +/* + * Helper for lookup tables with just one single lookup for a device. + */ +#define GPIO_LOOKUP_SINGLE(_name, _dev_id, _key, _chip_hwnum, _con_id, _flags) \ +static struct gpiod_lookup_table _name = { \ + .dev_id = _dev_id, \ + .table = { \ + GPIO_LOOKUP(_key, _chip_hwnum, _con_id, _flags), \ + {}, \ + }, \ +} + /* * Simple definition of a single GPIO under a con_id */ diff --git a/include/linux/mfd/tc6393xb.h b/include/linux/mfd/tc6393xb.h index fcc8e74f0e8d..d336c541b7df 100644 --- a/include/linux/mfd/tc6393xb.h +++ b/include/linux/mfd/tc6393xb.h @@ -27,9 +27,6 @@ struct tc6393xb_platform_data { int (*resume)(struct platform_device *dev); int irq_base; /* base for subdevice irqs */ - int gpio_base; - int (*setup)(struct platform_device *dev); - void (*teardown)(struct platform_device *dev); struct tmio_nand_data *nand_data; struct tmio_fb_data *fb_data; -- cgit v1.2.3 From ac70f4d80df414223130b04d9b4435bf56dda654 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 11 Sep 2019 10:58:26 +0200 Subject: ARM: pxa: poodle: use platform data for poodle asoc driver The poodle audio driver shows its age by using a custom gpio api for the "locomo" support chip. In a perfect world, this would get converted to use gpiolib and a gpio lookup table. As the world is not perfect, just pass all the required data in a custom platform_data structure. to avoid the globally visible mach/poodle.h header. Acked-by: Mark Brown Acked-by: Robert Jarzmik Cc: alsa-devel@alsa-project.org Signed-off-by: Arnd Bergmann --- include/linux/platform_data/asoc-poodle.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/linux/platform_data/asoc-poodle.h (limited to 'include') diff --git a/include/linux/platform_data/asoc-poodle.h b/include/linux/platform_data/asoc-poodle.h new file mode 100644 index 000000000000..2052fad55c5c --- /dev/null +++ b/include/linux/platform_data/asoc-poodle.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_PLATFORM_DATA_POODLE_AUDIO +#define __LINUX_PLATFORM_DATA_POODLE_AUDIO + +/* locomo is not a proper gpio driver, and uses its own api */ +struct poodle_audio_platform_data { + struct device *locomo_dev; + + int gpio_amp_on; + int gpio_mute_l; + int gpio_mute_r; + int gpio_232vcc_on; + int gpio_jk_b; +}; + +#endif -- cgit v1.2.3 From e217b085a1ac1c4108fe632bdaa08ea5b0ecd145 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Sep 2019 09:55:23 +0200 Subject: Input: touchscreen: use wrapper for pxa2xx ac97 registers To avoid a dependency on the pxa platform header files with hardcoded registers, change the driver to call a wrapper in the pxa2xx-ac97-lib that encapsulates all the other ac97 stuff. Acked-by: Dmitry Torokhov Acked-by: Robert Jarzmik Cc: linux-input@vger.kernel.org Cc: alsa-devel@alsa-project.org Signed-off-by: Arnd Bergmann --- include/sound/pxa2xx-lib.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/sound/pxa2xx-lib.h b/include/sound/pxa2xx-lib.h index 95100cff25d1..0a6f8dabf8c4 100644 --- a/include/sound/pxa2xx-lib.h +++ b/include/sound/pxa2xx-lib.h @@ -52,4 +52,8 @@ extern int pxa2xx_ac97_hw_resume(void); extern int pxa2xx_ac97_hw_probe(struct platform_device *dev); extern void pxa2xx_ac97_hw_remove(struct platform_device *dev); +/* modem registers, used by touchscreen driver */ +u32 pxa2xx_ac97_read_modr(void); +u32 pxa2xx_ac97_read_misr(void); + #endif -- cgit v1.2.3 From a2ef926143b84664f4823c82a437b29c4667a08c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 18 Oct 2019 13:48:33 -0700 Subject: Input: wm97xx - switch to using threaded IRQ Instead of manually disabling and enabling interrupts and scheduling work to access the device, let's use threaded oneshot interrupt handler. It simplifies things. Signed-off-by: Dmitry Torokhov Signed-off-by: Arnd Bergmann --- include/linux/wm97xx.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h index 462854f4f286..85bd8dd3caea 100644 --- a/include/linux/wm97xx.h +++ b/include/linux/wm97xx.h @@ -281,7 +281,6 @@ struct wm97xx { unsigned long ts_reader_min_interval; /* Minimum interval */ unsigned int pen_irq; /* Pen IRQ number in use */ struct workqueue_struct *ts_workq; - struct work_struct pen_event_work; u16 acc_slot; /* AC97 slot used for acc touch data */ u16 acc_rate; /* acc touch data rate */ unsigned pen_is_down:1; /* Pen is down */ -- cgit v1.2.3 From e1d8f31218aab302df9e18526345af189fd061f0 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 18 Oct 2019 13:48:34 -0700 Subject: Input: wm97xx - get rid of irq_enable method in wm97xx_mach_ops Now that we are using oneshot threaded IRQ this method is not used anymore. Signed-off-by: Dmitry Torokhov [arnd: add the db1300 change as well] Cc: Manuel Lauss Signed-off-by: Arnd Bergmann --- include/linux/wm97xx.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h index 85bd8dd3caea..332d2b0f29b9 100644 --- a/include/linux/wm97xx.h +++ b/include/linux/wm97xx.h @@ -254,9 +254,6 @@ struct wm97xx_mach_ops { int (*acc_startup) (struct wm97xx *); void (*acc_shutdown) (struct wm97xx *); - /* interrupt mask control - required for accelerated operation */ - void (*irq_enable) (struct wm97xx *, int enable); - /* GPIO pin used for accelerated operation */ int irq_gpio; -- cgit v1.2.3 From 6a946f1bd5cc966c9dd377b14efa4cec388101ce Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Sep 2019 14:50:37 +0200 Subject: ARM: pxa: pcmcia: move smemc configuration back to arch Rather than poking at the smemc registers directly from the pcmcia/pxa2xx_base driver, move those bits into machine file to have a cleaner interface. Cc: Dominik Brodowski Link: https://lore.kernel.org/lkml/87d0egjzxk.fsf@belgarion.home/ Signed-off-by: Arnd Bergmann --- include/linux/soc/pxa/smemc.h | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 include/linux/soc/pxa/smemc.h (limited to 'include') diff --git a/include/linux/soc/pxa/smemc.h b/include/linux/soc/pxa/smemc.h new file mode 100644 index 000000000000..cbf1a2d8af29 --- /dev/null +++ b/include/linux/soc/pxa/smemc.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __PXA_REGS_H +#define __PXA_REGS_H + +#include + +void pxa_smemc_set_pcmcia_timing(int sock, u32 mcmem, u32 mcatt, u32 mcio); +void pxa_smemc_set_pcmcia_socket(int nr); + +#endif -- cgit v1.2.3 From 5c6603e741921c75f67a724e798642ed50a6328e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Sep 2019 15:34:10 +0200 Subject: cpufreq: pxa3: move clk register access to clk driver The driver needs some low-level register access for setting the core and bus frequencies. These registers are owned by the clk driver, so move the low-level access into that driver with a slightly higher-level interface and avoid any machine header file dependencies. Cc: Michael Turquette Cc: Stephen Boyd Acked-by: Viresh Kumar Cc: linux-clk@vger.kernel.org Cc: linux-pm@vger.kernel.org Signed-off-by: Arnd Bergmann --- include/linux/clk/pxa.h | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 include/linux/clk/pxa.h (limited to 'include') diff --git a/include/linux/clk/pxa.h b/include/linux/clk/pxa.h new file mode 100644 index 000000000000..e5516c608c99 --- /dev/null +++ b/include/linux/clk/pxa.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifdef CONFIG_PXA3xx +extern unsigned pxa3xx_get_clk_frequency_khz(int); +extern void pxa3xx_clk_update_accr(u32 disable, u32 enable, u32 xclkcfg, u32 mask); +#else +#define pxa3xx_get_clk_frequency_khz(x) (0) +#define pxa3xx_clk_update_accr(disable, enable, xclkcfg, mask) do { } while (0) +#endif -- cgit v1.2.3 From fd13f8117f7a2d4054bf420ec1428e918a24a480 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Sep 2019 17:42:52 +0200 Subject: ARM: pxa: move smemc register access from clk to platform The get_sdram_rows() and get_memclkdiv() helpers need smemc register that are separate from the clk registers, move them out of the clk driver, and use an extern declaration instead. Cc: Michael Turquette Cc: Stephen Boyd Cc: linux-clk@vger.kernel.org Link: https://lore.kernel.org/lkml/87pnielzo4.fsf@belgarion.home/ Signed-off-by: Arnd Bergmann --- include/linux/soc/pxa/smemc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/soc/pxa/smemc.h b/include/linux/soc/pxa/smemc.h index cbf1a2d8af29..f1ffea236c15 100644 --- a/include/linux/soc/pxa/smemc.h +++ b/include/linux/soc/pxa/smemc.h @@ -6,5 +6,8 @@ void pxa_smemc_set_pcmcia_timing(int sock, u32 mcmem, u32 mcatt, u32 mcio); void pxa_smemc_set_pcmcia_socket(int nr); +int pxa2xx_smemc_get_sdram_rows(void); +unsigned int pxa3xx_smemc_get_memclkdiv(void); +void __iomem *pxa_smemc_get_mdrefr(void); #endif -- cgit v1.2.3 From 3c816d950a494ae6e16b1fa017af29bc53cb7791 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Sep 2019 20:54:17 +0200 Subject: ARM: pxa: move clk register definitions to driver The clock register definitions are now used (almost) exclusively in the clk driver, and that relies on no other mach/*.h header files any more. Remove the dependency on mach/pxa*-regs.h by addressing the registers as offsets from a void __iomem * pointer, which is either passed from a board file, or (for the moment) ioremapped at boot time from a hardcoded address in case of DT (this should be moved into the DT of course). Cc: linux-clk@vger.kernel.org Acked-by: Stephen Boyd Acked-by: Robert Jarzmik Signed-off-by: Arnd Bergmann --- include/linux/clk/pxa.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/clk/pxa.h b/include/linux/clk/pxa.h index e5516c608c99..736b8bb91bd7 100644 --- a/include/linux/clk/pxa.h +++ b/include/linux/clk/pxa.h @@ -1,5 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0-only */ +#include +#include + +extern int pxa25x_clocks_init(void __iomem *regs); +extern int pxa27x_clocks_init(void __iomem *regs); +extern int pxa3xx_clocks_init(void __iomem *regs, void __iomem *oscc_reg); + #ifdef CONFIG_PXA3xx extern unsigned pxa3xx_get_clk_frequency_khz(int); extern void pxa3xx_clk_update_accr(u32 disable, u32 enable, u32 xclkcfg, u32 mask); -- cgit v1.2.3 From 64dbc4dd7a7cc6642c522963a6194b62480e2a68 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 20 Sep 2019 13:33:40 +0200 Subject: ARM: pxa: move plat-pxa to drivers/soc/ There are two drivers in arch/arm/plat-pxa: mfp and ssp. Both of them should ideally not be needed at all, as there are proper subsystems to replace them. OTOH, they are self-contained and can simply be normal SoC drivers, so move them over there to eliminate one more of the plat-* directories. Acked-by: Robert Jarzmik (mach-pxa) Acked-by: Lubomir Rintel (mach-mmp) Signed-off-by: Arnd Bergmann --- include/linux/soc/pxa/mfp.h | 470 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 470 insertions(+) create mode 100644 include/linux/soc/pxa/mfp.h (limited to 'include') diff --git a/include/linux/soc/pxa/mfp.h b/include/linux/soc/pxa/mfp.h new file mode 100644 index 000000000000..39779cbed0c0 --- /dev/null +++ b/include/linux/soc/pxa/mfp.h @@ -0,0 +1,470 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Common Multi-Function Pin Definitions + * + * Copyright (C) 2007 Marvell International Ltd. + * + * 2007-8-21: eric miao + * initial version + */ + +#ifndef __ASM_PLAT_MFP_H +#define __ASM_PLAT_MFP_H + +#define mfp_to_gpio(m) ((m) % 256) + +/* list of all the configurable MFP pins */ +enum { + MFP_PIN_INVALID = -1, + + MFP_PIN_GPIO0 = 0, + MFP_PIN_GPIO1, + MFP_PIN_GPIO2, + MFP_PIN_GPIO3, + MFP_PIN_GPIO4, + MFP_PIN_GPIO5, + MFP_PIN_GPIO6, + MFP_PIN_GPIO7, + MFP_PIN_GPIO8, + MFP_PIN_GPIO9, + MFP_PIN_GPIO10, + MFP_PIN_GPIO11, + MFP_PIN_GPIO12, + MFP_PIN_GPIO13, + MFP_PIN_GPIO14, + MFP_PIN_GPIO15, + MFP_PIN_GPIO16, + MFP_PIN_GPIO17, + MFP_PIN_GPIO18, + MFP_PIN_GPIO19, + MFP_PIN_GPIO20, + MFP_PIN_GPIO21, + MFP_PIN_GPIO22, + MFP_PIN_GPIO23, + MFP_PIN_GPIO24, + MFP_PIN_GPIO25, + MFP_PIN_GPIO26, + MFP_PIN_GPIO27, + MFP_PIN_GPIO28, + MFP_PIN_GPIO29, + MFP_PIN_GPIO30, + MFP_PIN_GPIO31, + MFP_PIN_GPIO32, + MFP_PIN_GPIO33, + MFP_PIN_GPIO34, + MFP_PIN_GPIO35, + MFP_PIN_GPIO36, + MFP_PIN_GPIO37, + MFP_PIN_GPIO38, + MFP_PIN_GPIO39, + MFP_PIN_GPIO40, + MFP_PIN_GPIO41, + MFP_PIN_GPIO42, + MFP_PIN_GPIO43, + MFP_PIN_GPIO44, + MFP_PIN_GPIO45, + MFP_PIN_GPIO46, + MFP_PIN_GPIO47, + MFP_PIN_GPIO48, + MFP_PIN_GPIO49, + MFP_PIN_GPIO50, + MFP_PIN_GPIO51, + MFP_PIN_GPIO52, + MFP_PIN_GPIO53, + MFP_PIN_GPIO54, + MFP_PIN_GPIO55, + MFP_PIN_GPIO56, + MFP_PIN_GPIO57, + MFP_PIN_GPIO58, + MFP_PIN_GPIO59, + MFP_PIN_GPIO60, + MFP_PIN_GPIO61, + MFP_PIN_GPIO62, + MFP_PIN_GPIO63, + MFP_PIN_GPIO64, + MFP_PIN_GPIO65, + MFP_PIN_GPIO66, + MFP_PIN_GPIO67, + MFP_PIN_GPIO68, + MFP_PIN_GPIO69, + MFP_PIN_GPIO70, + MFP_PIN_GPIO71, + MFP_PIN_GPIO72, + MFP_PIN_GPIO73, + MFP_PIN_GPIO74, + MFP_PIN_GPIO75, + MFP_PIN_GPIO76, + MFP_PIN_GPIO77, + MFP_PIN_GPIO78, + MFP_PIN_GPIO79, + MFP_PIN_GPIO80, + MFP_PIN_GPIO81, + MFP_PIN_GPIO82, + MFP_PIN_GPIO83, + MFP_PIN_GPIO84, + MFP_PIN_GPIO85, + MFP_PIN_GPIO86, + MFP_PIN_GPIO87, + MFP_PIN_GPIO88, + MFP_PIN_GPIO89, + MFP_PIN_GPIO90, + MFP_PIN_GPIO91, + MFP_PIN_GPIO92, + MFP_PIN_GPIO93, + MFP_PIN_GPIO94, + MFP_PIN_GPIO95, + MFP_PIN_GPIO96, + MFP_PIN_GPIO97, + MFP_PIN_GPIO98, + MFP_PIN_GPIO99, + MFP_PIN_GPIO100, + MFP_PIN_GPIO101, + MFP_PIN_GPIO102, + MFP_PIN_GPIO103, + MFP_PIN_GPIO104, + MFP_PIN_GPIO105, + MFP_PIN_GPIO106, + MFP_PIN_GPIO107, + MFP_PIN_GPIO108, + MFP_PIN_GPIO109, + MFP_PIN_GPIO110, + MFP_PIN_GPIO111, + MFP_PIN_GPIO112, + MFP_PIN_GPIO113, + MFP_PIN_GPIO114, + MFP_PIN_GPIO115, + MFP_PIN_GPIO116, + MFP_PIN_GPIO117, + MFP_PIN_GPIO118, + MFP_PIN_GPIO119, + MFP_PIN_GPIO120, + MFP_PIN_GPIO121, + MFP_PIN_GPIO122, + MFP_PIN_GPIO123, + MFP_PIN_GPIO124, + MFP_PIN_GPIO125, + MFP_PIN_GPIO126, + MFP_PIN_GPIO127, + + MFP_PIN_GPIO128, + MFP_PIN_GPIO129, + MFP_PIN_GPIO130, + MFP_PIN_GPIO131, + MFP_PIN_GPIO132, + MFP_PIN_GPIO133, + MFP_PIN_GPIO134, + MFP_PIN_GPIO135, + MFP_PIN_GPIO136, + MFP_PIN_GPIO137, + MFP_PIN_GPIO138, + MFP_PIN_GPIO139, + MFP_PIN_GPIO140, + MFP_PIN_GPIO141, + MFP_PIN_GPIO142, + MFP_PIN_GPIO143, + MFP_PIN_GPIO144, + MFP_PIN_GPIO145, + MFP_PIN_GPIO146, + MFP_PIN_GPIO147, + MFP_PIN_GPIO148, + MFP_PIN_GPIO149, + MFP_PIN_GPIO150, + MFP_PIN_GPIO151, + MFP_PIN_GPIO152, + MFP_PIN_GPIO153, + MFP_PIN_GPIO154, + MFP_PIN_GPIO155, + MFP_PIN_GPIO156, + MFP_PIN_GPIO157, + MFP_PIN_GPIO158, + MFP_PIN_GPIO159, + MFP_PIN_GPIO160, + MFP_PIN_GPIO161, + MFP_PIN_GPIO162, + MFP_PIN_GPIO163, + MFP_PIN_GPIO164, + MFP_PIN_GPIO165, + MFP_PIN_GPIO166, + MFP_PIN_GPIO167, + MFP_PIN_GPIO168, + MFP_PIN_GPIO169, + MFP_PIN_GPIO170, + MFP_PIN_GPIO171, + MFP_PIN_GPIO172, + MFP_PIN_GPIO173, + MFP_PIN_GPIO174, + MFP_PIN_GPIO175, + MFP_PIN_GPIO176, + MFP_PIN_GPIO177, + MFP_PIN_GPIO178, + MFP_PIN_GPIO179, + MFP_PIN_GPIO180, + MFP_PIN_GPIO181, + MFP_PIN_GPIO182, + MFP_PIN_GPIO183, + MFP_PIN_GPIO184, + MFP_PIN_GPIO185, + MFP_PIN_GPIO186, + MFP_PIN_GPIO187, + MFP_PIN_GPIO188, + MFP_PIN_GPIO189, + MFP_PIN_GPIO190, + MFP_PIN_GPIO191, + + MFP_PIN_GPIO255 = 255, + + MFP_PIN_GPIO0_2, + MFP_PIN_GPIO1_2, + MFP_PIN_GPIO2_2, + MFP_PIN_GPIO3_2, + MFP_PIN_GPIO4_2, + MFP_PIN_GPIO5_2, + MFP_PIN_GPIO6_2, + MFP_PIN_GPIO7_2, + MFP_PIN_GPIO8_2, + MFP_PIN_GPIO9_2, + MFP_PIN_GPIO10_2, + MFP_PIN_GPIO11_2, + MFP_PIN_GPIO12_2, + MFP_PIN_GPIO13_2, + MFP_PIN_GPIO14_2, + MFP_PIN_GPIO15_2, + MFP_PIN_GPIO16_2, + MFP_PIN_GPIO17_2, + + MFP_PIN_ULPI_STP, + MFP_PIN_ULPI_NXT, + MFP_PIN_ULPI_DIR, + + MFP_PIN_nXCVREN, + MFP_PIN_DF_CLE_nOE, + MFP_PIN_DF_nADV1_ALE, + MFP_PIN_DF_SCLK_E, + MFP_PIN_DF_SCLK_S, + MFP_PIN_nBE0, + MFP_PIN_nBE1, + MFP_PIN_DF_nADV2_ALE, + MFP_PIN_DF_INT_RnB, + MFP_PIN_DF_nCS0, + MFP_PIN_DF_nCS1, + MFP_PIN_nLUA, + MFP_PIN_nLLA, + MFP_PIN_DF_nWE, + MFP_PIN_DF_ALE_nWE, + MFP_PIN_DF_nRE_nOE, + MFP_PIN_DF_ADDR0, + MFP_PIN_DF_ADDR1, + MFP_PIN_DF_ADDR2, + MFP_PIN_DF_ADDR3, + MFP_PIN_DF_IO0, + MFP_PIN_DF_IO1, + MFP_PIN_DF_IO2, + MFP_PIN_DF_IO3, + MFP_PIN_DF_IO4, + MFP_PIN_DF_IO5, + MFP_PIN_DF_IO6, + MFP_PIN_DF_IO7, + MFP_PIN_DF_IO8, + MFP_PIN_DF_IO9, + MFP_PIN_DF_IO10, + MFP_PIN_DF_IO11, + MFP_PIN_DF_IO12, + MFP_PIN_DF_IO13, + MFP_PIN_DF_IO14, + MFP_PIN_DF_IO15, + MFP_PIN_DF_nCS0_SM_nCS2, + MFP_PIN_DF_nCS1_SM_nCS3, + MFP_PIN_SM_nCS0, + MFP_PIN_SM_nCS1, + MFP_PIN_DF_WEn, + MFP_PIN_DF_REn, + MFP_PIN_DF_CLE_SM_OEn, + MFP_PIN_DF_ALE_SM_WEn, + MFP_PIN_DF_RDY0, + MFP_PIN_DF_RDY1, + + MFP_PIN_SM_SCLK, + MFP_PIN_SM_BE0, + MFP_PIN_SM_BE1, + MFP_PIN_SM_ADV, + MFP_PIN_SM_ADVMUX, + MFP_PIN_SM_RDY, + + MFP_PIN_MMC1_DAT7, + MFP_PIN_MMC1_DAT6, + MFP_PIN_MMC1_DAT5, + MFP_PIN_MMC1_DAT4, + MFP_PIN_MMC1_DAT3, + MFP_PIN_MMC1_DAT2, + MFP_PIN_MMC1_DAT1, + MFP_PIN_MMC1_DAT0, + MFP_PIN_MMC1_CMD, + MFP_PIN_MMC1_CLK, + MFP_PIN_MMC1_CD, + MFP_PIN_MMC1_WP, + + /* additional pins on PXA930 */ + MFP_PIN_GSIM_UIO, + MFP_PIN_GSIM_UCLK, + MFP_PIN_GSIM_UDET, + MFP_PIN_GSIM_nURST, + MFP_PIN_PMIC_INT, + MFP_PIN_RDY, + + /* additional pins on MMP2 */ + MFP_PIN_TWSI1_SCL, + MFP_PIN_TWSI1_SDA, + MFP_PIN_TWSI4_SCL, + MFP_PIN_TWSI4_SDA, + MFP_PIN_CLK_REQ, + + MFP_PIN_MAX, +}; + +/* + * a possible MFP configuration is represented by a 32-bit integer + * + * bit 0.. 9 - MFP Pin Number (1024 Pins Maximum) + * bit 10..12 - Alternate Function Selection + * bit 13..15 - Drive Strength + * bit 16..18 - Low Power Mode State + * bit 19..20 - Low Power Mode Edge Detection + * bit 21..22 - Run Mode Pull State + * + * to facilitate the definition, the following macros are provided + * + * MFP_CFG_DEFAULT - default MFP configuration value, with + * alternate function = 0, + * drive strength = fast 3mA (MFP_DS03X) + * low power mode = default + * edge detection = none + * + * MFP_CFG - default MFPR value with alternate function + * MFP_CFG_DRV - default MFPR value with alternate function and + * pin drive strength + * MFP_CFG_LPM - default MFPR value with alternate function and + * low power mode + * MFP_CFG_X - default MFPR value with alternate function, + * pin drive strength and low power mode + */ + +typedef unsigned long mfp_cfg_t; + +#define MFP_PIN(x) ((x) & 0x3ff) + +#define MFP_AF0 (0x0 << 10) +#define MFP_AF1 (0x1 << 10) +#define MFP_AF2 (0x2 << 10) +#define MFP_AF3 (0x3 << 10) +#define MFP_AF4 (0x4 << 10) +#define MFP_AF5 (0x5 << 10) +#define MFP_AF6 (0x6 << 10) +#define MFP_AF7 (0x7 << 10) +#define MFP_AF_MASK (0x7 << 10) +#define MFP_AF(x) (((x) >> 10) & 0x7) + +#define MFP_DS01X (0x0 << 13) +#define MFP_DS02X (0x1 << 13) +#define MFP_DS03X (0x2 << 13) +#define MFP_DS04X (0x3 << 13) +#define MFP_DS06X (0x4 << 13) +#define MFP_DS08X (0x5 << 13) +#define MFP_DS10X (0x6 << 13) +#define MFP_DS13X (0x7 << 13) +#define MFP_DS_MASK (0x7 << 13) +#define MFP_DS(x) (((x) >> 13) & 0x7) + +#define MFP_LPM_DEFAULT (0x0 << 16) +#define MFP_LPM_DRIVE_LOW (0x1 << 16) +#define MFP_LPM_DRIVE_HIGH (0x2 << 16) +#define MFP_LPM_PULL_LOW (0x3 << 16) +#define MFP_LPM_PULL_HIGH (0x4 << 16) +#define MFP_LPM_FLOAT (0x5 << 16) +#define MFP_LPM_INPUT (0x6 << 16) +#define MFP_LPM_STATE_MASK (0x7 << 16) +#define MFP_LPM_STATE(x) (((x) >> 16) & 0x7) + +#define MFP_LPM_EDGE_NONE (0x0 << 19) +#define MFP_LPM_EDGE_RISE (0x1 << 19) +#define MFP_LPM_EDGE_FALL (0x2 << 19) +#define MFP_LPM_EDGE_BOTH (0x3 << 19) +#define MFP_LPM_EDGE_MASK (0x3 << 19) +#define MFP_LPM_EDGE(x) (((x) >> 19) & 0x3) + +#define MFP_PULL_NONE (0x0 << 21) +#define MFP_PULL_LOW (0x1 << 21) +#define MFP_PULL_HIGH (0x2 << 21) +#define MFP_PULL_BOTH (0x3 << 21) +#define MFP_PULL_FLOAT (0x4 << 21) +#define MFP_PULL_MASK (0x7 << 21) +#define MFP_PULL(x) (((x) >> 21) & 0x7) + +#define MFP_CFG_DEFAULT (MFP_AF0 | MFP_DS03X | MFP_LPM_DEFAULT |\ + MFP_LPM_EDGE_NONE | MFP_PULL_NONE) + +#define MFP_CFG(pin, af) \ + ((MFP_CFG_DEFAULT & ~MFP_AF_MASK) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af)) + +#define MFP_CFG_DRV(pin, af, drv) \ + ((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_DS_MASK)) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_##drv)) + +#define MFP_CFG_LPM(pin, af, lpm) \ + ((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_LPM_STATE_MASK)) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_LPM_##lpm)) + +#define MFP_CFG_X(pin, af, drv, lpm) \ + ((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_DS_MASK | MFP_LPM_STATE_MASK)) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_##drv | MFP_LPM_##lpm)) + +#if defined(CONFIG_PXA3xx) || defined(CONFIG_ARCH_MMP) +/* + * each MFP pin will have a MFPR register, since the offset of the + * register varies between processors, the processor specific code + * should initialize the pin offsets by mfp_init() + * + * mfp_init_base() - accepts a virtual base for all MFPR registers and + * initialize the MFP table to a default state + * + * mfp_init_addr() - accepts a table of "mfp_addr_map" structure, which + * represents a range of MFP pins from "start" to "end", with the offset + * beginning at "offset", to define a single pin, let "end" = -1. + * + * use + * + * MFP_ADDR_X() to define a range of pins + * MFP_ADDR() to define a single pin + * MFP_ADDR_END to signal the end of pin offset definitions + */ +struct mfp_addr_map { + unsigned int start; + unsigned int end; + unsigned long offset; +}; + +#define MFP_ADDR_X(start, end, offset) \ + { MFP_PIN_##start, MFP_PIN_##end, offset } + +#define MFP_ADDR(pin, offset) \ + { MFP_PIN_##pin, -1, offset } + +#define MFP_ADDR_END { MFP_PIN_INVALID, 0 } + +void mfp_init_base(void __iomem *mfpr_base); +void mfp_init_addr(struct mfp_addr_map *map); + +/* + * mfp_{read, write}() - for direct read/write access to the MFPR register + * mfp_config() - for configuring a group of MFPR registers + * mfp_config_lpm() - configuring all low power MFPR registers for suspend + * mfp_config_run() - configuring all run time MFPR registers after resume + */ +unsigned long mfp_read(int mfp); +void mfp_write(int mfp, unsigned long mfpr_val); +void mfp_config(unsigned long *mfp_cfgs, int num); +void mfp_config_run(void); +void mfp_config_lpm(void); +#endif /* CONFIG_PXA3xx || CONFIG_ARCH_MMP */ + +#endif /* __ASM_PLAT_MFP_H */ -- cgit v1.2.3 From 645b302673bb74930b5f38f1d5b7e7532f164595 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 24 Apr 2022 14:36:35 +0200 Subject: ARM: pxa/sa1100: move I/O space to PCI_IOBASE PXA and StrongARM1100 traditionally map their I/O space 1:1 into virtual memory, using a per-bus io_offset that matches the base address of the ioremap mapping. In order for PXA to work in a multiplatform config, this needs to change so I/O space starts at PCI_IOBASE (0xfee00000). Since the pcmcia soc_common support is shared with StrongARM1100, both have to change at the same time. The affected machines are: - Anything with a PCMCIA slot now uses pci_remap_iospace, which is made available to PCMCIA configurations as well, rather than just PCI. The first PCMCIA slot now starts at port number 0x10000. - The Zeus and Viper platforms have PC/104-style ISA buses, which have a static mapping for both I/O and memory space at 0xf1000000, which can no longer work. It does not appear to have any in-tree users, so moving it to port number 0 makes them behave like a traditional PC. - SA1100 does support ISA slots in theory, but all machines that originally enabled this appear to have been removed from the tree ages ago, and the I/O space is never mapped anywhere. - The Nanoengine machine has support for PCI slots, but looks like this never included I/O space, the resources only define the location for memory and config space. With this, the definitions of __io() and IO_SPACE_LIMIT can be simplified, as the only remaining cases are the generic PCI_IOBASE and the custom inb()/outb() macros on RiscPC. S3C24xx still has a custom inb()/outb() in this here, but this is already removed in another branch. Signed-off-by: Arnd Bergmann --- include/pcmcia/soc_common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/pcmcia/soc_common.h b/include/pcmcia/soc_common.h index 26f1473a06c5..d4f18f4679df 100644 --- a/include/pcmcia/soc_common.h +++ b/include/pcmcia/soc_common.h @@ -46,9 +46,9 @@ struct soc_pcmcia_socket { struct resource res_skt; struct resource res_io; + struct resource res_io_io; struct resource res_mem; struct resource res_attr; - void __iomem *virt_io; struct { int gpio; -- cgit v1.2.3 From 3b5eed3c71a2fb60aa4405ad92a2a6ad2677f220 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 3 May 2022 13:54:58 -0700 Subject: netfs: Eliminate Clang randstruct warning Clang's structure layout randomization feature gets upset when it sees struct inode (which is randomized) cast to struct netfs_i_context. This is due to seeing the inode pointer as being treated as an array of inodes, rather than "something else, following struct inode". Since netfs can't use container_of() (since it doesn't know what the true containing struct is), it uses this direct offset instead. Adjust the code to better reflect what is happening: an arbitrary pointer is being adjusted and cast to something else: use a "void *" for the math. The resulting binary output is the same, but Clang no longer sees an unexpected cross-structure cast: In file included from ../fs/nfs/inode.c:50: In file included from ../fs/nfs/fscache.h:15: In file included from ../include/linux/fscache.h:18: ../include/linux/netfs.h:298:9: error: casting from randomized structure pointer type 'struct inode *' to 'struct netfs_i_context *' return (struct netfs_i_context *)(inode + 1); ^ 1 error generated. Cc: David Howells Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220503205503.3054173-2-keescook@chromium.org Reviewed-by: Jeff Layton Link: https://lore.kernel.org/lkml/7562f8eccd7cc0e447becfe9912179088784e3b9.camel@kernel.org --- include/linux/netfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c7bf1eaf51d5..0c33b715cbfd 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -295,7 +295,7 @@ extern void netfs_stats_show(struct seq_file *); */ static inline struct netfs_i_context *netfs_i_context(struct inode *inode) { - return (struct netfs_i_context *)(inode + 1); + return (void *)inode + sizeof(*inode); } /** @@ -307,7 +307,7 @@ static inline struct netfs_i_context *netfs_i_context(struct inode *inode) */ static inline struct inode *netfs_inode(struct netfs_i_context *ctx) { - return ((struct inode *)ctx) - 1; + return (void *)ctx - sizeof(struct inode); } /** -- cgit v1.2.3 From 595b893e2087de306d0781795fb8ec47873596a6 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 3 May 2022 13:55:00 -0700 Subject: randstruct: Reorganize Kconfigs and attribute macros In preparation for Clang supporting randstruct, reorganize the Kconfigs, move the attribute macros, and generalize the feature to be named CONFIG_RANDSTRUCT for on/off, CONFIG_RANDSTRUCT_FULL for the full randomization mode, and CONFIG_RANDSTRUCT_PERFORMANCE for the cache-line sized mode. Cc: linux-hardening@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220503205503.3054173-4-keescook@chromium.org --- include/linux/compiler-gcc.h | 8 -------- include/linux/compiler_types.h | 14 +++++++------- include/linux/vermagic.h | 8 ++++---- 3 files changed, 11 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 52299c957c98..a0c55eeaeaf1 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -66,14 +66,6 @@ __builtin_unreachable(); \ } while (0) -#if defined(RANDSTRUCT_PLUGIN) && !defined(__CHECKER__) -#define __randomize_layout __attribute__((randomize_layout)) -#define __no_randomize_layout __attribute__((no_randomize_layout)) -/* This anon struct can add padding, so only enable it under randstruct. */ -#define randomized_struct_fields_start struct { -#define randomized_struct_fields_end } __randomize_layout; -#endif - /* * GCC 'asm goto' miscompiles certain code sequences: * diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 1c2c33ae1b37..d08dfcb0ac68 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -242,15 +242,15 @@ struct ftrace_likely_data { # define __latent_entropy #endif -#ifndef __randomize_layout +#if defined(RANDSTRUCT) && !defined(__CHECKER__) +# define __randomize_layout __designated_init __attribute__((randomize_layout)) +# define __no_randomize_layout __attribute__((no_randomize_layout)) +/* This anon struct can add padding, so only enable it under randstruct. */ +# define randomized_struct_fields_start struct { +# define randomized_struct_fields_end } __randomize_layout; +#else # define __randomize_layout __designated_init -#endif - -#ifndef __no_randomize_layout # define __no_randomize_layout -#endif - -#ifndef randomized_struct_fields_start # define randomized_struct_fields_start # define randomized_struct_fields_end #endif diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 329d63babaeb..efb51a2da599 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -32,11 +32,11 @@ #else #define MODULE_VERMAGIC_MODVERSIONS "" #endif -#ifdef RANDSTRUCT_PLUGIN +#ifdef RANDSTRUCT #include -#define MODULE_RANDSTRUCT_PLUGIN "RANDSTRUCT_PLUGIN_" RANDSTRUCT_HASHED_SEED +#define MODULE_RANDSTRUCT "RANDSTRUCT_" RANDSTRUCT_HASHED_SEED #else -#define MODULE_RANDSTRUCT_PLUGIN +#define MODULE_RANDSTRUCT #endif #define VERMAGIC_STRING \ @@ -44,6 +44,6 @@ MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT \ MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS \ MODULE_ARCH_VERMAGIC \ - MODULE_RANDSTRUCT_PLUGIN + MODULE_RANDSTRUCT #endif /* _LINUX_VERMAGIC_H */ -- cgit v1.2.3 From be2b34fa9be31c60a95989f984c9a5d40cd781b6 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 3 May 2022 13:55:02 -0700 Subject: randstruct: Move seed generation into scripts/basic/ To enable Clang randstruct support, move the structure layout randomization seed generation out of scripts/gcc-plugins/ into scripts/basic/ so it happens early enough that it can be used by either compiler implementation. The gcc-plugin still builds its own header file, but now does so from the common "randstruct.seed" file. Cc: linux-hardening@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220503205503.3054173-6-keescook@chromium.org --- include/linux/vermagic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index efb51a2da599..a54046bf37e5 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -33,7 +33,7 @@ #define MODULE_VERMAGIC_MODVERSIONS "" #endif #ifdef RANDSTRUCT -#include +#include #define MODULE_RANDSTRUCT "RANDSTRUCT_" RANDSTRUCT_HASHED_SEED #else #define MODULE_RANDSTRUCT -- cgit v1.2.3 From 9ec79840d6afaf472294588a6bbe145bcdffa28b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 27 Apr 2022 18:31:19 +0100 Subject: stackleak: rework stack low bound handling In stackleak_task_init(), stackleak_track_stack(), and __stackleak_erase(), we open-code skipping the STACK_END_MAGIC at the bottom of the stack. Each case is implemented slightly differently, and only the __stackleak_erase() case is commented. In stackleak_task_init() and stackleak_track_stack() we unconditionally add sizeof(unsigned long) to the lowest stack address. In stackleak_task_init() we use end_of_stack() for this, and in stackleak_track_stack() we use task_stack_page(). In __stackleak_erase() we handle this by detecting if `kstack_ptr` has hit the stack end boundary, and if so, conditionally moving it above the magic. This patch adds a new stackleak_task_low_bound() helper which is used in all three cases, which unconditionally adds sizeof(unsigned long) to the lowest address on the task stack, with commentary as to why. This uses end_of_stack() as stackleak_task_init() did prior to this patch, as this is consistent with the code in kernel/fork.c which initializes the STACK_END_MAGIC value. In __stackleak_erase() we no longer need to check whether we've spilled into the STACK_END_MAGIC value, as stackleak_track_stack() ensures that `current->lowest_stack` stops immediately above this, and similarly the poison scan will stop immediately above this. For stackleak_task_init() and stackleak_track_stack() this results in no change to code generation. For __stackleak_erase() the generated assembly is slightly simpler and shorter. Signed-off-by: Mark Rutland Cc: Alexander Popov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220427173128.2603085-5-mark.rutland@arm.com --- include/linux/stackleak.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index ccaab2043fcd..67430faa5c51 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -15,9 +15,22 @@ #ifdef CONFIG_GCC_PLUGIN_STACKLEAK #include +/* + * The lowest address on tsk's stack which we can plausibly erase. + */ +static __always_inline unsigned long +stackleak_task_low_bound(const struct task_struct *tsk) +{ + /* + * The lowest unsigned long on the task stack contains STACK_END_MAGIC, + * which we must not corrupt. + */ + return (unsigned long)end_of_stack(tsk) + sizeof(unsigned long); +} + static inline void stackleak_task_init(struct task_struct *t) { - t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); + t->lowest_stack = stackleak_task_low_bound(t); # ifdef CONFIG_STACKLEAK_METRICS t->prev_lowest_stack = t->lowest_stack; # endif -- cgit v1.2.3 From 0cfa2ccd285d98ad62218add2eebdcfff69fb2c0 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 27 Apr 2022 18:31:21 +0100 Subject: stackleak: rework stack high bound handling Prior to returning to userspace, we reset current->lowest_stack to a reasonable high bound. Currently we do this by subtracting the arbitrary value `THREAD_SIZE/64` from the top of the stack, for reasons lost to history. Looking at configurations today: * On i386 where THREAD_SIZE is 8K, the bound will be 128 bytes. The pt_regs at the top of the stack is 68 bytes (with 0 to 16 bytes of padding above), and so this covers an additional portion of 44 to 60 bytes. * On x86_64 where THREAD_SIZE is at least 16K (up to 32K with KASAN) the bound will be at least 256 bytes (up to 512 with KASAN). The pt_regs at the top of the stack is 168 bytes, and so this cover an additional 88 bytes of stack (up to 344 with KASAN). * On arm64 where THREAD_SIZE is at least 16K (up to 64K with 64K pages and VMAP_STACK), the bound will be at least 256 bytes (up to 1024 with KASAN). The pt_regs at the top of the stack is 336 bytes, so this can fall within the pt_regs, or can cover an additional 688 bytes of stack. Clearly the `THREAD_SIZE/64` value doesn't make much sense -- in the worst case, this will cause more than 600 bytes of stack to be erased for every syscall, even if actual stack usage were substantially smaller. This patches makes this slightly less nonsensical by consistently resetting current->lowest_stack to the base of the task pt_regs. For clarity and for consistency with the handling of the low bound, the generation of the high bound is split into a helper with commentary explaining why. Since the pt_regs at the top of the stack will be clobbered upon the next exception entry, we don't need to poison these at exception exit. By using task_pt_regs() as the high stack boundary instead of current_top_of_stack() we avoid some redundant poisoning, and the compiler can share the address generation between the poisoning and resetting of `current->lowest_stack`, making the generated code more optimal. It's not clear to me whether the existing `THREAD_SIZE/64` offset was a dodgy heuristic to skip the pt_regs, or whether it was attempting to minimize the number of times stackleak_check_stack() would have to update `current->lowest_stack` when stack usage was shallow at the cost of unconditionally poisoning a small portion of the stack for every exit to userspace. For now I've simply removed the offset, and if we need/want to minimize updates for shallow stack usage it should be easy to add a better heuristic atop, with appropriate commentary so we know what's going on. Signed-off-by: Mark Rutland Cc: Alexander Popov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220427173128.2603085-7-mark.rutland@arm.com --- include/linux/stackleak.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 67430faa5c51..467661aeb413 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -28,6 +28,20 @@ stackleak_task_low_bound(const struct task_struct *tsk) return (unsigned long)end_of_stack(tsk) + sizeof(unsigned long); } +/* + * The address immediately after the highest address on tsk's stack which we + * can plausibly erase. + */ +static __always_inline unsigned long +stackleak_task_high_bound(const struct task_struct *tsk) +{ + /* + * The task's pt_regs lives at the top of the task stack and will be + * overwritten by exception entry, so there's no need to erase them. + */ + return (unsigned long)task_pt_regs(tsk); +} + static inline void stackleak_task_init(struct task_struct *t) { t->lowest_stack = stackleak_task_low_bound(t); -- cgit v1.2.3 From 77cf2b6dee6680536a3109d894f1b1ccda3fc5bf Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 27 Apr 2022 18:31:22 +0100 Subject: stackleak: rework poison scanning Currently we over-estimate the region of stack which must be erased. To determine the region to be erased, we scan downwards for a contiguous block of poison values (or the low bound of the stack). There are a few minor problems with this today: * When we find a block of poison values, we include this block within the region to erase. As this is included within the region to erase, this causes us to redundantly overwrite 'STACKLEAK_SEARCH_DEPTH' (128) bytes with poison. * As the loop condition checks 'poison_count <= depth', it will run an additional iteration after finding the contiguous block of poison, decrementing 'erase_low' once more than necessary. As this is included within the region to erase, this causes us to redundantly overwrite an additional unsigned long with poison. * As we always decrement 'erase_low' after checking an element on the stack, we always include the element below this within the region to erase. As this is included within the region to erase, this causes us to redundantly overwrite an additional unsigned long with poison. Note that this is not a functional problem. As the loop condition checks 'erase_low > task_stack_low', we'll never clobber the STACK_END_MAGIC. As we always decrement 'erase_low' after this, we'll never fail to erase the element immediately above the STACK_END_MAGIC. In total, this can cause us to erase `128 + 2 * sizeof(unsigned long)` bytes more than necessary, which is unfortunate. This patch reworks the logic to find the address immediately above the poisoned region, by finding the lowest non-poisoned address. This is factored into a stackleak_find_top_of_poison() helper both for clarity and so that this can be shared with the LKDTM test in subsequent patches. Signed-off-by: Mark Rutland Cc: Alexander Popov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220427173128.2603085-8-mark.rutland@arm.com --- include/linux/stackleak.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 467661aeb413..c36e7a3b45e7 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -42,6 +42,32 @@ stackleak_task_high_bound(const struct task_struct *tsk) return (unsigned long)task_pt_regs(tsk); } +/* + * Find the address immediately above the poisoned region of the stack, where + * that region falls between 'low' (inclusive) and 'high' (exclusive). + */ +static __always_inline unsigned long +stackleak_find_top_of_poison(const unsigned long low, const unsigned long high) +{ + const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + unsigned int poison_count = 0; + unsigned long poison_high = high; + unsigned long sp = high; + + while (sp > low && poison_count < depth) { + sp -= sizeof(unsigned long); + + if (*(unsigned long *)sp == STACKLEAK_POISON) { + poison_count++; + } else { + poison_count = 0; + poison_high = sp; + } + } + + return poison_high; +} + static inline void stackleak_task_init(struct task_struct *t) { t->lowest_stack = stackleak_task_low_bound(t); -- cgit v1.2.3 From 1d6866e8f15c978e82ef16ce6d21ee96b2eca7ee Mon Sep 17 00:00:00 2001 From: Runyang Chen Date: Tue, 1 Mar 2022 13:37:32 +0800 Subject: dt-bindings: reset: mt8186: add reset-controller header file 1. Add toprgu reset-controller header file for MT8186. 2. Add DSI software reset bit which is controlled in MMSYS for MT8186. Signed-off-by: Runyang Chen Signed-off-by: Rex-BC Chen Acked-by: Rob Herring Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20220301054405.25021-3-rex-bc.chen@mediatek.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/dt-bindings/reset/mt8186-resets.h | 36 +++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 include/dt-bindings/reset/mt8186-resets.h (limited to 'include') diff --git a/include/dt-bindings/reset/mt8186-resets.h b/include/dt-bindings/reset/mt8186-resets.h new file mode 100644 index 000000000000..5f850370c42c --- /dev/null +++ b/include/dt-bindings/reset/mt8186-resets.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Runyang Chen + */ + +#ifndef _DT_BINDINGS_RESET_CONTROLLER_MT8186 +#define _DT_BINDINGS_RESET_CONTROLLER_MT8186 + +#define MT8186_TOPRGU_INFRA_SW_RST 0 +#define MT8186_TOPRGU_MM_SW_RST 1 +#define MT8186_TOPRGU_MFG_SW_RST 2 +#define MT8186_TOPRGU_VENC_SW_RST 3 +#define MT8186_TOPRGU_VDEC_SW_RST 4 +#define MT8186_TOPRGU_IMG_SW_RST 5 +#define MT8186_TOPRGU_DDR_SW_RST 6 +#define MT8186_TOPRGU_INFRA_AO_SW_RST 8 +#define MT8186_TOPRGU_CONNSYS_SW_RST 9 +#define MT8186_TOPRGU_APMIXED_SW_RST 10 +#define MT8186_TOPRGU_PWRAP_SW_RST 11 +#define MT8186_TOPRGU_CONN_MCU_SW_RST 12 +#define MT8186_TOPRGU_IPNNA_SW_RST 13 +#define MT8186_TOPRGU_WPE_SW_RST 14 +#define MT8186_TOPRGU_ADSP_SW_RST 15 +#define MT8186_TOPRGU_AUDIO_SW_RST 17 +#define MT8186_TOPRGU_CAM_MAIN_SW_RST 18 +#define MT8186_TOPRGU_CAM_RAWA_SW_RST 19 +#define MT8186_TOPRGU_CAM_RAWB_SW_RST 20 +#define MT8186_TOPRGU_IPE_SW_RST 21 +#define MT8186_TOPRGU_IMG2_SW_RST 22 +#define MT8186_TOPRGU_SW_RST_NUM 23 + +/* MMSYS resets */ +#define MT8186_MMSYS_SW0_RST_B_DISP_DSI0 19 + +#endif /* _DT_BINDINGS_RESET_CONTROLLER_MT8186 */ -- cgit v1.2.3 From 5794dda109fc870fce48a8cdf580750b40bf9d15 Mon Sep 17 00:00:00 2001 From: Sam Shih Date: Wed, 5 Jan 2022 18:04:55 +0800 Subject: dt-bindings: reset: mt7986: Add reset-controller header file Add infracfg, toprgu, and ethsys reset-controller header file for MT7986 platform. Signed-off-by: Sam Shih Acked-by: Rob Herring Acked-by: Guenter Roeck Link: https://lore.kernel.org/r/20220105100456.7126-2-sam.shih@mediatek.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/dt-bindings/reset/mt7986-resets.h | 55 +++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 include/dt-bindings/reset/mt7986-resets.h (limited to 'include') diff --git a/include/dt-bindings/reset/mt7986-resets.h b/include/dt-bindings/reset/mt7986-resets.h new file mode 100644 index 000000000000..af3d16c81192 --- /dev/null +++ b/include/dt-bindings/reset/mt7986-resets.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Sam Shih + */ + +#ifndef _DT_BINDINGS_RESET_CONTROLLER_MT7986 +#define _DT_BINDINGS_RESET_CONTROLLER_MT7986 + +/* INFRACFG resets */ +#define MT7986_INFRACFG_PEXTP_MAC_SW_RST 6 +#define MT7986_INFRACFG_SSUSB_SW_RST 7 +#define MT7986_INFRACFG_EIP97_SW_RST 8 +#define MT7986_INFRACFG_AUDIO_SW_RST 13 +#define MT7986_INFRACFG_CQ_DMA_SW_RST 14 + +#define MT7986_INFRACFG_TRNG_SW_RST 17 +#define MT7986_INFRACFG_AP_DMA_SW_RST 32 +#define MT7986_INFRACFG_I2C_SW_RST 33 +#define MT7986_INFRACFG_NFI_SW_RST 34 +#define MT7986_INFRACFG_SPI0_SW_RST 35 +#define MT7986_INFRACFG_SPI1_SW_RST 36 +#define MT7986_INFRACFG_UART0_SW_RST 37 +#define MT7986_INFRACFG_UART1_SW_RST 38 +#define MT7986_INFRACFG_UART2_SW_RST 39 +#define MT7986_INFRACFG_AUXADC_SW_RST 43 + +#define MT7986_INFRACFG_APXGPT_SW_RST 66 +#define MT7986_INFRACFG_PWM_SW_RST 68 + +#define MT7986_INFRACFG_SW_RST_NUM 69 + +/* TOPRGU resets */ +#define MT7986_TOPRGU_APMIXEDSYS_SW_RST 0 +#define MT7986_TOPRGU_SGMII0_SW_RST 1 +#define MT7986_TOPRGU_SGMII1_SW_RST 2 +#define MT7986_TOPRGU_INFRA_SW_RST 3 +#define MT7986_TOPRGU_U2PHY_SW_RST 5 +#define MT7986_TOPRGU_PCIE_SW_RST 6 +#define MT7986_TOPRGU_SSUSB_SW_RST 7 +#define MT7986_TOPRGU_ETHDMA_SW_RST 20 +#define MT7986_TOPRGU_CONSYS_SW_RST 23 + +#define MT7986_TOPRGU_SW_RST_NUM 24 + +/* ETHSYS Subsystem resets */ +#define MT7986_ETHSYS_FE_SW_RST 6 +#define MT7986_ETHSYS_PMTR_SW_RST 8 +#define MT7986_ETHSYS_GMAC_SW_RST 23 +#define MT7986_ETHSYS_PPE0_SW_RST 30 +#define MT7986_ETHSYS_PPE1_SW_RST 31 + +#define MT7986_ETHSYS_SW_RST_NUM 32 + +#endif /* _DT_BINDINGS_RESET_CONTROLLER_MT7986 */ -- cgit v1.2.3 From 2e3afb42dd480d755cd7d97ca04586a5616c1a5e Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Sun, 8 May 2022 11:37:09 +0200 Subject: blk-mq: remove the error_count from struct request The last two users were floppy.c and ataflop.c respectively, it was verified that no other drivers makes use of this, so let's remove it. Suggested-by: Linus Torvalds Cc: Minh Yuan Cc: Denis Efremov , Cc: Geert Uytterhoeven Cc: Christoph Hellwig Signed-off-by: Willy Tarreau Signed-off-by: Linus Torvalds --- include/linux/blk-mq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 7aa5c54901a9..9f07061418db 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -163,7 +163,6 @@ struct request { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; - int error_count; /* for legacy drivers, don't use */ }; -- cgit v1.2.3 From 56f5746c414d92ae8e8314f46760822b4ecf8be3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 09:40:54 -0500 Subject: namei: Merge page_symlink() and __page_symlink() There are no callers of __page_symlink() left, so we can remove that entry point. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Christian Brauner --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..e108aff23a28 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3109,8 +3109,6 @@ extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); -extern int __page_symlink(struct inode *inode, const char *symname, int len, - int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); -- cgit v1.2.3 From 236d93c4bf2d6da83241cc8e4625e89d9604cb43 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 10:40:11 -0500 Subject: fs: Remove AOP_FLAG_NOFS With all users of this flag gone, we can stop testing whether it's set. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/fs.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index e108aff23a28..f81bc5cbcbb6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -275,10 +275,6 @@ enum positive_aop_returns { AOP_TRUNCATED_PAGE = 0x80001, }; -#define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct - * helper code (eg buffer layer) - * to clear GFP_FS from alloc */ - /* * oh the beauties of C type declarations. */ -- cgit v1.2.3 From de2a931150177957d37e9c975025604f4a1fe853 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 10:47:09 -0500 Subject: fs: Remove aop_flags parameter from netfs_write_begin() There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/netfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c7bf1eaf51d5..1c29f317d907 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -276,7 +276,7 @@ struct readahead_control; extern void netfs_readahead(struct readahead_control *); extern int netfs_readpage(struct file *, struct page *); extern int netfs_write_begin(struct file *, struct address_space *, - loff_t, unsigned int, unsigned int, struct folio **, + loff_t, unsigned int, struct folio **, void **); extern void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); -- cgit v1.2.3 From b3992d1e2ebcd478e0614494a6abd95e902a029b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 11:25:12 -0500 Subject: fs: Remove aop flags parameter from block_write_begin() There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index bcb4fe9b8575..63e49dfa7738 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -226,7 +226,7 @@ int __block_write_full_page(struct inode *inode, struct page *page, int block_read_full_page(struct page*, get_block_t*); bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, - unsigned flags, struct page **pagep, get_block_t *get_block); + struct page **pagep, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, -- cgit v1.2.3 From be3bbbc588118bdc10e21fdd7bfa6ee6b8c2555d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 11:25:12 -0500 Subject: fs: Remove aop flags parameter from cont_write_begin() There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 63e49dfa7738..127b60fad77e 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -238,7 +238,7 @@ int generic_write_end(struct file *, struct address_space *, void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, - unsigned, unsigned, struct page **, void **, + unsigned, struct page **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); -- cgit v1.2.3 From b7446e7cf15f0926866c8e5de90ab278998bf8c8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 11:25:12 -0500 Subject: fs: Remove aop flags parameter from grab_cache_page_write_begin() There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/pagemap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 993994cd943a..65ae8f96554b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -735,7 +735,7 @@ static inline unsigned find_get_pages_tag(struct address_space *mapping, } struct page *grab_cache_page_write_begin(struct address_space *mapping, - pgoff_t index, unsigned flags); + pgoff_t index); /* * Returns locked page at given index in given cache, creating it if needed. -- cgit v1.2.3 From 8371f30cf774a20fd627a0f7b1ecf00e8257f3bc Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 11:54:56 -0500 Subject: fs: Remove aop flags parameter from nobh_write_begin() There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 127b60fad77e..6e5a64005fef 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -258,7 +258,7 @@ static inline vm_fault_t block_page_mkwrite_return(int err) } sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); -int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned, +int nobh_write_begin(struct address_space *, loff_t, unsigned len, struct page **, void **, get_block_t*); int nobh_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, -- cgit v1.2.3 From 9d6b0cd7579844761ed68926eb3073bab1dca87b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 14:31:43 -0500 Subject: fs: Remove flags parameter from aops->write_begin There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/fs.h | 4 ++-- include/trace/events/ext4.h | 21 ++++++++------------- include/trace/events/f2fs.h | 12 ++++-------- 3 files changed, 14 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index f81bc5cbcbb6..a0e73432526f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -346,7 +346,7 @@ struct address_space_operations { void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, @@ -3179,7 +3179,7 @@ extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index d06ffffad434..229e8fae66a3 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -335,17 +335,15 @@ TRACE_EVENT(ext4_begin_ordered_truncate, DECLARE_EVENT_CLASS(ext4__write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags), + TP_ARGS(inode, pos, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) - __field( unsigned int, flags ) ), TP_fast_assign( @@ -353,29 +351,26 @@ DECLARE_EVENT_CLASS(ext4__write_begin, __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; - __entry->flags = flags; ), - TP_printk("dev %d,%d ino %lu pos %lld len %u flags %u", + TP_printk("dev %d,%d ino %lu pos %lld len %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->pos, __entry->len, __entry->flags) + __entry->pos, __entry->len) ); DEFINE_EVENT(ext4__write_begin, ext4_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags) + TP_ARGS(inode, pos, len) ); DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags) + TP_ARGS(inode, pos, len) ); DECLARE_EVENT_CLASS(ext4__write_end, diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 1779e133cea0..bea654a85e6b 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -1159,17 +1159,15 @@ DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_submit_write_bio, TRACE_EVENT(f2fs_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags), + TP_ARGS(inode, pos, len), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, pos) __field(unsigned int, len) - __field(unsigned int, flags) ), TP_fast_assign( @@ -1177,14 +1175,12 @@ TRACE_EVENT(f2fs_write_begin, __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; - __entry->flags = flags; ), - TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u, flags = %u", + TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u", show_dev_ino(__entry), (unsigned long long)__entry->pos, - __entry->len, - __entry->flags) + __entry->len) ); TRACE_EVENT(f2fs_write_end, -- cgit v1.2.3 From defec178df76e0caadd4e8ef68f3d655a2088198 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 5 Apr 2022 18:48:41 -0700 Subject: soc: rockchip: power-domain: Manage resource conflicts with firmware On RK3399 platforms, power domains are managed mostly by the kernel (drivers/soc/rockchip/pm_domains.c), but there are a few exceptions where ARM Trusted Firmware has to be involved: (1) system suspend/resume (2) DRAM DVFS (a.k.a., "ddrfreq") Exception (1) does not cause much conflict, since the kernel has quiesced itself by the time we make the relevant PSCI call. Exception (2) can cause conflict, because of two actions: (a) ARM Trusted Firmware needs to read/modify/write the PMU_BUS_IDLE_REQ register to idle the memory controller domain; the kernel driver also has to touch this register for other domains. (b) ARM Trusted Firmware needs to manage the clocks associated with these domains. To elaborate on (b): idling a power domain has always required ungating an array of clocks; see this old explanation from Rockchip: https://lore.kernel.org/linux-arm-kernel/54503C19.9060607@rock-chips.com/ Historically, ARM Trusted Firmware has avoided this issue by using a special PMU_CRU_GATEDIS_CON0 register -- this register ungates all the necessary clocks -- when idling the memory controller. Unfortunately, we've found that this register is not 100% sufficient; it does not turn the relevant PLLs on [0]. So it's possible to trigger issues with something like the following: 1. enable a power domain (e.g., RK3399_PD_VDU) -- kernel will temporarily enable relevant clocks/PLLs, then turn them back off 2. a PLL (e.g., PLL_NPLL) is part of the clock tree for RK3399_PD_VDU's clocks but otherwise unused; NPLL is disabled 3. perform a ddrfreq transition (rk3399_dmcfreq_target() -> ... drivers/clk/rockchip/clk-ddr.c / ROCKCHIP_SIP_DRAM_FREQ) 4. ARM Trusted Firmware unagates VDU clocks (via PMU_CRU_GATEDIS_CON0) 5. ARM Trusted firmware idles the memory controller domain 6. Step 5 waits on the VDU domain/clocks, but NPLL is still off i.e., we hang the system. So for (b), we need to at a minimum manage the relevant PLLs on behalf of firmware. It's easier to simply manage the whole clock tree, in a similar way we do in rockchip_pd_power(). For (a), we need to provide mutual exclusion betwen rockchip_pd_power() and firmware. To resolve that, we simply grab the PMU mutex and release it when ddrfreq is done. The Chromium OS kernel has been carrying versions of part of this hack for a while, based on some new custom notifiers [1]. I've rewritten as a simple function call between the drivers, which is OK because: * the PMU driver isn't enabled, and we don't have this problem at all (the firmware should have left us in an OK state, and there are no runtime conflicts); or * the PMU driver is present, and is a single instance. And the power-domain driver cannot be removed, so there's no lifetime management to worry about. For completeness, there's a 'dmc_pmu_mutex' to guard (likely theoretical?) probe()-time races. It's OK for the memory controller driver to start running before the PMU, because the PMU will avoid any critical actions during the block() sequence. [0] The RK3399 TRM for PMU_CRU_GATEDIS_CON0 only talks about ungating clocks. Based on experimentation, we've found that it does not power up the necessary PLLs. [1] CHROMIUM: soc: rockchip: power-domain: Add notifier to dmc driver https://chromium-review.googlesource.com/q/I242dbd706d352f74ff706f5cbf42ebb92f9bcc60 Notably, the Chromium solution only handled conflict (a), not (b). In practice, item (b) wasn't a problem in many cases because we never managed to fully power off PLLs. Now that the (upstream) video decoder driver performs runtime clock management, we often power off NPLL. Signed-off-by: Brian Norris Tested-by: Peter Geis Reviewed-by: Heiko Stuebner Signed-off-by: Chanwoo Choi --- include/soc/rockchip/pm_domains.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/soc/rockchip/pm_domains.h (limited to 'include') diff --git a/include/soc/rockchip/pm_domains.h b/include/soc/rockchip/pm_domains.h new file mode 100644 index 000000000000..7dbd941fc937 --- /dev/null +++ b/include/soc/rockchip/pm_domains.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2022, The Chromium OS Authors. All rights reserved. + */ + +#ifndef __SOC_ROCKCHIP_PM_DOMAINS_H__ +#define __SOC_ROCKCHIP_PM_DOMAINS_H__ + +#ifdef CONFIG_ROCKCHIP_PM_DOMAINS + +int rockchip_pmu_block(void); +void rockchip_pmu_unblock(void); + +#else /* CONFIG_ROCKCHIP_PM_DOMAINS */ + +static inline int rockchip_pmu_block(void) +{ + return 0; +} + +static inline void rockchip_pmu_unblock(void) { } + +#endif /* CONFIG_ROCKCHIP_PM_DOMAINS */ + +#endif /* __SOC_ROCKCHIP_PM_DOMAINS_H__ */ -- cgit v1.2.3 From 84a1041c60ff8f648a09d28af7b2e50a8f6345ed Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 3 Mar 2022 15:00:20 -0500 Subject: fs: Remove pagecache_write_begin() and pagecache_write_end() These wrappers have no more users; remove them. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/fs.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index a0e73432526f..b35ce086a7a1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -380,18 +380,6 @@ struct address_space_operations { extern const struct address_space_operations empty_aops; -/* - * pagecache_write_begin/pagecache_write_end must be used by general code - * to write into the pagecache. - */ -int pagecache_write_begin(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata); - -int pagecache_write_end(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); - /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. -- cgit v1.2.3 From 65aa6b5a18294b3713a90c120312ed5d63a16b82 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Mon, 4 Apr 2022 11:38:20 -0400 Subject: filemap: Remove obsolete comment in lock_page We no longer need the page's inode pinned. This comment dates back to commit db37648cd6ce ("[PATCH] mm: non syncing lock_page()") which added lock_page_nosync(). That was removed by commit 7eaceaccab5f ("block: remove per-queue plugging") which also made this comment obsolete. Signed-off-by: Miaohe Lin Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/pagemap.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 65ae8f96554b..ab47579af434 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -908,9 +908,6 @@ static inline void folio_lock(struct folio *folio) __folio_lock(folio); } -/* - * lock_page may only be called if we have the page's inode pinned. - */ static inline void lock_page(struct page *page) { struct folio *folio; -- cgit v1.2.3 From cd125eeab2de8ef8ca3a0f3a284bc695375c73af Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 4 Apr 2022 13:24:36 -0400 Subject: filemap: Update the folio_lock documentation Add kernel-doc for several functions relating to take the folio lock. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/pagemap.h | 59 +++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 57 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ab47579af434..60657132080f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -888,6 +888,18 @@ bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, void unlock_page(struct page *page); void folio_unlock(struct folio *folio); +/** + * folio_trylock() - Attempt to lock a folio. + * @folio: The folio to attempt to lock. + * + * Sometimes it is undesirable to wait for a folio to be unlocked (eg + * when the locks are being taken in the wrong order, or if making + * progress through a batch of folios is more important than processing + * them in order). Usually folio_lock() is the correct function to call. + * + * Context: Any context. + * Return: Whether the lock was successfully acquired. + */ static inline bool folio_trylock(struct folio *folio) { return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0))); @@ -901,6 +913,28 @@ static inline int trylock_page(struct page *page) return folio_trylock(page_folio(page)); } +/** + * folio_lock() - Lock this folio. + * @folio: The folio to lock. + * + * The folio lock protects against many things, probably more than it + * should. It is primarily held while a folio is being brought uptodate, + * either from its backing file or from swap. It is also held while a + * folio is being truncated from its address_space, so holding the lock + * is sufficient to keep folio->mapping stable. + * + * The folio lock is also held while write() is modifying the page to + * provide POSIX atomicity guarantees (as long as the write does not + * cross a page boundary). Other modifications to the data in the folio + * do not hold the folio lock and can race with writes, eg DMA and stores + * to mapped pages. + * + * Context: May sleep. If you need to acquire the locks of two or + * more folios, they must be in order of ascending index, if they are + * in the same address_space. If they are in different address_spaces, + * acquire the lock of the folio which belongs to the address_space which + * has the lowest address in memory first. + */ static inline void folio_lock(struct folio *folio) { might_sleep(); @@ -908,6 +942,17 @@ static inline void folio_lock(struct folio *folio) __folio_lock(folio); } +/** + * lock_page() - Lock the folio containing this page. + * @page: The page to lock. + * + * See folio_lock() for a description of what the lock protects. + * This is a legacy function and new code should probably use folio_lock() + * instead. + * + * Context: May sleep. Pages in the same folio share a lock, so do not + * attempt to lock two pages which share a folio. + */ static inline void lock_page(struct page *page) { struct folio *folio; @@ -918,6 +963,16 @@ static inline void lock_page(struct page *page) __folio_lock(folio); } +/** + * folio_lock_killable() - Lock this folio, interruptible by a fatal signal. + * @folio: The folio to lock. + * + * Attempts to lock the folio, like folio_lock(), except that the sleep + * to acquire the lock is interruptible by a fatal signal. + * + * Context: May sleep; see folio_lock(). + * Return: 0 if the lock was acquired; -EINTR if a fatal signal was received. + */ static inline int folio_lock_killable(struct folio *folio) { might_sleep(); @@ -964,8 +1019,8 @@ int folio_wait_bit_killable(struct folio *folio, int bit_nr); * Wait for a folio to be unlocked. * * This must be called with the caller "holding" the folio, - * ie with increased "page->count" so that the folio won't - * go away during the wait.. + * ie with increased folio reference count so that the folio won't + * go away during the wait. */ static inline void folio_wait_locked(struct folio *folio) { -- cgit v1.2.3 From 520f301c54faa3484e820b80d4505d48ee587163 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 17 Jan 2022 14:35:22 -0500 Subject: fs: Convert is_dirty_writeback() to take a folio Pass a folio instead of a page to aops->is_dirty_writeback(). Convert both implementations and the caller. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/buffer_head.h | 2 +- include/linux/fs.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 6e5a64005fef..805c4e12700a 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -146,7 +146,7 @@ BUFFER_FNS(Defer_Completion, defer_completion) #define page_has_buffers(page) PagePrivate(page) #define folio_buffers(folio) folio_get_private(folio) -void buffer_check_dirty_writeback(struct page *page, +void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback); /* diff --git a/include/linux/fs.h b/include/linux/fs.h index b35ce086a7a1..2be852661a29 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -369,7 +369,7 @@ struct address_space_operations { int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); - void (*is_dirty_writeback) (struct page *, bool *, bool *); + void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_page)(struct address_space *, struct page *); /* swapfile support */ -- cgit v1.2.3 From 2ebdd1df316636c2faf25a1780e12553adf09cf7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 17 Mar 2021 22:38:26 -0400 Subject: mm/readahead: Convert page_cache_async_readahead to take a folio Removes a couple of calls to compound_head and saves a few bytes. Also convert verity's read_file_data_page() to be folio-based. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/pagemap.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 60657132080f..b70192f56454 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1242,7 +1242,7 @@ void page_cache_sync_readahead(struct address_space *mapping, * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. - * @page: The page at @index which triggered the readahead call. + * @folio: The folio at @index which triggered the readahead call. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * @@ -1254,10 +1254,10 @@ void page_cache_sync_readahead(struct address_space *mapping, static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, - struct page *page, pgoff_t index, unsigned long req_count) + struct folio *folio, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, index); - page_cache_async_ra(&ractl, page_folio(page), req_count); + page_cache_async_ra(&ractl, folio, req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) -- cgit v1.2.3 From 7b43e6d795623e23834dd528c36023f692468480 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Wed, 4 May 2022 17:12:34 +0100 Subject: ASoC: cs42l42: Move CS42L42 register descriptions to general include This is to allow the hda driver to have access to the register names, for improved maintainability. Also ensure new header is aligned to 100 columns. Signed-off-by: Stefan Binding Acked-by: Mark Brown Link: https://lore.kernel.org/r/20220504161236.2490532-2-sbinding@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs42l42.h | 810 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 810 insertions(+) create mode 100644 include/sound/cs42l42.h (limited to 'include') diff --git a/include/sound/cs42l42.h b/include/sound/cs42l42.h new file mode 100644 index 000000000000..a55d522f1772 --- /dev/null +++ b/include/sound/cs42l42.h @@ -0,0 +1,810 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/sound/cs42l42.h -- Platform data for CS42L42 ALSA SoC audio driver header + * + * Copyright 2016-2022 Cirrus Logic, Inc. + * + * Author: James Schulman + * Author: Brian Austin + * Author: Michael White + */ + +#ifndef __CS42L42_H +#define __CS42L42_H + +#define CS42L42_PAGE_REGISTER 0x00 /* Page Select Register */ +#define CS42L42_WIN_START 0x00 +#define CS42L42_WIN_LEN 0x100 +#define CS42L42_RANGE_MIN 0x00 +#define CS42L42_RANGE_MAX 0x7F + +#define CS42L42_PAGE_10 0x1000 +#define CS42L42_PAGE_11 0x1100 +#define CS42L42_PAGE_12 0x1200 +#define CS42L42_PAGE_13 0x1300 +#define CS42L42_PAGE_15 0x1500 +#define CS42L42_PAGE_19 0x1900 +#define CS42L42_PAGE_1B 0x1B00 +#define CS42L42_PAGE_1C 0x1C00 +#define CS42L42_PAGE_1D 0x1D00 +#define CS42L42_PAGE_1F 0x1F00 +#define CS42L42_PAGE_20 0x2000 +#define CS42L42_PAGE_21 0x2100 +#define CS42L42_PAGE_23 0x2300 +#define CS42L42_PAGE_24 0x2400 +#define CS42L42_PAGE_25 0x2500 +#define CS42L42_PAGE_26 0x2600 +#define CS42L42_PAGE_28 0x2800 +#define CS42L42_PAGE_29 0x2900 +#define CS42L42_PAGE_2A 0x2A00 +#define CS42L42_PAGE_30 0x3000 + +#define CS42L42_CHIP_ID 0x42A42 + +/* Page 0x10 Global Registers */ +#define CS42L42_DEVID_AB (CS42L42_PAGE_10 + 0x01) +#define CS42L42_DEVID_CD (CS42L42_PAGE_10 + 0x02) +#define CS42L42_DEVID_E (CS42L42_PAGE_10 + 0x03) +#define CS42L42_FABID (CS42L42_PAGE_10 + 0x04) +#define CS42L42_REVID (CS42L42_PAGE_10 + 0x05) +#define CS42L42_FRZ_CTL (CS42L42_PAGE_10 + 0x06) + +#define CS42L42_SRC_CTL (CS42L42_PAGE_10 + 0x07) +#define CS42L42_SRC_BYPASS_DAC_SHIFT 1 +#define CS42L42_SRC_BYPASS_DAC_MASK (1 << CS42L42_SRC_BYPASS_DAC_SHIFT) + +#define CS42L42_MCLK_STATUS (CS42L42_PAGE_10 + 0x08) + +#define CS42L42_MCLK_CTL (CS42L42_PAGE_10 + 0x09) +#define CS42L42_INTERNAL_FS_SHIFT 1 +#define CS42L42_INTERNAL_FS_MASK (1 << CS42L42_INTERNAL_FS_SHIFT) + +#define CS42L42_SFTRAMP_RATE (CS42L42_PAGE_10 + 0x0A) +#define CS42L42_SLOW_START_ENABLE (CS42L42_PAGE_10 + 0x0B) +#define CS42L42_SLOW_START_EN_MASK GENMASK(6, 4) +#define CS42L42_SLOW_START_EN_SHIFT 4 +#define CS42L42_I2C_DEBOUNCE (CS42L42_PAGE_10 + 0x0E) +#define CS42L42_I2C_STRETCH (CS42L42_PAGE_10 + 0x0F) +#define CS42L42_I2C_TIMEOUT (CS42L42_PAGE_10 + 0x10) + +/* Page 0x11 Power and Headset Detect Registers */ +#define CS42L42_PWR_CTL1 (CS42L42_PAGE_11 + 0x01) +#define CS42L42_ASP_DAO_PDN_SHIFT 7 +#define CS42L42_ASP_DAO_PDN_MASK (1 << CS42L42_ASP_DAO_PDN_SHIFT) +#define CS42L42_ASP_DAI_PDN_SHIFT 6 +#define CS42L42_ASP_DAI_PDN_MASK (1 << CS42L42_ASP_DAI_PDN_SHIFT) +#define CS42L42_MIXER_PDN_SHIFT 5 +#define CS42L42_MIXER_PDN_MASK (1 << CS42L42_MIXER_PDN_SHIFT) +#define CS42L42_EQ_PDN_SHIFT 4 +#define CS42L42_EQ_PDN_MASK (1 << CS42L42_EQ_PDN_SHIFT) +#define CS42L42_HP_PDN_SHIFT 3 +#define CS42L42_HP_PDN_MASK (1 << CS42L42_HP_PDN_SHIFT) +#define CS42L42_ADC_PDN_SHIFT 2 +#define CS42L42_ADC_PDN_MASK (1 << CS42L42_ADC_PDN_SHIFT) +#define CS42L42_PDN_ALL_SHIFT 0 +#define CS42L42_PDN_ALL_MASK (1 << CS42L42_PDN_ALL_SHIFT) + +#define CS42L42_PWR_CTL2 (CS42L42_PAGE_11 + 0x02) +#define CS42L42_ADC_SRC_PDNB_SHIFT 0 +#define CS42L42_ADC_SRC_PDNB_MASK (1 << CS42L42_ADC_SRC_PDNB_SHIFT) +#define CS42L42_DAC_SRC_PDNB_SHIFT 1 +#define CS42L42_DAC_SRC_PDNB_MASK (1 << CS42L42_DAC_SRC_PDNB_SHIFT) +#define CS42L42_ASP_DAI1_PDN_SHIFT 2 +#define CS42L42_ASP_DAI1_PDN_MASK (1 << CS42L42_ASP_DAI1_PDN_SHIFT) +#define CS42L42_SRC_PDN_OVERRIDE_SHIFT 3 +#define CS42L42_SRC_PDN_OVERRIDE_MASK (1 << CS42L42_SRC_PDN_OVERRIDE_SHIFT) +#define CS42L42_DISCHARGE_FILT_SHIFT 4 +#define CS42L42_DISCHARGE_FILT_MASK (1 << CS42L42_DISCHARGE_FILT_SHIFT) + +#define CS42L42_PWR_CTL3 (CS42L42_PAGE_11 + 0x03) +#define CS42L42_RING_SENSE_PDNB_SHIFT 1 +#define CS42L42_RING_SENSE_PDNB_MASK (1 << CS42L42_RING_SENSE_PDNB_SHIFT) +#define CS42L42_VPMON_PDNB_SHIFT 2 +#define CS42L42_VPMON_PDNB_MASK (1 << CS42L42_VPMON_PDNB_SHIFT) +#define CS42L42_SW_CLK_STP_STAT_SEL_SHIFT 5 +#define CS42L42_SW_CLK_STP_STAT_SEL_MASK (3 << CS42L42_SW_CLK_STP_STAT_SEL_SHIFT) + +#define CS42L42_RSENSE_CTL1 (CS42L42_PAGE_11 + 0x04) +#define CS42L42_RS_TRIM_R_SHIFT 0 +#define CS42L42_RS_TRIM_R_MASK (1 << CS42L42_RS_TRIM_R_SHIFT) +#define CS42L42_RS_TRIM_T_SHIFT 1 +#define CS42L42_RS_TRIM_T_MASK (1 << CS42L42_RS_TRIM_T_SHIFT) +#define CS42L42_HPREF_RS_SHIFT 2 +#define CS42L42_HPREF_RS_MASK (1 << CS42L42_HPREF_RS_SHIFT) +#define CS42L42_HSBIAS_FILT_REF_RS_SHIFT 3 +#define CS42L42_HSBIAS_FILT_REF_RS_MASK (1 << CS42L42_HSBIAS_FILT_REF_RS_SHIFT) +#define CS42L42_RING_SENSE_PU_HIZ_SHIFT 6 +#define CS42L42_RING_SENSE_PU_HIZ_MASK (1 << CS42L42_RING_SENSE_PU_HIZ_SHIFT) + +#define CS42L42_RSENSE_CTL2 (CS42L42_PAGE_11 + 0x05) +#define CS42L42_TS_RS_GATE_SHIFT 7 +#define CS42L42_TS_RS_GATE_MAS (1 << CS42L42_TS_RS_GATE_SHIFT) + +#define CS42L42_OSC_SWITCH (CS42L42_PAGE_11 + 0x07) +#define CS42L42_SCLK_PRESENT_SHIFT 0 +#define CS42L42_SCLK_PRESENT_MASK (1 << CS42L42_SCLK_PRESENT_SHIFT) + +#define CS42L42_OSC_SWITCH_STATUS (CS42L42_PAGE_11 + 0x09) +#define CS42L42_OSC_SW_SEL_STAT_SHIFT 0 +#define CS42L42_OSC_SW_SEL_STAT_MASK (3 << CS42L42_OSC_SW_SEL_STAT_SHIFT) +#define CS42L42_OSC_PDNB_STAT_SHIFT 2 +#define CS42L42_OSC_PDNB_STAT_MASK (1 << CS42L42_OSC_SW_SEL_STAT_SHIFT) + +#define CS42L42_RSENSE_CTL3 (CS42L42_PAGE_11 + 0x12) +#define CS42L42_RS_RISE_DBNCE_TIME_SHIFT 0 +#define CS42L42_RS_RISE_DBNCE_TIME_MASK (7 << CS42L42_RS_RISE_DBNCE_TIME_SHIFT) +#define CS42L42_RS_FALL_DBNCE_TIME_SHIFT 3 +#define CS42L42_RS_FALL_DBNCE_TIME_MASK (7 << CS42L42_RS_FALL_DBNCE_TIME_SHIFT) +#define CS42L42_RS_PU_EN_SHIFT 6 +#define CS42L42_RS_PU_EN_MASK (1 << CS42L42_RS_PU_EN_SHIFT) +#define CS42L42_RS_INV_SHIFT 7 +#define CS42L42_RS_INV_MASK (1 << CS42L42_RS_INV_SHIFT) + +#define CS42L42_TSENSE_CTL (CS42L42_PAGE_11 + 0x13) +#define CS42L42_TS_RISE_DBNCE_TIME_SHIFT 0 +#define CS42L42_TS_RISE_DBNCE_TIME_MASK (7 << CS42L42_TS_RISE_DBNCE_TIME_SHIFT) +#define CS42L42_TS_FALL_DBNCE_TIME_SHIFT 3 +#define CS42L42_TS_FALL_DBNCE_TIME_MASK (7 << CS42L42_TS_FALL_DBNCE_TIME_SHIFT) +#define CS42L42_TS_INV_SHIFT 7 +#define CS42L42_TS_INV_MASK (1 << CS42L42_TS_INV_SHIFT) + +#define CS42L42_TSRS_INT_DISABLE (CS42L42_PAGE_11 + 0x14) +#define CS42L42_D_RS_PLUG_DBNC_SHIFT 0 +#define CS42L42_D_RS_PLUG_DBNC_MASK (1 << CS42L42_D_RS_PLUG_DBNC_SHIFT) +#define CS42L42_D_RS_UNPLUG_DBNC_SHIFT 1 +#define CS42L42_D_RS_UNPLUG_DBNC_MASK (1 << CS42L42_D_RS_UNPLUG_DBNC_SHIFT) +#define CS42L42_D_TS_PLUG_DBNC_SHIFT 2 +#define CS42L42_D_TS_PLUG_DBNC_MASK (1 << CS42L42_D_TS_PLUG_DBNC_SHIFT) +#define CS42L42_D_TS_UNPLUG_DBNC_SHIFT 3 +#define CS42L42_D_TS_UNPLUG_DBNC_MASK (1 << CS42L42_D_TS_UNPLUG_DBNC_SHIFT) + +#define CS42L42_TRSENSE_STATUS (CS42L42_PAGE_11 + 0x15) +#define CS42L42_RS_PLUG_DBNC_SHIFT 0 +#define CS42L42_RS_PLUG_DBNC_MASK (1 << CS42L42_RS_PLUG_DBNC_SHIFT) +#define CS42L42_RS_UNPLUG_DBNC_SHIFT 1 +#define CS42L42_RS_UNPLUG_DBNC_MASK (1 << CS42L42_RS_UNPLUG_DBNC_SHIFT) +#define CS42L42_TS_PLUG_DBNC_SHIFT 2 +#define CS42L42_TS_PLUG_DBNC_MASK (1 << CS42L42_TS_PLUG_DBNC_SHIFT) +#define CS42L42_TS_UNPLUG_DBNC_SHIFT 3 +#define CS42L42_TS_UNPLUG_DBNC_MASK (1 << CS42L42_TS_UNPLUG_DBNC_SHIFT) + +#define CS42L42_HSDET_CTL1 (CS42L42_PAGE_11 + 0x1F) +#define CS42L42_HSDET_COMP1_LVL_SHIFT 0 +#define CS42L42_HSDET_COMP1_LVL_MASK (15 << CS42L42_HSDET_COMP1_LVL_SHIFT) +#define CS42L42_HSDET_COMP2_LVL_SHIFT 4 +#define CS42L42_HSDET_COMP2_LVL_MASK (15 << CS42L42_HSDET_COMP2_LVL_SHIFT) + +#define CS42L42_HSDET_COMP1_LVL_VAL 12 /* 1.25V Comparator */ +#define CS42L42_HSDET_COMP2_LVL_VAL 2 /* 1.75V Comparator */ +#define CS42L42_HSDET_COMP1_LVL_DEFAULT 7 /* 1V Comparator */ +#define CS42L42_HSDET_COMP2_LVL_DEFAULT 7 /* 2V Comparator */ + +#define CS42L42_HSDET_CTL2 (CS42L42_PAGE_11 + 0x20) +#define CS42L42_HSDET_AUTO_TIME_SHIFT 0 +#define CS42L42_HSDET_AUTO_TIME_MASK (3 << CS42L42_HSDET_AUTO_TIME_SHIFT) +#define CS42L42_HSBIAS_REF_SHIFT 3 +#define CS42L42_HSBIAS_REF_MASK (1 << CS42L42_HSBIAS_REF_SHIFT) +#define CS42L42_HSDET_SET_SHIFT 4 +#define CS42L42_HSDET_SET_MASK (3 << CS42L42_HSDET_SET_SHIFT) +#define CS42L42_HSDET_CTRL_SHIFT 6 +#define CS42L42_HSDET_CTRL_MASK (3 << CS42L42_HSDET_CTRL_SHIFT) + +#define CS42L42_HS_SWITCH_CTL (CS42L42_PAGE_11 + 0x21) +#define CS42L42_SW_GNDHS_HS4_SHIFT 0 +#define CS42L42_SW_GNDHS_HS4_MASK (1 << CS42L42_SW_GNDHS_HS4_SHIFT) +#define CS42L42_SW_GNDHS_HS3_SHIFT 1 +#define CS42L42_SW_GNDHS_HS3_MASK (1 << CS42L42_SW_GNDHS_HS3_SHIFT) +#define CS42L42_SW_HSB_HS4_SHIFT 2 +#define CS42L42_SW_HSB_HS4_MASK (1 << CS42L42_SW_HSB_HS4_SHIFT) +#define CS42L42_SW_HSB_HS3_SHIFT 3 +#define CS42L42_SW_HSB_HS3_MASK (1 << CS42L42_SW_HSB_HS3_SHIFT) +#define CS42L42_SW_HSB_FILT_HS4_SHIFT 4 +#define CS42L42_SW_HSB_FILT_HS4_MASK (1 << CS42L42_SW_HSB_FILT_HS4_SHIFT) +#define CS42L42_SW_HSB_FILT_HS3_SHIFT 5 +#define CS42L42_SW_HSB_FILT_HS3_MASK (1 << CS42L42_SW_HSB_FILT_HS3_SHIFT) +#define CS42L42_SW_REF_HS4_SHIFT 6 +#define CS42L42_SW_REF_HS4_MASK (1 << CS42L42_SW_REF_HS4_SHIFT) +#define CS42L42_SW_REF_HS3_SHIFT 7 +#define CS42L42_SW_REF_HS3_MASK (1 << CS42L42_SW_REF_HS3_SHIFT) + +#define CS42L42_HS_DET_STATUS (CS42L42_PAGE_11 + 0x24) +#define CS42L42_HSDET_TYPE_SHIFT 0 +#define CS42L42_HSDET_TYPE_MASK (3 << CS42L42_HSDET_TYPE_SHIFT) +#define CS42L42_HSDET_COMP1_OUT_SHIFT 6 +#define CS42L42_HSDET_COMP1_OUT_MASK (1 << CS42L42_HSDET_COMP1_OUT_SHIFT) +#define CS42L42_HSDET_COMP2_OUT_SHIFT 7 +#define CS42L42_HSDET_COMP2_OUT_MASK (1 << CS42L42_HSDET_COMP2_OUT_SHIFT) +#define CS42L42_PLUG_CTIA 0 +#define CS42L42_PLUG_OMTP 1 +#define CS42L42_PLUG_HEADPHONE 2 +#define CS42L42_PLUG_INVALID 3 + +#define CS42L42_HSDET_SW_COMP1 ((0 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (1 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (0 << CS42L42_SW_REF_HS4_SHIFT) | \ + (1 << CS42L42_SW_REF_HS3_SHIFT)) +#define CS42L42_HSDET_SW_COMP2 ((1 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (0 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (1 << CS42L42_SW_REF_HS4_SHIFT) | \ + (0 << CS42L42_SW_REF_HS3_SHIFT)) +#define CS42L42_HSDET_SW_TYPE1 ((0 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (1 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (0 << CS42L42_SW_REF_HS4_SHIFT) | \ + (1 << CS42L42_SW_REF_HS3_SHIFT)) +#define CS42L42_HSDET_SW_TYPE2 ((1 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (0 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (1 << CS42L42_SW_REF_HS4_SHIFT) | \ + (0 << CS42L42_SW_REF_HS3_SHIFT)) +#define CS42L42_HSDET_SW_TYPE3 ((1 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (1 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (1 << CS42L42_SW_REF_HS4_SHIFT) | \ + (1 << CS42L42_SW_REF_HS3_SHIFT)) +#define CS42L42_HSDET_SW_TYPE4 ((0 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (1 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (0 << CS42L42_SW_REF_HS4_SHIFT) | \ + (1 << CS42L42_SW_REF_HS3_SHIFT)) + +#define CS42L42_HSDET_COMP_TYPE1 1 +#define CS42L42_HSDET_COMP_TYPE2 2 +#define CS42L42_HSDET_COMP_TYPE3 0 +#define CS42L42_HSDET_COMP_TYPE4 3 + +#define CS42L42_HS_CLAMP_DISABLE (CS42L42_PAGE_11 + 0x29) +#define CS42L42_HS_CLAMP_DISABLE_SHIFT 0 +#define CS42L42_HS_CLAMP_DISABLE_MASK (1 << CS42L42_HS_CLAMP_DISABLE_SHIFT) + +/* Page 0x12 Clocking Registers */ +#define CS42L42_MCLK_SRC_SEL (CS42L42_PAGE_12 + 0x01) +#define CS42L42_MCLKDIV_SHIFT 1 +#define CS42L42_MCLKDIV_MASK (1 << CS42L42_MCLKDIV_SHIFT) +#define CS42L42_MCLK_SRC_SEL_SHIFT 0 +#define CS42L42_MCLK_SRC_SEL_MASK (1 << CS42L42_MCLK_SRC_SEL_SHIFT) + +#define CS42L42_SPDIF_CLK_CFG (CS42L42_PAGE_12 + 0x02) +#define CS42L42_FSYNC_PW_LOWER (CS42L42_PAGE_12 + 0x03) + +#define CS42L42_FSYNC_PW_UPPER (CS42L42_PAGE_12 + 0x04) +#define CS42L42_FSYNC_PULSE_WIDTH_SHIFT 0 +#define CS42L42_FSYNC_PULSE_WIDTH_MASK (0xff << \ + CS42L42_FSYNC_PULSE_WIDTH_SHIFT) + +#define CS42L42_FSYNC_P_LOWER (CS42L42_PAGE_12 + 0x05) + +#define CS42L42_FSYNC_P_UPPER (CS42L42_PAGE_12 + 0x06) +#define CS42L42_FSYNC_PERIOD_SHIFT 0 +#define CS42L42_FSYNC_PERIOD_MASK (0xff << CS42L42_FSYNC_PERIOD_SHIFT) + +#define CS42L42_ASP_CLK_CFG (CS42L42_PAGE_12 + 0x07) +#define CS42L42_ASP_SCLK_EN_SHIFT 5 +#define CS42L42_ASP_SCLK_EN_MASK (1 << CS42L42_ASP_SCLK_EN_SHIFT) +#define CS42L42_ASP_MASTER_MODE 0x01 +#define CS42L42_ASP_SLAVE_MODE 0x00 +#define CS42L42_ASP_MODE_SHIFT 4 +#define CS42L42_ASP_MODE_MASK (1 << CS42L42_ASP_MODE_SHIFT) +#define CS42L42_ASP_SCPOL_SHIFT 2 +#define CS42L42_ASP_SCPOL_MASK (3 << CS42L42_ASP_SCPOL_SHIFT) +#define CS42L42_ASP_SCPOL_NOR 3 +#define CS42L42_ASP_LCPOL_SHIFT 0 +#define CS42L42_ASP_LCPOL_MASK (3 << CS42L42_ASP_LCPOL_SHIFT) +#define CS42L42_ASP_LCPOL_INV 3 + +#define CS42L42_ASP_FRM_CFG (CS42L42_PAGE_12 + 0x08) +#define CS42L42_ASP_STP_SHIFT 4 +#define CS42L42_ASP_STP_MASK (1 << CS42L42_ASP_STP_SHIFT) +#define CS42L42_ASP_5050_SHIFT 3 +#define CS42L42_ASP_5050_MASK (1 << CS42L42_ASP_5050_SHIFT) +#define CS42L42_ASP_FSD_SHIFT 0 +#define CS42L42_ASP_FSD_MASK (7 << CS42L42_ASP_FSD_SHIFT) +#define CS42L42_ASP_FSD_0_5 1 +#define CS42L42_ASP_FSD_1_0 2 +#define CS42L42_ASP_FSD_1_5 3 +#define CS42L42_ASP_FSD_2_0 4 + +#define CS42L42_FS_RATE_EN (CS42L42_PAGE_12 + 0x09) +#define CS42L42_FS_EN_SHIFT 0 +#define CS42L42_FS_EN_MASK (0xf << CS42L42_FS_EN_SHIFT) +#define CS42L42_FS_EN_IASRC_96K 0x1 +#define CS42L42_FS_EN_OASRC_96K 0x2 + +#define CS42L42_IN_ASRC_CLK (CS42L42_PAGE_12 + 0x0A) +#define CS42L42_CLK_IASRC_SEL_SHIFT 0 +#define CS42L42_CLK_IASRC_SEL_MASK (1 << CS42L42_CLK_IASRC_SEL_SHIFT) +#define CS42L42_CLK_IASRC_SEL_6 0 +#define CS42L42_CLK_IASRC_SEL_12 1 + +#define CS42L42_OUT_ASRC_CLK (CS42L42_PAGE_12 + 0x0B) +#define CS42L42_CLK_OASRC_SEL_SHIFT 0 +#define CS42L42_CLK_OASRC_SEL_MASK (1 << CS42L42_CLK_OASRC_SEL_SHIFT) +#define CS42L42_CLK_OASRC_SEL_12 1 + +#define CS42L42_PLL_DIV_CFG1 (CS42L42_PAGE_12 + 0x0C) +#define CS42L42_SCLK_PREDIV_SHIFT 0 +#define CS42L42_SCLK_PREDIV_MASK (3 << CS42L42_SCLK_PREDIV_SHIFT) + +/* Page 0x13 Interrupt Registers */ +/* Interrupts */ +#define CS42L42_ADC_OVFL_STATUS (CS42L42_PAGE_13 + 0x01) +#define CS42L42_MIXER_STATUS (CS42L42_PAGE_13 + 0x02) +#define CS42L42_SRC_STATUS (CS42L42_PAGE_13 + 0x03) +#define CS42L42_ASP_RX_STATUS (CS42L42_PAGE_13 + 0x04) +#define CS42L42_ASP_TX_STATUS (CS42L42_PAGE_13 + 0x05) +#define CS42L42_CODEC_STATUS (CS42L42_PAGE_13 + 0x08) +#define CS42L42_DET_INT_STATUS1 (CS42L42_PAGE_13 + 0x09) +#define CS42L42_DET_INT_STATUS2 (CS42L42_PAGE_13 + 0x0A) +#define CS42L42_SRCPL_INT_STATUS (CS42L42_PAGE_13 + 0x0B) +#define CS42L42_VPMON_STATUS (CS42L42_PAGE_13 + 0x0D) +#define CS42L42_PLL_LOCK_STATUS (CS42L42_PAGE_13 + 0x0E) +#define CS42L42_TSRS_PLUG_STATUS (CS42L42_PAGE_13 + 0x0F) +/* Masks */ +#define CS42L42_ADC_OVFL_INT_MASK (CS42L42_PAGE_13 + 0x16) +#define CS42L42_ADC_OVFL_SHIFT 0 +#define CS42L42_ADC_OVFL_MASK (1 << CS42L42_ADC_OVFL_SHIFT) +#define CS42L42_ADC_OVFL_VAL_MASK CS42L42_ADC_OVFL_MASK + +#define CS42L42_MIXER_INT_MASK (CS42L42_PAGE_13 + 0x17) +#define CS42L42_MIX_CHB_OVFL_SHIFT 0 +#define CS42L42_MIX_CHB_OVFL_MASK (1 << CS42L42_MIX_CHB_OVFL_SHIFT) +#define CS42L42_MIX_CHA_OVFL_SHIFT 1 +#define CS42L42_MIX_CHA_OVFL_MASK (1 << CS42L42_MIX_CHA_OVFL_SHIFT) +#define CS42L42_EQ_OVFL_SHIFT 2 +#define CS42L42_EQ_OVFL_MASK (1 << CS42L42_EQ_OVFL_SHIFT) +#define CS42L42_EQ_BIQUAD_OVFL_SHIFT 3 +#define CS42L42_EQ_BIQUAD_OVFL_MASK (1 << CS42L42_EQ_BIQUAD_OVFL_SHIFT) +#define CS42L42_MIXER_VAL_MASK (CS42L42_MIX_CHB_OVFL_MASK | \ + CS42L42_MIX_CHA_OVFL_MASK | \ + CS42L42_EQ_OVFL_MASK | \ + CS42L42_EQ_BIQUAD_OVFL_MASK) + +#define CS42L42_SRC_INT_MASK (CS42L42_PAGE_13 + 0x18) +#define CS42L42_SRC_ILK_SHIFT 0 +#define CS42L42_SRC_ILK_MASK (1 << CS42L42_SRC_ILK_SHIFT) +#define CS42L42_SRC_OLK_SHIFT 1 +#define CS42L42_SRC_OLK_MASK (1 << CS42L42_SRC_OLK_SHIFT) +#define CS42L42_SRC_IUNLK_SHIFT 2 +#define CS42L42_SRC_IUNLK_MASK (1 << CS42L42_SRC_IUNLK_SHIFT) +#define CS42L42_SRC_OUNLK_SHIFT 3 +#define CS42L42_SRC_OUNLK_MASK (1 << CS42L42_SRC_OUNLK_SHIFT) +#define CS42L42_SRC_VAL_MASK (CS42L42_SRC_ILK_MASK | \ + CS42L42_SRC_OLK_MASK | \ + CS42L42_SRC_IUNLK_MASK | \ + CS42L42_SRC_OUNLK_MASK) + +#define CS42L42_ASP_RX_INT_MASK (CS42L42_PAGE_13 + 0x19) +#define CS42L42_ASPRX_NOLRCK_SHIFT 0 +#define CS42L42_ASPRX_NOLRCK_MASK (1 << CS42L42_ASPRX_NOLRCK_SHIFT) +#define CS42L42_ASPRX_EARLY_SHIFT 1 +#define CS42L42_ASPRX_EARLY_MASK (1 << CS42L42_ASPRX_EARLY_SHIFT) +#define CS42L42_ASPRX_LATE_SHIFT 2 +#define CS42L42_ASPRX_LATE_MASK (1 << CS42L42_ASPRX_LATE_SHIFT) +#define CS42L42_ASPRX_ERROR_SHIFT 3 +#define CS42L42_ASPRX_ERROR_MASK (1 << CS42L42_ASPRX_ERROR_SHIFT) +#define CS42L42_ASPRX_OVLD_SHIFT 4 +#define CS42L42_ASPRX_OVLD_MASK (1 << CS42L42_ASPRX_OVLD_SHIFT) +#define CS42L42_ASP_RX_VAL_MASK (CS42L42_ASPRX_NOLRCK_MASK | \ + CS42L42_ASPRX_EARLY_MASK | \ + CS42L42_ASPRX_LATE_MASK | \ + CS42L42_ASPRX_ERROR_MASK | \ + CS42L42_ASPRX_OVLD_MASK) + +#define CS42L42_ASP_TX_INT_MASK (CS42L42_PAGE_13 + 0x1A) +#define CS42L42_ASPTX_NOLRCK_SHIFT 0 +#define CS42L42_ASPTX_NOLRCK_MASK (1 << CS42L42_ASPTX_NOLRCK_SHIFT) +#define CS42L42_ASPTX_EARLY_SHIFT 1 +#define CS42L42_ASPTX_EARLY_MASK (1 << CS42L42_ASPTX_EARLY_SHIFT) +#define CS42L42_ASPTX_LATE_SHIFT 2 +#define CS42L42_ASPTX_LATE_MASK (1 << CS42L42_ASPTX_LATE_SHIFT) +#define CS42L42_ASPTX_SMERROR_SHIFT 3 +#define CS42L42_ASPTX_SMERROR_MASK (1 << CS42L42_ASPTX_SMERROR_SHIFT) +#define CS42L42_ASP_TX_VAL_MASK (CS42L42_ASPTX_NOLRCK_MASK | \ + CS42L42_ASPTX_EARLY_MASK | \ + CS42L42_ASPTX_LATE_MASK | \ + CS42L42_ASPTX_SMERROR_MASK) + +#define CS42L42_CODEC_INT_MASK (CS42L42_PAGE_13 + 0x1B) +#define CS42L42_PDN_DONE_SHIFT 0 +#define CS42L42_PDN_DONE_MASK (1 << CS42L42_PDN_DONE_SHIFT) +#define CS42L42_HSDET_AUTO_DONE_SHIFT 1 +#define CS42L42_HSDET_AUTO_DONE_MASK (1 << CS42L42_HSDET_AUTO_DONE_SHIFT) +#define CS42L42_CODEC_VAL_MASK (CS42L42_PDN_DONE_MASK | \ + CS42L42_HSDET_AUTO_DONE_MASK) + +#define CS42L42_SRCPL_INT_MASK (CS42L42_PAGE_13 + 0x1C) +#define CS42L42_SRCPL_ADC_LK_SHIFT 0 +#define CS42L42_SRCPL_ADC_LK_MASK (1 << CS42L42_SRCPL_ADC_LK_SHIFT) +#define CS42L42_SRCPL_DAC_LK_SHIFT 2 +#define CS42L42_SRCPL_DAC_LK_MASK (1 << CS42L42_SRCPL_DAC_LK_SHIFT) +#define CS42L42_SRCPL_ADC_UNLK_SHIFT 5 +#define CS42L42_SRCPL_ADC_UNLK_MASK (1 << CS42L42_SRCPL_ADC_UNLK_SHIFT) +#define CS42L42_SRCPL_DAC_UNLK_SHIFT 6 +#define CS42L42_SRCPL_DAC_UNLK_MASK (1 << CS42L42_SRCPL_DAC_UNLK_SHIFT) +#define CS42L42_SRCPL_VAL_MASK (CS42L42_SRCPL_ADC_LK_MASK | \ + CS42L42_SRCPL_DAC_LK_MASK | \ + CS42L42_SRCPL_ADC_UNLK_MASK | \ + CS42L42_SRCPL_DAC_UNLK_MASK) + +#define CS42L42_VPMON_INT_MASK (CS42L42_PAGE_13 + 0x1E) +#define CS42L42_VPMON_SHIFT 0 +#define CS42L42_VPMON_MASK (1 << CS42L42_VPMON_SHIFT) +#define CS42L42_VPMON_VAL_MASK CS42L42_VPMON_MASK + +#define CS42L42_PLL_LOCK_INT_MASK (CS42L42_PAGE_13 + 0x1F) +#define CS42L42_PLL_LOCK_SHIFT 0 +#define CS42L42_PLL_LOCK_MASK (1 << CS42L42_PLL_LOCK_SHIFT) +#define CS42L42_PLL_LOCK_VAL_MASK CS42L42_PLL_LOCK_MASK + +#define CS42L42_TSRS_PLUG_INT_MASK (CS42L42_PAGE_13 + 0x20) +#define CS42L42_RS_PLUG_SHIFT 0 +#define CS42L42_RS_PLUG_MASK (1 << CS42L42_RS_PLUG_SHIFT) +#define CS42L42_RS_UNPLUG_SHIFT 1 +#define CS42L42_RS_UNPLUG_MASK (1 << CS42L42_RS_UNPLUG_SHIFT) +#define CS42L42_TS_PLUG_SHIFT 2 +#define CS42L42_TS_PLUG_MASK (1 << CS42L42_TS_PLUG_SHIFT) +#define CS42L42_TS_UNPLUG_SHIFT 3 +#define CS42L42_TS_UNPLUG_MASK (1 << CS42L42_TS_UNPLUG_SHIFT) +#define CS42L42_TSRS_PLUG_VAL_MASK (CS42L42_RS_PLUG_MASK | \ + CS42L42_RS_UNPLUG_MASK | \ + CS42L42_TS_PLUG_MASK | \ + CS42L42_TS_UNPLUG_MASK) +#define CS42L42_TS_PLUG 3 +#define CS42L42_TS_UNPLUG 0 +#define CS42L42_TS_TRANS 1 + +/* + * NOTE: PLL_START must be 0 while both ADC_PDN=1 and HP_PDN=1. + * Otherwise it will prevent FILT+ from charging properly. + */ +#define CS42L42_PLL_CTL1 (CS42L42_PAGE_15 + 0x01) +#define CS42L42_PLL_START_SHIFT 0 +#define CS42L42_PLL_START_MASK (1 << CS42L42_PLL_START_SHIFT) + +#define CS42L42_PLL_DIV_FRAC0 (CS42L42_PAGE_15 + 0x02) +#define CS42L42_PLL_DIV_FRAC_SHIFT 0 +#define CS42L42_PLL_DIV_FRAC_MASK (0xff << CS42L42_PLL_DIV_FRAC_SHIFT) + +#define CS42L42_PLL_DIV_FRAC1 (CS42L42_PAGE_15 + 0x03) +#define CS42L42_PLL_DIV_FRAC2 (CS42L42_PAGE_15 + 0x04) + +#define CS42L42_PLL_DIV_INT (CS42L42_PAGE_15 + 0x05) +#define CS42L42_PLL_DIV_INT_SHIFT 0 +#define CS42L42_PLL_DIV_INT_MASK (0xff << CS42L42_PLL_DIV_INT_SHIFT) + +#define CS42L42_PLL_CTL3 (CS42L42_PAGE_15 + 0x08) +#define CS42L42_PLL_DIVOUT_SHIFT 0 +#define CS42L42_PLL_DIVOUT_MASK (0xff << CS42L42_PLL_DIVOUT_SHIFT) + +#define CS42L42_PLL_CAL_RATIO (CS42L42_PAGE_15 + 0x0A) +#define CS42L42_PLL_CAL_RATIO_SHIFT 0 +#define CS42L42_PLL_CAL_RATIO_MASK (0xff << CS42L42_PLL_CAL_RATIO_SHIFT) + +#define CS42L42_PLL_CTL4 (CS42L42_PAGE_15 + 0x1B) +#define CS42L42_PLL_MODE_SHIFT 0 +#define CS42L42_PLL_MODE_MASK (3 << CS42L42_PLL_MODE_SHIFT) + +/* Page 0x19 HP Load Detect Registers */ +#define CS42L42_LOAD_DET_RCSTAT (CS42L42_PAGE_19 + 0x25) +#define CS42L42_RLA_STAT_SHIFT 0 +#define CS42L42_RLA_STAT_MASK (3 << CS42L42_RLA_STAT_SHIFT) +#define CS42L42_RLA_STAT_15_OHM 0 + +#define CS42L42_LOAD_DET_DONE (CS42L42_PAGE_19 + 0x26) +#define CS42L42_HPLOAD_DET_DONE_SHIFT 0 +#define CS42L42_HPLOAD_DET_DONE_MASK (1 << CS42L42_HPLOAD_DET_DONE_SHIFT) + +#define CS42L42_LOAD_DET_EN (CS42L42_PAGE_19 + 0x27) +#define CS42L42_HP_LD_EN_SHIFT 0 +#define CS42L42_HP_LD_EN_MASK (1 << CS42L42_HP_LD_EN_SHIFT) + +/* Page 0x1B Headset Interface Registers */ +#define CS42L42_HSBIAS_SC_AUTOCTL (CS42L42_PAGE_1B + 0x70) +#define CS42L42_HSBIAS_SENSE_TRIP_SHIFT 0 +#define CS42L42_HSBIAS_SENSE_TRIP_MASK (7 << CS42L42_HSBIAS_SENSE_TRIP_SHIFT) +#define CS42L42_TIP_SENSE_EN_SHIFT 5 +#define CS42L42_TIP_SENSE_EN_MASK (1 << CS42L42_TIP_SENSE_EN_SHIFT) +#define CS42L42_AUTO_HSBIAS_HIZ_SHIFT 6 +#define CS42L42_AUTO_HSBIAS_HIZ_MASK (1 << CS42L42_AUTO_HSBIAS_HIZ_SHIFT) +#define CS42L42_HSBIAS_SENSE_EN_SHIFT 7 +#define CS42L42_HSBIAS_SENSE_EN_MASK (1 << CS42L42_HSBIAS_SENSE_EN_SHIFT) + +#define CS42L42_WAKE_CTL (CS42L42_PAGE_1B + 0x71) +#define CS42L42_WAKEB_CLEAR_SHIFT 0 +#define CS42L42_WAKEB_CLEAR_MASK (1 << CS42L42_WAKEB_CLEAR_SHIFT) +#define CS42L42_WAKEB_MODE_SHIFT 5 +#define CS42L42_WAKEB_MODE_MASK (1 << CS42L42_WAKEB_MODE_SHIFT) +#define CS42L42_M_HP_WAKE_SHIFT 6 +#define CS42L42_M_HP_WAKE_MASK (1 << CS42L42_M_HP_WAKE_SHIFT) +#define CS42L42_M_MIC_WAKE_SHIFT 7 +#define CS42L42_M_MIC_WAKE_MASK (1 << CS42L42_M_MIC_WAKE_SHIFT) + +#define CS42L42_ADC_DISABLE_MUTE (CS42L42_PAGE_1B + 0x72) +#define CS42L42_ADC_DISABLE_S0_MUTE_SHIFT 7 +#define CS42L42_ADC_DISABLE_S0_MUTE_MASK (1 << CS42L42_ADC_DISABLE_S0_MUTE_SHIFT) + +#define CS42L42_TIPSENSE_CTL (CS42L42_PAGE_1B + 0x73) +#define CS42L42_TIP_SENSE_DEBOUNCE_SHIFT 0 +#define CS42L42_TIP_SENSE_DEBOUNCE_MASK (3 << CS42L42_TIP_SENSE_DEBOUNCE_SHIFT) +#define CS42L42_TIP_SENSE_INV_SHIFT 5 +#define CS42L42_TIP_SENSE_INV_MASK (1 << CS42L42_TIP_SENSE_INV_SHIFT) +#define CS42L42_TIP_SENSE_CTRL_SHIFT 6 +#define CS42L42_TIP_SENSE_CTRL_MASK (3 << CS42L42_TIP_SENSE_CTRL_SHIFT) + +/* + * NOTE: DETECT_MODE must be 0 while both ADC_PDN=1 and HP_PDN=1. + * Otherwise it will prevent FILT+ from charging properly. + */ +#define CS42L42_MISC_DET_CTL (CS42L42_PAGE_1B + 0x74) +#define CS42L42_PDN_MIC_LVL_DET_SHIFT 0 +#define CS42L42_PDN_MIC_LVL_DET_MASK (1 << CS42L42_PDN_MIC_LVL_DET_SHIFT) +#define CS42L42_HSBIAS_CTL_SHIFT 1 +#define CS42L42_HSBIAS_CTL_MASK (3 << CS42L42_HSBIAS_CTL_SHIFT) +#define CS42L42_DETECT_MODE_SHIFT 3 +#define CS42L42_DETECT_MODE_MASK (3 << CS42L42_DETECT_MODE_SHIFT) + +#define CS42L42_MIC_DET_CTL1 (CS42L42_PAGE_1B + 0x75) +#define CS42L42_HS_DET_LEVEL_SHIFT 0 +#define CS42L42_HS_DET_LEVEL_MASK (0x3F << CS42L42_HS_DET_LEVEL_SHIFT) +#define CS42L42_EVENT_STAT_SEL_SHIFT 6 +#define CS42L42_EVENT_STAT_SEL_MASK (1 << CS42L42_EVENT_STAT_SEL_SHIFT) +#define CS42L42_LATCH_TO_VP_SHIFT 7 +#define CS42L42_LATCH_TO_VP_MASK (1 << CS42L42_LATCH_TO_VP_SHIFT) + +#define CS42L42_MIC_DET_CTL2 (CS42L42_PAGE_1B + 0x76) +#define CS42L42_DEBOUNCE_TIME_SHIFT 5 +#define CS42L42_DEBOUNCE_TIME_MASK (0x07 << CS42L42_DEBOUNCE_TIME_SHIFT) + +#define CS42L42_DET_STATUS1 (CS42L42_PAGE_1B + 0x77) +#define CS42L42_HSBIAS_HIZ_MODE_SHIFT 6 +#define CS42L42_HSBIAS_HIZ_MODE_MASK (1 << CS42L42_HSBIAS_HIZ_MODE_SHIFT) +#define CS42L42_TIP_SENSE_SHIFT 7 +#define CS42L42_TIP_SENSE_MASK (1 << CS42L42_TIP_SENSE_SHIFT) + +#define CS42L42_DET_STATUS2 (CS42L42_PAGE_1B + 0x78) +#define CS42L42_SHORT_TRUE_SHIFT 0 +#define CS42L42_SHORT_TRUE_MASK (1 << CS42L42_SHORT_TRUE_SHIFT) +#define CS42L42_HS_TRUE_SHIFT 1 +#define CS42L42_HS_TRUE_MASK (1 << CS42L42_HS_TRUE_SHIFT) + +#define CS42L42_DET_INT1_MASK (CS42L42_PAGE_1B + 0x79) +#define CS42L42_TIP_SENSE_UNPLUG_SHIFT 5 +#define CS42L42_TIP_SENSE_UNPLUG_MASK (1 << CS42L42_TIP_SENSE_UNPLUG_SHIFT) +#define CS42L42_TIP_SENSE_PLUG_SHIFT 6 +#define CS42L42_TIP_SENSE_PLUG_MASK (1 << CS42L42_TIP_SENSE_PLUG_SHIFT) +#define CS42L42_HSBIAS_SENSE_SHIFT 7 +#define CS42L42_HSBIAS_SENSE_MASK (1 << CS42L42_HSBIAS_SENSE_SHIFT) +#define CS42L42_DET_INT_VAL1_MASK (CS42L42_TIP_SENSE_UNPLUG_MASK | \ + CS42L42_TIP_SENSE_PLUG_MASK | \ + CS42L42_HSBIAS_SENSE_MASK) + +#define CS42L42_DET_INT2_MASK (CS42L42_PAGE_1B + 0x7A) +#define CS42L42_M_SHORT_DET_SHIFT 0 +#define CS42L42_M_SHORT_DET_MASK (1 << CS42L42_M_SHORT_DET_SHIFT) +#define CS42L42_M_SHORT_RLS_SHIFT 1 +#define CS42L42_M_SHORT_RLS_MASK (1 << CS42L42_M_SHORT_RLS_SHIFT) +#define CS42L42_M_HSBIAS_HIZ_SHIFT 2 +#define CS42L42_M_HSBIAS_HIZ_MASK (1 << CS42L42_M_HSBIAS_HIZ_SHIFT) +#define CS42L42_M_DETECT_FT_SHIFT 6 +#define CS42L42_M_DETECT_FT_MASK (1 << CS42L42_M_DETECT_FT_SHIFT) +#define CS42L42_M_DETECT_TF_SHIFT 7 +#define CS42L42_M_DETECT_TF_MASK (1 << CS42L42_M_DETECT_TF_SHIFT) +#define CS42L42_DET_INT_VAL2_MASK (CS42L42_M_SHORT_DET_MASK | \ + CS42L42_M_SHORT_RLS_MASK | \ + CS42L42_M_HSBIAS_HIZ_MASK | \ + CS42L42_M_DETECT_FT_MASK | \ + CS42L42_M_DETECT_TF_MASK) + +/* Page 0x1C Headset Bias Registers */ +#define CS42L42_HS_BIAS_CTL (CS42L42_PAGE_1C + 0x03) +#define CS42L42_HSBIAS_RAMP_SHIFT 0 +#define CS42L42_HSBIAS_RAMP_MASK (3 << CS42L42_HSBIAS_RAMP_SHIFT) +#define CS42L42_HSBIAS_PD_SHIFT 4 +#define CS42L42_HSBIAS_PD_MASK (1 << CS42L42_HSBIAS_PD_SHIFT) +#define CS42L42_HSBIAS_CAPLESS_SHIFT 7 +#define CS42L42_HSBIAS_CAPLESS_MASK (1 << CS42L42_HSBIAS_CAPLESS_SHIFT) + +/* Page 0x1D ADC Registers */ +#define CS42L42_ADC_CTL (CS42L42_PAGE_1D + 0x01) +#define CS42L42_ADC_NOTCH_DIS_SHIFT 5 +#define CS42L42_ADC_FORCE_WEAK_VCM_SHIFT 4 +#define CS42L42_ADC_INV_SHIFT 2 +#define CS42L42_ADC_DIG_BOOST_SHIFT 0 + +#define CS42L42_ADC_VOLUME (CS42L42_PAGE_1D + 0x03) +#define CS42L42_ADC_VOL_SHIFT 0 + +#define CS42L42_ADC_WNF_HPF_CTL (CS42L42_PAGE_1D + 0x04) +#define CS42L42_ADC_WNF_CF_SHIFT 4 +#define CS42L42_ADC_WNF_EN_SHIFT 3 +#define CS42L42_ADC_HPF_CF_SHIFT 1 +#define CS42L42_ADC_HPF_EN_SHIFT 0 + +/* Page 0x1F DAC Registers */ +#define CS42L42_DAC_CTL1 (CS42L42_PAGE_1F + 0x01) +#define CS42L42_DACB_INV_SHIFT 1 +#define CS42L42_DACA_INV_SHIFT 0 + +#define CS42L42_DAC_CTL2 (CS42L42_PAGE_1F + 0x06) +#define CS42L42_HPOUT_PULLDOWN_SHIFT 4 +#define CS42L42_HPOUT_PULLDOWN_MASK (15 << CS42L42_HPOUT_PULLDOWN_SHIFT) +#define CS42L42_HPOUT_LOAD_SHIFT 3 +#define CS42L42_HPOUT_LOAD_MASK (1 << CS42L42_HPOUT_LOAD_SHIFT) +#define CS42L42_HPOUT_CLAMP_SHIFT 2 +#define CS42L42_HPOUT_CLAMP_MASK (1 << CS42L42_HPOUT_CLAMP_SHIFT) +#define CS42L42_DAC_HPF_EN_SHIFT 1 +#define CS42L42_DAC_HPF_EN_MASK (1 << CS42L42_DAC_HPF_EN_SHIFT) +#define CS42L42_DAC_MON_EN_SHIFT 0 +#define CS42L42_DAC_MON_EN_MASK (1 << CS42L42_DAC_MON_EN_SHIFT) + +/* Page 0x20 HP CTL Registers */ +#define CS42L42_HP_CTL (CS42L42_PAGE_20 + 0x01) +#define CS42L42_HP_ANA_BMUTE_SHIFT 3 +#define CS42L42_HP_ANA_BMUTE_MASK (1 << CS42L42_HP_ANA_BMUTE_SHIFT) +#define CS42L42_HP_ANA_AMUTE_SHIFT 2 +#define CS42L42_HP_ANA_AMUTE_MASK (1 << CS42L42_HP_ANA_AMUTE_SHIFT) +#define CS42L42_HP_FULL_SCALE_VOL_SHIFT 1 +#define CS42L42_HP_FULL_SCALE_VOL_MASK (1 << CS42L42_HP_FULL_SCALE_VOL_SHIFT) + +/* Page 0x21 Class H Registers */ +#define CS42L42_CLASSH_CTL (CS42L42_PAGE_21 + 0x01) + +/* Page 0x23 Mixer Volume Registers */ +#define CS42L42_MIXER_CHA_VOL (CS42L42_PAGE_23 + 0x01) +#define CS42L42_MIXER_ADC_VOL (CS42L42_PAGE_23 + 0x02) + +#define CS42L42_MIXER_CHB_VOL (CS42L42_PAGE_23 + 0x03) +#define CS42L42_MIXER_CH_VOL_SHIFT 0 +#define CS42L42_MIXER_CH_VOL_MASK (0x3f << CS42L42_MIXER_CH_VOL_SHIFT) + +/* Page 0x24 EQ Registers */ +#define CS42L42_EQ_COEF_IN0 (CS42L42_PAGE_24 + 0x01) +#define CS42L42_EQ_COEF_IN1 (CS42L42_PAGE_24 + 0x02) +#define CS42L42_EQ_COEF_IN2 (CS42L42_PAGE_24 + 0x03) +#define CS42L42_EQ_COEF_IN3 (CS42L42_PAGE_24 + 0x04) +#define CS42L42_EQ_COEF_RW (CS42L42_PAGE_24 + 0x06) +#define CS42L42_EQ_COEF_OUT0 (CS42L42_PAGE_24 + 0x07) +#define CS42L42_EQ_COEF_OUT1 (CS42L42_PAGE_24 + 0x08) +#define CS42L42_EQ_COEF_OUT2 (CS42L42_PAGE_24 + 0x09) +#define CS42L42_EQ_COEF_OUT3 (CS42L42_PAGE_24 + 0x0A) +#define CS42L42_EQ_INIT_STAT (CS42L42_PAGE_24 + 0x0B) +#define CS42L42_EQ_START_FILT (CS42L42_PAGE_24 + 0x0C) +#define CS42L42_EQ_MUTE_CTL (CS42L42_PAGE_24 + 0x0E) + +/* Page 0x25 Audio Port Registers */ +#define CS42L42_SP_RX_CH_SEL (CS42L42_PAGE_25 + 0x01) +#define CS42L42_SP_RX_CHB_SEL_SHIFT 2 +#define CS42L42_SP_RX_CHB_SEL_MASK (3 << CS42L42_SP_RX_CHB_SEL_SHIFT) + +#define CS42L42_SP_RX_ISOC_CTL (CS42L42_PAGE_25 + 0x02) +#define CS42L42_SP_RX_RSYNC_SHIFT 6 +#define CS42L42_SP_RX_RSYNC_MASK (1 << CS42L42_SP_RX_RSYNC_SHIFT) +#define CS42L42_SP_RX_NSB_POS_SHIFT 3 +#define CS42L42_SP_RX_NSB_POS_MASK (7 << CS42L42_SP_RX_NSB_POS_SHIFT) +#define CS42L42_SP_RX_NFS_NSBB_SHIFT 2 +#define CS42L42_SP_RX_NFS_NSBB_MASK (1 << CS42L42_SP_RX_NFS_NSBB_SHIFT) +#define CS42L42_SP_RX_ISOC_MODE_SHIFT 0 +#define CS42L42_SP_RX_ISOC_MODE_MASK (3 << CS42L42_SP_RX_ISOC_MODE_SHIFT) + +#define CS42L42_SP_RX_FS (CS42L42_PAGE_25 + 0x03) +#define CS42l42_SPDIF_CH_SEL (CS42L42_PAGE_25 + 0x04) +#define CS42L42_SP_TX_ISOC_CTL (CS42L42_PAGE_25 + 0x05) +#define CS42L42_SP_TX_FS (CS42L42_PAGE_25 + 0x06) +#define CS42L42_SPDIF_SW_CTL1 (CS42L42_PAGE_25 + 0x07) + +/* Page 0x26 SRC Registers */ +#define CS42L42_SRC_SDIN_FS (CS42L42_PAGE_26 + 0x01) +#define CS42L42_SRC_SDIN_FS_SHIFT 0 +#define CS42L42_SRC_SDIN_FS_MASK (0x1f << CS42L42_SRC_SDIN_FS_SHIFT) + +#define CS42L42_SRC_SDOUT_FS (CS42L42_PAGE_26 + 0x09) + +/* Page 0x28 S/PDIF Registers */ +#define CS42L42_SPDIF_CTL1 (CS42L42_PAGE_28 + 0x01) +#define CS42L42_SPDIF_CTL2 (CS42L42_PAGE_28 + 0x02) +#define CS42L42_SPDIF_CTL3 (CS42L42_PAGE_28 + 0x03) +#define CS42L42_SPDIF_CTL4 (CS42L42_PAGE_28 + 0x04) + +/* Page 0x29 Serial Port TX Registers */ +#define CS42L42_ASP_TX_SZ_EN (CS42L42_PAGE_29 + 0x01) +#define CS42L42_ASP_TX_EN_SHIFT 0 +#define CS42L42_ASP_TX_CH_EN (CS42L42_PAGE_29 + 0x02) +#define CS42L42_ASP_TX0_CH2_SHIFT 1 +#define CS42L42_ASP_TX0_CH1_SHIFT 0 + +#define CS42L42_ASP_TX_CH_AP_RES (CS42L42_PAGE_29 + 0x03) +#define CS42L42_ASP_TX_CH1_AP_SHIFT 7 +#define CS42L42_ASP_TX_CH1_AP_MASK (1 << CS42L42_ASP_TX_CH1_AP_SHIFT) +#define CS42L42_ASP_TX_CH2_AP_SHIFT 6 +#define CS42L42_ASP_TX_CH2_AP_MASK (1 << CS42L42_ASP_TX_CH2_AP_SHIFT) +#define CS42L42_ASP_TX_CH2_RES_SHIFT 2 +#define CS42L42_ASP_TX_CH2_RES_MASK (3 << CS42L42_ASP_TX_CH2_RES_SHIFT) +#define CS42L42_ASP_TX_CH1_RES_SHIFT 0 +#define CS42L42_ASP_TX_CH1_RES_MASK (3 << CS42L42_ASP_TX_CH1_RES_SHIFT) +#define CS42L42_ASP_TX_CH1_BIT_MSB (CS42L42_PAGE_29 + 0x04) +#define CS42L42_ASP_TX_CH1_BIT_LSB (CS42L42_PAGE_29 + 0x05) +#define CS42L42_ASP_TX_HIZ_DLY_CFG (CS42L42_PAGE_29 + 0x06) +#define CS42L42_ASP_TX_CH2_BIT_MSB (CS42L42_PAGE_29 + 0x0A) +#define CS42L42_ASP_TX_CH2_BIT_LSB (CS42L42_PAGE_29 + 0x0B) + +/* Page 0x2A Serial Port RX Registers */ +#define CS42L42_ASP_RX_DAI0_EN (CS42L42_PAGE_2A + 0x01) +#define CS42L42_ASP_RX0_CH_EN_SHIFT 2 +#define CS42L42_ASP_RX0_CH_EN_MASK (0xf << CS42L42_ASP_RX0_CH_EN_SHIFT) +#define CS42L42_ASP_RX0_CH1_SHIFT 2 +#define CS42L42_ASP_RX0_CH2_SHIFT 3 +#define CS42L42_ASP_RX0_CH3_SHIFT 4 +#define CS42L42_ASP_RX0_CH4_SHIFT 5 + +#define CS42L42_ASP_RX_DAI0_CH1_AP_RES (CS42L42_PAGE_2A + 0x02) +#define CS42L42_ASP_RX_DAI0_CH1_BIT_MSB (CS42L42_PAGE_2A + 0x03) +#define CS42L42_ASP_RX_DAI0_CH1_BIT_LSB (CS42L42_PAGE_2A + 0x04) +#define CS42L42_ASP_RX_DAI0_CH2_AP_RES (CS42L42_PAGE_2A + 0x05) +#define CS42L42_ASP_RX_DAI0_CH2_BIT_MSB (CS42L42_PAGE_2A + 0x06) +#define CS42L42_ASP_RX_DAI0_CH2_BIT_LSB (CS42L42_PAGE_2A + 0x07) +#define CS42L42_ASP_RX_DAI0_CH3_AP_RES (CS42L42_PAGE_2A + 0x08) +#define CS42L42_ASP_RX_DAI0_CH3_BIT_MSB (CS42L42_PAGE_2A + 0x09) +#define CS42L42_ASP_RX_DAI0_CH3_BIT_LSB (CS42L42_PAGE_2A + 0x0A) +#define CS42L42_ASP_RX_DAI0_CH4_AP_RES (CS42L42_PAGE_2A + 0x0B) +#define CS42L42_ASP_RX_DAI0_CH4_BIT_MSB (CS42L42_PAGE_2A + 0x0C) +#define CS42L42_ASP_RX_DAI0_CH4_BIT_LSB (CS42L42_PAGE_2A + 0x0D) +#define CS42L42_ASP_RX_DAI1_CH1_AP_RES (CS42L42_PAGE_2A + 0x0E) +#define CS42L42_ASP_RX_DAI1_CH1_BIT_MSB (CS42L42_PAGE_2A + 0x0F) +#define CS42L42_ASP_RX_DAI1_CH1_BIT_LSB (CS42L42_PAGE_2A + 0x10) +#define CS42L42_ASP_RX_DAI1_CH2_AP_RES (CS42L42_PAGE_2A + 0x11) +#define CS42L42_ASP_RX_DAI1_CH2_BIT_MSB (CS42L42_PAGE_2A + 0x12) +#define CS42L42_ASP_RX_DAI1_CH2_BIT_LSB (CS42L42_PAGE_2A + 0x13) + +#define CS42L42_ASP_RX_CH_AP_SHIFT 6 +#define CS42L42_ASP_RX_CH_AP_MASK (1 << CS42L42_ASP_RX_CH_AP_SHIFT) +#define CS42L42_ASP_RX_CH_AP_LOW 0 +#define CS42L42_ASP_RX_CH_AP_HI 1 +#define CS42L42_ASP_RX_CH_RES_SHIFT 0 +#define CS42L42_ASP_RX_CH_RES_MASK (3 << CS42L42_ASP_RX_CH_RES_SHIFT) +#define CS42L42_ASP_RX_CH_RES_32 3 +#define CS42L42_ASP_RX_CH_RES_16 1 +#define CS42L42_ASP_RX_CH_BIT_ST_SHIFT 0 +#define CS42L42_ASP_RX_CH_BIT_ST_MASK (0xff << CS42L42_ASP_RX_CH_BIT_ST_SHIFT) + +/* Page 0x30 ID Registers */ +#define CS42L42_SUB_REVID (CS42L42_PAGE_30 + 0x14) +#define CS42L42_MAX_REGISTER (CS42L42_PAGE_30 + 0x14) + +/* Defines for fracturing values spread across multiple registers */ +#define CS42L42_FRAC0_VAL(val) ((val) & 0x0000ff) +#define CS42L42_FRAC1_VAL(val) (((val) & 0x00ff00) >> 8) +#define CS42L42_FRAC2_VAL(val) (((val) & 0xff0000) >> 16) + +#define CS42L42_NUM_SUPPLIES 5 +#define CS42L42_BOOT_TIME_US 3000 +#define CS42L42_PLL_DIVOUT_TIME_US 800 +#define CS42L42_CLOCK_SWITCH_DELAY_US 150 +#define CS42L42_PLL_LOCK_POLL_US 250 +#define CS42L42_PLL_LOCK_TIMEOUT_US 1250 +#define CS42L42_HP_ADC_EN_TIME_US 20000 +#define CS42L42_PDN_DONE_POLL_US 1000 +#define CS42L42_PDN_DONE_TIMEOUT_US 200000 +#define CS42L42_PDN_DONE_TIME_MS 100 +#define CS42L42_FILT_DISCHARGE_TIME_MS 46 + +#endif /* __CS42L42_H */ -- cgit v1.2.3 From a7cffa11fa9232eabf0c4f441dc53002978ab526 Mon Sep 17 00:00:00 2001 From: Ashish Mhetre Date: Fri, 6 May 2022 15:23:11 +0200 Subject: memory: tegra: Add memory controller channels support From Tegra186 onwards, the memory controller supports multiple channels. Add support for mapping the address spaces of these channels and specify the number of channels supported by Tegra186, Tegra194 and Tegra234. In case of old bindings, channels won't be present. If channels are not present then print a warning and continue so that backward compatibility will be preserved in driver. During error interrupts from memory controller, appropriate registers from these channels need to be accessed for logging error info. Signed-off-by: Ashish Mhetre Reviewed-by: Dmitry Osipenko Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20220506132312.3910637-4-thierry.reding@gmail.com Signed-off-by: Krzysztof Kozlowski --- include/soc/tegra/mc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h index 1066b1194a5a..40f1d02a1358 100644 --- a/include/soc/tegra/mc.h +++ b/include/soc/tegra/mc.h @@ -194,6 +194,7 @@ struct tegra_mc_soc { unsigned int atom_size; u8 client_id_mask; + u8 num_channels; const struct tegra_smmu_soc *smmu; @@ -212,6 +213,8 @@ struct tegra_mc { struct tegra_smmu *smmu; struct gart_device *gart; void __iomem *regs; + void __iomem *bcast_ch_regs; + void __iomem **ch_regs; struct clk *clk; int irq; -- cgit v1.2.3 From 54a85e09f44c5fa322a2d186f50862d09f517225 Mon Sep 17 00:00:00 2001 From: Ashish Mhetre Date: Fri, 6 May 2022 15:23:12 +0200 Subject: memory: tegra: Add MC error logging on Tegra186 onward Add support for logging memory controller errors on Tegra186, Tegra194 and Tegra234. On these SoCs, interrupts can occur on multiple channels. Add support required to read the status of interrupts across multiple channels, log and clear them. Also add new interrupts supported on these SoCs. Reviewed-by: Dmitry Osipenko Signed-off-by: Ashish Mhetre Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20220506132312.3910637-5-thierry.reding@gmail.com Signed-off-by: Krzysztof Kozlowski --- include/soc/tegra/mc.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h index 40f1d02a1358..47ce6d434427 100644 --- a/include/soc/tegra/mc.h +++ b/include/soc/tegra/mc.h @@ -193,12 +193,15 @@ struct tegra_mc_soc { unsigned int num_address_bits; unsigned int atom_size; - u8 client_id_mask; + u16 client_id_mask; u8 num_channels; const struct tegra_smmu_soc *smmu; u32 intmask; + u32 ch_intmask; + u32 global_intstatus_channel_shift; + bool has_addr_hi_reg; const struct tegra_mc_reset_ops *reset_ops; const struct tegra_mc_reset *resets; -- cgit v1.2.3 From 6d97af487dee3176cb1342d4ab16637e495440ad Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Wed, 4 May 2022 08:23:50 +0200 Subject: entry: Rename arch_check_user_regs() to arch_enter_from_user_mode() arch_check_user_regs() is used at the moment to verify that struct pt_regs contains valid values when entering the kernel from userspace. s390 needs a place in the generic entry code to modify a cpu data structure when switching from userspace to kernel mode. As arch_check_user_regs() is exactly this, rename it to arch_enter_from_user_mode(). When entering the kernel from userspace, arch_check_user_regs() is used to verify that struct pt_regs contains valid values. Note that the NMI codepath doesn't call this function. s390 needs a place in the generic entry code to modify a cpu data structure when switching from userspace to kernel mode. As arch_check_user_regs() is exactly this, rename it to arch_enter_from_user_mode(). Signed-off-by: Sven Schnelle Reviewed-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Link: https://lore.kernel.org/r/20220504062351.2954280-2-tmricht@linux.ibm.com Signed-off-by: Heiko Carstens --- include/linux/entry-common.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index ab78bd4c2eb0..c92ac75d6556 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -63,7 +63,7 @@ ARCH_EXIT_TO_USER_MODE_WORK) /** - * arch_check_user_regs - Architecture specific sanity check for user mode regs + * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs * @regs: Pointer to currents pt_regs * * Defaults to an empty implementation. Can be replaced by architecture @@ -73,10 +73,10 @@ * section. Use __always_inline so the compiler cannot push it out of line * and make it instrumentable. */ -static __always_inline void arch_check_user_regs(struct pt_regs *regs); +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs); -#ifndef arch_check_user_regs -static __always_inline void arch_check_user_regs(struct pt_regs *regs) {} +#ifndef arch_enter_from_user_mode +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {} #endif /** -- cgit v1.2.3 From 2fbdf45d7d26361a0c3ec8833fd96edf0f5812da Mon Sep 17 00:00:00 2001 From: Ricardo Martinez Date: Fri, 6 May 2022 11:12:57 -0700 Subject: list: Add list_next_entry_circular() and list_prev_entry_circular() Add macros to get the next or previous entries and wraparound if needed. For example, calling list_next_entry_circular() on the last element should return the first element in the list. Signed-off-by: Ricardo Martinez Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- include/linux/list.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index dd6c2041d09c..c147eeb2d39d 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -563,6 +563,19 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_next_entry(pos, member) \ list_entry((pos)->member.next, typeof(*(pos)), member) +/** + * list_next_entry_circular - get the next element in list + * @pos: the type * to cursor. + * @head: the list head to take the element from. + * @member: the name of the list_head within the struct. + * + * Wraparound if pos is the last element (return the first element). + * Note, that list is expected to be not empty. + */ +#define list_next_entry_circular(pos, head, member) \ + (list_is_last(&(pos)->member, head) ? \ + list_first_entry(head, typeof(*(pos)), member) : list_next_entry(pos, member)) + /** * list_prev_entry - get the prev element in list * @pos: the type * to cursor @@ -571,6 +584,19 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_prev_entry(pos, member) \ list_entry((pos)->member.prev, typeof(*(pos)), member) +/** + * list_prev_entry_circular - get the prev element in list + * @pos: the type * to cursor. + * @head: the list head to take the element from. + * @member: the name of the list_head within the struct. + * + * Wraparound if pos is the first element (return the last element). + * Note, that list is expected to be not empty. + */ +#define list_prev_entry_circular(pos, head, member) \ + (list_is_first(&(pos)->member, head) ? \ + list_last_entry(head, typeof(*(pos)), member) : list_prev_entry(pos, member)) + /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. -- cgit v1.2.3 From a4ff365346c98081311c299955d91d657123e8aa Mon Sep 17 00:00:00 2001 From: Ricardo Martinez Date: Fri, 6 May 2022 11:12:58 -0700 Subject: net: skb: introduce skb_data_area_size() Helper to calculate the linear data space in the skb. Signed-off-by: Ricardo Martinez Reviewed-by: Sergey Ryazanov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5c2599e3fe7d..d58669d6cb91 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1665,6 +1665,11 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +static inline unsigned int skb_data_area_size(struct sk_buff *skb) +{ + return skb_end_pointer(skb) - skb->data; +} + struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); -- cgit v1.2.3 From 6cc2df8e3a3967e7c13a424f87f6efb1d4a62d80 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Fri, 6 May 2022 18:05:07 +0200 Subject: landlock: Add clang-format exceptions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to a following commit, add clang-format on and clang-format off stanzas around constant definitions. This enables to keep aligned values, which is much more readable than packed definitions. Link: https://lore.kernel.org/r/20220506160513.523257-2-mic@digikod.net Cc: stable@vger.kernel.org Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index b3d952067f59..15c31abb0d76 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -33,7 +33,9 @@ struct landlock_ruleset_attr { * - %LANDLOCK_CREATE_RULESET_VERSION: Get the highest supported Landlock ABI * version. */ +/* clang-format off */ #define LANDLOCK_CREATE_RULESET_VERSION (1U << 0) +/* clang-format on */ /** * enum landlock_rule_type - Landlock rule type @@ -120,6 +122,7 @@ struct landlock_path_beneath_attr { * :manpage:`access(2)`. * Future Landlock evolutions will enable to restrict them. */ +/* clang-format off */ #define LANDLOCK_ACCESS_FS_EXECUTE (1ULL << 0) #define LANDLOCK_ACCESS_FS_WRITE_FILE (1ULL << 1) #define LANDLOCK_ACCESS_FS_READ_FILE (1ULL << 2) @@ -133,5 +136,6 @@ struct landlock_path_beneath_attr { #define LANDLOCK_ACCESS_FS_MAKE_FIFO (1ULL << 10) #define LANDLOCK_ACCESS_FS_MAKE_BLOCK (1ULL << 11) #define LANDLOCK_ACCESS_FS_MAKE_SYM (1ULL << 12) +/* clang-format on */ #endif /* _UAPI_LINUX_LANDLOCK_H */ -- cgit v1.2.3 From ca4567f1e6f660f86fcd04f3563c0045b0d4772f Mon Sep 17 00:00:00 2001 From: Alaa Mohamed Date: Thu, 5 May 2022 17:09:57 +0200 Subject: rtnetlink: add extack support in fdb del handlers Add extack support to .ndo_fdb_del in netdevice.h and all related methods. Signed-off-by: Alaa Mohamed Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8cf0ac616cb9..74c97a34921d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1513,7 +1513,7 @@ struct net_device_ops { struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, - u16 vid); + u16 vid, struct netlink_ext_ack *extack); int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, -- cgit v1.2.3 From 90532850eb210dff70423eaf20e323a91ef542d8 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 6 May 2022 06:23:52 +0200 Subject: net: phy: introduce genphy_c45_pma_baset1_setup_master_slave() Move baset1 specific part of genphy_c45_pma_setup_forced() code to separate function to make it reusable by PHY drivers. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 2d12054932ba..d3f924d3b235 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1614,6 +1614,7 @@ int genphy_c45_read_link(struct phy_device *phydev); int genphy_c45_read_lpa(struct phy_device *phydev); int genphy_c45_read_pma(struct phy_device *phydev); int genphy_c45_pma_setup_forced(struct phy_device *phydev); +int genphy_c45_pma_baset1_setup_master_slave(struct phy_device *phydev); int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); -- cgit v1.2.3 From b9a366f3d874ce1c9c0148ec399f2ce4ab05a467 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 6 May 2022 06:23:54 +0200 Subject: net: phy: introduce genphy_c45_pma_baset1_read_master_slave() Move baset1 specific part of genphy_c45_read_pma() code to separate function to make it reusable by PHY drivers. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index d3f924d3b235..4713c95d65fb 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1619,6 +1619,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); +int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); int genphy_c45_loopback(struct phy_device *phydev, bool enable); -- cgit v1.2.3 From 2013ad8836aceb828c0fb5b16fa8bb98fd3d9b28 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 6 May 2022 06:23:56 +0200 Subject: net: phy: export genphy_c45_baset1_read_status() Export genphy_c45_baset1_read_status() to make it reusable by PHY drivers. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 4713c95d65fb..508f1149665b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1621,6 +1621,7 @@ int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); +int genphy_c45_baset1_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); int genphy_c45_loopback(struct phy_device *phydev, bool enable); int genphy_c45_pma_resume(struct phy_device *phydev); -- cgit v1.2.3 From 0257be79fc4a16a3252ce80aa13b3640f728c425 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Fri, 29 Apr 2022 12:20:18 +0200 Subject: mtd: spi-nor: expose internal parameters via debugfs There is no way to gather all information to verify support for a new flash chip. Also if you want to convert an existing flash chip to the new SFDP parsing, there is not enough information to determine if the flash will work like before. To ease this development, expose internal parameters via the debugfs. Signed-off-by: Michael Walle Signed-off-by: Pratyush Yadav Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/r/20220429102018.2361038-2-michael@walle.cc --- include/linux/mtd/spi-nor.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index e505c4a5c530..1ede4c89805a 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -363,6 +363,7 @@ struct spi_nor_flash_parameter; * @write_proto: the SPI protocol for write operations * @reg_proto: the SPI protocol for read_reg/write_reg/erase operations * @sfdp: the SFDP data of the flash + * @debugfs_root: pointer to the debugfs directory * @controller_ops: SPI NOR controller driver specific operations. * @params: [FLASH-SPECIFIC] SPI NOR flash parameters and settings. * The structure includes legacy flash parameters and @@ -392,6 +393,7 @@ struct spi_nor { u32 flags; enum spi_nor_cmd_ext cmd_ext_type; struct sfdp *sfdp; + struct dentry *debugfs_root; const struct spi_nor_controller_ops *controller_ops; -- cgit v1.2.3 From 5c832efdbf8651e2800a0169a870786bd85ee230 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 4 May 2022 18:08:28 +0100 Subject: ASoC: soc-component: Add comment for the endianness flag Add a comment to make the purpose of the endianness flag on the snd_soc_component structure more clear. Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20220504170905.332415-2-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc-component.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h index 766dc6f009c0..5a764c3099d3 100644 --- a/include/sound/soc-component.h +++ b/include/sound/soc-component.h @@ -169,6 +169,15 @@ struct snd_soc_component_driver { unsigned int idle_bias_on:1; unsigned int suspend_bias_off:1; unsigned int use_pmdown_time:1; /* care pmdown_time at stop */ + /* + * Indicates that the component does not care about the endianness of + * PCM audio data and the core will ensure that both LE and BE variants + * of each used format are present. Typically this is because the + * component sits behind a bus that abstracts away the endian of the + * original data, ie. one for which the transmission endian is defined + * (I2S/SLIMbus/SoundWire), or the concept of endian doesn't exist (PDM, + * analogue). + */ unsigned int endianness:1; unsigned int non_legacy_dai_naming:1; -- cgit v1.2.3 From a36e07dfe6ee71e209383ea9288cd8d1617e14f9 Mon Sep 17 00:00:00 2001 From: Gleb Fotengauer-Malinovskiy Date: Fri, 6 May 2022 17:24:54 +0000 Subject: rfkill: uapi: fix RFKILL_IOCTL_MAX_SIZE ioctl request definition The definition of RFKILL_IOCTL_MAX_SIZE introduced by commit 54f586a91532 ("rfkill: make new event layout opt-in") is unusable since it is based on RFKILL_IOC_EXT_SIZE which has not been defined. Fix that by replacing the undefined constant with the constant which is intended to be used in this definition. Fixes: 54f586a91532 ("rfkill: make new event layout opt-in") Cc: stable@vger.kernel.org # 5.11+ Signed-off-by: Gleb Fotengauer-Malinovskiy Signed-off-by: Dmitry V. Levin Link: https://lore.kernel.org/r/20220506172454.120319-1-glebfm@altlinux.org [add commit message provided later by Dmitry] Signed-off-by: Johannes Berg --- include/uapi/linux/rfkill.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index 283c5a7b3f2c..db6c8588c1d0 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -184,7 +184,7 @@ struct rfkill_event_ext { #define RFKILL_IOC_NOINPUT 1 #define RFKILL_IOCTL_NOINPUT _IO(RFKILL_IOC_MAGIC, RFKILL_IOC_NOINPUT) #define RFKILL_IOC_MAX_SIZE 2 -#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_EXT_SIZE, __u32) +#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_MAX_SIZE, __u32) /* and that's all userspace gets */ -- cgit v1.2.3 From ebdeb7c01d025cb059f05dc26b9dc914e46dd43f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 31 Mar 2022 19:27:52 -0600 Subject: io_uring: add support for 128-byte SQEs Normal SQEs are 64-bytes in length, which is fine for all the commands we support. However, in preparation for supporting passthrough IO, provide an option for setting up a ring with 128-byte SQEs. We continue to use the same type for io_uring_sqe, it's marked and commented with a zero sized array pad at the end. This provides up to 80 bytes of data for a passthrough command - 64 bytes for the extra added data, and 16 bytes available at the end of the existing SQE. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 31e719f38615..ee84132cadad 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -63,6 +63,12 @@ struct io_uring_sqe { }; __u64 addr3; __u64 __pad2[1]; + + /* + * If the ring is initialized with IORING_SETUP_SQE128, then this field + * contains 64-bytes of padding, doubling the size of the SQE. + */ + __u64 __big_sqe_pad[0]; }; enum { @@ -119,6 +125,8 @@ enum { */ #define IORING_SETUP_TASKRUN_FLAG (1U << 9) +#define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, -- cgit v1.2.3 From 7a51e5b44b92686eebd3e1b46b86e1eb4db975db Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Tue, 26 Apr 2022 11:21:23 -0700 Subject: io_uring: support CQE32 in io_uring_cqe This adds the big_cqe array to the struct io_uring_cqe to support large CQE's. Co-developed-by: Jens Axboe Signed-off-by: Stefan Roesch Reviewed-by: Kanchan Joshi Link: https://lore.kernel.org/r/20220426182134.136504-2-shr@fb.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ee84132cadad..ac2d90d669c3 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -126,6 +126,7 @@ enum { #define IORING_SETUP_TASKRUN_FLAG (1U << 9) #define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ +#define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */ enum io_uring_op { IORING_OP_NOP, @@ -245,6 +246,12 @@ struct io_uring_cqe { __u64 user_data; /* sqe->data submission passed back */ __s32 res; /* result code for this event */ __u32 flags; + + /* + * If the ring is initialized with IORING_SETUP_CQE32, then this field + * contains 16-bytes of padding, doubling the size of the CQE. + */ + __u64 big_cqe[]; }; /* -- cgit v1.2.3 From c4bb964fa092fb68645a852365dfe9855fef178a Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Tue, 26 Apr 2022 11:21:31 -0700 Subject: io_uring: add tracing for additional CQE32 fields This adds tracing for the extra1 and extra2 fields. Co-developed-by: Jens Axboe Signed-off-by: Stefan Roesch Reviewed-by: Kanchan Joshi Link: https://lore.kernel.org/r/20220426182134.136504-10-shr@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 3f2961baebcc..630982b3c34c 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -321,13 +321,16 @@ TRACE_EVENT(io_uring_fail_link, * @user_data: user data associated with the request * @res: result of the request * @cflags: completion flags + * @extra1: extra 64-bit data for CQE32 + * @extra2: extra 64-bit data for CQE32 * */ TRACE_EVENT(io_uring_complete, - TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags), + TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags, + u64 extra1, u64 extra2), - TP_ARGS(ctx, req, user_data, res, cflags), + TP_ARGS(ctx, req, user_data, res, cflags, extra1, extra2), TP_STRUCT__entry ( __field( void *, ctx ) @@ -335,6 +338,8 @@ TRACE_EVENT(io_uring_complete, __field( u64, user_data ) __field( int, res ) __field( unsigned, cflags ) + __field( u64, extra1 ) + __field( u64, extra2 ) ), TP_fast_assign( @@ -343,12 +348,17 @@ TRACE_EVENT(io_uring_complete, __entry->user_data = user_data; __entry->res = res; __entry->cflags = cflags; + __entry->extra1 = extra1; + __entry->extra2 = extra2; ), - TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x", + TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x " + "extra1 %llu extra2 %llu ", __entry->ctx, __entry->req, __entry->user_data, - __entry->res, __entry->cflags) + __entry->res, __entry->cflags, + (unsigned long long) __entry->extra1, + (unsigned long long) __entry->extra2) ); /** -- cgit v1.2.3 From b1c5f3085149e9643b125eb10aae0e74644d7dcc Mon Sep 17 00:00:00 2001 From: Ricky WU Date: Mon, 21 Mar 2022 11:18:30 +0000 Subject: misc: rtsx: add rts5261 efuse function move rts5261_fetch_vendor_settings() to rts5261_init_from_hw() make sure it be called from S3 or D3 add more register setting when efuse is set read efuse setting to register on init flow Signed-off-by: Ricky Wu Link: https://lore.kernel.org/r/18101ecb0f0749ccb9f564eda171ba40@realtek.com Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 3d780b44e678..534038d962e4 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1067,6 +1067,9 @@ #define PCR_SETTING_REG1 0x724 #define PCR_SETTING_REG2 0x814 #define PCR_SETTING_REG3 0x747 +#define PCR_SETTING_REG4 0x818 +#define PCR_SETTING_REG5 0x81C + #define rtsx_pci_init_cmd(pcr) ((pcr)->ci = 0) -- cgit v1.2.3 From bd32889e841c12533d09a1bd02bba932baa9ed8f Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Fri, 29 Apr 2022 23:56:41 +0000 Subject: binder: add BINDER_GET_EXTENDED_ERROR ioctl Provide a userspace mechanism to pull precise error information upon failed operations. Extending the current error codes returned by the interfaces allows userspace to better determine the course of action. This could be for instance, retrying a failed transaction at a later point and thus offloading the error handling from the driver. Acked-by: Christian Brauner (Microsoft) Acked-by: Todd Kjos Signed-off-by: Carlos Llamas Link: https://lore.kernel.org/r/20220429235644.697372-3-cmllamas@google.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/android/binder.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 11157fae8a8e..e6ee8cae303b 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -236,6 +236,21 @@ struct binder_frozen_status_info { __u32 async_recv; }; +/* struct binder_extened_error - extended error information + * @id: identifier for the failed operation + * @command: command as defined by binder_driver_return_protocol + * @param: parameter holding a negative errno value + * + * Used with BINDER_GET_EXTENDED_ERROR. This extends the error information + * returned by the driver upon a failed operation. Userspace can pull this + * data to properly handle specific error scenarios. + */ +struct binder_extended_error { + __u32 id; + __u32 command; + __s32 param; +}; + #define BINDER_WRITE_READ _IOWR('b', 1, struct binder_write_read) #define BINDER_SET_IDLE_TIMEOUT _IOW('b', 3, __s64) #define BINDER_SET_MAX_THREADS _IOW('b', 5, __u32) @@ -249,6 +264,7 @@ struct binder_frozen_status_info { #define BINDER_FREEZE _IOW('b', 14, struct binder_freeze_info) #define BINDER_GET_FROZEN_INFO _IOWR('b', 15, struct binder_frozen_status_info) #define BINDER_ENABLE_ONEWAY_SPAM_DETECTION _IOW('b', 16, __u32) +#define BINDER_GET_EXTENDED_ERROR _IOWR('b', 17, struct binder_extended_error) /* * NOTE: Two special error codes you should check for when calling -- cgit v1.2.3 From dbc2f62061c6bfba0aee93161ee3194dcee84bd0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Fri, 29 Apr 2022 17:26:46 +0100 Subject: nvmem: core: support passing DT node in cell info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some hardware may have NVMEM cells described in Device Tree using individual nodes. Let drivers pass such nodes to the NVMEM subsystem so they can be later used by NVMEM consumers. Signed-off-by: Rafał Miłecki Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20220429162701.2222-2-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index c0c0cefc3b92..980f9c9ac0bc 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -25,6 +25,7 @@ struct nvmem_cell_info { unsigned int bytes; unsigned int bit_offset; unsigned int nbits; + struct device_node *np; }; /** -- cgit v1.2.3 From 5efe7448a1426250b5747c10ad438517f44f1e51 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 08:43:23 -0400 Subject: fs: Introduce aops->read_folio Change all the callers of ->readpage to call ->read_folio in preference, if it exists. This is a transitional duplication, and will be removed by the end of the series. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2be852661a29..5ad942183a2c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -336,6 +336,7 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); + int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); -- cgit v1.2.3 From 6c62371b7fd77628feb5b806bc29433caecedff8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 08:49:28 -0400 Subject: fs: Convert netfs_readpage to netfs_read_folio This is straightforward because netfs already worked in terms of folios. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/netfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 1c29f317d907..4bd5ee709daa 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -274,7 +274,7 @@ struct netfs_cache_ops { struct readahead_control; extern void netfs_readahead(struct readahead_control *); -extern int netfs_readpage(struct file *, struct page *); +int netfs_read_folio(struct file *, struct folio *); extern int netfs_write_begin(struct file *, struct address_space *, loff_t, unsigned int, struct folio **, void **); -- cgit v1.2.3 From 7479c505b4ab5ed5f81f35fdd68c44c58d6f0439 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 08:54:32 -0400 Subject: fs: Convert iomap_readpage to iomap_read_folio A straightforward conversion as iomap_readpage already worked in folios. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/iomap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index b76f0dd149fb..5b2aa45ddda3 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -225,7 +225,7 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); -int iomap_readpage(struct page *page, const struct iomap_ops *ops); +int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); int iomap_releasepage(struct page *page, gfp_t gfp_mask); -- cgit v1.2.3 From 2c69e2057962b6bd76d72446453862eb59325b49 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 10:40:40 -0400 Subject: fs: Convert block_read_full_page() to block_read_full_folio() This function is NOT converted to handle large folios, so include an assert that the filesystem isn't passing one in. Otherwise, use the folio functions instead of the page functions, where they exist. Convert all filesystems which use block_read_full_page(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 805c4e12700a..31d82fd9abe8 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -223,7 +223,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block, int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler); -int block_read_full_page(struct page*, get_block_t*); +int block_read_full_folio(struct folio *, get_block_t *); bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, get_block_t *get_block); -- cgit v1.2.3 From f132ab7d3ab03c5bae28d31fb80ba77c4da05500 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 11:47:39 -0400 Subject: fs: Convert mpage_readpage to mpage_read_folio mpage_readpage still works in terms of pages, and has not been audited for correctness with large folios, so include an assertion that the filesystem is not passing it large folios. Convert all the filesystems to call mpage_read_folio() instead of mpage_readpage(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mpage.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mpage.h b/include/linux/mpage.h index f4f5e90a6844..43986f7ec4dd 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -16,7 +16,7 @@ struct writeback_control; struct readahead_control; void mpage_readahead(struct readahead_control *, get_block_t get_block); -int mpage_readpage(struct page *page, get_block_t get_block); +int mpage_read_folio(struct folio *folio, get_block_t get_block); int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); int mpage_writepage(struct page *page, get_block_t *get_block, -- cgit v1.2.3 From 65d023af7f29eb1250a6105141a74776bae7e1f8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 11:12:16 -0400 Subject: nfs: Convert nfs to read_folio This is a "weak" conversion which converts straight back to using pages. A full conversion should be performed at some point, hopefully by someone familiar with the filesystem. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b48b9259e02c..1bba71757d62 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -594,7 +594,7 @@ static inline bool nfs_have_writebacks(const struct inode *inode) /* * linux/fs/nfs/read.c */ -extern int nfs_readpage(struct file *, struct page *); +int nfs_read_folio(struct file *, struct folio *); void nfs_readahead(struct readahead_control *); /* -- cgit v1.2.3 From 7e0a126519b82648b254afcd95a168c15f65ea40 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 11:53:28 -0400 Subject: mm,fs: Remove aops->readpage With all implementations of aops->readpage converted to aops->read_folio, we can stop checking whether it's set and remove the member from aops. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5ad942183a2c..f812f5aa07dd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -262,7 +262,7 @@ struct iattr { * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned - * by readpage(). + * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a @@ -335,7 +335,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); - int (*readpage)(struct file *, struct page *); int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ -- cgit v1.2.3 From e9b5b23e957ef9260fec811d8d8081125889308a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 1 May 2022 21:39:29 -0400 Subject: fs: Change the type of filler_t By making filler_t the same as read_folio, we can use the same function for both in gfs2. We can push the use of folios down one more level in jffs2 and nfs. We also increase type safety for future users of the various read_cache_page() family of functions by forcing the parameter to be a pointer to struct file (or NULL). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Andreas Gruenbacher --- include/linux/pagemap.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b70192f56454..831b28dab01a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -492,7 +492,7 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x) return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; } -typedef int filler_t(void *, struct page *); +typedef int filler_t(struct file *, struct folio *); pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); @@ -747,9 +747,9 @@ static inline struct page *grab_cache_page(struct address_space *mapping, } struct folio *read_cache_folio(struct address_space *, pgoff_t index, - filler_t *filler, void *data); + filler_t *filler, struct file *file); struct page *read_cache_page(struct address_space *, pgoff_t index, - filler_t *filler, void *data); + filler_t *filler, struct file *file); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); -- cgit v1.2.3 From 218d921b581eadf312c8ef0e09113b111f104eeb Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sat, 30 Apr 2022 22:08:54 -0700 Subject: fscrypt: add new helper functions for test_dummy_encryption Unfortunately the design of fscrypt_set_test_dummy_encryption() doesn't work properly for the new mount API, as it combines too many steps into one function: - Parse the argument to test_dummy_encryption - Check the setting against the filesystem instance - Apply the setting to the filesystem instance The new mount API has split these into separate steps. ext4 partially worked around this by duplicating some of the logic, but it still had some bugs. To address this, add some new helper functions that split up the steps of fscrypt_set_test_dummy_encryption(): - fscrypt_parse_test_dummy_encryption() - fscrypt_dummy_policies_equal() - fscrypt_add_test_dummy_key() While we're add it, also add a function fscrypt_is_dummy_policy_set() which will be useful to avoid some #ifdef's. Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20220501050857.538984-5-ebiggers@kernel.org --- include/linux/fscrypt.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index efc7f96e5e26..e60d57c99cb6 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -32,6 +32,7 @@ union fscrypt_policy; struct fscrypt_info; +struct fs_parameter; struct seq_file; struct fscrypt_str { @@ -289,10 +290,19 @@ struct fscrypt_dummy_policy { const union fscrypt_policy *policy; }; +int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, + struct fscrypt_dummy_policy *dummy_policy); +bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, + const struct fscrypt_dummy_policy *p2); int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg, struct fscrypt_dummy_policy *dummy_policy); void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb); +static inline bool +fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy) +{ + return dummy_policy->policy != NULL; +} static inline void fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { @@ -303,6 +313,8 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) /* keyring.c */ void fscrypt_sb_free(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); +int fscrypt_add_test_dummy_key(struct super_block *sb, + const struct fscrypt_dummy_policy *dummy_policy); int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); @@ -477,12 +489,32 @@ static inline int fscrypt_set_context(struct inode *inode, void *fs_data) struct fscrypt_dummy_policy { }; +static inline int +fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, + struct fscrypt_dummy_policy *dummy_policy) +{ + return -EINVAL; +} + +static inline bool +fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, + const struct fscrypt_dummy_policy *p2) +{ + return true; +} + static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb) { } +static inline bool +fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy) +{ + return false; +} + static inline void fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { @@ -498,6 +530,13 @@ static inline int fscrypt_ioctl_add_key(struct file *filp, void __user *arg) return -EOPNOTSUPP; } +static inline int +fscrypt_add_test_dummy_key(struct super_block *sb, + const struct fscrypt_dummy_policy *dummy_policy) +{ + return 0; +} + static inline int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg) { return -EOPNOTSUPP; -- cgit v1.2.3 From 623a1ddfeb232526275ddd0c8378771e6712aad4 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:42 -0700 Subject: mm/hugetlb: take src_mm->write_protect_seq in copy_hugetlb_page_range() Let's do it just like copy_page_range(), taking the seqlock and making sure the mmap_lock is held in write mode. This allows for add a VM_BUG_ON to page_needs_cow_for_dma() and properly synchronizes concurrent fork() with GUP-fast of hugetlb pages, which will be relevant for further changes. Link: https://lkml.kernel.org/r/20220428083441.37290-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index b9316b2c11ce..a02812178562 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1576,6 +1576,8 @@ static inline bool page_maybe_dma_pinned(struct page *page) /* * This should most likely only be called during fork() to see whether we * should break the cow immediately for a page on the src mm. + * + * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, struct page *page) @@ -1583,6 +1585,8 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, if (!is_cow_mapping(vma->vm_flags)) return false; + VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); + if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) return false; -- cgit v1.2.3 From fb3d824d1a46c5bb0584ea88f32dc2495544aebf Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: split page_dup_rmap() into page_dup_file_rmap() and page_try_dup_anon_rmap() ... and move the special check for pinned pages into page_try_dup_anon_rmap() to prepare for tracking exclusive anonymous pages via a new pageflag, clearing it only after making sure that there are no GUP pins on the anonymous page. We really only care about pins on anonymous pages, because they are prone to getting replaced in the COW handler once mapped R/O. For !anon pages in cow-mappings (!VM_SHARED && VM_MAYWRITE) we shouldn't really care about that, at least not that I could come up with an example. Let's drop the is_cow_mapping() check from page_needs_cow_for_dma(), as we know we're dealing with anonymous pages. Also, drop the handling of pinned pages from copy_huge_pud() and add a comment if ever supporting anonymous pages on the PUD level. This is a preparation for tracking exclusivity of anonymous pages in the rmap code, and disallowing marking a page shared (-> failing to duplicate) if there are GUP pins on a page. Link: https://lkml.kernel.org/r/20220428083441.37290-5-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/mm.h | 5 +---- include/linux/rmap.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 49 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index a02812178562..9ee3ae51e8e3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1575,16 +1575,13 @@ static inline bool page_maybe_dma_pinned(struct page *page) /* * This should most likely only be called during fork() to see whether we - * should break the cow immediately for a page on the src mm. + * should break the cow immediately for an anon page on the src mm. * * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, struct page *page) { - if (!is_cow_mapping(vma->vm_flags)) - return false; - VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 8573aae50d96..73f41544084f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -12,6 +12,7 @@ #include #include #include +#include /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -182,11 +183,57 @@ void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address); -static inline void page_dup_rmap(struct page *page, bool compound) +static inline void __page_dup_rmap(struct page *page, bool compound) { atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount); } +static inline void page_dup_file_rmap(struct page *page, bool compound) +{ + __page_dup_rmap(page, compound); +} + +/** + * page_try_dup_anon_rmap - try duplicating a mapping of an already mapped + * anonymous page + * @page: the page to duplicate the mapping for + * @compound: the page is mapped as compound or as a small page + * @vma: the source vma + * + * The caller needs to hold the PT lock and the vma->vma_mm->write_protect_seq. + * + * Duplicating the mapping can only fail if the page may be pinned; device + * private pages cannot get pinned and consequently this function cannot fail. + * + * If duplicating the mapping succeeds, the page has to be mapped R/O into + * the parent and the child. It must *not* get mapped writable after this call. + * + * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise. + */ +static inline int page_try_dup_anon_rmap(struct page *page, bool compound, + struct vm_area_struct *vma) +{ + VM_BUG_ON_PAGE(!PageAnon(page), page); + + /* + * If this page may have been pinned by the parent process, + * don't allow to duplicate the mapping but instead require to e.g., + * copy the page immediately for the child so that we'll always + * guarantee the pinned page won't be randomly replaced in the + * future on write faults. + */ + if (likely(!is_device_private_page(page) && + unlikely(page_needs_cow_for_dma(vma, page)))) + return -EBUSY; + + /* + * It's okay to share the anon page between both processes, mapping + * the page R/O into both processes. + */ + __page_dup_rmap(page, compound); + return 0; +} + /* * Called from mm/vmscan.c to handle paging out */ -- cgit v1.2.3 From 14f9135d547060d1d0c182501201f8da19895fe3 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: convert RMAP flags to a proper distinct rmap_t type We want to pass the flags to more than one anon rmap function, getting rid of special "do_page_add_anon_rmap()". So let's pass around a distinct __bitwise type and refine documentation. Link: https://lkml.kernel.org/r/20220428083441.37290-6-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 73f41544084f..c53a38151089 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -160,9 +160,23 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, struct anon_vma *page_get_anon_vma(struct page *page); -/* bitflags for do_page_add_anon_rmap() */ -#define RMAP_EXCLUSIVE 0x01 -#define RMAP_COMPOUND 0x02 +/* RMAP flags, currently only relevant for some anon rmap operations. */ +typedef int __bitwise rmap_t; + +/* + * No special request: if the page is a subpage of a compound page, it is + * mapped via a PTE. The mapped (sub)page is possibly shared between processes. + */ +#define RMAP_NONE ((__force rmap_t)0) + +/* The (sub)page is exclusive to a single process. */ +#define RMAP_EXCLUSIVE ((__force rmap_t)BIT(0)) + +/* + * The compound page is not mapped via PTEs, but instead via a single PMD and + * should be accounted accordingly. + */ +#define RMAP_COMPOUND ((__force rmap_t)BIT(1)) /* * rmap interfaces called when adding or removing pte of page @@ -171,7 +185,7 @@ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, bool compound); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, int flags); + unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, bool compound); void page_add_file_rmap(struct page *, struct vm_area_struct *, -- cgit v1.2.3 From f1e2db12e45baaa2d366f87c885968096c2ff5aa Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: remove do_page_add_anon_rmap() ... and instead convert page_add_anon_rmap() to accept flags. Passing flags instead of bools is usually nicer either way, and we want to more often also pass RMAP_EXCLUSIVE in follow up patches when detecting that an anonymous page is exclusive: for example, when restoring an anonymous page from a writable migration entry. This is a preparation for marking an anonymous page inside page_add_anon_rmap() as exclusive when RMAP_EXCLUSIVE is passed. Link: https://lkml.kernel.org/r/20220428083441.37290-7-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index c53a38151089..643801a937f3 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -183,8 +183,6 @@ typedef int __bitwise rmap_t; */ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, bool compound); -void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, bool compound); -- cgit v1.2.3 From 28c5209dfd5f86f4398ce01bfac8508b2c4d4050 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: pass rmap flags to hugepage_add_anon_rmap() Let's prepare for passing RMAP_EXCLUSIVE, similarly as we do for page_add_anon_rmap() now. RMAP_COMPOUND is implicit for hugetlb pages and ignored. Link: https://lkml.kernel.org/r/20220428083441.37290-8-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 643801a937f3..90e1e6925789 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -191,7 +191,7 @@ void page_add_file_rmap(struct page *, struct vm_area_struct *, void page_remove_rmap(struct page *, struct vm_area_struct *, bool compound); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address); + unsigned long address, rmap_t flags); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address); -- cgit v1.2.3 From 40f2bbf71161fa9195c7869004290003af152375 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: drop "compound" parameter from page_add_new_anon_rmap() New anonymous pages are always mapped natively: only THP/khugepaged code maps a new compound anonymous page and passes "true". Otherwise, we're just dealing with simple, non-compound pages. Let's give the interface clearer semantics and document these. Remove the PageTransCompound() sanity check from page_add_new_anon_rmap(). Link: https://lkml.kernel.org/r/20220428083441.37290-9-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 90e1e6925789..e4156921eea9 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -185,11 +185,12 @@ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, bool compound); + unsigned long address); void page_add_file_rmap(struct page *, struct vm_area_struct *, bool compound); void page_remove_rmap(struct page *, struct vm_area_struct *, bool compound); + void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, -- cgit v1.2.3 From 78fbe906cc900b33ce078102e13e0e99b5b8c406 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:44 -0700 Subject: mm/page-flags: reuse PG_mappedtodisk as PG_anon_exclusive for PageAnon() pages The basic question we would like to have a reliable and efficient answer to is: is this anonymous page exclusive to a single process or might it be shared? We need that information for ordinary/single pages, hugetlb pages, and possibly each subpage of a THP. Introduce a way to mark an anonymous page as exclusive, with the ultimate goal of teaching our COW logic to not do "wrong COWs", whereby GUP pins lose consistency with the pages mapped into the page table, resulting in reported memory corruptions. Most pageflags already have semantics for anonymous pages, however, PG_mappedtodisk should never apply to pages in the swapcache, so let's reuse that flag. As PG_has_hwpoisoned also uses that flag on the second tail page of a compound page, convert it to PG_error instead, which is marked as PF_NO_TAIL, so never used for tail pages. Use custom page flag modification functions such that we can do additional sanity checks. The semantics we'll put into some kernel doc in the future are: " PG_anon_exclusive is *usually* only expressive in combination with a page table entry. Depending on the page table entry type it might store the following information: Is what's mapped via this page table entry exclusive to the single process and can be mapped writable without further checks? If not, it might be shared and we might have to COW. For now, we only expect PTE-mapped THPs to make use of PG_anon_exclusive in subpages. For other anonymous compound folios (i.e., hugetlb), only the head page is logically mapped and holds this information. For example, an exclusive, PMD-mapped THP only has PG_anon_exclusive set on the head page. When replacing the PMD by a page table full of PTEs, PG_anon_exclusive, if set on the head page, will be set on all tail pages accordingly. Note that converting from a PTE-mapping to a PMD mapping using the same compound page is currently not possible and consequently doesn't require care. If GUP wants to take a reliable pin (FOLL_PIN) on an anonymous page, it should only pin if the relevant PG_anon_exclusive is set. In that case, the pin will be fully reliable and stay consistent with the pages mapped into the page table, as the bit cannot get cleared (e.g., by fork(), KSM) while the page is pinned. For anonymous pages that are mapped R/W, PG_anon_exclusive can be assumed to always be set because such pages cannot possibly be shared. The page table lock protecting the page table entry is the primary synchronization mechanism for PG_anon_exclusive; GUP-fast that does not take the PT lock needs special care when trying to clear the flag. Page table entry types and PG_anon_exclusive: * Present: PG_anon_exclusive applies. * Swap: the information is lost. PG_anon_exclusive was cleared. * Migration: the entry holds this information instead. PG_anon_exclusive was cleared. * Device private: PG_anon_exclusive applies. * Device exclusive: PG_anon_exclusive applies. * HW Poison: PG_anon_exclusive is stale and not changed. If the page may be pinned (FOLL_PIN), clearing PG_anon_exclusive is not allowed and the flag will stick around until the page is freed and folio->mapping is cleared. " We won't be clearing PG_anon_exclusive on destructive unmapping (i.e., zapping) of page table entries, page freeing code will handle that when also invalidate page->mapping to not indicate PageAnon() anymore. Letting information about exclusivity stick around will be an important property when adding sanity checks to unpinning code. Note that we properly clear the flag in free_pages_prepare() via PAGE_FLAGS_CHECK_AT_PREP for each individual subpage of a compound page, so there is no need to manually clear the flag. Link: https://lkml.kernel.org/r/20220428083441.37290-12-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1ea896887ee4..b70124b9c7c1 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -142,6 +142,15 @@ enum pageflags { PG_readahead = PG_reclaim, + /* + * Depending on the way an anonymous folio can be mapped into a page + * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped + * THP), PG_anon_exclusive may be set only for the head page or for + * tail pages of an anonymous folio. For now, we only expect it to be + * set on tail pages for PTE-mapped THP. + */ + PG_anon_exclusive = PG_mappedtodisk, + /* Filesystems */ PG_checked = PG_owner_priv_1, @@ -176,7 +185,7 @@ enum pageflags { * Indicates that at least one subpage is hwpoisoned in the * THP. */ - PG_has_hwpoisoned = PG_mappedtodisk, + PG_has_hwpoisoned = PG_error, #endif /* non-lru isolated movable page */ @@ -1002,6 +1011,34 @@ extern bool is_free_buddy_page(struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); +static __always_inline int PageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + +static __always_inline void SetPageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + +static __always_inline void ClearPageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + +static __always_inline void __ClearPageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else -- cgit v1.2.3 From 6c287605fd56466e645693eff3ae7c08fba56e0a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:44 -0700 Subject: mm: remember exclusively mapped anonymous pages with PG_anon_exclusive Let's mark exclusively mapped anonymous pages with PG_anon_exclusive as exclusive, and use that information to make GUP pins reliable and stay consistent with the page mapped into the page table even if the page table entry gets write-protected. With that information at hand, we can extend our COW logic to always reuse anonymous pages that are exclusive. For anonymous pages that might be shared, the existing logic applies. As already documented, PG_anon_exclusive is usually only expressive in combination with a page table entry. Especially PTE vs. PMD-mapped anonymous pages require more thought, some examples: due to mremap() we can easily have a single compound page PTE-mapped into multiple page tables exclusively in a single process -- multiple page table locks apply. Further, due to MADV_WIPEONFORK we might not necessarily write-protect all PTEs, and only some subpages might be pinned. Long story short: once PTE-mapped, we have to track information about exclusivity per sub-page, but until then, we can just track it for the compound page in the head page and not having to update a whole bunch of subpages all of the time for a simple PMD mapping of a THP. For simplicity, this commit mostly talks about "anonymous pages", while it's for THP actually "the part of an anonymous folio referenced via a page table entry". To not spill PG_anon_exclusive code all over the mm code-base, we let the anon rmap code to handle all PG_anon_exclusive logic it can easily handle. If a writable, present page table entry points at an anonymous (sub)page, that (sub)page must be PG_anon_exclusive. If GUP wants to take a reliably pin (FOLL_PIN) on an anonymous page references via a present page table entry, it must only pin if PG_anon_exclusive is set for the mapped (sub)page. This commit doesn't adjust GUP, so this is only implicitly handled for FOLL_WRITE, follow-up commits will teach GUP to also respect it for FOLL_PIN without FOLL_WRITE, to make all GUP pins of anonymous pages fully reliable. Whenever an anonymous page is to be shared (fork(), KSM), or when temporarily unmapping an anonymous page (swap, migration), the relevant PG_anon_exclusive bit has to be cleared to mark the anonymous page possibly shared. Clearing will fail if there are GUP pins on the page: * For fork(), this means having to copy the page and not being able to share it. fork() protects against concurrent GUP using the PT lock and the src_mm->write_protect_seq. * For KSM, this means sharing will fail. For swap this means, unmapping will fail, For migration this means, migration will fail early. All three cases protect against concurrent GUP using the PT lock and a proper clear/invalidate+flush of the relevant page table entry. This fixes memory corruptions reported for FOLL_PIN | FOLL_WRITE, when a pinned page gets mapped R/O and the successive write fault ends up replacing the page instead of reusing it. It improves the situation for O_DIRECT/vmsplice/... that still use FOLL_GET instead of FOLL_PIN, if fork() is *not* involved, however swapout and fork() are still problematic. Properly using FOLL_PIN instead of FOLL_GET for these GUP users will fix the issue for them. I. Details about basic handling I.1. Fresh anonymous pages page_add_new_anon_rmap() and hugepage_add_new_anon_rmap() will mark the given page exclusive via __page_set_anon_rmap(exclusive=1). As that is the mechanism fresh anonymous pages come into life (besides migration code where we copy the page->mapping), all fresh anonymous pages will start out as exclusive. I.2. COW reuse handling of anonymous pages When a COW handler stumbles over a (sub)page that's marked exclusive, it simply reuses it. Otherwise, the handler tries harder under page lock to detect if the (sub)page is exclusive and can be reused. If exclusive, page_move_anon_rmap() will mark the given (sub)page exclusive. Note that hugetlb code does not yet check for PageAnonExclusive(), as it still uses the old COW logic that is prone to the COW security issue because hugetlb code cannot really tolerate unnecessary/wrong COW as huge pages are a scarce resource. I.3. Migration handling try_to_migrate() has to try marking an exclusive anonymous page shared via page_try_share_anon_rmap(). If it fails because there are GUP pins on the page, unmap fails. migrate_vma_collect_pmd() and __split_huge_pmd_locked() are handled similarly. Writable migration entries implicitly point at shared anonymous pages. For readable migration entries that information is stored via a new "readable-exclusive" migration entry, specific to anonymous pages. When restoring a migration entry in remove_migration_pte(), information about exlusivity is detected via the migration entry type, and RMAP_EXCLUSIVE is set accordingly for page_add_anon_rmap()/hugepage_add_anon_rmap() to restore that information. I.4. Swapout handling try_to_unmap() has to try marking the mapped page possibly shared via page_try_share_anon_rmap(). If it fails because there are GUP pins on the page, unmap fails. For now, information about exclusivity is lost. In the future, we might want to remember that information in the swap entry in some cases, however, it requires more thought, care, and a way to store that information in swap entries. I.5. Swapin handling do_swap_page() will never stumble over exclusive anonymous pages in the swap cache, as try_to_migrate() prohibits that. do_swap_page() always has to detect manually if an anonymous page is exclusive and has to set RMAP_EXCLUSIVE for page_add_anon_rmap() accordingly. I.6. THP handling __split_huge_pmd_locked() has to move the information about exclusivity from the PMD to the PTEs. a) In case we have a readable-exclusive PMD migration entry, simply insert readable-exclusive PTE migration entries. b) In case we have a present PMD entry and we don't want to freeze ("convert to migration entries"), simply forward PG_anon_exclusive to all sub-pages, no need to temporarily clear the bit. c) In case we have a present PMD entry and want to freeze, handle it similar to try_to_migrate(): try marking the page shared first. In case we fail, we ignore the "freeze" instruction and simply split ordinarily. try_to_migrate() will properly fail because the THP is still mapped via PTEs. When splitting a compound anonymous folio (THP), the information about exclusivity is implicitly handled via the migration entries: no need to replicate PG_anon_exclusive manually. I.7. fork() handling fork() handling is relatively easy, because PG_anon_exclusive is only expressive for some page table entry types. a) Present anonymous pages page_try_dup_anon_rmap() will mark the given subpage shared -- which will fail if the page is pinned. If it failed, we have to copy (or PTE-map a PMD to handle it on the PTE level). Note that device exclusive entries are just a pointer at a PageAnon() page. fork() will first convert a device exclusive entry to a present page table and handle it just like present anonymous pages. b) Device private entry Device private entries point at PageAnon() pages that cannot be mapped directly and, therefore, cannot get pinned. page_try_dup_anon_rmap() will mark the given subpage shared, which cannot fail because they cannot get pinned. c) HW poison entries PG_anon_exclusive will remain untouched and is stale -- the page table entry is just a placeholder after all. d) Migration entries Writable and readable-exclusive entries are converted to readable entries: possibly shared. I.8. mprotect() handling mprotect() only has to properly handle the new readable-exclusive migration entry: When write-protecting a migration entry that points at an anonymous page, remember the information about exclusivity via the "readable-exclusive" migration entry type. II. Migration and GUP-fast Whenever replacing a present page table entry that maps an exclusive anonymous page by a migration entry, we have to mark the page possibly shared and synchronize against GUP-fast by a proper clear/invalidate+flush to make the following scenario impossible: 1. try_to_migrate() places a migration entry after checking for GUP pins and marks the page possibly shared. 2. GUP-fast pins the page due to lack of synchronization 3. fork() converts the "writable/readable-exclusive" migration entry into a readable migration entry 4. Migration fails due to the GUP pin (failing to freeze the refcount) 5. Migration entries are restored. PG_anon_exclusive is lost -> We have a pinned page that is not marked exclusive anymore. Note that we move information about exclusivity from the page to the migration entry as it otherwise highly overcomplicates fork() and PTE-mapping a THP. III. Swapout and GUP-fast Whenever replacing a present page table entry that maps an exclusive anonymous page by a swap entry, we have to mark the page possibly shared and synchronize against GUP-fast by a proper clear/invalidate+flush to make the following scenario impossible: 1. try_to_unmap() places a swap entry after checking for GUP pins and clears exclusivity information on the page. 2. GUP-fast pins the page due to lack of synchronization. -> We have a pinned page that is not marked exclusive anymore. If we'd ever store information about exclusivity in the swap entry, similar to migration handling, the same considerations as in II would apply. This is future work. Link: https://lkml.kernel.org/r/20220428083441.37290-13-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/swap.h | 15 +++++++++++---- include/linux/swapops.h | 25 +++++++++++++++++++++++++ 3 files changed, 76 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index e4156921eea9..cbe279a6f0de 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -228,6 +228,13 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound, { VM_BUG_ON_PAGE(!PageAnon(page), page); + /* + * No need to check+clear for already shared pages, including KSM + * pages. + */ + if (!PageAnonExclusive(page)) + goto dup; + /* * If this page may have been pinned by the parent process, * don't allow to duplicate the mapping but instead require to e.g., @@ -239,14 +246,47 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound, unlikely(page_needs_cow_for_dma(vma, page)))) return -EBUSY; + ClearPageAnonExclusive(page); /* * It's okay to share the anon page between both processes, mapping * the page R/O into both processes. */ +dup: __page_dup_rmap(page, compound); return 0; } +/** + * page_try_share_anon_rmap - try marking an exclusive anonymous page possibly + * shared to prepare for KSM or temporary unmapping + * @page: the exclusive anonymous page to try marking possibly shared + * + * The caller needs to hold the PT lock and has to have the page table entry + * cleared/invalidated+flushed, to properly sync against GUP-fast. + * + * This is similar to page_try_dup_anon_rmap(), however, not used during fork() + * to duplicate a mapping, but instead to prepare for KSM or temporarily + * unmapping a page (swap, migration) via page_remove_rmap(). + * + * Marking the page shared can only fail if the page may be pinned; device + * private pages cannot get pinned and consequently this function cannot fail. + * + * Returns 0 if marking the page possibly shared succeeded. Returns -EBUSY + * otherwise. + */ +static inline int page_try_share_anon_rmap(struct page *page) +{ + VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page); + + /* See page_try_dup_anon_rmap(). */ + if (likely(!is_device_private_page(page) && + unlikely(page_maybe_dma_pinned(page)))) + return -EBUSY; + + ClearPageAnonExclusive(page); + return 0; +} + /* * Called from mm/vmscan.c to handle paging out */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 27093b477c5f..e6d70a4156e8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -78,12 +78,19 @@ static inline int current_is_kswapd(void) #endif /* - * NUMA node memory migration support + * Page migration support. + * + * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and + * indicates that the referenced (part of) an anonymous page is exclusive to + * a single process. For SWP_MIGRATION_WRITE, that information is implicit: + * (part of) an anonymous page that are mapped writable are exclusive to a + * single process. */ #ifdef CONFIG_MIGRATION -#define SWP_MIGRATION_NUM 2 -#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) -#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_NUM 3 +#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) +#define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 5af852b68805..6648b97244e7 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -194,6 +194,7 @@ static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || + swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE || swp_type(entry) == SWP_MIGRATION_WRITE); } @@ -202,11 +203,26 @@ static inline int is_writable_migration_entry(swp_entry_t entry) return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ); +} + +static inline int is_readable_exclusive_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE); +} + static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ, offset); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset); +} + static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_WRITE, offset); @@ -224,6 +240,11 @@ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) return swp_entry(0, 0); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} + static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); @@ -244,6 +265,10 @@ static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return 0; +} #endif -- cgit v1.2.3 From 7f5abe609b3dcbc62a36e18b1437f4f3521ecb75 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:44 -0700 Subject: mm/rmap: fail try_to_migrate() early when setting a PMD migration entry fails Let's fail right away in case we cannot clear PG_anon_exclusive because the anon THP may be pinned. Right now, we continue trying to install migration entries and the caller of try_to_migrate() will realize that the page is still mapped and has to restore the migration entries. Let's just fail fast just like for PTE migration entries. Link: https://lkml.kernel.org/r/20220428083441.37290-14-david@redhat.com Signed-off-by: David Hildenbrand Suggested-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/swapops.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 6648b97244e7..e476a8fed537 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -299,7 +299,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry) struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION -extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, +extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, @@ -332,7 +332,7 @@ static inline int is_pmd_migration_entry(pmd_t pmd) return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else -static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, +static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); -- cgit v1.2.3 From c89357e27f20dda3fff6791d27bb6c91eae99f4a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:45 -0700 Subject: mm: support GUP-triggered unsharing of anonymous pages Whenever GUP currently ends up taking a R/O pin on an anonymous page that might be shared -- mapped R/O and !PageAnonExclusive() -- any write fault on the page table entry will end up replacing the mapped anonymous page due to COW, resulting in the GUP pin no longer being consistent with the page actually mapped into the page table. The possible ways to deal with this situation are: (1) Ignore and pin -- what we do right now. (2) Fail to pin -- which would be rather surprising to callers and could break user space. (3) Trigger unsharing and pin the now exclusive page -- reliable R/O pins. We want to implement 3) because it provides the clearest semantics and allows for checking in unpin_user_pages() and friends for possible BUGs: when trying to unpin a page that's no longer exclusive, clearly something went very wrong and might result in memory corruptions that might be hard to debug. So we better have a nice way to spot such issues. To implement 3), we need a way for GUP to trigger unsharing: FAULT_FLAG_UNSHARE. FAULT_FLAG_UNSHARE is only applicable to R/O mapped anonymous pages and resembles COW logic during a write fault. However, in contrast to a write fault, GUP-triggered unsharing will, for example, still maintain the write protection. Let's implement FAULT_FLAG_UNSHARE by hooking into the existing write fault handlers for all applicable anonymous page types: ordinary pages, THP and hugetlb. * If FAULT_FLAG_UNSHARE finds a R/O-mapped anonymous page that has been marked exclusive in the meantime by someone else, there is nothing to do. * If FAULT_FLAG_UNSHARE finds a R/O-mapped anonymous page that's not marked exclusive, it will try detecting if the process is the exclusive owner. If exclusive, it can be set exclusive similar to reuse logic during write faults via page_move_anon_rmap() and there is nothing else to do; otherwise, we either have to copy and map a fresh, anonymous exclusive page R/O (ordinary pages, hugetlb), or split the THP. This commit is heavily based on patches by Andrea. Link: https://lkml.kernel.org/r/20220428083441.37290-16-david@redhat.com Signed-off-by: Andrea Arcangeli Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Co-developed-by: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 87eddd509de2..7216d77a5884 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -819,6 +819,9 @@ typedef struct { * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. + * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to unshare (and mark + * exclusive) a possibly shared anonymous page that is + * mapped R/O. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -838,6 +841,10 @@ typedef struct { * continuous faults with flags (b). We should always try to detect pending * signals before a retry to make sure the continuous page faults can still be * interrupted if necessary. + * + * The combination FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE is illegal. + * FAULT_FLAG_UNSHARE is ignored and treated like an ordinary read fault when + * no existing R/O-mapped anonymous page is encountered. */ enum fault_flag { FAULT_FLAG_WRITE = 1 << 0, @@ -850,6 +857,7 @@ enum fault_flag { FAULT_FLAG_REMOTE = 1 << 7, FAULT_FLAG_INSTRUCTION = 1 << 8, FAULT_FLAG_INTERRUPTIBLE = 1 << 9, + FAULT_FLAG_UNSHARE = 1 << 10, }; #endif /* _LINUX_MM_TYPES_H */ -- cgit v1.2.3 From a7f226604170acd6b142b76472c1a49c12ebb83d Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:45 -0700 Subject: mm/gup: trigger FAULT_FLAG_UNSHARE when R/O-pinning a possibly shared anonymous page Whenever GUP currently ends up taking a R/O pin on an anonymous page that might be shared -- mapped R/O and !PageAnonExclusive() -- any write fault on the page table entry will end up replacing the mapped anonymous page due to COW, resulting in the GUP pin no longer being consistent with the page actually mapped into the page table. The possible ways to deal with this situation are: (1) Ignore and pin -- what we do right now. (2) Fail to pin -- which would be rather surprising to callers and could break user space. (3) Trigger unsharing and pin the now exclusive page -- reliable R/O pins. Let's implement 3) because it provides the clearest semantics and allows for checking in unpin_user_pages() and friends for possible BUGs: when trying to unpin a page that's no longer exclusive, clearly something went very wrong and might result in memory corruptions that might be hard to debug. So we better have a nice way to spot such issues. This change implies that whenever user space *wrote* to a private mapping (IOW, we have an anonymous page mapped), that GUP pins will always remain consistent: reliable R/O GUP pins of anonymous pages. As a side note, this commit fixes the COW security issue for hugetlb with FOLL_PIN as documented in: https://lore.kernel.org/r/3ae33b08-d9ef-f846-56fb-645e3b9b4c66@redhat.com The vmsplice reproducer still applies, because vmsplice uses FOLL_GET instead of FOLL_PIN. Note that follow_huge_pmd() doesn't apply because we cannot end up in there with FOLL_PIN. This commit is heavily based on prototype patches by Andrea. Link: https://lkml.kernel.org/r/20220428083441.37290-17-david@redhat.com Signed-off-by: Andrea Arcangeli Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Co-developed-by: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/mm.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9ee3ae51e8e3..5dc5005ccc9b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3002,6 +3002,45 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) return 0; } +/* + * Indicates for which pages that are write-protected in the page table, + * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the + * GUP pin will remain consistent with the pages mapped into the page tables + * of the MM. + * + * Temporary unmapping of PageAnonExclusive() pages or clearing of + * PageAnonExclusive() has to protect against concurrent GUP: + * * Ordinary GUP: Using the PT lock + * * GUP-fast and fork(): mm->write_protect_seq + * * GUP-fast and KSM or temporary unmapping (swap, migration): + * clear/invalidate+flush of the page table entry + * + * Must be called with the (sub)page that's actually referenced via the + * page table entry, which might not necessarily be the head page for a + * PTE-mapped THP. + */ +static inline bool gup_must_unshare(unsigned int flags, struct page *page) +{ + /* + * FOLL_WRITE is implicitly handled correctly as the page table entry + * has to be writable -- and if it references (part of) an anonymous + * folio, that part is required to be marked exclusive. + */ + if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) + return false; + /* + * Note: PageAnon(page) is stable until the page is actually getting + * freed. + */ + if (!PageAnon(page)) + return false; + /* + * Note that PageKsm() pages cannot be exclusive, and consequently, + * cannot get pinned. + */ + return !PageAnonExclusive(page); +} + typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -- cgit v1.2.3 From 1493a1913e34b0ac366e33f9ebad721e69fd06ac Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:45 -0700 Subject: mm/swap: remember PG_anon_exclusive via a swp pte bit Patch series "mm: COW fixes part 3: reliable GUP R/W FOLL_GET of anonymous pages", v2. This series fixes memory corruptions when a GUP R/W reference (FOLL_WRITE | FOLL_GET) was taken on an anonymous page and COW logic fails to detect exclusivity of the page to then replacing the anonymous page by a copy in the page table: The GUP reference lost synchronicity with the pages mapped into the page tables. This series focuses on x86, arm64, s390x and ppc64/book3s -- other architectures are fairly easy to support by implementing __HAVE_ARCH_PTE_SWP_EXCLUSIVE. This primarily fixes the O_DIRECT memory corruptions that can happen on concurrent swapout, whereby we lose DMA reads to a page (modifying the user page by writing to it). O_DIRECT currently uses FOLL_GET for short-term (!FOLL_LONGTERM) DMA from/to a user page. In the long run, we want to convert it to properly use FOLL_PIN, and John is working on it, but that might take a while and might not be easy to backport. In the meantime, let's restore what used to work before we started modifying our COW logic: make R/W FOLL_GET references reliable as long as there is no fork() after GUP involved. This is just the natural follow-up of part 2, that will also further reduce "wrong COW" on the swapin path, for example, when we cannot remove a page from the swapcache due to concurrent writeback, or if we have two threads faulting on the same swapped-out page. Fixing O_DIRECT is just a nice side-product This issue, including other related COW issues, has been summarized in [3] under 2): " 2. Intra Process Memory Corruptions due to Wrong COW (FOLL_GET) It was discovered that we can create a memory corruption by reading a file via O_DIRECT to a part (e.g., first 512 bytes) of a page, concurrently writing to an unrelated part (e.g., last byte) of the same page, and concurrently write-protecting the page via clear_refs SOFTDIRTY tracking [6]. For the reproducer, the issue is that O_DIRECT grabs a reference of the target page (via FOLL_GET) and clear_refs write-protects the relevant page table entry. On successive write access to the page from the process itself, we wrongly COW the page when resolving the write fault, resulting in a loss of synchronicity and consequently a memory corruption. While some people might think that using clear_refs in this combination is a corner cases, it turns out to be a more generic problem unfortunately. For example, it was just recently discovered that we can similarly create a memory corruption without clear_refs, simply by concurrently swapping out the buffer pages [7]. Note that we nowadays even use the swap infrastructure in Linux without an actual swap disk/partition: the prime example is zram which is enabled as default under Fedora [10]. The root issue is that a write-fault on a page that has additional references results in a COW and thereby a loss of synchronicity and consequently a memory corruption if two parties believe they are referencing the same page. " We don't particularly care about R/O FOLL_GET references: they were never reliable and O_DIRECT doesn't expect to observe modifications from a page after DMA was started. Note that: * this only fixes the issue on x86, arm64, s390x and ppc64/book3s ("enterprise architectures"). Other architectures have to implement __HAVE_ARCH_PTE_SWP_EXCLUSIVE to achieve the same. * this does *not * consider any kind of fork() after taking the reference: fork() after GUP never worked reliably with FOLL_GET. * Not losing PG_anon_exclusive during swapout was the last remaining piece. KSM already makes sure that there are no other references on a page before considering it for sharing. Page migration maintains PG_anon_exclusive and simply fails when there are additional references (freezing the refcount fails). Only swapout code dropped the PG_anon_exclusive flag because it requires more work to remember + restore it. With this series in place, most COW issues of [3] are fixed on said architectures. Other architectures can implement __HAVE_ARCH_PTE_SWP_EXCLUSIVE fairly easily. [1] https://lkml.kernel.org/r/20220329160440.193848-1-david@redhat.com [2] https://lkml.kernel.org/r/20211217113049.23850-1-david@redhat.com [3] https://lore.kernel.org/r/3ae33b08-d9ef-f846-56fb-645e3b9b4c66@redhat.com This patch (of 8): Currently, we clear PG_anon_exclusive in try_to_unmap() and forget about it. We do this, to keep fork() logic on swap entries easy and efficient: for example, if we wouldn't clear it when unmapping, we'd have to lookup the page in the swapcache for each and every swap entry during fork() and clear PG_anon_exclusive if set. Instead, we want to store that information directly in the swap pte, protected by the page table lock, similarly to how we handle SWP_MIGRATION_READ_EXCLUSIVE for migration entries. However, for actual swap entries, we don't want to mess with the swap type (e.g., still one bit) because it overcomplicates swap code. In try_to_unmap(), we already reject to unmap in case the page might be pinned, because we must not lose PG_anon_exclusive on pinned pages ever. Checking if there are other unexpected references reliably *before* completely unmapping a page is unfortunately not really possible: THP heavily overcomplicate the situation. Once fully unmapped it's easier -- we, for example, make sure that there are no unexpected references *after* unmapping a page before starting writeback on that page. So, we currently might end up unmapping a page and clearing PG_anon_exclusive if that page has additional references, for example, due to a FOLL_GET. do_swap_page() has to re-determine if a page is exclusive, which will easily fail if there are other references on a page, most prominently GUP references via FOLL_GET. This can currently result in memory corruptions when taking a FOLL_GET | FOLL_WRITE reference on a page even when fork() is never involved: try_to_unmap() will succeed, and when refaulting the page, it cannot be marked exclusive and will get replaced by a copy in the page tables on the next write access, resulting in writes via the GUP reference to the page being lost. In an ideal world, everybody that uses GUP and wants to modify page content, such as O_DIRECT, would properly use FOLL_PIN. However, that conversion will take a while. It's easier to fix what used to work in the past (FOLL_GET | FOLL_WRITE) remembering PG_anon_exclusive. In addition, by remembering PG_anon_exclusive we can further reduce unnecessary COW in some cases, so it's the natural thing to do. So let's transfer the PG_anon_exclusive information to the swap pte and store it via an architecture-dependant pte bit; use that information when restoring the swap pte in do_swap_page() and unuse_pte(). During fork(), we simply have to clear the pte bit and are done. Of course, there is one corner case to handle: swap backends that don't support concurrent page modifications while the page is under writeback. Special case these, and drop the exclusive marker. Add a comment why that is just fine (also, reuse_swap_page() would have done the same in the past). In the future, we'll hopefully have all architectures support __HAVE_ARCH_PTE_SWP_EXCLUSIVE, such that we can get rid of the empty stubs and the define completely. Then, we can also convert SWP_MIGRATION_READ_EXCLUSIVE. For architectures it's fairly easy to support: either simply use a yet unused pte bit that can be used for swap entries, steal one from the arch type bits if they exceed 5, or steal one from the offset bits. Note: R/O FOLL_GET references were never really reliable, especially when taking one on a shared page and then writing to the page (e.g., GUP after fork()). FOLL_GET, including R/W references, were never really reliable once fork was involved (e.g., GUP before fork(), GUP during fork()). KSM steps back in case it stumbles over unexpected references and is, therefore, fine. [david@redhat.com: fix SWP_STABLE_WRITES test] Link: https://lkml.kernel.org/r/ac725bcb-313a-4fff-250a-68ba9a8f85fb@redhat.comLink: https://lkml.kernel.org/r/20220329164329.208407-1-david@redhat.com Link: https://lkml.kernel.org/r/20220329164329.208407-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Hugh Dickins Cc: Shakeel Butt Cc: John Hubbard Cc: Jason Gunthorpe Cc: Mike Kravetz Cc: Mike Rapoport Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox (Oracle) Cc: Jann Horn Cc: Michal Hocko Cc: Nadav Amit Cc: Rik van Riel Cc: Roman Gushchin Cc: Andrea Arcangeli Cc: Peter Xu Cc: Don Dutile Cc: Christoph Hellwig Cc: Oleg Nesterov Cc: Jan Kara Cc: Liang Zhang Cc: Pedro Demarchi Gomes Cc: Oded Gabbay Cc: Catalin Marinas Cc: Will Deacon Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: Gerald Schaefer Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 29 +++++++++++++++++++++++++++++ include/linux/swapops.h | 2 ++ 2 files changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index f4f4077b97aa..53750224e176 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1003,6 +1003,35 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define arch_start_context_switch(prev) do {} while (0) #endif +/* + * When replacing an anonymous page by a real (!non) swap entry, we clear + * PG_anon_exclusive from the page and instead remember whether the flag was + * set in the swp pte. During fork(), we have to mark the entry as !exclusive + * (possibly shared). On swapin, we use that information to restore + * PG_anon_exclusive, which is very helpful in cases where we might have + * additional (e.g., FOLL_GET) references on a page and wouldn't be able to + * detect exclusivity. + * + * These functions don't apply to non-swap entries (e.g., migration, hwpoison, + * ...). + */ +#ifndef __HAVE_ARCH_PTE_SWP_EXCLUSIVE +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return pte; +} + +static inline int pte_swp_exclusive(pte_t pte) +{ + return false; +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return pte; +} +#endif + #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) diff --git a/include/linux/swapops.h b/include/linux/swapops.h index e476a8fed537..d1b728904d4e 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -26,6 +26,8 @@ /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { + if (pte_swp_exclusive(pte)) + pte = pte_swp_clear_exclusive(pte); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); if (pte_swp_uffd_wp(pte)) -- cgit v1.2.3 From 014bb1de4fc17d54907d54418126a9a9736f4aff Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:47 -0700 Subject: mm: create new mm/swap.h header file Patch series "MM changes to improve swap-over-NFS support". Assorted improvements for swap-via-filesystem. This is a resend of these patches, rebased on current HEAD. The only substantial changes is that swap_dirty_folio has replaced swap_set_page_dirty. Currently swap-via-fs (SWP_FS_OPS) doesn't work for any filesystem. It has previously worked for NFS but that broke a few releases back. This series changes to use a new ->swap_rw rather than ->readpage and ->direct_IO. It also makes other improvements. There is a companion series already in linux-next which fixes various issues with NFS. Once both series land, a final patch is needed which changes NFS over to use ->swap_rw. This patch (of 10): Many functions declared in include/linux/swap.h are only used within mm/ Create a new "mm/swap.h" and move some of these declarations there. Remove the redundant 'extern' from the function declarations. [akpm@linux-foundation.org: mm/memory-failure.c needs mm/swap.h] Link: https://lkml.kernel.org/r/164859751830.29473.5309689752169286816.stgit@noble.brown Link: https://lkml.kernel.org/r/164859778120.29473.11725907882296224053.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Trond Myklebust Cc: Hugh Dickins Cc: Mel Gorman Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/swap.h | 121 --------------------------------------------------- 1 file changed, 121 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index e6d70a4156e8..def67112dce4 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -427,62 +427,19 @@ extern void kswapd_stop(int nid); #ifdef CONFIG_SWAP -#include /* for bio_end_io_t */ - -/* linux/mm/page_io.c */ -extern int swap_readpage(struct page *page, bool do_poll); -extern int swap_writepage(struct page *page, struct writeback_control *wbc); -extern void end_swap_bio_write(struct bio *bio); -extern int __swap_writepage(struct page *page, struct writeback_control *wbc, - bio_end_io_t end_write_func); bool swap_dirty_folio(struct address_space *mapping, struct folio *folio); - int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); -/* linux/mm/swap_state.c */ -/* One swap address space for each 64M swap space */ -#define SWAP_ADDRESS_SPACE_SHIFT 14 -#define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) -extern struct address_space *swapper_spaces[]; -#define swap_address_space(entry) \ - (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ - >> SWAP_ADDRESS_SPACE_SHIFT]) static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } -extern void show_swap_cache_info(void); -extern int add_to_swap(struct page *page); -extern void *get_shadow_from_swap_cache(swp_entry_t entry); -extern int add_to_swap_cache(struct page *page, swp_entry_t entry, - gfp_t gfp, void **shadowp); -extern void __delete_from_swap_cache(struct page *page, - swp_entry_t entry, void *shadow); -extern void delete_from_swap_cache(struct page *); -extern void clear_shadow_from_swap_cache(int type, unsigned long begin, - unsigned long end); -extern void free_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); -extern struct page *lookup_swap_cache(swp_entry_t entry, - struct vm_area_struct *vma, - unsigned long addr); -struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index); -extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr, - bool do_poll); -extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr, - bool *new_page_allocated); -extern struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, - struct vm_fault *vmf); -extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, - struct vm_fault *vmf); - /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; @@ -535,12 +492,6 @@ static inline void put_swap_device(struct swap_info_struct *si) } #else /* CONFIG_SWAP */ - -static inline int swap_readpage(struct page *page, bool do_poll) -{ - return 0; -} - static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return NULL; @@ -555,11 +506,6 @@ static inline void put_swap_device(struct swap_info_struct *si) { } -static inline struct address_space *swap_address_space(swp_entry_t entry) -{ - return NULL; -} - #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL @@ -574,14 +520,6 @@ static inline struct address_space *swap_address_space(swp_entry_t entry) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); -static inline void free_swap_cache(struct page *page) -{ -} - -static inline void show_swap_cache_info(void) -{ -} - /* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ #define free_swap_and_cache(e) is_pfn_swap_entry(e) @@ -607,65 +545,6 @@ static inline void put_swap_page(struct page *page, swp_entry_t swp) { } -static inline struct page *swap_cluster_readahead(swp_entry_t entry, - gfp_t gfp_mask, struct vm_fault *vmf) -{ - return NULL; -} - -static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, - struct vm_fault *vmf) -{ - return NULL; -} - -static inline int swap_writepage(struct page *p, struct writeback_control *wbc) -{ - return 0; -} - -static inline struct page *lookup_swap_cache(swp_entry_t swp, - struct vm_area_struct *vma, - unsigned long addr) -{ - return NULL; -} - -static inline -struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) -{ - return find_get_page(mapping, index); -} - -static inline int add_to_swap(struct page *page) -{ - return 0; -} - -static inline void *get_shadow_from_swap_cache(swp_entry_t entry) -{ - return NULL; -} - -static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, - gfp_t gfp_mask, void **shadowp) -{ - return -1; -} - -static inline void __delete_from_swap_cache(struct page *page, - swp_entry_t entry, void *shadow) -{ -} - -static inline void delete_from_swap_cache(struct page *page) -{ -} - -static inline void clear_shadow_from_swap_cache(int type, unsigned long begin, - unsigned long end) -{ -} static inline int page_swapcount(struct page *page) { -- cgit v1.2.3 From 4c4a763406ef903b78334bd2ccea168d2f7a741a Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:47 -0700 Subject: mm: drop swap_dirty_folio folios that are written to swap are owned by the MM subsystem - not any filesystem. When such a folio is passed to a filesystem to be written out to a swap-file, the filesystem handles the data, but the folio itself does not belong to the filesystem. So calling the filesystem's ->dirty_folio() address_space operation makes no sense. This is for folios in the given address space, and a folio to be written to swap does not exist in the given address space. So drop swap_dirty_folio() which calls the address-space's ->dirty_folio(), and always use noop_dirty_folio(), which is appropriate for folios being swapped out. Link: https://lkml.kernel.org/r/164859778123.29473.6900942583784889976.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Hugh Dickins Cc: Mel Gorman Cc: Trond Myklebust Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index def67112dce4..8170254c56b0 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -427,7 +427,6 @@ extern void kswapd_stop(int nid); #ifdef CONFIG_SWAP -bool swap_dirty_folio(struct address_space *mapping, struct folio *folio); int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, -- cgit v1.2.3 From 4b60c0ff2f2021ab99b7fb9da63b7ed1579ef1d8 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:48 -0700 Subject: mm: move responsibility for setting SWP_FS_OPS to ->swap_activate If a filesystem wishes to handle all swap IO itself (via ->direct_IO and ->readpage), rather than just providing devices addresses for submit_bio(), SWP_FS_OPS must be set. Currently the protocol for setting this it to have ->swap_activate return zero. In that case SWP_FS_OPS is set, and add_swap_extent() is called for the entire file. This is a little clumsy as different return values for ->swap_activate have quite different meanings, and it makes it hard to search for which filesystems require SWP_FS_OPS to be set. So remove the special meaning of a zero return, and require the filesystem to set SWP_FS_OPS if it so desires, and to always call add_swap_extent() as required. Currently only NFS and CIFS return zero for add_swap_extent(). Link: https://lkml.kernel.org/r/164859778123.29473.17908205846599043598.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Hugh Dickins Cc: Mel Gorman Cc: Trond Myklebust Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/swap.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 8170254c56b0..7daae5a4b3e1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -577,6 +577,12 @@ static inline swp_entry_t get_swap_page(struct page *page) return entry; } +static inline int add_swap_extent(struct swap_info_struct *sis, + unsigned long start_page, + unsigned long nr_pages, sector_t start_block) +{ + return -EINVAL; +} #endif /* CONFIG_SWAP */ #ifdef CONFIG_THP_SWAP -- cgit v1.2.3 From e1209d3a7a67c281260ba9989621060ba7328b8c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:48 -0700 Subject: mm: introduce ->swap_rw and use it for reads from SWP_FS_OPS swap-space swap currently uses ->readpage to read swap pages. This can only request one page at a time from the filesystem, which is not most efficient. swap uses ->direct_IO for writes which while this is adequate is an inappropriate over-loading. ->direct_IO may need to had handle allocate space for holes or other details that are not relevant for swap. So this patch introduces a new address_space operation: ->swap_rw. In this patch it is used for reads, and a subsequent patch will switch writes to use it. No filesystem yet supports ->swap_rw, but that is not a problem because no filesystem actually works with filesystem-based swap. Only two filesystems set SWP_FS_OPS: - cifs sets the flag, but ->direct_IO always fails so swap cannot work. - nfs sets the flag, but ->direct_IO calls generic_write_checks() which has failed on swap files for several releases. To ensure that a NULL ->swap_rw isn't called, ->activate_swap() for both NFS and cifs are changed to fail if ->swap_rw is not set. This can be removed if/when the function is added. Future patches will restore swap-over-NFS functionality. To submit an async read with ->swap_rw() we need to allocate a structure to hold the kiocb and other details. swap_readpage() cannot handle transient failure, so we create a mempool to provide the structures. Link: https://lkml.kernel.org/r/164859778125.29473.13430559328221330589.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Hugh Dickins Cc: Mel Gorman Cc: Trond Myklebust Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..dbc5d10328df 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -380,6 +380,7 @@ struct address_space_operations { int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); + int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; -- cgit v1.2.3 From eb79f3af9395fbe448e91b0940a6c395b7d06be4 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:48 -0700 Subject: nfs: rename nfs_direct_IO and use as ->swap_rw The nfs_direct_IO() exists to support SWAP IO, but hasn't worked for a while. We now need a ->swap_rw function which behaves slightly differently, returning zero for success rather than a byte count. So modify nfs_direct_IO accordingly, rename it, and use it as the ->swap_rw function. Link: https://lkml.kernel.org/r/165119301493.15698.7491285551903597618.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: Geert Uytterhoeven (on Renesas RSK+RZA1 with 32 MiB of SDRAM) Cc: David Howells Cc: Hugh Dickins Cc: Mel Gorman Cc: Miaohe Lin Cc: Trond Myklebust Signed-off-by: Andrew Morton --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b48b9259e02c..fd5543486a3f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -507,7 +507,7 @@ static inline const struct cred *nfs_file_cred(struct file *file) /* * linux/fs/nfs/direct.c */ -extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *); +int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter); ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, bool swap); ssize_t nfs_file_direct_write(struct kiocb *iocb, -- cgit v1.2.3 From 2282679fb20bf036a714ed49fadd0230c278a203 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:49 -0700 Subject: mm: submit multipage write for SWP_FS_OPS swap-space swap_writepage() is given one page at a time, but may be called repeatedly in succession. For block-device swapspace, the blk_plug functionality allows the multiple pages to be combined together at lower layers. That cannot be used for SWP_FS_OPS as blk_plug may not exist - it is only active when CONFIG_BLOCK=y. Consequently all swap reads over NFS are single page reads. With this patch we pass a pointer-to-pointer via the wbc. swap_writepage can store state between calls - much like the pointer passed explicitly to swap_readpage. After calling swap_writepage() some number of times, the state will be passed to swap_write_unplug() which can submit the combined request. Link: https://lkml.kernel.org/r/164859778128.29473.5191868522654408537.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Hugh Dickins Cc: Mel Gorman Cc: Trond Myklebust Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/writeback.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fec248ab1fec..32b35f21cb97 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -80,6 +80,13 @@ struct writeback_control { unsigned punt_to_cgroup:1; /* cgrp punting, see __REQ_CGROUP_PUNT */ + /* To enable batching of swap writes to non-block-device backends, + * "plug" can be set point to a 'struct swap_iocb *'. When all swap + * writes have been submitted, if with swap_iocb is not NULL, + * swap_write_unplug() should be called. + */ + struct swap_iocb **swap_plug; + #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ -- cgit v1.2.3 From a2ad63daa88b9d6846976fd2a0b5e4f5cfc58377 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:49 -0700 Subject: VFS: add FMODE_CAN_ODIRECT file flag Currently various places test if direct IO is possible on a file by checking for the existence of the direct_IO address space operation. This is a poor choice, as the direct_IO operation may not be used - it is only used if the generic_file_*_iter functions are called for direct IO and some filesystems - particularly NFS - don't do this. Instead, introduce a new f_mode flag: FMODE_CAN_ODIRECT and change the various places to check this (avoiding pointer dereferences). do_dentry_open() will set this flag if ->direct_IO is present, so filesystems do not need to be changed. NFS *is* changed, to set the flag explicitly and discard the direct_IO entry in the address_space_operations for files. Other filesystems which currently use noop_direct_IO could usefully be changed to set this flag instead. Link: https://lkml.kernel.org/r/164859778128.29473.15189737957277399416.stgit@noble.brown Reviewed-by: Christoph Hellwig Signed-off-by: NeilBrown Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Hugh Dickins Cc: Mel Gorman Cc: Trond Myklebust Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index dbc5d10328df..b81cacc51d2f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -162,6 +162,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)0x200000) +/* File supports DIRECT IO */ +#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) -- cgit v1.2.3 From fa29000b6b2603ec2bfdc4c73249fcb00cd54f85 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 17:00:05 -0400 Subject: fs: Add aops->release_folio This replaces aops->releasepage. Update the documentation, and call it if it exists. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jeff Layton --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index f812f5aa07dd..ad768f13f485 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -355,6 +355,7 @@ struct address_space_operations { /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); + bool (*release_folio)(struct folio *, gfp_t); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); -- cgit v1.2.3 From 8597447dc565a6a3fa7bc503674452b7ae2b914c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 30 Apr 2022 23:01:08 -0400 Subject: iomap: Convert to release_folio Change all the filesystems which used iomap_releasepage to use the new function. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jeff Layton --- include/linux/iomap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 5b2aa45ddda3..0d674695b6d3 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -228,7 +228,7 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); -int iomap_releasepage(struct page *page, gfp_t gfp_mask); +bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); #ifdef CONFIG_MIGRATION int iomap_migrate_page(struct address_space *mapping, struct page *newpage, -- cgit v1.2.3 From 704ead2bed202579f025a4754e52e9ab21ff3ada Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 1 May 2022 00:27:53 -0400 Subject: fs: Remove last vestiges of releasepage All users are now converted to release_folio Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jeff Layton --- include/linux/fs.h | 1 - include/linux/page-flags.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index ad768f13f485..1cee64d9724b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -356,7 +356,6 @@ struct address_space_operations { sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); - int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 9d8eeaa67d05..af10149a6c31 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -516,7 +516,7 @@ PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. - * - PG_private and PG_private_2 cause releasepage() and co to be invoked + * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) -- cgit v1.2.3 From c56a6eb03deb187c989a966fda5a254249b56c2a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 1 May 2022 00:46:03 -0400 Subject: jbd2: Convert jbd2_journal_try_to_free_buffers to take a folio Also convert it to return a bool since it's called from release_folio(). Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Theodore Ts'o Reviewed-by: Jeff Layton --- include/linux/jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index de9536680b2b..e79d6e0b14e8 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1529,7 +1529,7 @@ extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); int jbd2_journal_invalidate_folio(journal_t *, struct folio *, size_t offset, size_t length); -extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); +bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); -- cgit v1.2.3 From 68189fef88c7d02eb92e038be3d6428ebd0d2945 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 1 May 2022 01:08:08 -0400 Subject: fs: Change try_to_free_buffers() to take a folio All but two of the callers already have a folio; pass a folio into try_to_free_buffers(). This removes the last user of cancel_dirty_page() so remove that wrapper function too. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jeff Layton --- include/linux/buffer_head.h | 4 ++-- include/linux/pagemap.h | 4 ---- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 31d82fd9abe8..c9d1463bb20f 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -158,7 +158,7 @@ void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); -int try_to_free_buffers(struct page *); +bool try_to_free_buffers(struct folio *); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, @@ -402,7 +402,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio); #else /* CONFIG_BLOCK */ static inline void buffer_init(void) {} -static inline int try_to_free_buffers(struct page *page) { return 1; } +static inline bool try_to_free_buffers(struct folio *folio) { return true; } static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 831b28dab01a..82dfb279e0c4 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1067,10 +1067,6 @@ static inline void folio_cancel_dirty(struct folio *folio) if (folio_test_dirty(folio)) __folio_cancel_dirty(folio); } -static inline void cancel_dirty_page(struct page *page) -{ - folio_cancel_dirty(page_folio(page)); -} bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); -- cgit v1.2.3 From d2329aa0c78f4a8dd368bb706f196ab99f692eaa Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 1 May 2022 07:35:31 -0400 Subject: fs: Add free_folio address space operation Include documentation and convert the callers to use ->free_folio as well as ->freepage. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1cee64d9724b..915844e6293e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -356,6 +356,7 @@ struct address_space_operations { sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); + void (*free_folio)(struct folio *folio); void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* -- cgit v1.2.3 From 8560cb1a7d75048af275dd23fb0cf05382b3c2b9 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 5 May 2022 00:43:09 -0400 Subject: fs: Remove aops->freepage All implementations now use free_folio so we can delete the callers and the method. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 915844e6293e..6f305f1097a5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -357,7 +357,6 @@ struct address_space_operations { void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); void (*free_folio)(struct folio *folio); - void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a page to the specified target. If -- cgit v1.2.3 From 8324a02c342a36336114a497130826612ed5520d Mon Sep 17 00:00:00 2001 From: Gavin Li Date: Sun, 27 Mar 2022 17:45:32 +0300 Subject: net/mlx5: Add exit route when waiting for FW Currently, removing a device needs to get the driver interface lock before doing any cleanup. If the driver is waiting in a loop for FW init, there is no way to cancel the wait, instead the device cleanup waits for the loop to conclude and release the lock. To allow immediate response to remove device commands, check the TEARDOWN flag while waiting for FW init, and exit the loop if it has been set. Signed-off-by: Gavin Li Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ff47d49d8be4..f327d0544038 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -632,6 +632,7 @@ enum mlx5_device_state { enum mlx5_interface_state { MLX5_INTERFACE_STATE_UP = BIT(0), + MLX5_BREAK_FW_WAIT = BIT(1), }; enum mlx5_pci_status { -- cgit v1.2.3 From 34a30d7635a8e37275a7b63bec09035ed762969b Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 1 Mar 2022 15:42:01 +0000 Subject: net/mlx5: Lag, expose number of lag ports Downstream patches will add support for hardware lag with more than 2 ports. Add a way for users to query the number of lag ports. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f327d0544038..62ea1120de9c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1142,6 +1142,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, int num_counters, size_t *offsets); struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev); +u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev); struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, -- cgit v1.2.3 From 4cd14d44b11dabf195d1e66dadbb954336224658 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 1 Mar 2022 17:34:58 +0000 Subject: net/mlx5: Support devices with more than 2 ports Increase the define MLX5_MAX_PORTS to 4 as the driver is ready to support NICs with 4 ports. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 62ea1120de9c..fdb9d07a05a4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -84,7 +84,7 @@ enum mlx5_sqp_t { }; enum { - MLX5_MAX_PORTS = 2, + MLX5_MAX_PORTS = 4, }; enum { -- cgit v1.2.3 From 7f46a0b7327ae261f9981888708dbca22c283900 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 15 Mar 2022 16:56:50 +0000 Subject: net/mlx5: Lag, add debugfs to query hardware lag state Lag state has become very complicated with many modes, flags, types and port selections methods and future work will add additional features. Add a debugfs to query the current lag state. A new directory named "lag" will be created under the mlx5 debugfs directory. As the driver has debugfs per pci function the location will be: /mlx5//lag For example: /sys/kernel/debug/mlx5/0000:08:00.0/lag The following files are exposed: - state: Returns "active" or "disabled". If "active" it means hardware lag is active. - members: Returns the BDFs of all the members of lag object. - type: Returns the type of the lag currently configured. Valid only if hardware lag is active. * "roce" - Members are bare metal PFs. * "switchdev" - Members are in switchdev mode. * "multipath" - ECMP offloads. - port_sel_mode: Returns the egress port selection method, valid only if hardware lag is active. * "queue_affinity" - Egress port is selected by the QP/SQ affinity. * "hash" - Egress port is selected by hash done on each packet. Controlled by: xmit_hash_policy of the bond device. - flags: Returns flags that are specific per lag @type. Valid only if hardware lag is active. * "shared_fdb" - "on" or "off", if "on" single FDB is used. - mapping: Returns the mapping which is used to select egress port. Valid only if hardware lag is active. If @port_sel_mode is "hash" returns the active egress ports. The hash result will select only active ports. if @port_sel_mode is "queue_affinity" returns the mapping between the configured port affinity of the QP/SQ and actual egress port. For example: * 1:1 - Mapping means if the configured affinity is port 1 traffic will egress via port 1. * 1:2 - Mapping means if the configured affinity is port 1 traffic will egress via port 2. This can happen if port 1 is down or in active/backup mode and port 1 is backup. Signed-off-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fdb9d07a05a4..d6bac3976913 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -558,6 +558,7 @@ struct mlx5_debugfs_entries { struct dentry *cq_debugfs; struct dentry *cmdif_debugfs; struct dentry *pages_debugfs; + struct dentry *lag_debugfs; }; struct mlx5_ft_pool; -- cgit v1.2.3 From 42704b26b0f1d891f6cf4ebc877dbac0d17c690d Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 6 May 2022 22:01:37 +0200 Subject: ptp: Add cycles support for virtual clocks ptp vclocks require a free running time for their timecounter. Currently only a physical clock forced to free running is supported. If vclocks are used, then the physical clock cannot be synchronized anymore. The synchronized time is not available in hardware in this case. As a result, timed transmission with TAPRIO hardware support is not possible anymore. If hardware would support a free running time additionally to the physical clock, then the physical clock does not need to be forced to free running. Thus, the physical clocks can still be synchronized while vclocks are in use. The physical clock could be used to synchronize the time domain of the TSN network and trigger TAPRIO. In parallel vclocks can be used to synchronize other time domains. Introduce support for a free running cycle counter called cycles to physical clocks. Rework ptp vclocks to use this free running cycle counter. Default implementation is based on time of physical clock. Thus, behavior of ptp vclocks based on physical clocks without free running cycle counter is identical to previous behavior. Signed-off-by: Gerhard Engleder Acked-by: Richard Cochran Signed-off-by: Paolo Abeni --- include/linux/ptp_clock_kernel.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index e8cc8b6bbf50..ad309202cf9f 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -108,6 +108,32 @@ struct ptp_system_timestamp { * @settime64: Set the current time on the hardware clock. * parameter ts: Time value to set. * + * @getcycles64: Reads the current free running cycle counter from the hardware + * clock. + * If @getcycles64 and @getcyclesx64 are not supported, then + * @gettime64 or @gettimex64 will be used as default + * implementation. + * parameter ts: Holds the result. + * + * @getcyclesx64: Reads the current free running cycle counter from the + * hardware clock and optionally also the system clock. + * If @getcycles64 and @getcyclesx64 are not supported, then + * @gettimex64 will be used as default implementation if + * available. + * parameter ts: Holds the PHC timestamp. + * parameter sts: If not NULL, it holds a pair of timestamps + * from the system clock. The first reading is made right before + * reading the lowest bits of the PHC timestamp and the second + * reading immediately follows that. + * + * @getcrosscycles: Reads the current free running cycle counter from the + * hardware clock and system clock simultaneously. + * If @getcycles64 and @getcyclesx64 are not supported, then + * @getcrosststamp will be used as default implementation if + * available. + * parameter cts: Contains timestamp (device,system) pair, + * where system time is realtime and monotonic. + * * @enable: Request driver to enable or disable an ancillary feature. * parameter request: Desired resource to enable or disable. * parameter on: Caller passes one to enable or zero to disable. @@ -155,6 +181,11 @@ struct ptp_clock_info { int (*getcrosststamp)(struct ptp_clock_info *ptp, struct system_device_crosststamp *cts); int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts); + int (*getcycles64)(struct ptp_clock_info *ptp, struct timespec64 *ts); + int (*getcyclesx64)(struct ptp_clock_info *ptp, struct timespec64 *ts, + struct ptp_system_timestamp *sts); + int (*getcrosscycles)(struct ptp_clock_info *ptp, + struct system_device_crosststamp *cts); int (*enable)(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on); int (*verify)(struct ptp_clock_info *ptp, unsigned int pin, -- cgit v1.2.3 From 51eb7492af276b5b4d27cfa4474d40bdac7b9cf8 Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 6 May 2022 22:01:38 +0200 Subject: ptp: Request cycles for TX timestamp The free running cycle counter of physical clocks called cycles shall be used for hardware timestamps to enable synchronisation. Introduce new flag SKBTX_HW_TSTAMP_USE_CYCLES, which signals driver to provide a TX timestamp based on cycles if cycles are supported. Signed-off-by: Gerhard Engleder Acked-by: Richard Cochran Signed-off-by: Paolo Abeni --- include/linux/skbuff.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d58669d6cb91..4a4f25975ca2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -615,6 +615,9 @@ enum { /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, + /* generate hardware time stamp based on cycles if supported */ + SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3, + /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, @@ -624,7 +627,9 @@ enum { #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) -#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) +#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ + SKBTX_HW_TSTAMP_USE_CYCLES | \ + SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ enum { -- cgit v1.2.3 From d58809d854c9ee19e4cd41023e137e65e9dc3f94 Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 6 May 2022 22:01:39 +0200 Subject: ptp: Pass hwtstamp to ptp_convert_timestamp() ptp_convert_timestamp() converts only the timestamp hwtstamp, which is a field of the argument with the type struct skb_shared_hwtstamps *. So a pointer to the hwtstamp field of this structure is sufficient. Rework ptp_convert_timestamp() to use an argument of type ktime_t *. This allows to add additional timestamp manipulation stages before the call of ptp_convert_timestamp(). Signed-off-by: Gerhard Engleder Acked-by: Richard Cochran Signed-off-by: Paolo Abeni --- include/linux/ptp_clock_kernel.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index ad309202cf9f..92b44161408e 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -384,17 +384,16 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); /** * ptp_convert_timestamp() - convert timestamp to a ptp vclock time * - * @hwtstamps: skb_shared_hwtstamps structure pointer + * @hwtstamp: timestamp * @vclock_index: phc index of ptp vclock. * * Returns converted timestamp, or 0 on error. */ -ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, - int vclock_index); +ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index); #else static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { return 0; } -static inline ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, +static inline ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index) { return 0; } -- cgit v1.2.3 From 97dc7cd92ac67f6e05df418df1772ba4a7fbf693 Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 6 May 2022 22:01:40 +0200 Subject: ptp: Support late timestamp determination If a physical clock supports a free running cycle counter, then timestamps shall be based on this time too. For TX it is known in advance before the transmission if a timestamp based on the free running cycle counter is needed. For RX it is impossible to know which timestamp is needed before the packet is received and assigned to a socket. Support late timestamp determination by a network device. Therefore, an address/cookie is stored within the new netdev_data field of struct skb_shared_hwtstamps. This address/cookie is provided to a new network device function called ndo_get_tstamp(), which returns a timestamp based on the normal/adjustable time or based on the free running cycle counter. If function is not supported, then timestamp handling is not changed. This mechanism is intended for RX, but TX use is also possible. Signed-off-by: Gerhard Engleder Acked-by: Jonathan Lemon Acked-by: Richard Cochran Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 21 +++++++++++++++++++++ include/linux/skbuff.h | 14 +++++++++++--- 2 files changed, 32 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 74c97a34921d..51fe143091cf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1356,6 +1356,12 @@ struct netdev_net_notifier { * The caller must be under RCU read context. * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); * Get the forwarding path to reach the real device from the HW destination address + * ktime_t (*ndo_get_tstamp)(struct net_device *dev, + * const struct skb_shared_hwtstamps *hwtstamps, + * bool cycles); + * Get hardware timestamp based on normal/adjustable time or free running + * cycle counter. This function is required if physical clock supports a + * free running cycle counter. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1578,6 +1584,9 @@ struct net_device_ops { struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); + ktime_t (*ndo_get_tstamp)(struct net_device *dev, + const struct skb_shared_hwtstamps *hwtstamps, + bool cycles); }; /** @@ -4761,6 +4770,18 @@ static inline void netdev_rx_csum_fault(struct net_device *dev, void net_enable_timestamp(void); void net_disable_timestamp(void); +static inline ktime_t netdev_get_tstamp(struct net_device *dev, + const struct skb_shared_hwtstamps *hwtstamps, + bool cycles) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_get_tstamp) + return ops->ndo_get_tstamp(dev, hwtstamps, cycles); + + return hwtstamps->hwtstamp; +} + static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, bool more) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4a4f25975ca2..97de40bcfef6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -588,8 +588,10 @@ static inline bool skb_frag_must_loop(struct page *p) /** * struct skb_shared_hwtstamps - hardware time stamps - * @hwtstamp: hardware time stamp transformed into duration - * since arbitrary point in time + * @hwtstamp: hardware time stamp transformed into duration + * since arbitrary point in time + * @netdev_data: address/cookie of network device driver used as + * reference to actual hardware time stamp * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. @@ -601,7 +603,10 @@ static inline bool skb_frag_must_loop(struct page *p) * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { - ktime_t hwtstamp; + union { + ktime_t hwtstamp; + void *netdev_data; + }; }; /* Definitions for tx_flags in struct skb_shared_info */ @@ -621,6 +626,9 @@ enum { /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, + /* determine hardware time stamp based on time or cycles */ + SKBTX_HW_TSTAMP_NETDEV = 1 << 5, + /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, }; -- cgit v1.2.3 From 57ce2e406fe1fa005e8fdbf20936c791252ac7bc Mon Sep 17 00:00:00 2001 From: Nava kishore Manne Date: Sat, 23 Apr 2022 22:32:32 +0530 Subject: fpga: fix for coding style issues fixes the below checks reported by checkpatch.pl: - Lines should not end with a '(' - Alignment should match open parenthesis Signed-off-by: Nava kishore Manne Link: https://lore.kernel.org/r/20220423170235.2115479-3-nava.manne@xilinx.com Signed-off-by: Xu Yilun --- include/linux/fpga/fpga-region.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index 3b87f232425c..9d4d32909340 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -52,9 +52,9 @@ struct fpga_region { #define to_fpga_region(d) container_of(d, struct fpga_region, dev) -struct fpga_region *fpga_region_class_find( - struct device *start, const void *data, - int (*match)(struct device *, const void *)); +struct fpga_region * +fpga_region_class_find(struct device *start, const void *data, + int (*match)(struct device *, const void *)); int fpga_region_program_fpga(struct fpga_region *region); -- cgit v1.2.3 From 7ff960a6fe399fdcbca6159063684671ae57eee9 Mon Sep 17 00:00:00 2001 From: Shunsuke Mie Date: Tue, 10 May 2022 19:27:23 +0900 Subject: virtio: fix virtio transitional ids This commit fixes the transitional PCI device ID. Fixes: d61914ea6ada ("virtio: update virtio id table, add transitional ids") Signed-off-by: Shunsuke Mie Link: https://lore.kernel.org/r/20220510102723.87666-1-mie@igel.co.jp Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_ids.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 80d76b75bccd..7aa2eb766205 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -73,12 +73,12 @@ * Virtio Transitional IDs */ -#define VIRTIO_TRANS_ID_NET 1000 /* transitional virtio net */ -#define VIRTIO_TRANS_ID_BLOCK 1001 /* transitional virtio block */ -#define VIRTIO_TRANS_ID_BALLOON 1002 /* transitional virtio balloon */ -#define VIRTIO_TRANS_ID_CONSOLE 1003 /* transitional virtio console */ -#define VIRTIO_TRANS_ID_SCSI 1004 /* transitional virtio SCSI */ -#define VIRTIO_TRANS_ID_RNG 1005 /* transitional virtio rng */ -#define VIRTIO_TRANS_ID_9P 1009 /* transitional virtio 9p console */ +#define VIRTIO_TRANS_ID_NET 0x1000 /* transitional virtio net */ +#define VIRTIO_TRANS_ID_BLOCK 0x1001 /* transitional virtio block */ +#define VIRTIO_TRANS_ID_BALLOON 0x1002 /* transitional virtio balloon */ +#define VIRTIO_TRANS_ID_CONSOLE 0x1003 /* transitional virtio console */ +#define VIRTIO_TRANS_ID_SCSI 0x1004 /* transitional virtio SCSI */ +#define VIRTIO_TRANS_ID_RNG 0x1005 /* transitional virtio rng */ +#define VIRTIO_TRANS_ID_9P 0x1009 /* transitional virtio 9p console */ #endif /* _LINUX_VIRTIO_IDS_H */ -- cgit v1.2.3 From c23d47abee3a54e4991ed3993340596d04aabd6a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Apr 2022 08:33:03 +0200 Subject: loop: remove most the top-of-file boilerplate comment from the UAPI header Just leave the SPDX marker and the copyright notice and remove the irrelevant rest. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220419063303.583106-5-hch@lst.de Signed-off-by: Jens Axboe --- include/uapi/linux/loop.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index 98e60801195e..6f63527dd2ed 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -1,11 +1,6 @@ /* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* - * include/linux/loop.h - * - * Written by Theodore Ts'o, 3/29/93. - * - * Copyright 1993 by Theodore Ts'o. Redistribution of this file is - * permitted under the GNU General Public License. + * Copyright 1993 by Theodore Ts'o. */ #ifndef _UAPI_LINUX_LOOP_H #define _UAPI_LINUX_LOOP_H -- cgit v1.2.3 From 846e437387e74c44ddc9f3eeec472fd37ca3cdb9 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 10 May 2022 12:02:03 +0300 Subject: net/mlx5: Expose mlx5_sriov_blocking_notifier_register / unregister APIs Expose mlx5_sriov_blocking_notifier_register / unregister APIs to let a VF register to be notified for its enablement / disablement by the PF. Upon VF probe it will call mlx5_sriov_blocking_notifier_register() with its notifier block and upon VF remove it will call mlx5_sriov_blocking_notifier_unregister() to drop its registration. This can give a VF the ability to clean some resources upon disable before that the command interface goes down and on the other hand sets some stuff before that it's enabled. This may be used by a VF which is migration capable in few cases.(e.g. PF load/unload upon an health recovery). Link: https://lore.kernel.org/r/20220510090206.90374-2-yishaih@nvidia.com Signed-off-by: Yishai Hadas Signed-off-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ff47d49d8be4..6fac5427d899 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -445,6 +445,11 @@ struct mlx5_qp_table { struct radix_tree_root tree; }; +enum { + MLX5_PF_NOTIFY_DISABLE_VF, + MLX5_PF_NOTIFY_ENABLE_VF, +}; + struct mlx5_vf_context { int enabled; u64 port_guid; @@ -455,6 +460,7 @@ struct mlx5_vf_context { u8 port_guid_valid:1; u8 node_guid_valid:1; enum port_state_policy policy; + struct blocking_notifier_head notifier; }; struct mlx5_core_sriov { @@ -1152,6 +1158,12 @@ int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev); void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev); +int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev, + int vf_id, + struct notifier_block *nb); +void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev, + int vf_id, + struct notifier_block *nb); #ifdef CONFIG_MLX5_CORE_IPOIB struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, struct ib_device *ibdev, -- cgit v1.2.3 From 2cb29da3f2c29e62311eec6446be92aa5f2c1620 Mon Sep 17 00:00:00 2001 From: YC Hung Date: Mon, 9 May 2022 12:04:25 -0500 Subject: ASoC: SOF: ipc: introduce cont_update_posn in sof_ipc_stream_params struct The host stream position is updated when no_stream_position is set as 0. However current implementation updates host stream position only when report data is larger than or equal to host period size which is decided by the period size of host side. It maybe cause host stream position update not in time. Therefore this patch introduces another field "cont_update_posn", a boolean value aimed to update host stream position continuously and based on period size of pipeline. It can get better precise when need to update host stream position from firmware. Reviewed-by: Daniel Baluta Reviewed-by: Ranjani Sridharan Reviewed-by: Kai Vehmanen Signed-off-by: YC Hung Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20220509170425.54640-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/stream.h | 3 ++- include/uapi/sound/sof/abi.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/sof/stream.h b/include/sound/sof/stream.h index 58a0d49977d6..1db3bbc3e65d 100644 --- a/include/sound/sof/stream.h +++ b/include/sound/sof/stream.h @@ -85,8 +85,9 @@ struct sof_ipc_stream_params { uint32_t host_period_bytes; uint16_t no_stream_position; /**< 1 means don't send stream position */ + uint8_t cont_update_posn; /**< 1 means continuous update stream position */ - uint16_t reserved[3]; + uint8_t reserved[5]; uint16_t chmap[SOF_IPC_MAX_CHANNELS]; /**< channel map - SOF_CHMAP_ */ } __packed; diff --git a/include/uapi/sound/sof/abi.h b/include/uapi/sound/sof/abi.h index b87e46684623..0e7dccdc25fd 100644 --- a/include/uapi/sound/sof/abi.h +++ b/include/uapi/sound/sof/abi.h @@ -26,7 +26,7 @@ /* SOF ABI version major, minor and patch numbers */ #define SOF_ABI_MAJOR 3 -#define SOF_ABI_MINOR 20 +#define SOF_ABI_MINOR 21 #define SOF_ABI_PATCH 0 /* SOF ABI version number. Format within 32bit word is MMmmmppp */ -- cgit v1.2.3 From 1ff297584fad2eef390f212b860e0fbb7363e0e8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 10 May 2022 10:29:36 -0700 Subject: randomize_kstack: Improve docs on requirements/rationale There were some recent questions about where and why to use the random_kstack routines when applying them to new architectures[1]. Update the header comments to reflect the design choices for the routines. [1] https://lore.kernel.org/lkml/1652173338.7bltwybi0c.astroid@bobo.none Cc: Nicholas Piggin Cc: Xiu Jianfeng Signed-off-by: Kees Cook --- include/linux/randomize_kstack.h | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index 1468caf001c0..5d868505a94e 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -40,10 +40,14 @@ DECLARE_PER_CPU(u32, kstack_offset); */ #define KSTACK_OFFSET_MAX(x) ((x) & 0x3FF) -/* - * These macros must be used during syscall entry when interrupts and +/** + * add_random_kstack_offset - Increase stack utilization by previously + * chosen random offset + * + * This should be used in the syscall entry path when interrupts and * preempt are disabled, and after user registers have been stored to - * the stack. + * the stack. For testing the resulting entropy, please see: + * tools/testing/selftests/lkdtm/stack-entropy.sh */ #define add_random_kstack_offset() do { \ if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ @@ -55,6 +59,23 @@ DECLARE_PER_CPU(u32, kstack_offset); } \ } while (0) +/** + * choose_random_kstack_offset - Choose the random offset for the next + * add_random_kstack_offset() + * + * This should only be used during syscall exit when interrupts and + * preempt are disabled. This position in the syscall flow is done to + * frustrate attacks from userspace attempting to learn the next offset: + * - Maximize the timing uncertainty visible from userspace: if the + * offset is chosen at syscall entry, userspace has much more control + * over the timing between choosing offsets. "How long will we be in + * kernel mode?" tends to be more difficult to predict than "how long + * will we be in user mode?" + * - Reduce the lifetime of the new offset sitting in memory during + * kernel mode execution. Exposure of "thread-local" memory content + * (e.g. current, percpu, etc) tends to be easier than arbitrary + * location memory exposure. + */ #define choose_random_kstack_offset(rand) do { \ if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ -- cgit v1.2.3 From 26101f5ab6bdf30ac25c8e578e0b4873e7849e0c Mon Sep 17 00:00:00 2001 From: Kaixi Fan Date: Sat, 30 Apr 2022 15:48:42 +0800 Subject: bpf: Add source ip in "struct bpf_tunnel_key" Add tunnel source ip field in "struct bpf_tunnel_key". Add related code to set and get tunnel source field. Signed-off-by: Kaixi Fan Link: https://lore.kernel.org/r/20220430074844.69214-2-fankaixi.li@bytedance.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 444fe6f1cf35..95a3d1ff6255 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5604,6 +5604,10 @@ struct bpf_tunnel_key { __u8 tunnel_ttl; __u16 tunnel_ext; /* Padding, future use. */ __u32 tunnel_label; + union { + __u32 local_ipv4; + __u32 local_ipv6[4]; + }; }; /* user accessible mirror of in-kernel xfrm_state. -- cgit v1.2.3 From 9f88361273082825d9f0d13a543d49f9fa0d44a8 Mon Sep 17 00:00:00 2001 From: Dmitrii Dolgov <9erthalion6@gmail.com> Date: Tue, 10 May 2022 17:52:30 +0200 Subject: bpf: Add bpf_link iterator Implement bpf_link iterator to traverse links via bpf_seq_file operations. The changeset is mostly shamelessly copied from commit a228a64fc1e4 ("bpf: Add bpf_prog iterator") Signed-off-by: Dmitrii Dolgov <9erthalion6@gmail.com> Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20220510155233.9815-2-9erthalion6@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be94833d390a..551b7198ae8a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1544,6 +1544,7 @@ void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); struct bpf_link *bpf_link_get_from_fd(u32 ufd); +struct bpf_link *bpf_link_get_curr_or_next(u32 *id); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); -- cgit v1.2.3 From d721def7392a7348ffb9f3583b264239cbd3702c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 10 May 2022 14:26:12 +0200 Subject: kallsyms: Make kallsyms_on_each_symbol generally available Making kallsyms_on_each_symbol generally available, so it can be used outside CONFIG_LIVEPATCH option in following changes. Rather than adding another ifdef option let's make the function generally available (when CONFIG_KALLSYMS option is defined). Cc: Christoph Hellwig Reviewed-by: Masami Hiramatsu Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20220510122616.2652285-2-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/kallsyms.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index ce1bd2fbf23e..ad39636e0c3f 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -65,11 +65,11 @@ static inline void *dereference_symbol_descriptor(void *ptr) return ptr; } +#ifdef CONFIG_KALLSYMS int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); -#ifdef CONFIG_KALLSYMS /* Lookup the address for a symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name); @@ -163,6 +163,11 @@ static inline bool kallsyms_show_value(const struct cred *cred) return false; } +static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, + unsigned long), void *data) +{ + return -EOPNOTSUPP; +} #endif /*CONFIG_KALLSYMS*/ static inline void print_ip_sym(const char *loglvl, unsigned long ip) -- cgit v1.2.3 From bed0d9a50dacee6fcf785c555cfb0d2573355afc Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 10 May 2022 14:26:13 +0200 Subject: ftrace: Add ftrace_lookup_symbols function Adding ftrace_lookup_symbols function that resolves array of symbols with single pass over kallsyms. The user provides array of string pointers with count and pointer to allocated array for resolved values. int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs) It iterates all kallsyms symbols and tries to loop up each in provided symbols array with bsearch. The symbols array needs to be sorted by name for this reason. We also check each symbol to pass ftrace_location, because this API will be used for fprobe symbols resolving. Suggested-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Reviewed-by: Masami Hiramatsu Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20220510122616.2652285-3-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/ftrace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 4816b7e11047..820500430eae 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -303,6 +303,8 @@ int unregister_ftrace_function(struct ftrace_ops *ops); extern void ftrace_stub(unsigned long a0, unsigned long a1, struct ftrace_ops *op, struct ftrace_regs *fregs); + +int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs); #else /* !CONFIG_FUNCTION_TRACER */ /* * (un)register_ftrace_function must be a macro since the ops parameter @@ -313,6 +315,10 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1, static inline void ftrace_kill(void) { } static inline void ftrace_free_init_mem(void) { } static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } +static inline int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_FUNCTION_TRACER */ struct ftrace_func_entry { -- cgit v1.2.3 From ddccc9ef55992716ad477d38fbcd9f8f1d34fc67 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 May 2022 09:04:54 -0700 Subject: skbuff: add a basic intro doc Add basic skb documentation. It's mostly an intro to the subsequent patches - it would looks strange if we documented advanced topics without covering the basics in any way. Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 97de40bcfef6..69802624276d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -800,6 +800,46 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +/** + * DOC: Basic sk_buff geometry + * + * struct sk_buff itself is a metadata structure and does not hold any packet + * data. All the data is held in associated buffers. + * + * &sk_buff.head points to the main "head" buffer. The head buffer is divided + * into two parts: + * + * - data buffer, containing headers and sometimes payload; + * this is the part of the skb operated on by the common helpers + * such as skb_put() or skb_pull(); + * - shared info (struct skb_shared_info) which holds an array of pointers + * to read-only data in the (page, offset, length) format. + * + * Optionally &skb_shared_info.frag_list may point to another skb. + * + * Basic diagram may look like this:: + * + * --------------- + * | sk_buff | + * --------------- + * ,--------------------------- + head + * / ,----------------- + data + * / / ,----------- + tail + * | | | , + end + * | | | | + * v v v v + * ----------------------------------------------- + * | headroom | data | tailroom | skb_shared_info | + * ----------------------------------------------- + * + [page frag] + * + [page frag] + * + [page frag] + * + [page frag] --------- + * + frag_list --> | sk_buff | + * --------- + * + */ + /** * struct sk_buff - socket buffer * @next: Next buffer in list -- cgit v1.2.3 From 9ec7ea1462084df695f34c5ac2d2d2250d9d6897 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 May 2022 09:04:55 -0700 Subject: skbuff: rewrite the doc for data-only skbs The comment about shinfo->dataref split is really unhelpful, at least to me. Rewrite it and render it to skb documentation. Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 42 ++++++++++++++++++++++++++++++------------ 1 file changed, 30 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 69802624276d..0e492f9bf532 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -727,16 +727,32 @@ struct skb_shared_info { skb_frag_t frags[MAX_SKB_FRAGS]; }; -/* We divide dataref into two halves. The higher 16 bits hold references - * to the payload part of skb->data. The lower 16 bits hold references to - * the entire skb->data. A clone of a headerless skb holds the length of - * the header in skb->hdr_len. - * - * All users must obey the rule that the skb->data reference count must be - * greater than or equal to the payload reference count. - * - * Holding a reference to the payload part means that the user does not - * care about modifications to the header part of skb->data. +/** + * DOC: dataref and headerless skbs + * + * Transport layers send out clones of payload skbs they hold for + * retransmissions. To allow lower layers of the stack to prepend their headers + * we split &skb_shared_info.dataref into two halves. + * The lower 16 bits count the overall number of references. + * The higher 16 bits indicate how many of the references are payload-only. + * skb_header_cloned() checks if skb is allowed to add / write the headers. + * + * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr + * (via __skb_header_release()). Any clone created from marked skb will get + * &sk_buff.hdr_len populated with the available headroom. + * If there's the only clone in existence it's able to modify the headroom + * at will. The sequence of calls inside the transport layer is:: + * + * + * skb_reserve() + * __skb_header_release() + * skb_clone() + * // send the clone down the stack + * + * This is not a very generic construct and it depends on the transport layers + * doing the right thing. In practice there's usually only one payload-only skb. + * Having multiple payload-only skbs with different lengths of hdr_len is not + * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) @@ -2027,8 +2043,10 @@ static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) } /** - * __skb_header_release - release reference to header - * @skb: buffer to operate on + * __skb_header_release() - allow clones to use the headroom + * @skb: buffer to operate on + * + * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { -- cgit v1.2.3 From 9facd94114b59afebd405e74b3bc2bf184efe986 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 May 2022 09:04:56 -0700 Subject: skbuff: render the checksum comment to documentation Long time ago Tom added a giant comment to skbuff.h explaining checksums. Now that we have a place in Documentation for skbuff docs we should render it. Sprinkle some markup while at it. Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 219 ++++++++++++++++++++++++++++--------------------- 1 file changed, 124 insertions(+), 95 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0e492f9bf532..5296b2c37f62 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -43,98 +43,112 @@ #include #endif -/* The interface for checksum offload between the stack and networking drivers +/** + * DOC: skb checksums + * + * The interface for checksum offload between the stack and networking drivers * is as follows... * - * A. IP checksum related features + * IP checksum related features + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * - * The checksum related features are: - * - * NETIF_F_HW_CSUM - The driver (or its device) is able to compute one - * IP (one's complement) checksum for any combination - * of protocols or protocol layering. The checksum is - * computed and set in a packet per the CHECKSUM_PARTIAL - * interface (see below). - * - * NETIF_F_IP_CSUM - Driver (device) is only able to checksum plain - * TCP or UDP packets over IPv4. These are specifically - * unencapsulated packets of the form IPv4|TCP or - * IPv4|UDP where the Protocol field in the IPv4 header - * is TCP or UDP. The IPv4 header may contain IP options. - * This feature cannot be set in features for a device - * with NETIF_F_HW_CSUM also set. This feature is being - * DEPRECATED (see below). - * - * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain - * TCP or UDP packets over IPv6. These are specifically - * unencapsulated packets of the form IPv6|TCP or - * IPv6|UDP where the Next Header field in the IPv6 - * header is either TCP or UDP. IPv6 extension headers - * are not supported with this feature. This feature - * cannot be set in features for a device with - * NETIF_F_HW_CSUM also set. This feature is being - * DEPRECATED (see below). - * - * NETIF_F_RXCSUM - Driver (device) performs receive checksum offload. - * This flag is only used to disable the RX checksum - * feature for a device. The stack will accept receive - * checksum indication in packets received on a device - * regardless of whether NETIF_F_RXCSUM is set. - * - * B. Checksumming of received packets by device. Indication of checksum - * verification is set in skb->ip_summed. Possible values are: - * - * CHECKSUM_NONE: + * .. flat-table:: Checksum related device features + * :widths: 1 10 + * + * * - %NETIF_F_HW_CSUM + * - The driver (or its device) is able to compute one + * IP (one's complement) checksum for any combination + * of protocols or protocol layering. The checksum is + * computed and set in a packet per the CHECKSUM_PARTIAL + * interface (see below). + * + * * - %NETIF_F_IP_CSUM + * - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv4. These are specifically + * unencapsulated packets of the form IPv4|TCP or + * IPv4|UDP where the Protocol field in the IPv4 header + * is TCP or UDP. The IPv4 header may contain IP options. + * This feature cannot be set in features for a device + * with NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * * - %NETIF_F_IPV6_CSUM + * - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv6. These are specifically + * unencapsulated packets of the form IPv6|TCP or + * IPv6|UDP where the Next Header field in the IPv6 + * header is either TCP or UDP. IPv6 extension headers + * are not supported with this feature. This feature + * cannot be set in features for a device with + * NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * * - %NETIF_F_RXCSUM + * - Driver (device) performs receive checksum offload. + * This flag is only used to disable the RX checksum + * feature for a device. The stack will accept receive + * checksum indication in packets received on a device + * regardless of whether NETIF_F_RXCSUM is set. + * + * Checksumming of received packets by device + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * Indication of checksum verification is set in &sk_buff.ip_summed. + * Possible values are: + * + * - %CHECKSUM_NONE * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * - * CHECKSUM_UNNECESSARY: + * - %CHECKSUM_UNNECESSARY * * The hardware you're dealing with doesn't calculate the full checksum - * (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums - * for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY - * if their checksums are okay. skb->csum is still undefined in this case + * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums + * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY + * if their checksums are okay. &sk_buff.csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * - * CHECKSUM_UNNECESSARY is applicable to following protocols: - * TCP: IPv6 and IPv4. - * UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a + * %CHECKSUM_UNNECESSARY is applicable to following protocols: + * + * - TCP: IPv6 and IPv4. + * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. - * GRE: only if the checksum is present in the header. - * SCTP: indicates the CRC in SCTP header has been validated. - * FCOE: indicates the CRC in FC frame has been validated. + * - GRE: only if the checksum is present in the header. + * - SCTP: indicates the CRC in SCTP header has been validated. + * - FCOE: indicates the CRC in FC frame has been validated. * - * skb->csum_level indicates the number of consecutive checksums found in - * the packet minus one that have been verified as CHECKSUM_UNNECESSARY. + * &sk_buff.csum_level indicates the number of consecutive checksums found in + * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), - * GRE (checksum flag is set) and TCP, skb->csum_level would be set to + * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * - * CHECKSUM_COMPLETE: + * - %CHECKSUM_COMPLETE * * This is the most generic way. The device supplied checksum of the _whole_ - * packet as seen by netif_rx() and fills in skb->csum. This means the + * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: + * * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * - * CHECKSUM_PARTIAL: + * - %CHECKSUM_PARTIAL * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet @@ -146,14 +160,18 @@ * packet that are after the checksum being offloaded are not considered to * be verified. * - * C. Checksumming on transmit for non-GSO. The stack requests checksum offload - * in the skb->ip_summed for a packet. Values are: + * Checksumming on transmit for non-GSO + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * The stack requests checksum offload in the &sk_buff.ip_summed for a packet. + * Values are: * - * CHECKSUM_PARTIAL: + * - %CHECKSUM_PARTIAL * * The driver is required to checksum the packet as seen by hard_start_xmit() - * from skb->csum_start up to the end, and to record/write the checksum at - * offset skb->csum_start + skb->csum_offset. A driver may verify that the + * from &sk_buff.csum_start up to the end, and to record/write the checksum at + * offset &sk_buff.csum_start + &sk_buff.csum_offset. + * A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the @@ -165,55 +183,66 @@ * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * - * NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of - * NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate + * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of + * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate * checksum offload capability. - * skb_csum_hwoffload_help() can be called to resolve CHECKSUM_PARTIAL based + * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match - * them, skb_checksum_help or skb_crc32c_help (depending on the value of - * csum_not_inet, see item D.) is called to resolve the checksum. + * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of + * &sk_buff.csum_not_inet, see :ref:`crc`) + * is called to resolve the checksum. * - * CHECKSUM_NONE: + * - %CHECKSUM_NONE * * The skb was already checksummed by the protocol, or a checksum is not * required. * - * CHECKSUM_UNNECESSARY: + * - %CHECKSUM_UNNECESSARY * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * - * CHECKSUM_COMPLETE: + * - %CHECKSUM_COMPLETE + * * Not used in checksum output. If a driver observes a packet with this value - * set in skbuff, it should treat the packet as if CHECKSUM_NONE were set. - * - * D. Non-IP checksum (CRC) offloads - * - * NETIF_F_SCTP_CRC - This feature indicates that a device is capable of - * offloading the SCTP CRC in a packet. To perform this offload the stack - * will set csum_start and csum_offset accordingly, set ip_summed to - * CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication in - * the skbuff that the CHECKSUM_PARTIAL refers to CRC32c. - * A driver that supports both IP checksum offload and SCTP CRC32c offload - * must verify which offload is configured for a packet by testing the - * value of skb->csum_not_inet; skb_crc32c_csum_help is provided to resolve - * CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. - * - * NETIF_F_FCOE_CRC - This feature indicates that a device is capable of - * offloading the FCOE CRC in a packet. To perform this offload the stack - * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset - * accordingly. Note that there is no indication in the skbuff that the - * CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports - * both IP checksum offload and FCOE CRC offload must verify which offload - * is configured for a packet, presumably by inspecting packet headers. - * - * E. Checksumming on output with GSO. - * - * In the case of a GSO packet (skb_is_gso(skb) is true), checksum offload + * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set. + * + * .. _crc: + * + * Non-IP checksum (CRC) offloads + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * .. flat-table:: + * :widths: 1 10 + * + * * - %NETIF_F_SCTP_CRC + * - This feature indicates that a device is capable of + * offloading the SCTP CRC in a packet. To perform this offload the stack + * will set csum_start and csum_offset accordingly, set ip_summed to + * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication + * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c. + * A driver that supports both IP checksum offload and SCTP CRC32c offload + * must verify which offload is configured for a packet by testing the + * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to + * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. + * + * * - %NETIF_F_FCOE_CRC + * - This feature indicates that a device is capable of offloading the FCOE + * CRC in a packet. To perform this offload the stack will set ip_summed + * to %CHECKSUM_PARTIAL and set csum_start and csum_offset + * accordingly. Note that there is no indication in the skbuff that the + * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports + * both IP checksum offload and FCOE CRC offload must verify which offload + * is configured for a packet, presumably by inspecting packet headers. + * + * Checksumming on output with GSO + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * In the case of a GSO packet (skb_is_gso() is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the - * gso_type is SKB_GSO_TCPV4 or SKB_GSO_TCPV6, TCP checksum offload as + * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded - * with GSO then ip_summed is CHECKSUM_PARTIAL, and both csum_start and + * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ -- cgit v1.2.3 From f7e0beaf39d3868dc700d4954b26cf8443c5d423 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Tue, 10 May 2022 13:59:19 -0700 Subject: bpf, x86: Generate trampolines from bpf_tramp_links Replace struct bpf_tramp_progs with struct bpf_tramp_links to collect struct bpf_tramp_link(s) for a trampoline. struct bpf_tramp_link extends bpf_link to act as a linked list node. arch_prepare_bpf_trampoline() accepts a struct bpf_tramp_links to collects all bpf_tramp_link(s) that a trampoline should call. Change BPF trampoline and bpf_struct_ops to pass bpf_tramp_links instead of bpf_tramp_progs. Signed-off-by: Kui-Feng Lee Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220510205923.3206889-2-kuifeng@fb.com --- include/linux/bpf.h | 36 ++++++++++++++++++++++++------------ include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 1 + 3 files changed, 26 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 551b7198ae8a..75e0110a65e1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -723,11 +723,11 @@ struct btf_func_model { /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ -#define BPF_MAX_TRAMP_PROGS 38 +#define BPF_MAX_TRAMP_LINKS 38 -struct bpf_tramp_progs { - struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS]; - int nr_progs; +struct bpf_tramp_links { + struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS]; + int nr_links; }; /* Different use cases for BPF trampoline: @@ -753,7 +753,7 @@ struct bpf_tramp_progs { struct bpf_tramp_image; int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, - struct bpf_tramp_progs *tprogs, + struct bpf_tramp_links *tlinks, void *orig_call); /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(struct bpf_prog *prog); @@ -852,9 +852,10 @@ static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( { return bpf_func(ctx, insnsi); } + #ifdef CONFIG_BPF_JIT -int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr); -int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr); +int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); +int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); @@ -905,12 +906,12 @@ int bpf_jit_charge_modmem(u32 size); void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else -static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, +static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { return -ENOTSUPP; } -static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog, +static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { return -ENOTSUPP; @@ -1009,7 +1010,6 @@ struct bpf_prog_aux { bool tail_call_reachable; bool xdp_has_frags; bool use_bpf_prog_pack; - struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ @@ -1096,6 +1096,18 @@ struct bpf_link_ops { struct bpf_link_info *info); }; +struct bpf_tramp_link { + struct bpf_link link; + struct hlist_node tramp_hlist; +}; + +struct bpf_tracing_link { + struct bpf_tramp_link link; + enum bpf_attach_type attach_type; + struct bpf_trampoline *trampoline; + struct bpf_prog *tgt_prog; +}; + struct bpf_link_primer { struct bpf_link *link; struct file *file; @@ -1133,8 +1145,8 @@ bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); -int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs, - struct bpf_prog *prog, +int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, + struct bpf_tramp_link *link, const struct btf_func_model *model, void *image, void *image_end); static inline bool bpf_try_module_get(const void *data, struct module *owner) diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 3e24ad0c4b3c..2b9112b80171 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -141,3 +141,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) #endif BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi) +BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 95a3d1ff6255..3d032ea1b6a3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1013,6 +1013,7 @@ enum bpf_link_type { BPF_LINK_TYPE_XDP = 6, BPF_LINK_TYPE_PERF_EVENT = 7, BPF_LINK_TYPE_KPROBE_MULTI = 8, + BPF_LINK_TYPE_STRUCT_OPS = 9, MAX_BPF_LINK_TYPE, }; -- cgit v1.2.3 From e384c7b7b46d0a5f4bf3c554f963e6e9622d0ab1 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Tue, 10 May 2022 13:59:20 -0700 Subject: bpf, x86: Create bpf_tramp_run_ctx on the caller thread's stack BPF trampolines will create a bpf_tramp_run_ctx, a bpf_run_ctx, on stacks and set/reset the current bpf_run_ctx before/after calling a bpf_prog. Signed-off-by: Kui-Feng Lee Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220510205923.3206889-3-kuifeng@fb.com --- include/linux/bpf.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 75e0110a65e1..256fb802e580 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -730,6 +730,8 @@ struct bpf_tramp_links { int nr_links; }; +struct bpf_tramp_run_ctx; + /* Different use cases for BPF trampoline: * 1. replace nop at the function entry (kprobe equivalent) * flags = BPF_TRAMP_F_RESTORE_REGS @@ -756,10 +758,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *i struct bpf_tramp_links *tlinks, void *orig_call); /* these two functions are called from generated trampoline */ -u64 notrace __bpf_prog_enter(struct bpf_prog *prog); -void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); -u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog); -void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); +u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); +u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); @@ -1351,6 +1354,12 @@ struct bpf_trace_run_ctx { u64 bpf_cookie; }; +struct bpf_tramp_run_ctx { + struct bpf_run_ctx run_ctx; + u64 bpf_cookie; + struct bpf_run_ctx *saved_run_ctx; +}; + static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) { struct bpf_run_ctx *old_ctx = NULL; -- cgit v1.2.3 From 66cd9d4ef74ae1ad459e3db3a3280182275c2ce9 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 28 Apr 2022 12:29:37 +0300 Subject: scsi: target: iscsi: Rename iscsi_cmd to iscsit_cmd The structure iscsi_cmd naming is used by the iSCSI initiator driver. Rename the target cmd to iscsit_cmd to have more readable code. Link: https://lore.kernel.org/r/20220428092939.36768-1-mgurtovoy@nvidia.com Reviewed-by: Mike Christie Signed-off-by: Max Gurtovoy Signed-off-by: Martin K. Petersen --- include/target/iscsi/iscsi_target_core.h | 34 ++++++------ include/target/iscsi/iscsi_transport.h | 92 ++++++++++++++++---------------- 2 files changed, 63 insertions(+), 63 deletions(-) (limited to 'include') diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index adc87de0362b..4f9ef2899488 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -143,7 +143,7 @@ enum tiqn_state_table { TIQN_STATE_SHUTDOWN = 2, }; -/* struct iscsi_cmd->cmd_flags */ +/* struct iscsit_cmd->cmd_flags */ enum cmd_flags_table { ICF_GOT_LAST_DATAOUT = 0x00000001, ICF_GOT_DATACK_SNACK = 0x00000002, @@ -157,7 +157,7 @@ enum cmd_flags_table { ICF_SENDTARGETS_SINGLE = 0x00000200, }; -/* struct iscsi_cmd->i_state */ +/* struct iscsit_cmd->i_state */ enum cmd_i_state_table { ISTATE_NO_STATE = 0, ISTATE_NEW_CMD = 1, @@ -297,7 +297,7 @@ struct iscsi_sess_ops { struct iscsi_queue_req { int state; - struct iscsi_cmd *cmd; + struct iscsit_cmd *cmd; struct list_head qr_list; }; @@ -327,7 +327,7 @@ struct iscsi_ooo_cmdsn { u32 batch_count; u32 cmdsn; u32 exp_cmdsn; - struct iscsi_cmd *cmd; + struct iscsit_cmd *cmd; struct list_head ooo_list; } ____cacheline_aligned; @@ -349,7 +349,7 @@ struct iscsi_r2t { struct list_head r2t_list; } ____cacheline_aligned; -struct iscsi_cmd { +struct iscsit_cmd { enum iscsi_timer_flags_table dataout_timer_flags; /* DataOUT timeout retries */ u8 dataout_timeout_retries; @@ -405,22 +405,22 @@ struct iscsi_cmd { u32 outstanding_r2ts; /* Next R2T Offset when DataSequenceInOrder=Yes */ u32 r2t_offset; - /* Iovec current and orig count for iscsi_cmd->iov_data */ + /* Iovec current and orig count for iscsit_cmd->iov_data */ u32 iov_data_count; u32 orig_iov_data_count; /* Number of miscellaneous iovecs used for IP stack calls */ u32 iov_misc_count; - /* Number of struct iscsi_pdu in struct iscsi_cmd->pdu_list */ + /* Number of struct iscsi_pdu in struct iscsit_cmd->pdu_list */ u32 pdu_count; - /* Next struct iscsi_pdu to send in struct iscsi_cmd->pdu_list */ + /* Next struct iscsi_pdu to send in struct iscsit_cmd->pdu_list */ u32 pdu_send_order; - /* Current struct iscsi_pdu in struct iscsi_cmd->pdu_list */ + /* Current struct iscsi_pdu in struct iscsit_cmd->pdu_list */ u32 pdu_start; - /* Next struct iscsi_seq to send in struct iscsi_cmd->seq_list */ + /* Next struct iscsi_seq to send in struct iscsit_cmd->seq_list */ u32 seq_send_order; - /* Number of struct iscsi_seq in struct iscsi_cmd->seq_list */ + /* Number of struct iscsi_seq in struct iscsit_cmd->seq_list */ u32 seq_count; - /* Current struct iscsi_seq in struct iscsi_cmd->seq_list */ + /* Current struct iscsi_seq in struct iscsit_cmd->seq_list */ u32 seq_no; /* Lowest offset in current DataOUT sequence */ u32 seq_start_offset; @@ -444,12 +444,12 @@ struct iscsi_cmd { enum dma_data_direction data_direction; /* iSCSI PDU Header + CRC */ unsigned char pdu[ISCSI_HDR_LEN + ISCSI_CRC_LEN]; - /* Number of times struct iscsi_cmd is present in immediate queue */ + /* Number of times struct iscsit_cmd is present in immediate queue */ atomic_t immed_queue_count; atomic_t response_queue_count; spinlock_t datain_lock; spinlock_t dataout_timeout_lock; - /* spinlock for protecting struct iscsi_cmd->i_state */ + /* spinlock for protecting struct iscsit_cmd->i_state */ spinlock_t istate_lock; /* spinlock for adding within command recovery entries */ spinlock_t error_lock; @@ -503,7 +503,7 @@ struct iscsi_cmd { struct iscsi_tmr_req { bool task_reassign:1; u32 exp_data_sn; - struct iscsi_cmd *ref_cmd; + struct iscsit_cmd *ref_cmd; struct iscsi_conn_recovery *conn_recovery; struct se_tmr_req *se_tmr_req; }; @@ -583,7 +583,7 @@ struct iscsi_conn { cpumask_var_t allowed_cpumask; unsigned int conn_rx_reset_cpumask:1; unsigned int conn_tx_reset_cpumask:1; - /* list_head of struct iscsi_cmd for this connection */ + /* list_head of struct iscsit_cmd for this connection */ struct list_head conn_cmd_list; struct list_head immed_queue_list; struct list_head response_queue_list; @@ -898,7 +898,7 @@ static inline u32 session_get_next_ttt(struct iscsi_session *session) return ttt; } -extern struct iscsi_cmd *iscsit_find_cmd_from_itt(struct iscsi_conn *, itt_t); +extern struct iscsit_cmd *iscsit_find_cmd_from_itt(struct iscsi_conn *, itt_t); extern void iscsit_thread_check_cpumask(struct iscsi_conn *conn, struct task_struct *p, diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index b8feba7ffebc..645de3542022 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#include "iscsi_target_core.h" /* struct iscsi_cmd */ +#include "iscsi_target_core.h" /* struct iscsit_cmd */ struct sockaddr_storage; @@ -18,23 +18,23 @@ struct iscsit_transport { void (*iscsit_free_conn)(struct iscsi_conn *); int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *); int (*iscsit_put_login_tx)(struct iscsi_conn *, struct iscsi_login *, u32); - int (*iscsit_immediate_queue)(struct iscsi_conn *, struct iscsi_cmd *, int); - int (*iscsit_response_queue)(struct iscsi_conn *, struct iscsi_cmd *, int); - int (*iscsit_get_dataout)(struct iscsi_conn *, struct iscsi_cmd *, bool); - int (*iscsit_queue_data_in)(struct iscsi_conn *, struct iscsi_cmd *); - int (*iscsit_queue_status)(struct iscsi_conn *, struct iscsi_cmd *); - void (*iscsit_aborted_task)(struct iscsi_conn *, struct iscsi_cmd *); - int (*iscsit_xmit_pdu)(struct iscsi_conn *, struct iscsi_cmd *, + int (*iscsit_immediate_queue)(struct iscsi_conn *, struct iscsit_cmd *, int); + int (*iscsit_response_queue)(struct iscsi_conn *, struct iscsit_cmd *, int); + int (*iscsit_get_dataout)(struct iscsi_conn *, struct iscsit_cmd *, bool); + int (*iscsit_queue_data_in)(struct iscsi_conn *, struct iscsit_cmd *); + int (*iscsit_queue_status)(struct iscsi_conn *, struct iscsit_cmd *); + void (*iscsit_aborted_task)(struct iscsi_conn *, struct iscsit_cmd *); + int (*iscsit_xmit_pdu)(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_datain_req *, const void *, u32); - void (*iscsit_unmap_cmd)(struct iscsi_conn *, struct iscsi_cmd *); + void (*iscsit_unmap_cmd)(struct iscsi_conn *, struct iscsit_cmd *); void (*iscsit_get_rx_pdu)(struct iscsi_conn *); int (*iscsit_validate_params)(struct iscsi_conn *); - void (*iscsit_get_r2t_ttt)(struct iscsi_conn *, struct iscsi_cmd *, + void (*iscsit_get_r2t_ttt)(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_r2t *); enum target_prot_op (*iscsit_get_sup_prot_ops)(struct iscsi_conn *); }; -static inline void *iscsit_priv_cmd(struct iscsi_cmd *cmd) +static inline void *iscsit_priv_cmd(struct iscsit_cmd *cmd) { return (void *)(cmd + 1); } @@ -51,61 +51,61 @@ extern void iscsit_put_transport(struct iscsit_transport *); /* * From iscsi_target.c */ -extern int iscsit_setup_scsi_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_setup_scsi_cmd(struct iscsi_conn *, struct iscsit_cmd *, unsigned char *); -extern void iscsit_set_unsolicited_dataout(struct iscsi_cmd *); -extern int iscsit_process_scsi_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern void iscsit_set_unsolicited_dataout(struct iscsit_cmd *); +extern int iscsit_process_scsi_cmd(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_scsi_req *); extern int __iscsit_check_dataout_hdr(struct iscsi_conn *, void *, - struct iscsi_cmd *, u32, bool *); + struct iscsit_cmd *, u32, bool *); extern int iscsit_check_dataout_hdr(struct iscsi_conn *conn, void *buf, - struct iscsi_cmd **out_cmd); -extern int iscsit_check_dataout_payload(struct iscsi_cmd *, struct iscsi_data *, + struct iscsit_cmd **out_cmd); +extern int iscsit_check_dataout_payload(struct iscsit_cmd *, struct iscsi_data *, bool); -extern int iscsit_setup_nop_out(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_setup_nop_out(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_nopout *); -extern int iscsit_process_nop_out(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_process_nop_out(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_nopout *); -extern int iscsit_handle_logout_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_handle_logout_cmd(struct iscsi_conn *, struct iscsit_cmd *, unsigned char *); -extern int iscsit_handle_task_mgt_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_handle_task_mgt_cmd(struct iscsi_conn *, struct iscsit_cmd *, unsigned char *); -extern int iscsit_setup_text_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_setup_text_cmd(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_text *); -extern int iscsit_process_text_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_process_text_cmd(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_text *); -extern void iscsit_build_rsp_pdu(struct iscsi_cmd *, struct iscsi_conn *, +extern void iscsit_build_rsp_pdu(struct iscsit_cmd *, struct iscsi_conn *, bool, struct iscsi_scsi_rsp *); -extern void iscsit_build_nopin_rsp(struct iscsi_cmd *, struct iscsi_conn *, +extern void iscsit_build_nopin_rsp(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_nopin *, bool); -extern void iscsit_build_task_mgt_rsp(struct iscsi_cmd *, struct iscsi_conn *, +extern void iscsit_build_task_mgt_rsp(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_tm_rsp *); -extern int iscsit_build_text_rsp(struct iscsi_cmd *, struct iscsi_conn *, +extern int iscsit_build_text_rsp(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_text_rsp *, enum iscsit_transport_type); -extern void iscsit_build_reject(struct iscsi_cmd *, struct iscsi_conn *, +extern void iscsit_build_reject(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_reject *); -extern int iscsit_build_logout_rsp(struct iscsi_cmd *, struct iscsi_conn *, +extern int iscsit_build_logout_rsp(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_logout_rsp *); -extern int iscsit_logout_post_handler(struct iscsi_cmd *, struct iscsi_conn *); -extern int iscsit_queue_rsp(struct iscsi_conn *, struct iscsi_cmd *); -extern void iscsit_aborted_task(struct iscsi_conn *, struct iscsi_cmd *); +extern int iscsit_logout_post_handler(struct iscsit_cmd *, struct iscsi_conn *); +extern int iscsit_queue_rsp(struct iscsi_conn *, struct iscsit_cmd *); +extern void iscsit_aborted_task(struct iscsi_conn *, struct iscsit_cmd *); extern int iscsit_add_reject(struct iscsi_conn *, u8, unsigned char *); -extern int iscsit_reject_cmd(struct iscsi_cmd *, u8, unsigned char *); +extern int iscsit_reject_cmd(struct iscsit_cmd *, u8, unsigned char *); extern int iscsit_handle_snack(struct iscsi_conn *, unsigned char *); -extern void iscsit_build_datain_pdu(struct iscsi_cmd *, struct iscsi_conn *, +extern void iscsit_build_datain_pdu(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_datain *, struct iscsi_data_rsp *, bool); -extern int iscsit_build_r2ts_for_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_build_r2ts_for_cmd(struct iscsi_conn *, struct iscsit_cmd *, bool); -extern int iscsit_immediate_queue(struct iscsi_conn *, struct iscsi_cmd *, int); -extern int iscsit_response_queue(struct iscsi_conn *, struct iscsi_cmd *, int); +extern int iscsit_immediate_queue(struct iscsi_conn *, struct iscsit_cmd *, int); +extern int iscsit_response_queue(struct iscsi_conn *, struct iscsit_cmd *, int); /* * From iscsi_target_device.c */ -extern void iscsit_increment_maxcmdsn(struct iscsi_cmd *, struct iscsi_session *); +extern void iscsit_increment_maxcmdsn(struct iscsit_cmd *, struct iscsi_session *); /* * From iscsi_target_erl0.c */ @@ -113,24 +113,24 @@ extern void iscsit_cause_connection_reinstatement(struct iscsi_conn *, int); /* * From iscsi_target_erl1.c */ -extern void iscsit_stop_dataout_timer(struct iscsi_cmd *); +extern void iscsit_stop_dataout_timer(struct iscsit_cmd *); /* * From iscsi_target_tmr.c */ -extern int iscsit_tmr_post_handler(struct iscsi_cmd *, struct iscsi_conn *); +extern int iscsit_tmr_post_handler(struct iscsit_cmd *, struct iscsi_conn *); /* * From iscsi_target_util.c */ -extern struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *, int); -extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern struct iscsit_cmd *iscsit_allocate_cmd(struct iscsi_conn *, int); +extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsit_cmd *, unsigned char *, __be32); -extern void iscsit_release_cmd(struct iscsi_cmd *); -extern void iscsit_free_cmd(struct iscsi_cmd *, bool); -extern void iscsit_add_cmd_to_immediate_queue(struct iscsi_cmd *, +extern void iscsit_release_cmd(struct iscsit_cmd *); +extern void iscsit_free_cmd(struct iscsit_cmd *, bool); +extern void iscsit_add_cmd_to_immediate_queue(struct iscsit_cmd *, struct iscsi_conn *, u8); -extern struct iscsi_cmd * +extern struct iscsit_cmd * iscsit_find_cmd_from_itt_or_dump(struct iscsi_conn *conn, itt_t init_task_tag, u32 length); -- cgit v1.2.3 From be36d683fc29e74bbd29347717be72beb6a74219 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 28 Apr 2022 12:29:38 +0300 Subject: scsi: target: iscsi: Rename iscsi_conn to iscsit_conn The structure iscsi_conn naming is used by the iSCSI initiator driver. Rename the target conn to iscsit_conn to have more readable code. Link: https://lore.kernel.org/r/20220428092939.36768-2-mgurtovoy@nvidia.com Reviewed-by: Mike Christie Signed-off-by: Max Gurtovoy Signed-off-by: Martin K. Petersen --- include/target/iscsi/iscsi_target_core.h | 10 ++-- include/target/iscsi/iscsi_transport.h | 100 +++++++++++++++---------------- 2 files changed, 55 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 4f9ef2899488..76581e0f3d98 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -478,7 +478,7 @@ struct iscsit_cmd { /* TMR Request when iscsi_opcode == ISCSI_OP_SCSI_TMFUNC */ struct iscsi_tmr_req *tmr_req; /* Connection this command is alligient to */ - struct iscsi_conn *conn; + struct iscsit_conn *conn; /* Pointer to connection recovery entry */ struct iscsi_conn_recovery *cr; /* Session the command is part of, used for connection recovery */ @@ -508,7 +508,7 @@ struct iscsi_tmr_req { struct se_tmr_req *se_tmr_req; }; -struct iscsi_conn { +struct iscsit_conn { wait_queue_head_t queues_wq; /* Authentication Successful for this connection */ u8 auth_complete; @@ -710,7 +710,7 @@ struct iscsi_login { char rsp[ISCSI_HDR_LEN]; char *req_buf; char *rsp_buf; - struct iscsi_conn *conn; + struct iscsit_conn *conn; struct iscsi_np *np; } ____cacheline_aligned; @@ -898,9 +898,9 @@ static inline u32 session_get_next_ttt(struct iscsi_session *session) return ttt; } -extern struct iscsit_cmd *iscsit_find_cmd_from_itt(struct iscsi_conn *, itt_t); +extern struct iscsit_cmd *iscsit_find_cmd_from_itt(struct iscsit_conn *, itt_t); -extern void iscsit_thread_check_cpumask(struct iscsi_conn *conn, +extern void iscsit_thread_check_cpumask(struct iscsit_conn *conn, struct task_struct *p, int mode); diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index 645de3542022..2ab26bb6f808 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -12,26 +12,26 @@ struct iscsit_transport { struct module *owner; struct list_head t_node; int (*iscsit_setup_np)(struct iscsi_np *, struct sockaddr_storage *); - int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *); + int (*iscsit_accept_np)(struct iscsi_np *, struct iscsit_conn *); void (*iscsit_free_np)(struct iscsi_np *); - void (*iscsit_wait_conn)(struct iscsi_conn *); - void (*iscsit_free_conn)(struct iscsi_conn *); - int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *); - int (*iscsit_put_login_tx)(struct iscsi_conn *, struct iscsi_login *, u32); - int (*iscsit_immediate_queue)(struct iscsi_conn *, struct iscsit_cmd *, int); - int (*iscsit_response_queue)(struct iscsi_conn *, struct iscsit_cmd *, int); - int (*iscsit_get_dataout)(struct iscsi_conn *, struct iscsit_cmd *, bool); - int (*iscsit_queue_data_in)(struct iscsi_conn *, struct iscsit_cmd *); - int (*iscsit_queue_status)(struct iscsi_conn *, struct iscsit_cmd *); - void (*iscsit_aborted_task)(struct iscsi_conn *, struct iscsit_cmd *); - int (*iscsit_xmit_pdu)(struct iscsi_conn *, struct iscsit_cmd *, + void (*iscsit_wait_conn)(struct iscsit_conn *); + void (*iscsit_free_conn)(struct iscsit_conn *); + int (*iscsit_get_login_rx)(struct iscsit_conn *, struct iscsi_login *); + int (*iscsit_put_login_tx)(struct iscsit_conn *, struct iscsi_login *, u32); + int (*iscsit_immediate_queue)(struct iscsit_conn *, struct iscsit_cmd *, int); + int (*iscsit_response_queue)(struct iscsit_conn *, struct iscsit_cmd *, int); + int (*iscsit_get_dataout)(struct iscsit_conn *, struct iscsit_cmd *, bool); + int (*iscsit_queue_data_in)(struct iscsit_conn *, struct iscsit_cmd *); + int (*iscsit_queue_status)(struct iscsit_conn *, struct iscsit_cmd *); + void (*iscsit_aborted_task)(struct iscsit_conn *, struct iscsit_cmd *); + int (*iscsit_xmit_pdu)(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_datain_req *, const void *, u32); - void (*iscsit_unmap_cmd)(struct iscsi_conn *, struct iscsit_cmd *); - void (*iscsit_get_rx_pdu)(struct iscsi_conn *); - int (*iscsit_validate_params)(struct iscsi_conn *); - void (*iscsit_get_r2t_ttt)(struct iscsi_conn *, struct iscsit_cmd *, + void (*iscsit_unmap_cmd)(struct iscsit_conn *, struct iscsit_cmd *); + void (*iscsit_get_rx_pdu)(struct iscsit_conn *); + int (*iscsit_validate_params)(struct iscsit_conn *); + void (*iscsit_get_r2t_ttt)(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_r2t *); - enum target_prot_op (*iscsit_get_sup_prot_ops)(struct iscsi_conn *); + enum target_prot_op (*iscsit_get_sup_prot_ops)(struct iscsit_conn *); }; static inline void *iscsit_priv_cmd(struct iscsit_cmd *cmd) @@ -51,57 +51,57 @@ extern void iscsit_put_transport(struct iscsit_transport *); /* * From iscsi_target.c */ -extern int iscsit_setup_scsi_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_setup_scsi_cmd(struct iscsit_conn *, struct iscsit_cmd *, unsigned char *); extern void iscsit_set_unsolicited_dataout(struct iscsit_cmd *); -extern int iscsit_process_scsi_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_process_scsi_cmd(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_scsi_req *); extern int -__iscsit_check_dataout_hdr(struct iscsi_conn *, void *, +__iscsit_check_dataout_hdr(struct iscsit_conn *, void *, struct iscsit_cmd *, u32, bool *); extern int -iscsit_check_dataout_hdr(struct iscsi_conn *conn, void *buf, +iscsit_check_dataout_hdr(struct iscsit_conn *conn, void *buf, struct iscsit_cmd **out_cmd); extern int iscsit_check_dataout_payload(struct iscsit_cmd *, struct iscsi_data *, bool); -extern int iscsit_setup_nop_out(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_setup_nop_out(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_nopout *); -extern int iscsit_process_nop_out(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_process_nop_out(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_nopout *); -extern int iscsit_handle_logout_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_handle_logout_cmd(struct iscsit_conn *, struct iscsit_cmd *, unsigned char *); -extern int iscsit_handle_task_mgt_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_handle_task_mgt_cmd(struct iscsit_conn *, struct iscsit_cmd *, unsigned char *); -extern int iscsit_setup_text_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_setup_text_cmd(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_text *); -extern int iscsit_process_text_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_process_text_cmd(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_text *); -extern void iscsit_build_rsp_pdu(struct iscsit_cmd *, struct iscsi_conn *, +extern void iscsit_build_rsp_pdu(struct iscsit_cmd *, struct iscsit_conn *, bool, struct iscsi_scsi_rsp *); -extern void iscsit_build_nopin_rsp(struct iscsit_cmd *, struct iscsi_conn *, +extern void iscsit_build_nopin_rsp(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_nopin *, bool); -extern void iscsit_build_task_mgt_rsp(struct iscsit_cmd *, struct iscsi_conn *, +extern void iscsit_build_task_mgt_rsp(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_tm_rsp *); -extern int iscsit_build_text_rsp(struct iscsit_cmd *, struct iscsi_conn *, +extern int iscsit_build_text_rsp(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_text_rsp *, enum iscsit_transport_type); -extern void iscsit_build_reject(struct iscsit_cmd *, struct iscsi_conn *, +extern void iscsit_build_reject(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_reject *); -extern int iscsit_build_logout_rsp(struct iscsit_cmd *, struct iscsi_conn *, +extern int iscsit_build_logout_rsp(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_logout_rsp *); -extern int iscsit_logout_post_handler(struct iscsit_cmd *, struct iscsi_conn *); -extern int iscsit_queue_rsp(struct iscsi_conn *, struct iscsit_cmd *); -extern void iscsit_aborted_task(struct iscsi_conn *, struct iscsit_cmd *); -extern int iscsit_add_reject(struct iscsi_conn *, u8, unsigned char *); +extern int iscsit_logout_post_handler(struct iscsit_cmd *, struct iscsit_conn *); +extern int iscsit_queue_rsp(struct iscsit_conn *, struct iscsit_cmd *); +extern void iscsit_aborted_task(struct iscsit_conn *, struct iscsit_cmd *); +extern int iscsit_add_reject(struct iscsit_conn *, u8, unsigned char *); extern int iscsit_reject_cmd(struct iscsit_cmd *, u8, unsigned char *); -extern int iscsit_handle_snack(struct iscsi_conn *, unsigned char *); -extern void iscsit_build_datain_pdu(struct iscsit_cmd *, struct iscsi_conn *, +extern int iscsit_handle_snack(struct iscsit_conn *, unsigned char *); +extern void iscsit_build_datain_pdu(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_datain *, struct iscsi_data_rsp *, bool); -extern int iscsit_build_r2ts_for_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_build_r2ts_for_cmd(struct iscsit_conn *, struct iscsit_cmd *, bool); -extern int iscsit_immediate_queue(struct iscsi_conn *, struct iscsit_cmd *, int); -extern int iscsit_response_queue(struct iscsi_conn *, struct iscsit_cmd *, int); +extern int iscsit_immediate_queue(struct iscsit_conn *, struct iscsit_cmd *, int); +extern int iscsit_response_queue(struct iscsit_conn *, struct iscsit_cmd *, int); /* * From iscsi_target_device.c */ @@ -109,7 +109,7 @@ extern void iscsit_increment_maxcmdsn(struct iscsit_cmd *, struct iscsi_session /* * From iscsi_target_erl0.c */ -extern void iscsit_cause_connection_reinstatement(struct iscsi_conn *, int); +extern void iscsit_cause_connection_reinstatement(struct iscsit_conn *, int); /* * From iscsi_target_erl1.c */ @@ -118,33 +118,33 @@ extern void iscsit_stop_dataout_timer(struct iscsit_cmd *); /* * From iscsi_target_tmr.c */ -extern int iscsit_tmr_post_handler(struct iscsit_cmd *, struct iscsi_conn *); +extern int iscsit_tmr_post_handler(struct iscsit_cmd *, struct iscsit_conn *); /* * From iscsi_target_util.c */ -extern struct iscsit_cmd *iscsit_allocate_cmd(struct iscsi_conn *, int); -extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern struct iscsit_cmd *iscsit_allocate_cmd(struct iscsit_conn *, int); +extern int iscsit_sequence_cmd(struct iscsit_conn *, struct iscsit_cmd *, unsigned char *, __be32); extern void iscsit_release_cmd(struct iscsit_cmd *); extern void iscsit_free_cmd(struct iscsit_cmd *, bool); extern void iscsit_add_cmd_to_immediate_queue(struct iscsit_cmd *, - struct iscsi_conn *, u8); + struct iscsit_conn *, u8); extern struct iscsit_cmd * -iscsit_find_cmd_from_itt_or_dump(struct iscsi_conn *conn, +iscsit_find_cmd_from_itt_or_dump(struct iscsit_conn *conn, itt_t init_task_tag, u32 length); /* * From iscsi_target_nego.c */ -extern int iscsi_target_check_login_request(struct iscsi_conn *, +extern int iscsi_target_check_login_request(struct iscsit_conn *, struct iscsi_login *); /* * From iscsi_target_login.c */ extern __printf(2, 3) int iscsi_change_param_sprintf( - struct iscsi_conn *, const char *, ...); + struct iscsit_conn *, const char *, ...); /* * From iscsi_target_parameters.c -- cgit v1.2.3 From 0873fe44e780eb8ff7932aed347de8dd4103cea7 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 28 Apr 2022 12:29:39 +0300 Subject: scsi: target: iscsi: Rename iscsi_session to iscsit_session The structure iscsi_session naming is used by the iSCSI initiator driver. Rename the target session to iscsit_session to have more readable code. Link: https://lore.kernel.org/r/20220428092939.36768-3-mgurtovoy@nvidia.com Reviewed-by: Mike Christie Signed-off-by: Max Gurtovoy Signed-off-by: Martin K. Petersen --- include/target/iscsi/iscsi_target_core.h | 10 +++++----- include/target/iscsi/iscsi_transport.h | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 76581e0f3d98..8e68ace428d9 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -482,7 +482,7 @@ struct iscsit_cmd { /* Pointer to connection recovery entry */ struct iscsi_conn_recovery *cr; /* Session the command is part of, used for connection recovery */ - struct iscsi_session *sess; + struct iscsit_session *sess; /* list_head for connection list */ struct list_head i_conn_node; /* The TCM I/O descriptor that is accessed via container_of() */ @@ -598,7 +598,7 @@ struct iscsit_conn { struct iscsi_portal_group *tpg; struct iscsi_tpg_np *tpg_np; /* Pointer to parent session */ - struct iscsi_session *sess; + struct iscsit_session *sess; int bitmap_id; int rx_thread_active; struct task_struct *rx_thread; @@ -618,11 +618,11 @@ struct iscsi_conn_recovery { struct list_head conn_recovery_cmd_list; spinlock_t conn_recovery_cmd_lock; struct timer_list time2retain_timer; - struct iscsi_session *sess; + struct iscsit_session *sess; struct list_head cr_list; } ____cacheline_aligned; -struct iscsi_session { +struct iscsit_session { u8 initiator_vendor; u8 isid[6]; enum iscsi_timer_flags_table time2retain_timer_flags; @@ -885,7 +885,7 @@ struct iscsit_global { struct iscsi_portal_group *discovery_tpg; }; -static inline u32 session_get_next_ttt(struct iscsi_session *session) +static inline u32 session_get_next_ttt(struct iscsit_session *session) { u32 ttt; diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index 2ab26bb6f808..42cfe02ea909 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -105,7 +105,7 @@ extern int iscsit_response_queue(struct iscsit_conn *, struct iscsit_cmd *, int) /* * From iscsi_target_device.c */ -extern void iscsit_increment_maxcmdsn(struct iscsit_cmd *, struct iscsi_session *); +extern void iscsit_increment_maxcmdsn(struct iscsit_cmd *, struct iscsit_session *); /* * From iscsi_target_erl0.c */ -- cgit v1.2.3 From 2fcc82411e74e5e6aba336561cf56fb899bfae4e Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Tue, 10 May 2022 13:59:21 -0700 Subject: bpf, x86: Attach a cookie to fentry/fexit/fmod_ret/lsm. Pass a cookie along with BPF_LINK_CREATE requests. Add a bpf_cookie field to struct bpf_tracing_link to attach a cookie. The cookie of a bpf_tracing_link is available by calling bpf_get_attach_cookie when running the BPF program of the attached link. The value of a cookie will be set at bpf_tramp_run_ctx by the trampoline of the link. Signed-off-by: Kui-Feng Lee Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220510205923.3206889-4-kuifeng@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 9 +++++++++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 256fb802e580..aba7ded56436 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1102,6 +1102,7 @@ struct bpf_link_ops { struct bpf_tramp_link { struct bpf_link link; struct hlist_node tramp_hlist; + u64 cookie; }; struct bpf_tracing_link { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3d032ea1b6a3..bc7f89948f54 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1490,6 +1490,15 @@ union bpf_attr { __aligned_u64 addrs; __aligned_u64 cookies; } kprobe_multi; + struct { + /* this is overlaid with the target_btf_id above. */ + __u32 target_btf_id; + /* black box user-provided value passed through + * to BPF program at the execution time and + * accessible through bpf_get_attach_cookie() BPF helper + */ + __u64 cookie; + } tracing; }; } link_create; -- cgit v1.2.3 From 5b87be9e4978fe507c7e14c0bdff147d10d39aec Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 May 2022 20:57:37 -0700 Subject: net: add include/net/net_debug.h Remove from include/linux/netdevice.h helpers that send debug/info/warnings to syslog. We plan adding more helpers in following patches. v2: added two includes, and 'struct net_device' forward declaration to avoid compile errors (kernel bots) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 141 +------------------------------------------ include/net/net_debug.h | 151 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 152 insertions(+), 140 deletions(-) create mode 100644 include/net/net_debug.h (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 51fe143091cf..536321691c72 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -50,6 +50,7 @@ #include #include #include +#include struct netpoll_info; struct device; @@ -5071,81 +5072,9 @@ static inline const char *netdev_reg_state(const struct net_device *dev) return " (unknown)"; } -__printf(3, 4) __cold -void netdev_printk(const char *level, const struct net_device *dev, - const char *format, ...); -__printf(2, 3) __cold -void netdev_emerg(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_alert(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_crit(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_err(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_warn(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_notice(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_info(const struct net_device *dev, const char *format, ...); - -#define netdev_level_once(level, dev, fmt, ...) \ -do { \ - static bool __section(".data.once") __print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - netdev_printk(level, dev, fmt, ##__VA_ARGS__); \ - } \ -} while (0) - -#define netdev_emerg_once(dev, fmt, ...) \ - netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__) -#define netdev_alert_once(dev, fmt, ...) \ - netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__) -#define netdev_crit_once(dev, fmt, ...) \ - netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__) -#define netdev_err_once(dev, fmt, ...) \ - netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__) -#define netdev_warn_once(dev, fmt, ...) \ - netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__) -#define netdev_notice_once(dev, fmt, ...) \ - netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__) -#define netdev_info_once(dev, fmt, ...) \ - netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__) - #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) -#if defined(CONFIG_DYNAMIC_DEBUG) || \ - (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) -#define netdev_dbg(__dev, format, args...) \ -do { \ - dynamic_netdev_dbg(__dev, format, ##args); \ -} while (0) -#elif defined(DEBUG) -#define netdev_dbg(__dev, format, args...) \ - netdev_printk(KERN_DEBUG, __dev, format, ##args) -#else -#define netdev_dbg(__dev, format, args...) \ -({ \ - if (0) \ - netdev_printk(KERN_DEBUG, __dev, format, ##args); \ -}) -#endif - -#if defined(VERBOSE_DEBUG) -#define netdev_vdbg netdev_dbg -#else - -#define netdev_vdbg(dev, format, args...) \ -({ \ - if (0) \ - netdev_printk(KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - /* * netdev_WARN() acts like dev_printk(), but with the key difference * of using a WARN/WARN_ON to get the message out, including the @@ -5159,74 +5088,6 @@ do { \ WARN_ONCE(1, "netdevice: %s%s: " format, netdev_name(dev), \ netdev_reg_state(dev), ##args) -/* netif printk helpers, similar to netdev_printk */ - -#define netif_printk(priv, type, level, dev, fmt, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - netdev_printk(level, (dev), fmt, ##args); \ -} while (0) - -#define netif_level(level, priv, type, dev, fmt, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - netdev_##level(dev, fmt, ##args); \ -} while (0) - -#define netif_emerg(priv, type, dev, fmt, args...) \ - netif_level(emerg, priv, type, dev, fmt, ##args) -#define netif_alert(priv, type, dev, fmt, args...) \ - netif_level(alert, priv, type, dev, fmt, ##args) -#define netif_crit(priv, type, dev, fmt, args...) \ - netif_level(crit, priv, type, dev, fmt, ##args) -#define netif_err(priv, type, dev, fmt, args...) \ - netif_level(err, priv, type, dev, fmt, ##args) -#define netif_warn(priv, type, dev, fmt, args...) \ - netif_level(warn, priv, type, dev, fmt, ##args) -#define netif_notice(priv, type, dev, fmt, args...) \ - netif_level(notice, priv, type, dev, fmt, ##args) -#define netif_info(priv, type, dev, fmt, args...) \ - netif_level(info, priv, type, dev, fmt, ##args) - -#if defined(CONFIG_DYNAMIC_DEBUG) || \ - (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) -#define netif_dbg(priv, type, netdev, format, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - dynamic_netdev_dbg(netdev, format, ##args); \ -} while (0) -#elif defined(DEBUG) -#define netif_dbg(priv, type, dev, format, args...) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args) -#else -#define netif_dbg(priv, type, dev, format, args...) \ -({ \ - if (0) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - -/* if @cond then downgrade to debug, else print at @level */ -#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \ - do { \ - if (cond) \ - netif_dbg(priv, type, netdev, fmt, ##args); \ - else \ - netif_ ## level(priv, type, netdev, fmt, ##args); \ - } while (0) - -#if defined(VERBOSE_DEBUG) -#define netif_vdbg netif_dbg -#else -#define netif_vdbg(priv, type, dev, format, args...) \ -({ \ - if (0) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - /* * The list of packet types we will receive (as opposed to discard) * and the routines to invoke. diff --git a/include/net/net_debug.h b/include/net/net_debug.h new file mode 100644 index 000000000000..19cd2700c20e --- /dev/null +++ b/include/net/net_debug.h @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_NET_DEBUG_H +#define _LINUX_NET_DEBUG_H + +#include +#include + +struct net_device; + +__printf(3, 4) __cold +void netdev_printk(const char *level, const struct net_device *dev, + const char *format, ...); +__printf(2, 3) __cold +void netdev_emerg(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_alert(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_crit(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_err(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_warn(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_notice(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_info(const struct net_device *dev, const char *format, ...); + +#define netdev_level_once(level, dev, fmt, ...) \ +do { \ + static bool __section(".data.once") __print_once; \ + \ + if (!__print_once) { \ + __print_once = true; \ + netdev_printk(level, dev, fmt, ##__VA_ARGS__); \ + } \ +} while (0) + +#define netdev_emerg_once(dev, fmt, ...) \ + netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__) +#define netdev_alert_once(dev, fmt, ...) \ + netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__) +#define netdev_crit_once(dev, fmt, ...) \ + netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__) +#define netdev_err_once(dev, fmt, ...) \ + netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__) +#define netdev_warn_once(dev, fmt, ...) \ + netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__) +#define netdev_notice_once(dev, fmt, ...) \ + netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__) +#define netdev_info_once(dev, fmt, ...) \ + netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__) + +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) +#define netdev_dbg(__dev, format, args...) \ +do { \ + dynamic_netdev_dbg(__dev, format, ##args); \ +} while (0) +#elif defined(DEBUG) +#define netdev_dbg(__dev, format, args...) \ + netdev_printk(KERN_DEBUG, __dev, format, ##args) +#else +#define netdev_dbg(__dev, format, args...) \ +({ \ + if (0) \ + netdev_printk(KERN_DEBUG, __dev, format, ##args); \ +}) +#endif + +#if defined(VERBOSE_DEBUG) +#define netdev_vdbg netdev_dbg +#else + +#define netdev_vdbg(dev, format, args...) \ +({ \ + if (0) \ + netdev_printk(KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + +/* netif printk helpers, similar to netdev_printk */ + +#define netif_printk(priv, type, level, dev, fmt, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + netdev_printk(level, (dev), fmt, ##args); \ +} while (0) + +#define netif_level(level, priv, type, dev, fmt, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + netdev_##level(dev, fmt, ##args); \ +} while (0) + +#define netif_emerg(priv, type, dev, fmt, args...) \ + netif_level(emerg, priv, type, dev, fmt, ##args) +#define netif_alert(priv, type, dev, fmt, args...) \ + netif_level(alert, priv, type, dev, fmt, ##args) +#define netif_crit(priv, type, dev, fmt, args...) \ + netif_level(crit, priv, type, dev, fmt, ##args) +#define netif_err(priv, type, dev, fmt, args...) \ + netif_level(err, priv, type, dev, fmt, ##args) +#define netif_warn(priv, type, dev, fmt, args...) \ + netif_level(warn, priv, type, dev, fmt, ##args) +#define netif_notice(priv, type, dev, fmt, args...) \ + netif_level(notice, priv, type, dev, fmt, ##args) +#define netif_info(priv, type, dev, fmt, args...) \ + netif_level(info, priv, type, dev, fmt, ##args) + +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) +#define netif_dbg(priv, type, netdev, format, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + dynamic_netdev_dbg(netdev, format, ##args); \ +} while (0) +#elif defined(DEBUG) +#define netif_dbg(priv, type, dev, format, args...) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args) +#else +#define netif_dbg(priv, type, dev, format, args...) \ +({ \ + if (0) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + +/* if @cond then downgrade to debug, else print at @level */ +#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \ + do { \ + if (cond) \ + netif_dbg(priv, type, netdev, fmt, ##args); \ + else \ + netif_ ## level(priv, type, netdev, fmt, ##args); \ + } while (0) + +#if defined(VERBOSE_DEBUG) +#define netif_vdbg netif_dbg +#else +#define netif_vdbg(priv, type, dev, format, args...) \ +({ \ + if (0) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + + +#endif /* _LINUX_NET_DEBUG_H */ -- cgit v1.2.3 From d268c1f5cfc92eb5bb605f7365769aacd93be234 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 May 2022 20:57:38 -0700 Subject: net: add CONFIG_DEBUG_NET This config option enables network debugging checks. This patch adds DEBUG_NET_WARN_ON_ONCE(cond) Note that this is not a replacement for WARN_ON_ONCE(cond) as (cond) is not evaluated if CONFIG_DEBUG_NET is not set. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/net_debug.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/net_debug.h b/include/net/net_debug.h index 19cd2700c20e..1e74684cbbdb 100644 --- a/include/net/net_debug.h +++ b/include/net/net_debug.h @@ -148,4 +148,10 @@ do { \ #endif +#if defined(CONFIG_DEBUG_NET) +#define DEBUG_NET_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) +#else +#define DEBUG_NET_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#endif + #endif /* _LINUX_NET_DEBUG_H */ -- cgit v1.2.3 From 66e4c8d950083df8e12981babca788e1635c92b6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 May 2022 20:57:39 -0700 Subject: net: warn if transport header was not set Make sure skb_transport_header() and skb_transport_offset() uses are not fooled if the transport header has not been set. This change will likely expose existing bugs in linux networking stacks. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5296b2c37f62..b91d225fdc13 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -42,6 +42,7 @@ #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif +#include /** * DOC: skb checksums @@ -2904,6 +2905,7 @@ static inline bool skb_transport_header_was_set(const struct sk_buff *skb) static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { + DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->head + skb->transport_header; } -- cgit v1.2.3 From a8641d7d8500d41d312350470464e03f3df3672a Mon Sep 17 00:00:00 2001 From: Basavaraj Natikar Date: Mon, 9 May 2022 18:50:25 +0530 Subject: HID: amd_sfh: Move bus declaration outside of amd-sfh This should allow external drivers to reference this bus ID reservation and detect data coming from amd-sfh. Signed-off-by: Mario Limonciello Signed-off-by: Basavaraj Natikar Signed-off-by: Jiri Kosina --- include/uapi/linux/input.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index ee3127461ee0..ef4257ab3026 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -271,6 +271,7 @@ struct input_mask { #define BUS_RMI 0x1D #define BUS_CEC 0x1E #define BUS_INTEL_ISHTP 0x1F +#define BUS_AMD_SFH 0x20 /* * MT_TOOL types -- cgit v1.2.3 From ee692a21e9bf8354bd3ec816f1cf4bff8619ed77 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 11 May 2022 11:17:45 +0530 Subject: fs,io_uring: add infrastructure for uring-cmd file_operations->uring_cmd is a file private handler. This is somewhat similar to ioctl but hopefully a lot more sane and useful as it can be used to enable many io_uring capabilities for the underlying operation. IORING_OP_URING_CMD is a file private kind of request. io_uring doesn't know what is in this command type, it's for the provider of ->uring_cmd() to deal with. Co-developed-by: Kanchan Joshi Signed-off-by: Kanchan Joshi Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220511054750.20432-2-joshi.k@samsung.com Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 ++ include/linux/io_uring.h | 33 +++++++++++++++++++++++++++++++++ include/uapi/linux/io_uring.h | 21 +++++++++++++-------- 3 files changed, 48 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..87b5af1d9fbe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1953,6 +1953,7 @@ struct dir_context { #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; +struct io_uring_cmd; struct file_operations { struct module *owner; @@ -1995,6 +1996,7 @@ struct file_operations { struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); + int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); } __randomize_layout; struct inode_operations { diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 24651c229ed2..4a2f6cc5a492 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -5,7 +5,32 @@ #include #include +enum io_uring_cmd_flags { + IO_URING_F_COMPLETE_DEFER = 1, + IO_URING_F_UNLOCKED = 2, + /* int's last bit, sign checks are usually faster than a bit test */ + IO_URING_F_NONBLOCK = INT_MIN, + + /* ctx state flags, for URING_CMD */ + IO_URING_F_SQE128 = 4, + IO_URING_F_CQE32 = 8, + IO_URING_F_IOPOLL = 16, +}; + +struct io_uring_cmd { + struct file *file; + const void *cmd; + /* callback to defer completions to task context */ + void (*task_work_cb)(struct io_uring_cmd *cmd); + u32 cmd_op; + u32 pad; + u8 pdu[32]; /* available inline for free use */ +}; + #if defined(CONFIG_IO_URING) +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2); +void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)); struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); @@ -30,6 +55,14 @@ static inline void io_uring_free(struct task_struct *tsk) __io_uring_free(tsk); } #else +static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, + ssize_t ret2) +{ +} +static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)) +{ +} static inline struct sock *io_uring_get_socket(struct file *file) { return NULL; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ac2d90d669c3..23618be55dd2 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -22,6 +22,7 @@ struct io_uring_sqe { union { __u64 off; /* offset into file */ __u64 addr2; + __u32 cmd_op; }; union { __u64 addr; /* pointer to buffer or iovecs */ @@ -61,14 +62,17 @@ struct io_uring_sqe { __s32 splice_fd_in; __u32 file_index; }; - __u64 addr3; - __u64 __pad2[1]; - - /* - * If the ring is initialized with IORING_SETUP_SQE128, then this field - * contains 64-bytes of padding, doubling the size of the SQE. - */ - __u64 __big_sqe_pad[0]; + union { + struct { + __u64 addr3; + __u64 __pad2[1]; + }; + /* + * If the ring is initialized with IORING_SETUP_SQE128, then + * this field is used for 80 bytes of arbitrary command data + */ + __u8 cmd[0]; + }; }; enum { @@ -175,6 +179,7 @@ enum io_uring_op { IORING_OP_FGETXATTR, IORING_OP_GETXATTR, IORING_OP_SOCKET, + IORING_OP_URING_CMD, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3 From 456cba386e94f22fa1b1426303fdcac9e66b1417 Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Wed, 11 May 2022 11:17:48 +0530 Subject: nvme: wire-up uring-cmd support for io-passthru on char-device. Introduce handler for fops->uring_cmd(), implementing async passthru on char device (/dev/ngX). The handler supports newly introduced operation NVME_URING_CMD_IO. This operates on a new structure nvme_uring_cmd, which is similar to struct nvme_passthru_cmd64 but without the embedded 8b result field. This field is not needed since uring-cmd allows to return additional result via big-CQE. Signed-off-by: Kanchan Joshi Signed-off-by: Anuj Gupta Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220511054750.20432-5-joshi.k@samsung.com Signed-off-by: Jens Axboe --- include/uapi/linux/nvme_ioctl.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index b2e43185e3b5..04e458c649ab 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -70,6 +70,28 @@ struct nvme_passthru_cmd64 { __u64 result; }; +/* same as struct nvme_passthru_cmd64, minus the 8b result field */ +struct nvme_uring_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd1; + __u32 nsid; + __u32 cdw2; + __u32 cdw3; + __u64 metadata; + __u64 addr; + __u32 metadata_len; + __u32 data_len; + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 rsvd2; +}; + #define nvme_admin_cmd nvme_passthru_cmd #define NVME_IOCTL_ID _IO('N', 0x40) @@ -83,4 +105,7 @@ struct nvme_passthru_cmd64 { #define NVME_IOCTL_IO64_CMD _IOWR('N', 0x48, struct nvme_passthru_cmd64) #define NVME_IOCTL_IO64_CMD_VEC _IOWR('N', 0x49, struct nvme_passthru_cmd64) +/* io_uring async commands: */ +#define NVME_URING_CMD_IO _IOWR('N', 0x80, struct nvme_uring_cmd) + #endif /* _UAPI_LINUX_NVME_IOCTL_H */ -- cgit v1.2.3 From f569add47119fa910ed7711b26b8d38e21f7ea77 Mon Sep 17 00:00:00 2001 From: Anuj Gupta Date: Wed, 11 May 2022 11:17:49 +0530 Subject: nvme: add vectored-io support for uring-cmd wire up support for async passthru that takes an array of buffers (using iovec). Exposed via a new op NVME_URING_CMD_IO_VEC. Same 'struct nvme_uring_cmd' is to be used with - 1. cmd.addr as base address of user iovec array 2. cmd.data_len as count of iovec array elements Signed-off-by: Kanchan Joshi Signed-off-by: Anuj Gupta Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220511054750.20432-6-joshi.k@samsung.com Signed-off-by: Jens Axboe --- include/uapi/linux/nvme_ioctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index 04e458c649ab..0b1876aa5a59 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -107,5 +107,6 @@ struct nvme_uring_cmd { /* io_uring async commands: */ #define NVME_URING_CMD_IO _IOWR('N', 0x80, struct nvme_uring_cmd) +#define NVME_URING_CMD_IO_VEC _IOWR('N', 0x81, struct nvme_uring_cmd) #endif /* _UAPI_LINUX_NVME_IOCTL_H */ -- cgit v1.2.3 From deaf7c4b4bf8b802cc465bb9b33fe6c76e812924 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 9 May 2022 21:03:43 +0200 Subject: lockdep: Delete local_irq_enable_in_hardirq() No more users and there is no desire to grow new ones. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/8735hir0j4.ffs@tglx --- include/linux/interrupt.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index f40754caaefa..b5e06a6e4019 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -222,24 +222,6 @@ devm_request_any_context_irq(struct device *dev, unsigned int irq, extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); -/* - * On lockdep we dont want to enable hardirqs in hardirq - * context. Use local_irq_enable_in_hardirq() to annotate - * kernel code that has to do this nevertheless (pretty much - * the only valid case is for old/broken hardware that is - * insanely slow). - * - * NOTE: in theory this might break fragile code that relies - * on hardirq delivery - in practice we dont seem to have such - * places left. So the only effect should be slightly increased - * irqs-off latencies. - */ -#ifdef CONFIG_LOCKDEP -# define local_irq_enable_in_hardirq() do { } while (0) -#else -# define local_irq_enable_in_hardirq() local_irq_enable() -#endif - bool irq_has_action(unsigned int irq); extern void disable_irq_nosync(unsigned int irq); extern bool disable_hardirq(unsigned int irq); -- cgit v1.2.3 From 434e09e7575b02e014931bc5672289fabd7a825c Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 10 May 2022 15:21:33 -0400 Subject: locking/qrwlock: Change "queue rwlock" to "queued rwlock" Queued rwlock was originally named "queue rwlock" which wasn't quite grammatically correct. However there are still some "queue rwlock" references in the code. Change those to "queued rwlock" for consistency. Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220510192134.434753-1-longman@redhat.com --- include/asm-generic/qrwlock.h | 28 ++++++++++++++-------------- include/asm-generic/qrwlock_types.h | 2 +- 2 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 7ae0ece07b4e..d4cd4cc4389c 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -33,8 +33,8 @@ extern void queued_read_lock_slowpath(struct qrwlock *lock); extern void queued_write_lock_slowpath(struct qrwlock *lock); /** - * queued_read_trylock - try to acquire read lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_read_trylock - try to acquire read lock of a queued rwlock + * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_read_trylock(struct qrwlock *lock) @@ -52,8 +52,8 @@ static inline int queued_read_trylock(struct qrwlock *lock) } /** - * queued_write_trylock - try to acquire write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_trylock - try to acquire write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_write_trylock(struct qrwlock *lock) @@ -68,8 +68,8 @@ static inline int queued_write_trylock(struct qrwlock *lock) _QW_LOCKED)); } /** - * queued_read_lock - acquire read lock of a queue rwlock - * @lock: Pointer to queue rwlock structure + * queued_read_lock - acquire read lock of a queued rwlock + * @lock: Pointer to queued rwlock structure */ static inline void queued_read_lock(struct qrwlock *lock) { @@ -84,8 +84,8 @@ static inline void queued_read_lock(struct qrwlock *lock) } /** - * queued_write_lock - acquire write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_lock - acquire write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_write_lock(struct qrwlock *lock) { @@ -98,8 +98,8 @@ static inline void queued_write_lock(struct qrwlock *lock) } /** - * queued_read_unlock - release read lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_read_unlock - release read lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_read_unlock(struct qrwlock *lock) { @@ -110,8 +110,8 @@ static inline void queued_read_unlock(struct qrwlock *lock) } /** - * queued_write_unlock - release write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_unlock - release write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_write_unlock(struct qrwlock *lock) { @@ -120,7 +120,7 @@ static inline void queued_write_unlock(struct qrwlock *lock) /** * queued_rwlock_is_contended - check if the lock is contended - * @lock : Pointer to queue rwlock structure + * @lock : Pointer to queued rwlock structure * Return: 1 if lock contended, 0 otherwise */ static inline int queued_rwlock_is_contended(struct qrwlock *lock) @@ -130,7 +130,7 @@ static inline int queued_rwlock_is_contended(struct qrwlock *lock) /* * Remapping rwlock architecture specific functions to the corresponding - * queue rwlock functions. + * queued rwlock functions. */ #define arch_read_lock(l) queued_read_lock(l) #define arch_write_lock(l) queued_write_lock(l) diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h index c36f1d5a2572..12392c14c4d0 100644 --- a/include/asm-generic/qrwlock_types.h +++ b/include/asm-generic/qrwlock_types.h @@ -7,7 +7,7 @@ #include /* - * The queue read/write lock data structure + * The queued read/write lock data structure */ typedef struct qrwlock { -- cgit v1.2.3 From abcebcd39fe094b68826cc04f2eca835606697f9 Mon Sep 17 00:00:00 2001 From: Michael Shych Date: Sat, 30 Apr 2022 14:58:07 +0300 Subject: platform_data/mlxreg: Add field for notification callback Add notification callback to inform caller that platform driver probing has been completed. It allows to caller to perform some initialization flow steps depending on specific driver probing completion. Signed-off-by: Michael Shych Reviewed-by: Vadim Pasternak Link: https://lore.kernel.org/r/20220430115809.54565-2-michaelsh@nvidia.com Signed-off-by: Hans de Goede --- include/linux/platform_data/mlxreg.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 40185f9d7c14..a6bd74e29b6b 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -216,6 +216,8 @@ struct mlxreg_core_platform_data { * @mask_low: low aggregation interrupt common mask; * @deferred_nr: I2C adapter number must be exist prior probing execution; * @shift_nr: I2C adapter numbers must be incremented by this value; + * @handle: handle to be passed by callback; + * @completion_notify: callback to notify when platform driver probing is done; */ struct mlxreg_core_hotplug_platform_data { struct mlxreg_core_item *items; @@ -228,6 +230,8 @@ struct mlxreg_core_hotplug_platform_data { u32 mask_low; int deferred_nr; int shift_nr; + void *handle; + int (*completion_notify)(void *handle, int id); }; #endif /* __LINUX_PLATFORM_DATA_MLXREG_H */ -- cgit v1.2.3 From f9d76d15072caf1ec5558fa7cc6d93c7b9d33488 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 10 May 2022 11:51:29 -0400 Subject: USB: gadget: Add ID numbers to gadget names Putting USB gadgets on a new bus of their own encounters a problem when multiple gadgets are present: They all have the same name! The driver core fails with a "sys: cannot create duplicate filename" error when creating any of the /sys/bus/gadget/devices/ symbolic links after the first. This patch fixes the problem by adding a ".N" suffix to each gadget's name when the gadget is registered (where N is a unique ID number), thus making the names distinct. Reported-and-tested-by: Geert Uytterhoeven Signed-off-by: Alan Stern Reviewed-by: Geert Uytterhoeven Fixes: fc274c1e9973 ("USB: gadget: Add a new bus for gadgets") Link: https://lore.kernel.org/r/YnqKAXKyp9Vq/pbn@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index cf7af8a0a6e9..3ad58b7a0824 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -386,6 +386,7 @@ struct usb_gadget_ops { * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag * indicates that it supports LPM as per the LPM ECN & errata. * @irq: the interrupt number for device controller. + * @id_number: a unique ID number for ensuring that gadget names are distinct * * Gadgets have a mostly-portable "gadget driver" implementing device * functions, handling all usb configurations and interfaces. Gadget @@ -446,6 +447,7 @@ struct usb_gadget { unsigned connected:1; unsigned lpm_capable:1; int irq; + int id_number; }; #define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) -- cgit v1.2.3 From 566fb90e050dfa2132340bbdab9533b727dda6f1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 22 Apr 2022 06:37:57 +0200 Subject: swiotlb-xen: fix DMA_ATTR_NO_KERNEL_MAPPING on arm swiotlb-xen uses very different ways to allocate coherent memory on x86 vs arm. On the former it allocates memory from the page allocator, while on the later it reuses the dma-direct allocator the handles the complexities of non-coherent DMA on arm platforms. Unfortunately the complexities of trying to deal with the two cases in the swiotlb-xen.c code lead to a bug in the handling of DMA_ATTR_NO_KERNEL_MAPPING on arm. With the DMA_ATTR_NO_KERNEL_MAPPING flag the coherent memory allocator does not actually allocate coherent memory, but just a DMA handle for some memory that is DMA addressable by the device, but which does not have to have a kernel mapping. Thus dereferencing the return value will lead to kernel crashed and memory corruption. Fix this by using the dma-direct allocator directly for arm, which works perfectly fine because on arm swiotlb-xen is only used when the domain is 1:1 mapped, and then simplifying the remaining code to only cater for the x86 case with DMA coherent device. Reported-by: Rahul Singh Signed-off-by: Christoph Hellwig Reviewed-by: Rahul Singh Reviewed-by: Stefano Stabellini Tested-by: Rahul Singh --- include/xen/arm/page-coherent.h | 20 -------------------- include/xen/swiotlb-xen.h | 6 ------ include/xen/xen-ops.h | 7 ------- 3 files changed, 33 deletions(-) delete mode 100644 include/xen/arm/page-coherent.h (limited to 'include') diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h deleted file mode 100644 index b9cc11e887ed..000000000000 --- a/include/xen/arm/page-coherent.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _XEN_ARM_PAGE_COHERENT_H -#define _XEN_ARM_PAGE_COHERENT_H - -#include -#include - -static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs) -{ - return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs); -} - -static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, - void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) -{ - dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs); -} - -#endif /* _XEN_ARM_PAGE_COHERENT_H */ diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h index 590ceb923f0c..808d17ad8d57 100644 --- a/include/xen/swiotlb-xen.h +++ b/include/xen/swiotlb-xen.h @@ -10,12 +10,6 @@ void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle, void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir); -#ifdef CONFIG_SWIOTLB_XEN -int xen_swiotlb_fixup(void *buf, unsigned long nslabs); -#else -#define xen_swiotlb_fixup NULL -#endif - extern const struct dma_map_ops xen_swiotlb_dma_ops; #endif /* __LINUX_SWIOTLB_XEN_H */ diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index a3584a357f35..c7c1b46ff4cd 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -42,13 +42,6 @@ int xen_setup_shutdown_event(void); extern unsigned long *xen_contiguous_bitmap; -#if defined(CONFIG_XEN_PV) || defined(CONFIG_ARM) || defined(CONFIG_ARM64) -int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, - unsigned int address_bits, - dma_addr_t *dma_handle); -void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order); -#endif - #if defined(CONFIG_XEN_PV) int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, -- cgit v1.2.3 From a6b94c6b49198266eaf78095a632df7245ef5196 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 2 May 2022 09:36:28 -0700 Subject: Drivers: hv: vmbus: Remove support for Hyper-V 2008 and Hyper-V 2008R2/Win7 The VMbus driver has special case code for running on the first released versions of Hyper-V: 2008 and 2008 R2/Windows 7. These versions are now out of support (except for extended security updates) and lack the performance features needed for effective production usage of Linux guests. Simplify the code by removing the negotiation of the VMbus protocol versions required for these releases of Hyper-V, and by removing the special case code for handling these VMbus protocol versions. Signed-off-by: Michael Kelley Reviewed-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/1651509391-2058-2-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index c440c45887c2..a2464295c14a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -230,15 +230,19 @@ static inline u32 hv_get_avail_to_write_percent( * two 16 bit quantities: major_number. minor_number. * * 0 . 13 (Windows Server 2008) - * 1 . 1 (Windows 7) - * 2 . 4 (Windows 8) - * 3 . 0 (Windows 8 R2) + * 1 . 1 (Windows 7, WS2008 R2) + * 2 . 4 (Windows 8, WS2012) + * 3 . 0 (Windows 8.1, WS2012 R2) * 4 . 0 (Windows 10) * 4 . 1 (Windows 10 RS3) * 5 . 0 (Newer Windows 10) * 5 . 1 (Windows 10 RS4) * 5 . 2 (Windows Server 2019, RS5) * 5 . 3 (Windows Server 2022) + * + * The WS2008 and WIN7 versions are listed here for + * completeness but are no longer supported in the + * Linux kernel. */ #define VERSION_WS2008 ((0 << 16) | (13)) -- cgit v1.2.3 From 1bce11126d57dde90a02ecf9bfe98175ab4e729e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Mar 2022 15:53:54 -0700 Subject: asm-generic: ticket-lock: New generic ticket-based spinlock This is a simple, fair spinlock. Specifically it doesn't have all the subtle memory model dependencies that qspinlock has, which makes it more suitable for simple systems as it is more likely to be correct. It is implemented entirely in terms of standard atomics and thus works fine without any arch-specific code. This replaces the existing asm-generic/spinlock.h, which just errored out on SMP systems. Signed-off-by: Peter Zijlstra (Intel) Tested-by: Heiko Stuebner Reviewed-by: Guo Ren Reviewed-by: Arnd Bergmann Signed-off-by: Palmer Dabbelt --- include/asm-generic/spinlock.h | 94 +++++++++++++++++++++++++++++++++--- include/asm-generic/spinlock_types.h | 17 +++++++ 2 files changed, 104 insertions(+), 7 deletions(-) create mode 100644 include/asm-generic/spinlock_types.h (limited to 'include') diff --git a/include/asm-generic/spinlock.h b/include/asm-generic/spinlock.h index adaf6acab172..fdfebcb050f4 100644 --- a/include/asm-generic/spinlock.h +++ b/include/asm-generic/spinlock.h @@ -1,12 +1,92 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_GENERIC_SPINLOCK_H -#define __ASM_GENERIC_SPINLOCK_H + /* - * You need to implement asm/spinlock.h for SMP support. The generic - * version does not handle SMP. + * 'Generic' ticket-lock implementation. + * + * It relies on atomic_fetch_add() having well defined forward progress + * guarantees under contention. If your architecture cannot provide this, stick + * to a test-and-set lock. + * + * It also relies on atomic_fetch_add() being safe vs smp_store_release() on a + * sub-word of the value. This is generally true for anything LL/SC although + * you'd be hard pressed to find anything useful in architecture specifications + * about this. If your architecture cannot do this you might be better off with + * a test-and-set. + * + * It further assumes atomic_*_release() + atomic_*_acquire() is RCpc and hence + * uses atomic_fetch_add() which is RCsc to create an RCsc hot path, along with + * a full fence after the spin to upgrade the otherwise-RCpc + * atomic_cond_read_acquire(). + * + * The implementation uses smp_cond_load_acquire() to spin, so if the + * architecture has WFE like instructions to sleep instead of poll for word + * modifications be sure to implement that (see ARM64 for example). + * */ -#ifdef CONFIG_SMP -#error need an architecture specific asm/spinlock.h -#endif + +#ifndef __ASM_GENERIC_SPINLOCK_H +#define __ASM_GENERIC_SPINLOCK_H + +#include +#include + +static __always_inline void arch_spin_lock(arch_spinlock_t *lock) +{ + u32 val = atomic_fetch_add(1<<16, lock); + u16 ticket = val >> 16; + + if (ticket == (u16)val) + return; + + /* + * atomic_cond_read_acquire() is RCpc, but rather than defining a + * custom cond_read_rcsc() here we just emit a full fence. We only + * need the prior reads before subsequent writes ordering from + * smb_mb(), but as atomic_cond_read_acquire() just emits reads and we + * have no outstanding writes due to the atomic_fetch_add() the extra + * orderings are free. + */ + atomic_cond_read_acquire(lock, ticket == (u16)VAL); + smp_mb(); +} + +static __always_inline bool arch_spin_trylock(arch_spinlock_t *lock) +{ + u32 old = atomic_read(lock); + + if ((old >> 16) != (old & 0xffff)) + return false; + + return atomic_try_cmpxchg(lock, &old, old + (1<<16)); /* SC, for RCsc */ +} + +static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + u16 *ptr = (u16 *)lock + IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); + u32 val = atomic_read(lock); + + smp_store_release(ptr, (u16)val + 1); +} + +static __always_inline int arch_spin_is_locked(arch_spinlock_t *lock) +{ + u32 val = atomic_read(lock); + + return ((val >> 16) != (val & 0xffff)); +} + +static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock) +{ + u32 val = atomic_read(lock); + + return (s16)((val >> 16) - (val & 0xffff)) > 1; +} + +static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return !arch_spin_is_locked(&lock); +} + +#include #endif /* __ASM_GENERIC_SPINLOCK_H */ diff --git a/include/asm-generic/spinlock_types.h b/include/asm-generic/spinlock_types.h new file mode 100644 index 000000000000..8962bb730945 --- /dev/null +++ b/include/asm-generic/spinlock_types.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_GENERIC_SPINLOCK_TYPES_H +#define __ASM_GENERIC_SPINLOCK_TYPES_H + +#include +typedef atomic_t arch_spinlock_t; + +/* + * qrwlock_types depends on arch_spinlock_t, so we must typedef that before the + * include. + */ +#include + +#define __ARCH_SPIN_LOCK_UNLOCKED ATOMIC_INIT(0) + +#endif /* __ASM_GENERIC_SPINLOCK_TYPES_H */ -- cgit v1.2.3 From a8ad07e5240c9e78633270be2fa2356b7e0f0af5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Mar 2022 15:48:29 -0700 Subject: asm-generic: qspinlock: Indicate the use of mixed-size atomics The qspinlock implementation depends on having well behaved mixed-size atomics. This is true on the more widely-used platforms, but these requirements are somewhat subtle and may not be satisfied by all the platforms that qspinlock is used on. Document these requirements, so ports that use qspinlock can more easily determine if they meet these requirements. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Waiman Long Reviewed-by: Arnd Bergmann Signed-off-by: Palmer Dabbelt --- include/asm-generic/qspinlock.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include') diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index d74b13825501..995513fa2690 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -2,6 +2,35 @@ /* * Queued spinlock * + * A 'generic' spinlock implementation that is based on MCS locks. For an + * architecture that's looking for a 'generic' spinlock, please first consider + * ticket-lock.h and only come looking here when you've considered all the + * constraints below and can show your hardware does actually perform better + * with qspinlock. + * + * qspinlock relies on atomic_*_release()/atomic_*_acquire() to be RCsc (or no + * weaker than RCtso if you're power), where regular code only expects atomic_t + * to be RCpc. + * + * qspinlock relies on a far greater (compared to asm-generic/spinlock.h) set + * of atomic operations to behave well together, please audit them carefully to + * ensure they all have forward progress. Many atomic operations may default to + * cmpxchg() loops which will not have good forward progress properties on + * LL/SC architectures. + * + * One notable example is atomic_fetch_or_acquire(), which x86 cannot (cheaply) + * do. Carefully read the patches that introduced + * queued_fetch_set_pending_acquire(). + * + * qspinlock also heavily relies on mixed size atomic operations, in specific + * it requires architectures to have xchg16; something which many LL/SC + * architectures need to implement as a 32bit and+or in order to satisfy the + * forward progress guarantees mentioned above. + * + * Further reading on mixed size atomics that might be relevant: + * + * http://www.cl.cam.ac.uk/~pes20/popl17/mixed-size.pdf + * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * -- cgit v1.2.3 From 493e2ba27635971565a991dc9f689553242890a4 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Thu, 14 Apr 2022 09:34:29 -0700 Subject: asm-generic: qrwlock: Document the spinlock fairness requirements I could only find the fairness requirements documented as the C code, this calls them out in a comment just to be a bit more explicit. Reviewed-by: Arnd Bergmann Signed-off-by: Palmer Dabbelt --- include/asm-generic/qrwlock.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 7ae0ece07b4e..24ae09c1db9f 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -2,6 +2,10 @@ /* * Queue read/write lock * + * These use generic atomic and locking routines, but depend on a fair spinlock + * implementation in order to be fair themselves. The implementation in + * asm-generic/spinlock.h meets these requirements. + * * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P. * * Authors: Waiman Long -- cgit v1.2.3 From 09ea48efffa3156218980e20aaf23dcc7d6000fc Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 11 May 2022 13:12:58 -0600 Subject: vfio: Make vfio_(un)register_notifier accept a vfio_device All callers have a struct vfio_device trivially available, pass it in directly and avoid calling the expensive vfio_group_get_from_dev(). Acked-by: Eric Farman Reviewed-by: Jason J. Herne Reviewed-by: Tony Krowiak Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/1-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 66dda06ec42d..a00fd722f044 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -178,11 +178,11 @@ enum vfio_notify_type { /* events for VFIO_GROUP_NOTIFY */ #define VFIO_GROUP_NOTIFY_SET_KVM BIT(0) -extern int vfio_register_notifier(struct device *dev, +extern int vfio_register_notifier(struct vfio_device *device, enum vfio_notify_type type, unsigned long *required_events, struct notifier_block *nb); -extern int vfio_unregister_notifier(struct device *dev, +extern int vfio_unregister_notifier(struct vfio_device *device, enum vfio_notify_type type, struct notifier_block *nb); -- cgit v1.2.3 From 8e432bb015b6c327d016b1dca509964e189c4770 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 11 May 2022 13:12:59 -0600 Subject: vfio/mdev: Pass in a struct vfio_device * to vfio_pin/unpin_pages() Every caller has a readily available vfio_device pointer, use that instead of passing in a generic struct device. The struct vfio_device already contains the group we need so this avoids complexity, extra refcountings, and a confusing lifecycle model. Reviewed-by: Christoph Hellwig Acked-by: Eric Farman Reviewed-by: Jason J. Herne Reviewed-by: Tony Krowiak Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/3-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index a00fd722f044..bddc70f88899 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -150,9 +150,9 @@ extern long vfio_external_check_extension(struct vfio_group *group, #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) -extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, +extern int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn, int npage, int prot, unsigned long *phys_pfn); -extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, +extern int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn, int npage); extern int vfio_group_pin_pages(struct vfio_group *group, -- cgit v1.2.3 From c6250ffbacc5989a5db3b9acce34b93570938f60 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 11 May 2022 13:12:59 -0600 Subject: vfio/mdev: Pass in a struct vfio_device * to vfio_dma_rw() Every caller has a readily available vfio_device pointer, use that instead of passing in a generic struct device. Change vfio_dma_rw() to take in the struct vfio_device and move the container users that would have been held by vfio_group_get_external_user_from_dev() to vfio_dma_rw() directly, like vfio_pin/unpin_pages(). Reviewed-by: Christoph Hellwig Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/4-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index bddc70f88899..8a1510258717 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -161,7 +161,7 @@ extern int vfio_group_pin_pages(struct vfio_group *group, extern int vfio_group_unpin_pages(struct vfio_group *group, unsigned long *user_iova_pfn, int npage); -extern int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova, +extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova, void *data, size_t len, bool write); extern struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group); -- cgit v1.2.3 From 231657b345046552b35670b45b892cfce2610e12 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 11 May 2022 13:13:00 -0600 Subject: vfio: Remove dead code Now that callers have been updated to use the vfio_device APIs the driver facing group interface is no longer used, delete it: - vfio_group_get_external_user_from_dev() - vfio_group_pin_pages() - vfio_group_unpin_pages() - vfio_group_iommu_domain() -- Reviewed-by: Christoph Hellwig Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/6-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 8a1510258717..6195edd2edcd 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -140,8 +140,6 @@ int vfio_mig_get_next_state(struct vfio_device *device, */ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); -extern struct vfio_group *vfio_group_get_external_user_from_dev(struct device - *dev); extern bool vfio_external_group_match_file(struct vfio_group *group, struct file *filep); extern int vfio_external_user_iommu_id(struct vfio_group *group); @@ -154,18 +152,9 @@ extern int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn, int npage, int prot, unsigned long *phys_pfn); extern int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn, int npage); - -extern int vfio_group_pin_pages(struct vfio_group *group, - unsigned long *user_iova_pfn, int npage, - int prot, unsigned long *phys_pfn); -extern int vfio_group_unpin_pages(struct vfio_group *group, - unsigned long *user_iova_pfn, int npage); - extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova, void *data, size_t len, bool write); -extern struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group); - /* each type has independent events */ enum vfio_notify_type { VFIO_IOMMU_NOTIFY = 0, -- cgit v1.2.3 From ff806cbd90bd2cc3d08a026e26157e5b5a6b5e03 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 11 May 2022 13:19:07 -0600 Subject: vfio/pci: Remove vfio_device_get_from_dev() The last user of this function is in PCI callbacks that want to convert their struct pci_dev to a vfio_device. Instead of searching use the vfio_device available trivially through the drvdata. When a callback in the device_driver is called, the caller must hold the device_lock() on dev. The purpose of the device_lock is to prevent remove() from being called (see __device_release_driver), and allow the driver to safely interact with its drvdata without races. The PCI core correctly follows this and holds the device_lock() when calling error_detected (see report_error_detected) and sriov_configure (see sriov_numvfs_store). Further, since the drvdata holds a positive refcount on the vfio_device any access of the drvdata, under the device_lock(), from a driver callback needs no further protection or refcounting. Thus the remark in the vfio_device_get_from_dev() comment does not apply here, VFIO PCI drivers all call vfio_unregister_group_dev() from their remove callbacks under the device_lock() and cannot race with the remaining callers. Reviewed-by: Kevin Tian Reviewed-by: Shameer Kolothum Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/2-v4-c841817a0349+8f-vfio_get_from_dev_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 2 -- include/linux/vfio_pci_core.h | 3 ++- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 6195edd2edcd..be1e7db4a314 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -125,8 +125,6 @@ void vfio_uninit_group_dev(struct vfio_device *device); int vfio_register_group_dev(struct vfio_device *device); int vfio_register_emulated_iommu_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); -extern struct vfio_device *vfio_device_get_from_dev(struct device *dev); -extern void vfio_device_put(struct vfio_device *device); int vfio_assign_device_set(struct vfio_device *device, void *set_id); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 48f2dd3c568c..23c176d4b073 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -227,8 +227,9 @@ void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev); void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev); void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev); -int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn); extern const struct pci_error_handlers vfio_pci_core_err_handlers; +int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, + int nr_virtfn); long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, unsigned long arg); int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags, -- cgit v1.2.3 From 157cc18122b4a1456d19048e151a164216c4a704 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 22 Apr 2022 09:48:54 -0500 Subject: signal: Rename send_signal send_signal_locked Rename send_signal and __send_signal to send_signal_locked and __send_signal_locked to make send_signal usable outside of signal.c. Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-1-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/signal.h b/include/linux/signal.h index a6db6f2ae113..55605bdf5ce9 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -283,6 +283,8 @@ extern int do_send_sig_info(int sig, struct kernel_siginfo *info, extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); +extern int send_signal_locked(int sig, struct kernel_siginfo *info, + struct task_struct *p, enum pid_type type); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); -- cgit v1.2.3 From e71ba124078e391879e0bf111529fa2d630d106c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 22 Apr 2022 09:28:50 -0500 Subject: signal: Replace __group_send_sig_info with send_signal_locked The function __group_send_sig_info is just a light wrapper around send_signal_locked with one parameter fixed to a constant value. As the wrapper adds no real value update the code to directly call the wrapped function. Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-2-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/signal.h b/include/linux/signal.h index 55605bdf5ce9..3b98e7a28538 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -282,7 +282,6 @@ extern int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); -extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern int send_signal_locked(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int sigprocmask(int, sigset_t *, sigset_t *); -- cgit v1.2.3 From c200e4bb44e80b343c09841e7caaaca0aac5e5fa Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Apr 2022 16:30:17 -0500 Subject: ptrace/um: Replace PT_DTRACE with TIF_SINGLESTEP User mode linux is the last user of the PT_DTRACE flag. Using the flag to indicate single stepping is a little confusing and worse changing tsk->ptrace without locking could potentionally cause problems. So use a thread info flag with a better name instead of flag in tsk->ptrace. Remove the definition PT_DTRACE as uml is the last user. Cc: stable@vger.kernel.org Acked-by: Johannes Berg Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-3-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/ptrace.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 15b3d176b6b4..4c06f9f8ef3f 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -30,7 +30,6 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, #define PT_SEIZED 0x00010000 /* SEIZE used, enable new behavior */ #define PT_PTRACED 0x00000001 -#define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */ #define PT_OPT_FLAG_SHIFT 3 /* PT_TRACE_* event enable flags */ -- cgit v1.2.3 From 4a3d2717d140401df7501a95e454180831a0c5af Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Apr 2022 16:45:37 -0500 Subject: ptrace/xtensa: Replace PT_SINGLESTEP with TIF_SINGLESTEP xtensa is the last user of the PT_SINGLESTEP flag. Changing tsk->ptrace in user_enable_single_step and user_disable_single_step without locking could potentiallly cause problems. So use a thread info flag instead of a flag in tsk->ptrace. Use TIF_SINGLESTEP that xtensa already had defined but unused. Remove the definitions of PT_SINGLESTEP and PT_BLOCKSTEP as they have no more users. Cc: stable@vger.kernel.org Acked-by: Max Filippov Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-4-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/ptrace.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 4c06f9f8ef3f..c952c5ba8fab 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -46,12 +46,6 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, #define PT_EXITKILL (PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT) #define PT_SUSPEND_SECCOMP (PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT) -/* single stepping state bits (used on ARM and PA-RISC) */ -#define PT_SINGLESTEP_BIT 31 -#define PT_SINGLESTEP (1< Date: Fri, 29 Apr 2022 08:43:34 -0500 Subject: ptrace: Don't change __state Stop playing with tsk->__state to remove TASK_WAKEKILL while a ptrace command is executing. Instead remove TASK_WAKEKILL from the definition of TASK_TRACED, and implement a new jobctl flag TASK_PTRACE_FROZEN. This new flag is set in jobctl_freeze_task and cleared when ptrace_stop is awoken or in jobctl_unfreeze_task (when ptrace_stop remains asleep). In signal_wake_up add __TASK_TRACED to state along with TASK_WAKEKILL when the wake up is for a fatal signal. Skip adding __TASK_TRACED when TASK_PTRACE_FROZEN is not set. This has the same effect as changing TASK_TRACED to __TASK_TRACED as all of the wake_ups that use TASK_KILLABLE go through signal_wake_up. Handle a ptrace_stop being called with a pending fatal signal. Previously it would have been handled by schedule simply failing to sleep. As TASK_WAKEKILL is no longer part of TASK_TRACED schedule will sleep with a fatal_signal_pending. The code in signal_wake_up guarantees that the code will be awaked by any fatal signal that codes after TASK_TRACED is set. Previously the __state value of __TASK_TRACED was changed to TASK_RUNNING when woken up or back to TASK_TRACED when the code was left in ptrace_stop. Now when woken up ptrace_stop now clears JOBCTL_PTRACE_FROZEN and when left sleeping ptrace_unfreezed_traced clears JOBCTL_PTRACE_FROZEN. Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-10-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched.h | 2 +- include/linux/sched/jobctl.h | 2 ++ include/linux/sched/signal.h | 5 +++-- 3 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index d5e3c00b74e1..610f2fdb1e2c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -103,7 +103,7 @@ struct task_group; /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) -#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED) +#define TASK_TRACED __TASK_TRACED #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index fa067de9f1a9..d556c3425963 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -19,6 +19,7 @@ struct task_struct; #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ +#define JOBCTL_PTRACE_FROZEN_BIT 24 /* frozen for ptrace */ #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) @@ -28,6 +29,7 @@ struct task_struct; #define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) #define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) +#define JOBCTL_PTRACE_FROZEN (1UL << JOBCTL_PTRACE_FROZEN_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..e66948abbee4 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -435,9 +435,10 @@ extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); -static inline void signal_wake_up(struct task_struct *t, bool resume) +static inline void signal_wake_up(struct task_struct *t, bool fatal) { - signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0); + fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN); + signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { -- cgit v1.2.3 From 31cae1eaae4fd65095ad6a3659db467bc3c2599e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 3 May 2022 15:57:47 -0500 Subject: sched,signal,ptrace: Rework TASK_TRACED, TASK_STOPPED state Currently ptrace_stop() / do_signal_stop() rely on the special states TASK_TRACED and TASK_STOPPED resp. to keep unique state. That is, this state exists only in task->__state and nowhere else. There's two spots of bother with this: - PREEMPT_RT has task->saved_state which complicates matters, meaning task_is_{traced,stopped}() needs to check an additional variable. - An alternative freezer implementation that itself relies on a special TASK state would loose TASK_TRACED/TASK_STOPPED and will result in misbehaviour. As such, add additional state to task->jobctl to track this state outside of task->__state. NOTE: this doesn't actually fix anything yet, just adds extra state. --EWB * didn't add a unnecessary newline in signal.h * Update t->jobctl in signal_wake_up and ptrace_signal_wake_up instead of in signal_wake_up_state. This prevents the clearing of TASK_STOPPED and TASK_TRACED from getting lost. * Added warnings if JOBCTL_STOPPED or JOBCTL_TRACED are not cleared Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220421150654.757693825@infradead.org Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-12-ebiederm@xmission.com Signed-off-by: Eric W. Biederman --- include/linux/sched.h | 8 +++----- include/linux/sched/jobctl.h | 6 ++++++ include/linux/sched/signal.h | 19 +++++++++++++++---- 3 files changed, 24 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 610f2fdb1e2c..cbe5c899599c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -118,11 +118,9 @@ struct task_group; #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) -#define task_is_traced(task) ((READ_ONCE(task->__state) & __TASK_TRACED) != 0) - -#define task_is_stopped(task) ((READ_ONCE(task->__state) & __TASK_STOPPED) != 0) - -#define task_is_stopped_or_traced(task) ((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0) +#define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0) +#define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0) +#define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index d556c3425963..68876d0a7ef9 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -21,6 +21,9 @@ struct task_struct; #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ #define JOBCTL_PTRACE_FROZEN_BIT 24 /* frozen for ptrace */ +#define JOBCTL_STOPPED_BIT 26 /* do_signal_stop() */ +#define JOBCTL_TRACED_BIT 27 /* ptrace_stop() */ + #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) #define JOBCTL_STOP_CONSUME (1UL << JOBCTL_STOP_CONSUME_BIT) @@ -31,6 +34,9 @@ struct task_struct; #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) #define JOBCTL_PTRACE_FROZEN (1UL << JOBCTL_PTRACE_FROZEN_BIT) +#define JOBCTL_STOPPED (1UL << JOBCTL_STOPPED_BIT) +#define JOBCTL_TRACED (1UL << JOBCTL_TRACED_BIT) + #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index e66948abbee4..07ba3404fcde 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -294,8 +294,10 @@ static inline int kernel_dequeue_signal(void) static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); - if (current->jobctl & JOBCTL_STOP_DEQUEUED) + if (current->jobctl & JOBCTL_STOP_DEQUEUED) { + current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); + } spin_unlock_irq(¤t->sighand->siglock); schedule(); @@ -437,12 +439,21 @@ extern void signal_wake_up_state(struct task_struct *t, unsigned int state); static inline void signal_wake_up(struct task_struct *t, bool fatal) { - fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN); - signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0); + unsigned int state = 0; + if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) { + t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED); + state = TASK_WAKEKILL | __TASK_TRACED; + } + signal_wake_up_state(t, state); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { - signal_wake_up_state(t, resume ? __TASK_TRACED : 0); + unsigned int state = 0; + if (resume) { + t->jobctl &= ~JOBCTL_TRACED; + state = __TASK_TRACED; + } + signal_wake_up_state(t, state); } void task_join_group_stop(struct task_struct *task); -- cgit v1.2.3 From 8b796475fd7882663a870456466a4fb315cc1bd6 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 10 May 2022 16:57:34 +0200 Subject: net/sched: act_pedit: really ensure the skb is writable Currently pedit tries to ensure that the accessed skb offset is writable via skb_unclone(). The action potentially allows touching any skb bytes, so it may end-up modifying shared data. The above causes some sporadic MPTCP self-test failures, due to this code: tc -n $ns2 filter add dev ns2eth$i egress \ protocol ip prio 1000 \ handle 42 fw \ action pedit munge offset 148 u8 invert \ pipe csum tcp \ index 100 The above modifies a data byte outside the skb head and the skb is a cloned one, carrying a TCP output packet. This change addresses the issue by keeping track of a rough over-estimate highest skb offset accessed by the action and ensuring such offset is really writable. Note that this may cause performance regressions in some scenarios, but hopefully pedit is not in the critical path. Fixes: db2c24175d14 ("act_pedit: access skb->data safely") Acked-by: Mat Martineau Tested-by: Geliang Tang Signed-off-by: Paolo Abeni Acked-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/1fcf78e6679d0a287dd61bb0f04730ce33b3255d.1652194627.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- include/net/tc_act/tc_pedit.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index 748cf87a4d7e..3e02709a1df6 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -14,6 +14,7 @@ struct tcf_pedit { struct tc_action common; unsigned char tcfp_nkeys; unsigned char tcfp_flags; + u32 tcfp_off_max_hint; struct tc_pedit_key *tcfp_keys; struct tcf_pedit_key_ex *tcfp_keys_ex; }; -- cgit v1.2.3 From 9c2136be0878c88c53dea26943ce40bb03ad8d8d Mon Sep 17 00:00:00 2001 From: Delyan Kratunov Date: Wed, 11 May 2022 18:28:36 +0000 Subject: sched/tracing: Append prev_state to tp args instead Commit fa2c3254d7cf (sched/tracing: Don't re-read p->state when emitting sched_switch event, 2022-01-20) added a new prev_state argument to the sched_switch tracepoint, before the prev task_struct pointer. This reordering of arguments broke BPF programs that use the raw tracepoint (e.g. tp_btf programs). The type of the second argument has changed and existing programs that assume a task_struct* argument (e.g. for bpf_task_storage access) will now fail to verify. If we instead append the new argument to the end, all existing programs would continue to work and can conditionally extract the prev_state argument on supported kernel versions. Fixes: fa2c3254d7cf (sched/tracing: Don't re-read p->state when emitting sched_switch event, 2022-01-20) Signed-off-by: Delyan Kratunov Signed-off-by: Peter Zijlstra (Intel) Acked-by: Steven Rostedt (Google) Link: https://lkml.kernel.org/r/c8a6930dfdd58a4a5755fc01732675472979732b.camel@fb.com --- include/trace/events/sched.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 65e786756321..fbb99a61f714 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -222,11 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next), + struct task_struct *next, + unsigned int prev_state), - TP_ARGS(preempt, prev_state, prev, next), + TP_ARGS(preempt, prev, next, prev_state), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) -- cgit v1.2.3 From 5b74c690e1c55953ec99fd9dab74f72dbee4fe95 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 12 May 2022 01:16:51 +0530 Subject: bpf: Fix sparse warning for bpf_kptr_xchg_proto Kernel Test Robot complained about missing static storage class annotation for bpf_kptr_xchg_proto variable. sparse: symbol 'bpf_kptr_xchg_proto' was not declared. Should it be static? This caused by missing extern definition in the header. Add it to suppress the sparse warning. Fixes: c0a5a21c25f3 ("bpf: Allow storing referenced kptr in map") Reported-by: kernel test robot Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220511194654.765705-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aba7ded56436..3ded8711457f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2246,6 +2246,7 @@ extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_strncmp_proto; extern const struct bpf_func_proto bpf_copy_from_user_task_proto; +extern const struct bpf_func_proto bpf_kptr_xchg_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 103a2f3255a95991252f8f13375c3a96a75011cd Mon Sep 17 00:00:00 2001 From: Itay Iellin Date: Sat, 7 May 2022 08:32:48 -0400 Subject: Bluetooth: Fix the creation of hdev->name Set a size limit of 8 bytes of the written buffer to "hdev->name" including the terminating null byte, as the size of "hdev->name" is 8 bytes. If an id value which is greater than 9999 is allocated, then the "snprintf(hdev->name, sizeof(hdev->name), "hci%d", id)" function call would lead to a truncation of the id value in decimal notation. Set an explicit maximum id parameter in the id allocation function call. The id allocation function defines the maximum allocated id value as the maximum id parameter value minus one. Therefore, HCI_MAX_ID is defined as 10000. Signed-off-by: Itay Iellin Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8abd08245326..62d7b81b1cb7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -36,6 +36,9 @@ /* HCI priority */ #define HCI_PRIO_MAX 7 +/* HCI maximum id value */ +#define HCI_MAX_ID 10000 + /* HCI Core structures */ struct inquiry_data { bdaddr_t bdaddr; -- cgit v1.2.3 From 07343110b293456d30393e89b86c4dee1ac051c8 Mon Sep 17 00:00:00 2001 From: Feng Zhou Date: Wed, 11 May 2022 17:38:53 +0800 Subject: bpf: add bpf_map_lookup_percpu_elem for percpu map Add new ebpf helpers bpf_map_lookup_percpu_elem. The implementation method is relatively simple, refer to the implementation method of map_lookup_elem of percpu map, increase the parameters of cpu, and obtain it according to the specified cpu. Signed-off-by: Feng Zhou Link: https://lore.kernel.org/r/20220511093854.411-2-zhoufeng.zf@bytedance.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ include/uapi/linux/bpf.h | 9 +++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3ded8711457f..5061ccd8b2dc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -89,6 +89,7 @@ struct bpf_map_ops { int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); int (*map_pop_elem)(struct bpf_map *map, void *value); int (*map_peek_elem)(struct bpf_map *map, void *value); + void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, @@ -2184,6 +2185,7 @@ extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_map_push_elem_proto; extern const struct bpf_func_proto bpf_map_pop_elem_proto; extern const struct bpf_func_proto bpf_map_peek_elem_proto; +extern const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bc7f89948f54..0210f85131b3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5164,6 +5164,14 @@ union bpf_attr { * if not NULL, is a reference which must be released using its * corresponding release function, or moved into a BPF map before * program exit. + * + * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu) + * Description + * Perform a lookup in *percpu map* for an entry associated to + * *key* on *cpu*. + * Return + * Map value associated to *key* on *cpu*, or **NULL** if no entry + * was found or *cpu* is invalid. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5361,6 +5369,7 @@ union bpf_attr { FN(skb_set_tstamp), \ FN(ima_file_hash), \ FN(kptr_xchg), \ + FN(map_lookup_percpu_elem), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 43213daed6d6cb60e8cf69058a6db8648a556d9d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 10 May 2022 19:53:01 -0700 Subject: fortify: Provide a memcpy trap door for sharp corners As we continue to narrow the scope of what the FORTIFY memcpy() will accept and build alternative APIs that give the compiler appropriate visibility into more complex memcpy scenarios, there is a need for "unfortified" memcpy use in rare cases where combinations of compiler behaviors, source code layout, etc, result in cases where the stricter memcpy checks need to be bypassed until appropriate solutions can be developed (i.e. fix compiler bugs, code refactoring, new API, etc). The intention is for this to be used only if there's no other reasonable solution, for its use to include a justification that can be used to assess future solutions, and for it to be temporary. Example usage included, based on analysis and discussion from: https://lore.kernel.org/netdev/CANn89iLS_2cshtuXPyNUGDPaic=sJiYfvTb_wNLgWrZRyBxZ_g@mail.gmail.com Cc: Jakub Kicinski Cc: Eric Dumazet Cc: "David S. Miller" Cc: Paolo Abeni Cc: Coco Li Cc: Tariq Toukan Cc: Saeed Mahameed Cc: Leon Romanovsky Cc: netdev@vger.kernel.org Cc: linux-hardening@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220511025301.3636666-1-keescook@chromium.org Signed-off-by: Paolo Abeni --- include/linux/fortify-string.h | 16 ++++++++++++++++ include/linux/string.h | 4 ++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 295637a66c46..3b401fa0f374 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -52,6 +52,22 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strncpy __builtin_strncpy #endif +/** + * unsafe_memcpy - memcpy implementation with no FORTIFY bounds checking + * + * @dst: Destination memory address to write to + * @src: Source memory address to read from + * @bytes: How many bytes to write to @dst from @src + * @justification: Free-form text or comment describing why the use is needed + * + * This should be used for corner cases where the compiler cannot do the + * right thing, or during transitions between APIs, etc. It should be used + * very rarely, and includes a place for justification detailing where bounds + * checking has happened, and why existing solutions cannot be employed. + */ +#define unsafe_memcpy(dst, src, bytes, justification) \ + __underlying_memcpy(dst, src, bytes) + /* * Clang's use of __builtin_object_size() within inlines needs hinting via * __pass_object_size(). The preference is to only ever use type 1 (member diff --git a/include/linux/string.h b/include/linux/string.h index b6572aeca2f5..61ec7e4f6311 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -252,6 +252,10 @@ static inline const char *kbasename(const char *path) #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) #include #endif +#ifndef unsafe_memcpy +#define unsafe_memcpy(dst, src, bytes, justification) \ + memcpy(dst, src, bytes) +#endif void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, int pad); -- cgit v1.2.3 From 71cb8ad1a78043ca0eec1686bdd2e65143943b78 Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Wed, 11 May 2022 10:16:46 -0700 Subject: ASoC: SOF: Add header for IPC4 manifest Add the header for the IPC4 manifest. Co-developed-by: Rander Wang Signed-off-by: Rander Wang Co-developed-by: Bard Liao Signed-off-by: Bard Liao Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Pierre-Louis Bossart Signed-off-by: Ranjani Sridharan Link: https://lore.kernel.org/r/20220511171648.1622993-4-ranjani.sridharan@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/ext_manifest4.h | 119 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 119 insertions(+) create mode 100644 include/sound/sof/ext_manifest4.h (limited to 'include') diff --git a/include/sound/sof/ext_manifest4.h b/include/sound/sof/ext_manifest4.h new file mode 100644 index 000000000000..ec97edcbbfc3 --- /dev/null +++ b/include/sound/sof/ext_manifest4.h @@ -0,0 +1,119 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * Copyright(c) 2022 Intel Corporation. All rights reserved. + */ + +/* + * Extended manifest is a place to store metadata about firmware, known during + * compilation time - for example firmware version or used compiler. + * Given information are read on host side before firmware startup. + * This part of output binary is not signed. + */ + +#ifndef __SOF_FIRMWARE_EXT_MANIFEST4_H__ +#define __SOF_FIRMWARE_EXT_MANIFEST4_H__ + +#include + +/* In ASCII $AE1 */ +#define SOF_EXT_MAN4_MAGIC_NUMBER 0x31454124 + +#define MAX_MODULE_NAME_LEN 8 +#define MAX_FW_BINARY_NAME 8 +#define DEFAULT_HASH_SHA256_LEN 32 +#define SOF_MAN4_FW_HDR_OFFSET 0x2000 +#define SOF_MAN4_FW_HDR_OFFSET_CAVS_1_5 0x284 + +/********************************************************************* + * extended manifest (struct sof_ext_manifest4_hdr) + *------------------- + * css_manifest hdr + *------------------- + * offset reserved for future + *------------------- + * fw_hdr (struct sof_man4_fw_binary_header) + *------------------- + * module_entry[0] (struct sof_man4_module) + *------------------- + * module_entry[1] + *------------------- + * ... + *------------------- + * module_entry[n] + *------------------- + * module_config[0] (struct sof_man4_module_config) + *------------------- + * module_config[1] + *------------------- + * ... + *------------------- + * module_config[m] + *------------------- + * FW content + *------------------- + *********************************************************************/ + +struct sof_ext_manifest4_hdr { + uint32_t id; + uint32_t len; /* length of extension manifest */ + uint16_t version_major; /* header version */ + uint16_t version_minor; + uint32_t num_module_entries; +} __packed; + +struct sof_man4_fw_binary_header { + /* This part must be unchanged to be backward compatible with SPT-LP ROM */ + uint32_t id; + uint32_t len; /* sizeof(sof_man4_fw_binary_header) in bytes */ + uint8_t name[MAX_FW_BINARY_NAME]; + uint32_t preload_page_count; /* number of pages of preloaded image */ + uint32_t fw_image_flags; + uint32_t feature_mask; + uint16_t major_version; /* Firmware version */ + uint16_t minor_version; + uint16_t hotfix_version; + uint16_t build_version; + uint32_t num_module_entries; + + /* This part may change to contain any additional data for BaseFw that is skipped by ROM */ + uint32_t hw_buf_base_addr; + uint32_t hw_buf_length; + uint32_t load_offset; /* This value is used by ROM */ +} __packed; + +struct sof_man4_segment_desc { + uint32_t flags; + uint32_t v_base_addr; + uint32_t file_offset; +} __packed; + +struct sof_man4_module { + uint32_t id; + uint8_t name[MAX_MODULE_NAME_LEN]; + guid_t uuid; + uint32_t type; + uint8_t hash[DEFAULT_HASH_SHA256_LEN]; + uint32_t entry_point; + uint16_t cfg_offset; + uint16_t cfg_count; + uint32_t affinity_mask; + uint16_t instance_max_count; + uint16_t instance_stack_size; + struct sof_man4_segment_desc segments[3]; +} __packed; + +struct sof_man4_module_config { + uint32_t par[4]; /* module parameters */ + uint32_t is_bytes; /* actual size of instance .bss (bytes) */ + uint32_t cps; /* cycles per second */ + uint32_t ibs; /* input buffer size (bytes) */ + uint32_t obs; /* output buffer size (bytes) */ + uint32_t module_flags; /* flags, reserved for future use */ + uint32_t cpc; /* cycles per single run */ + uint32_t obls; /* output block size, reserved for future use */ +} __packed; + +#endif /* __SOF_FIRMWARE_EXT_MANIFEST4_H__ */ -- cgit v1.2.3 From a44623d9279086c89f631201d993aa332f7c9e66 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 10 May 2022 14:46:29 +0530 Subject: usb: core: hcd: Add support for deferring roothub registration It has been observed with certain PCIe USB cards (like Inateck connected to AM64 EVM or J7200 EVM) that as soon as the primary roothub is registered, port status change is handled even before xHC is running leading to cold plug USB devices not detected. For such cases, registering both the root hubs along with the second HCD is required. Add support for deferring roothub registration in usb_add_hcd(), so that both primary and secondary roothubs are registered along with the second HCD. This patch has been added and reverted earier as it triggered a race in usb device enumeration. That race is now fixed in 5.16-rc3, and in stable back to 5.4 commit 6cca13de26ee ("usb: hub: Fix locking issues with address0_mutex") commit 6ae6dc22d2d1 ("usb: hub: Fix usb enumeration issue due to address0 race") CC: stable@vger.kernel.org # 5.4+ Suggested-by: Mathias Nyman Tested-by: Chris Chiu Acked-by: Alan Stern Signed-off-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20220510091630.16564-2-kishon@ti.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 548a028f2dab..2c1fc9212cf2 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -124,6 +124,7 @@ struct usb_hcd { #define HCD_FLAG_RH_RUNNING 5 /* root hub is running? */ #define HCD_FLAG_DEAD 6 /* controller has died? */ #define HCD_FLAG_INTF_AUTHORIZED 7 /* authorize interfaces? */ +#define HCD_FLAG_DEFER_RH_REGISTER 8 /* Defer roothub registration */ /* The flags can be tested using these macros; they are likely to * be slightly faster than test_bit(). @@ -134,6 +135,7 @@ struct usb_hcd { #define HCD_WAKEUP_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING)) #define HCD_RH_RUNNING(hcd) ((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING)) #define HCD_DEAD(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEAD)) +#define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER)) /* * Specifies if interfaces are authorized by default -- cgit v1.2.3 From 2d2d5cb6ca8424fa849ebb4edb8e8022c13860c7 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 12 May 2022 02:18:33 -0700 Subject: io_uring: fix ordering of args in io_uring_queue_async_work Fix arg ordering in TP_ARGS macro, which fixes the output. Fixes: 502c87d65564c ("io-uring: Make tracepoints consistent.") Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220512091834.728610-2-dylany@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index cddf5b6fbeb4..80d2588a090c 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -147,7 +147,7 @@ TRACE_EVENT(io_uring_queue_async_work, TP_PROTO(void *ctx, void * req, unsigned long long user_data, u8 opcode, unsigned int flags, struct io_wq_work *work, int rw), - TP_ARGS(ctx, req, user_data, flags, opcode, work, rw), + TP_ARGS(ctx, req, user_data, opcode, flags, work, rw), TP_STRUCT__entry ( __field( void *, ctx ) -- cgit v1.2.3 From 5ce7729f25c16d5045deff4c9577e6d565da2d8d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 12 May 2022 08:14:08 +0200 Subject: block: reorder the REQ_ flags Keep the op-specific flag last so that they are clearly separate from the generic flags. Various recent commits just kept adding new flags at the end. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220512061408.1826595-1-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4968cb17b13b..30f9a5391fd5 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -408,16 +408,17 @@ enum req_flag_bits { * work item to avoid such priority inversions. */ __REQ_CGROUP_PUNT, - - /* command specific flags for REQ_OP_WRITE_ZEROES: */ - __REQ_NOUNMAP, /* do not free blocks when zeroing */ - __REQ_POLLED, /* caller polls for completion using bio_poll */ __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ + __REQ_SWAP, /* swap I/O */ + __REQ_DRV, /* for driver use */ + + /* + * Command specific flags, keep last: + */ + /* for REQ_OP_WRITE_ZEROES: */ + __REQ_NOUNMAP, /* do not free blocks when zeroing */ - /* for driver use */ - __REQ_DRV, - __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; -- cgit v1.2.3 From 5d2ae14276e698c76fa0c8ce870103f343b38263 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 11 May 2022 16:51:52 -0700 Subject: block: Fix the bio.bi_opf comment Commit ef295ecf090d modified the Linux kernel such that the bottom bits of the bi_opf member contain the operation instead of the topmost bits. That commit did not update the comment next to bi_opf. Hence this patch. From commit ef295ecf090d: -#define bio_op(bio) ((bio)->bi_opf >> BIO_OP_SHIFT) +#define bio_op(bio) ((bio)->bi_opf & REQ_OP_MASK) Cc: Christoph Hellwig Cc: Ming Lei Fixes: ef295ecf090d ("block: better op and flags encoding") Signed-off-by: Bart Van Assche Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220511235152.1082246-1-bvanassche@acm.org Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 30f9a5391fd5..40e815400611 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -246,9 +246,8 @@ typedef unsigned int blk_qc_t; struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - unsigned int bi_opf; /* bottom bits req flags, - * top bits REQ_OP. Use - * accessors. + unsigned int bi_opf; /* bottom bits REQ_OP, top bits + * req_flags. */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; -- cgit v1.2.3 From 2760f5a415c3b86c6394738c6cff740c8b4ce664 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 6 May 2022 15:54:01 -0700 Subject: stop_machine: Add stop_core_cpuslocked() for per-core operations Hardware core level testing features require near simultaneous execution of WRMSR instructions on all threads of a core to initiate a test. Provide a customized cut down version of stop_machine_cpuslocked() that just operates on the threads of a single core. Suggested-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Tony Luck Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220506225410.1652287-4-tony.luck@intel.com Signed-off-by: Hans de Goede --- include/linux/stop_machine.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 46fb3ebdd16e..ea7a74ea7389 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -124,6 +124,22 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); */ int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); +/** + * stop_core_cpuslocked: - stop all threads on just one core + * @cpu: any cpu in the targeted core + * @fn: the function to run + * @data: the data ptr for @fn() + * + * Same as above, but instead of every CPU, only the logical CPUs of a + * single core are affected. + * + * Context: Must be called from within a cpus_read_lock() protected region. + * + * Return: 0 if all executions of @fn returned 0, any non zero return + * value if any returned non zero. + */ +int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data); + int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); #else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ -- cgit v1.2.3 From 51af802fc05152e84727a4293ccaa7e7e1b64d7e Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Fri, 6 May 2022 15:54:08 -0700 Subject: trace: platform/x86/intel/ifs: Add trace point to track Intel IFS operations Add tracing support which may be useful for debugging systems that fail to complete In Field Scan tests. Acked-by: Steven Rostedt (Google) Reviewed-by: Dan Williams Signed-off-by: Tony Luck Acked-by: Hans de Goede Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20220506225410.1652287-11-tony.luck@intel.com Signed-off-by: Hans de Goede --- include/trace/events/intel_ifs.h | 41 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/trace/events/intel_ifs.h (limited to 'include') diff --git a/include/trace/events/intel_ifs.h b/include/trace/events/intel_ifs.h new file mode 100644 index 000000000000..d7353024016c --- /dev/null +++ b/include/trace/events/intel_ifs.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM intel_ifs + +#if !defined(_TRACE_IFS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_IFS_H + +#include +#include + +TRACE_EVENT(ifs_status, + + TP_PROTO(int cpu, union ifs_scan activate, union ifs_status status), + + TP_ARGS(cpu, activate, status), + + TP_STRUCT__entry( + __field( u64, status ) + __field( int, cpu ) + __field( u8, start ) + __field( u8, stop ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->start = activate.start; + __entry->stop = activate.stop; + __entry->status = status.data; + ), + + TP_printk("cpu: %d, start: %.2x, stop: %.2x, status: %llx", + __entry->cpu, + __entry->start, + __entry->stop, + __entry->status) +); + +#endif /* _TRACE_IFS_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 75d6fe48a21a0ea1565228c12b9c16f3fb37b673 Mon Sep 17 00:00:00 2001 From: Siddh Raman Pant Date: Thu, 12 May 2022 20:06:45 +0530 Subject: spi: Doc fix - Describe add_lock and dma_map_dev in spi_controller This fixes the corresponding warnings during building the docs. Signed-off-by: Siddh Raman Pant Link: https://lore.kernel.org/r/4e6187a4-d0f8-4750-e407-e09cc1c91789@gmail.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 5f8c063ddff4..df70eb1a671e 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -347,6 +347,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @max_message_size: function that returns the max message size for * a &spi_device; may be %NULL, so the default %SIZE_MAX will be used. * @io_mutex: mutex for physical bus access + * @add_lock: mutex to avoid adding devices to the same chipselect * @bus_lock_spinlock: spinlock for SPI bus locking * @bus_lock_mutex: mutex for exclusion of multiple callers * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use @@ -361,6 +362,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @transfer: adds a message to the controller's transfer queue. * @cleanup: frees controller-specific state * @can_dma: determine whether this controller supports DMA + * @dma_map_dev: device which can be used for DMA mapping * @queued: whether this controller is providing an internal message queue * @kworker: pointer to thread struct for message pump * @pump_messages: work struct for scheduling work to the message pump -- cgit v1.2.3 From 9824117dd964ecebf5d81990dbf21dfb56445049 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Tue, 12 Apr 2022 15:38:51 -0500 Subject: ipmi: Add an intializer for ipmi_smi_msg struct There was a "type" element added to this structure, but some static values were missed. The default value will be zero, which is correct, but create an initializer for the type and initialize the type properly in the initializer to avoid future issues. Reported-by: Joe Wiese Signed-off-by: Corey Minyard --- include/linux/ipmi_smi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 9277d21c2690..5d69820d8b02 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -125,6 +125,12 @@ struct ipmi_smi_msg { void (*done)(struct ipmi_smi_msg *msg); }; +#define INIT_IPMI_SMI_MSG(done_handler) \ +{ \ + .done = done_handler, \ + .type = IPMI_SMI_MSG_TYPE_NORMAL \ +} + struct ipmi_smi_handlers { struct module *owner; -- cgit v1.2.3 From f214549d717310f795c20db9497db3938116399d Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Tue, 12 Apr 2022 15:49:47 -0500 Subject: ipmi: Add an intializer for ipmi_recv_msg struct Don't hand-initialize the struct here, create a macro to initialize it so new fields added don't get forgotten in places. Signed-off-by: Corey Minyard --- include/linux/ipmi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 163831a087ef..a1c9c0d48ebf 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -72,6 +72,11 @@ struct ipmi_recv_msg { unsigned char msg_data[IPMI_MAX_MSG_LENGTH]; }; +#define INIT_IPMI_RECV_MSG(done_handler) \ +{ \ + .done = done_handler \ +} + /* Allocate and free the receive message. */ void ipmi_free_recv_msg(struct ipmi_recv_msg *msg); -- cgit v1.2.3 From 3db1de0e582c358dd013f3703cd55b5fe4076436 Mon Sep 17 00:00:00 2001 From: Daeho Jeong Date: Thu, 28 Apr 2022 11:18:09 -0700 Subject: f2fs: change the current atomic write way Current atomic write has three major issues like below. - keeps the updates in non-reclaimable memory space and they are even hard to be migrated, which is not good for contiguous memory allocation. - disk spaces used for atomic files cannot be garbage collected, so this makes it difficult for the filesystem to be defragmented. - If atomic write operations hit the threshold of either memory usage or garbage collection failure count, All the atomic write operations will fail immediately. To resolve the issues, I will keep a COW inode internally for all the updates to be flushed from memory, when we need to flush them out in a situation like high memory pressure. These COW inodes will be tagged as orphan inodes to be reclaimed in case of sudden power-cut or system failure during atomic writes. Signed-off-by: Daeho Jeong Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 4d1ad64d4cab..7e915dbf3674 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -15,10 +15,6 @@ TRACE_DEFINE_ENUM(NODE); TRACE_DEFINE_ENUM(DATA); TRACE_DEFINE_ENUM(META); TRACE_DEFINE_ENUM(META_FLUSH); -TRACE_DEFINE_ENUM(INMEM); -TRACE_DEFINE_ENUM(INMEM_DROP); -TRACE_DEFINE_ENUM(INMEM_INVALIDATE); -TRACE_DEFINE_ENUM(INMEM_REVOKE); TRACE_DEFINE_ENUM(IPU); TRACE_DEFINE_ENUM(OPU); TRACE_DEFINE_ENUM(HOT); @@ -59,10 +55,6 @@ TRACE_DEFINE_ENUM(CP_RESIZE); { DATA, "DATA" }, \ { META, "META" }, \ { META_FLUSH, "META_FLUSH" }, \ - { INMEM, "INMEM" }, \ - { INMEM_DROP, "INMEM_DROP" }, \ - { INMEM_INVALIDATE, "INMEM_INVALIDATE" }, \ - { INMEM_REVOKE, "INMEM_REVOKE" }, \ { IPU, "IN-PLACE" }, \ { OPU, "OUT-OF-PLACE" }) @@ -1289,20 +1281,6 @@ DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite, TP_ARGS(page, type) ); -DEFINE_EVENT(f2fs__page, f2fs_register_inmem_page, - - TP_PROTO(struct page *page, int type), - - TP_ARGS(page, type) -); - -DEFINE_EVENT(f2fs__page, f2fs_commit_inmem_page, - - TP_PROTO(struct page *page, int type), - - TP_ARGS(page, type) -); - TRACE_EVENT(f2fs_filemap_fault, TP_PROTO(struct inode *inode, pgoff_t index, unsigned long ret), -- cgit v1.2.3 From ad69172ec930075d25e14220841dd96375088d28 Mon Sep 17 00:00:00 2001 From: David Gow Date: Sat, 2 Apr 2022 12:35:30 +0800 Subject: kunit: Rework kunit_resource allocation policy KUnit's test-managed resources can be created in two ways: - Using the kunit_add_resource() family of functions, which accept a struct kunit_resource pointer, typically allocated statically or on the stack during the test. - Using the kunit_alloc_resource() family of functions, which allocate a struct kunit_resource using kzalloc() behind the scenes. Both of these families of functions accept a 'free' function to be called when the resource is finally disposed of. At present, KUnit will kfree() the resource if this 'free' function is specified, and will not if it is NULL. However, this can lead kunit_alloc_resource() to leak memory (if no 'free' function is passed in), or kunit_add_resource() to incorrectly kfree() memory which was allocated by some other means (on the stack, as part of a larger allocation, etc), if a 'free' function is provided. Instead, always kfree() if the resource was allocated with kunit_alloc_resource(), and never kfree() if it was passed into kunit_add_resource() by the user. (If the user of kunit_add_resource() wishes the resource be kfree()ed, they can call kfree() on the resource from within the 'free' function. This is implemented by adding a 'should_free' member to struct kunit_resource and setting it appropriately. To facilitate this, the various resource add/alloc functions have been refactored somewhat, making them all call a __kunit_add_resource() helper after setting the 'should_free' member appropriately. In the process, all other functions have been made static inline functions. Signed-off-by: David Gow Tested-by: Daniel Latypov Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/resource.h | 142 ++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 115 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/kunit/resource.h b/include/kunit/resource.h index 7ab1fd83972b..09c2b34d1c61 100644 --- a/include/kunit/resource.h +++ b/include/kunit/resource.h @@ -25,11 +25,13 @@ typedef void (*kunit_resource_free_t)(struct kunit_resource *); * struct kunit_resource - represents a *test managed resource* * @data: for the user to store arbitrary data. * @name: optional name - * @free: a user supplied function to free the resource. Populated by - * kunit_resource_alloc(). + * @free: a user supplied function to free the resource. * * Represents a *test managed resource*, a resource which will automatically be - * cleaned up at the end of a test case. + * cleaned up at the end of a test case. This cleanup is performed by the 'free' + * function. The struct kunit_resource itself is freed automatically with + * kfree() if it was allocated by KUnit (e.g., by kunit_alloc_resource()), but + * must be freed by the user otherwise. * * Resources are reference counted so if a resource is retrieved via * kunit_alloc_and_get_resource() or kunit_find_resource(), we need @@ -86,18 +88,9 @@ struct kunit_resource { /* private: internal use only. */ struct kref refcount; struct list_head node; + bool should_kfree; }; -/* - * Like kunit_alloc_resource() below, but returns the struct kunit_resource - * object that contains the allocation. This is mostly for testing purposes. - */ -struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - gfp_t internal_gfp, - void *context); - /** * kunit_get_resource() - Hold resource for use. Should not need to be used * by most users as we automatically get resources @@ -118,11 +111,14 @@ static inline void kunit_release_resource(struct kref *kref) struct kunit_resource *res = container_of(kref, struct kunit_resource, refcount); - /* If free function is defined, resource was dynamically allocated. */ - if (res->free) { + if (res->free) res->free(res); + + /* 'res' is valid here, as if should_kfree is set, res->free may not free + * 'res' itself, just res->data + */ + if (res->should_kfree) kfree(res); - } } /** @@ -142,6 +138,24 @@ static inline void kunit_put_resource(struct kunit_resource *res) kref_put(&res->refcount, kunit_release_resource); } +/** + * __kunit_add_resource() - Internal helper to add a resource. + * + * res->should_kfree is not initialised. + * @test: The test context object. + * @init: a user-supplied function to initialize the result (if needed). If + * none is supplied, the resource data value is simply set to @data. + * If an init function is supplied, @data is passed to it instead. + * @free: a user-supplied function to free the resource (if needed). + * @res: The resource. + * @data: value to pass to init function or set in resource data field. + */ +int __kunit_add_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + struct kunit_resource *res, + void *data); + /** * kunit_add_resource() - Add a *test managed resource*. * @test: The test context object. @@ -152,11 +166,18 @@ static inline void kunit_put_resource(struct kunit_resource *res) * @res: The resource. * @data: value to pass to init function or set in resource data field. */ -int kunit_add_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - struct kunit_resource *res, - void *data); +static inline int kunit_add_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + struct kunit_resource *res, + void *data) +{ + res->should_kfree = false; + return __kunit_add_resource(test, init, free, res, data); +} + +static inline struct kunit_resource * +kunit_find_named_resource(struct kunit *test, const char *name); /** * kunit_add_named_resource() - Add a named *test managed resource*. @@ -167,18 +188,84 @@ int kunit_add_resource(struct kunit *test, * @name: name to be set for resource. * @data: value to pass to init function or set in resource data field. */ -int kunit_add_named_resource(struct kunit *test, +static inline int kunit_add_named_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + struct kunit_resource *res, + const char *name, + void *data) +{ + struct kunit_resource *existing; + + if (!name) + return -EINVAL; + + existing = kunit_find_named_resource(test, name); + if (existing) { + kunit_put_resource(existing); + return -EEXIST; + } + + res->name = name; + res->should_kfree = false; + + return __kunit_add_resource(test, init, free, res, data); +} + +/** + * kunit_alloc_and_get_resource() - Allocates and returns a *test managed resource*. + * @test: The test context object. + * @init: a user supplied function to initialize the resource. + * @free: a user supplied function to free the resource (if needed). + * @internal_gfp: gfp to use for internal allocations, if unsure, use GFP_KERNEL + * @context: for the user to pass in arbitrary data to the init function. + * + * Allocates a *test managed resource*, a resource which will automatically be + * cleaned up at the end of a test case. See &struct kunit_resource for an + * example. + * + * This is effectively identical to kunit_alloc_resource, but returns the + * struct kunit_resource pointer, not just the 'data' pointer. It therefore + * also increments the resource's refcount, so kunit_put_resource() should be + * called when you've finished with it. + * + * Note: KUnit needs to allocate memory for a kunit_resource object. You must + * specify an @internal_gfp that is compatible with the use context of your + * resource. + */ +static inline struct kunit_resource * +kunit_alloc_and_get_resource(struct kunit *test, kunit_resource_init_t init, kunit_resource_free_t free, - struct kunit_resource *res, - const char *name, - void *data); + gfp_t internal_gfp, + void *context) +{ + struct kunit_resource *res; + int ret; + + res = kzalloc(sizeof(*res), internal_gfp); + if (!res) + return NULL; + + res->should_kfree = true; + + ret = __kunit_add_resource(test, init, free, res, context); + if (!ret) { + /* + * bump refcount for get; kunit_resource_put() should be called + * when done. + */ + kunit_get_resource(res); + return res; + } + return NULL; +} /** * kunit_alloc_resource() - Allocates a *test managed resource*. * @test: The test context object. * @init: a user supplied function to initialize the resource. - * @free: a user supplied function to free the resource. + * @free: a user supplied function to free the resource (if needed). * @internal_gfp: gfp to use for internal allocations, if unsure, use GFP_KERNEL * @context: for the user to pass in arbitrary data to the init function. * @@ -202,7 +289,8 @@ static inline void *kunit_alloc_resource(struct kunit *test, if (!res) return NULL; - if (!kunit_add_resource(test, init, free, res, context)) + res->should_kfree = true; + if (!__kunit_add_resource(test, init, free, res, context)) return res->data; return NULL; -- cgit v1.2.3 From 80140a81f7f833998d732102eea0fea230b88067 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 27 Apr 2022 11:03:21 +0200 Subject: module.h: simplify MODULE_IMPORT_NS In commit ca321ec74322 ("module.h: allow #define strings to work with MODULE_IMPORT_NS") I fixed up the MODULE_IMPORT_NS() macro to allow defined strings to work with it. Unfortunatly I did it in a two-stage process, when it could just be done with the __stringify() macro as pointed out by Masahiro Yamada. Clean this up to only be one macro instead of two steps to achieve the same end result. Fixes: ca321ec74322 ("module.h: allow #define strings to work with MODULE_IMPORT_NS") Reported-by: Masahiro Yamada Cc: Luis Chamberlain Cc: Jessica Yu Cc: Matthias Maennich Signed-off-by: Greg Kroah-Hartman Signed-off-by: Luis Chamberlain --- include/linux/module.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 46d4d5f2516e..abd9fa916b7d 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -290,8 +290,7 @@ extern typeof(name) __mod_##type##__##name##_device_table \ * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) -#define _MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, #ns) -#define MODULE_IMPORT_NS(ns) _MODULE_IMPORT_NS(ns) +#define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, __stringify(ns)) struct notifier_block; -- cgit v1.2.3 From d147ea4adb969b03f7f1c7613cc6f44b70760eb3 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 6 May 2022 11:40:33 -0700 Subject: f2fs: introduce f2fs_gc_control to consolidate f2fs_gc parameters No functional change. - remove checkpoint=disable check for f2fs_write_checkpoint - get sec_freed all the time Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 7e915dbf3674..54ec9e543f09 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -644,19 +644,19 @@ TRACE_EVENT(f2fs_background_gc, TRACE_EVENT(f2fs_gc_begin, - TP_PROTO(struct super_block *sb, bool sync, bool background, + TP_PROTO(struct super_block *sb, int gc_type, bool no_bg_gc, long long dirty_nodes, long long dirty_dents, long long dirty_imeta, unsigned int free_sec, unsigned int free_seg, int reserved_seg, unsigned int prefree_seg), - TP_ARGS(sb, sync, background, dirty_nodes, dirty_dents, dirty_imeta, + TP_ARGS(sb, gc_type, no_bg_gc, dirty_nodes, dirty_dents, dirty_imeta, free_sec, free_seg, reserved_seg, prefree_seg), TP_STRUCT__entry( __field(dev_t, dev) - __field(bool, sync) - __field(bool, background) + __field(int, gc_type) + __field(bool, no_bg_gc) __field(long long, dirty_nodes) __field(long long, dirty_dents) __field(long long, dirty_imeta) @@ -668,8 +668,8 @@ TRACE_EVENT(f2fs_gc_begin, TP_fast_assign( __entry->dev = sb->s_dev; - __entry->sync = sync; - __entry->background = background; + __entry->gc_type = gc_type; + __entry->no_bg_gc = no_bg_gc; __entry->dirty_nodes = dirty_nodes; __entry->dirty_dents = dirty_dents; __entry->dirty_imeta = dirty_imeta; @@ -679,12 +679,12 @@ TRACE_EVENT(f2fs_gc_begin, __entry->prefree_seg = prefree_seg; ), - TP_printk("dev = (%d,%d), sync = %d, background = %d, nodes = %lld, " + TP_printk("dev = (%d,%d), gc_type = %s, no_background_GC = %d, nodes = %lld, " "dents = %lld, imeta = %lld, free_sec:%u, free_seg:%u, " "rsv_seg:%d, prefree_seg:%u", show_dev(__entry->dev), - __entry->sync, - __entry->background, + show_gc_type(__entry->gc_type), + (__entry->gc_type == BG_GC) ? __entry->no_bg_gc : -1, __entry->dirty_nodes, __entry->dirty_dents, __entry->dirty_imeta, -- cgit v1.2.3 From 0df65743537dd6e1c8b0924714f14dc367cba2be Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 May 2022 10:23:05 -0700 Subject: skbuff: replace a BUG_ON() with the new DEBUG_NET_WARN_ON_ONCE() Very few drivers actually have Kconfig knobs for adding -DDEBUG. 8 according to a quick grep, while there are 93 users of skb_checksum_none_assert(). Switch to the new DEBUG_NET_WARN_ON_ONCE() to catch bad skbs. Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220511172305.1382810-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b91d225fdc13..9d82a8b6c8f1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -5048,9 +5048,7 @@ static inline void skb_forward_csum(struct sk_buff *skb) */ static inline void skb_checksum_none_assert(const struct sk_buff *skb) { -#ifdef DEBUG - BUG_ON(skb->ip_summed != CHECKSUM_NONE); -#endif + DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE); } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); -- cgit v1.2.3 From 465c3de42b5dcdf0fa8cf996a81de6ba0e8553a3 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 12:50:16 +0300 Subject: net: dsa: introduce the dsa_cpu_ports() helper Similar to dsa_user_ports() which retrieves a port mask of all user ports, introduce dsa_cpu_ports() which retrieves the mask of all CPU ports of a switch. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index efd33956df37..76257a9f0e1b 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -590,6 +590,17 @@ static inline u32 dsa_user_ports(struct dsa_switch *ds) return mask; } +static inline u32 dsa_cpu_ports(struct dsa_switch *ds) +{ + struct dsa_port *cpu_dp; + u32 mask = 0; + + dsa_switch_for_each_cpu_port(cpu_dp, ds) + mask |= BIT(cpu_dp->index); + + return mask; +} + /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { -- cgit v1.2.3 From 72c3b0c7359a6f91dd03e08b839adccd9d4268a8 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 12:50:17 +0300 Subject: net: dsa: felix: manage host flooding using a specific driver callback At the time - commit 7569459a52c9 ("net: dsa: manage flooding on the CPU ports") - not introducing a dedicated switch callback for host flooding made sense, because for the only user, the felix driver, there was nothing different to do for the CPU port than set the flood flags on the CPU port just like on any other bridge port. There are 2 reasons why this approach is not good enough, however. (1) Other drivers, like sja1105, support configuring flooding as a function of {ingress port, egress port}, whereas the DSA ->port_bridge_flags() function only operates on an egress port. So with that driver we'd have useless host flooding from user ports which don't need it. (2) Even with the felix driver, support for multiple CPU ports makes it difficult to piggyback on ->port_bridge_flags(). The way in which the felix driver is going to support host-filtered addresses with multiple CPU ports is that it will direct these addresses towards both CPU ports (in a sort of multicast fashion), then restrict the forwarding to only one of the two using the forwarding masks. Consequently, flooding will also be enabled towards both CPU ports. However, ->port_bridge_flags() gets passed the index of a single CPU port, and that leaves the flood settings out of sync between the 2 CPU ports. This is to say, it's better to have a specific driver method for host flooding, which takes the user port as argument. This solves problem (1) by allowing the driver to do different things for different user ports, and problem (2) by abstracting the operation and letting the driver do whatever, rather than explicitly making the DSA core point to the CPU port it thinks needs to be touched. This new method also creates a problem, which is that cross-chip setups are not handled. However I don't have hardware right now where I can test what is the proper thing to do, and there isn't hardware compatible with multi-switch trees that supports host flooding. So it remains a problem to be tackled in the future. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 76257a9f0e1b..cfb287b0d311 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -978,6 +978,8 @@ struct dsa_switch_ops { int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); + void (*port_set_host_flood)(struct dsa_switch *ds, int port, + bool uc, bool mc); /* * VLAN support -- cgit v1.2.3 From bacf93b0561937695e9c6c1dc1d8ed10ca80eb81 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 12:50:18 +0300 Subject: net: dsa: remove port argument from ->change_tag_protocol() DSA has not supported (and probably will not support in the future either) independent tagging protocols per CPU port. Different switch drivers have different requirements, some may need to replicate some settings for each CPU port, some may need to apply some settings on a single CPU port, while some may have to configure some global settings and then some per-CPU-port settings. In any case, the current model where DSA calls ->change_tag_protocol for each CPU port turns out to be impractical for drivers where there are global things to be done. For example, felix calls dsa_tag_8021q_register(), which makes no sense per CPU port, so it suppresses the second call. Let drivers deal with replication towards all CPU ports, and remove the CPU port argument from the function prototype. Signed-off-by: Vladimir Oltean Acked-by: Luiz Angelo Daros de Luca Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index cfb287b0d311..14f07275852b 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -579,6 +579,10 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) +#define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ + dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ + if (dsa_port_is_cpu((_dp))) + static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; @@ -803,7 +807,7 @@ struct dsa_switch_ops { enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); - int (*change_tag_protocol)(struct dsa_switch *ds, int port, + int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver -- cgit v1.2.3 From 15f6d01e4829cd2a2dc4f02a00c51d7cec1c736d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 13:06:35 +0300 Subject: net: mscc: ocelot: delete ocelot_port :: xmit_template This is no longer used since commit 7c4bb540e917 ("net: dsa: tag_ocelot: create separate tagger for Seville"). Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index e88bcfe4b2cd..919be1989c7c 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -670,7 +670,6 @@ struct ocelot_port { phy_interface_t phy_mode; - u8 *xmit_template; bool is_dsa_8021q_cpu; bool learn_ena; -- cgit v1.2.3 From 6d0be600477089026c76fe529bd96fad4cf69c3b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 13:06:36 +0300 Subject: net: mscc: ocelot: minimize holes in struct ocelot_port Reorder members of struct ocelot_port to eliminate holes and reduce structure size. Pahole says: Before: struct ocelot_port { struct ocelot * ocelot; /* 0 8 */ struct regmap * target; /* 8 8 */ bool vlan_aware; /* 16 1 */ /* XXX 7 bytes hole, try to pack */ const struct ocelot_bridge_vlan * pvid_vlan; /* 24 8 */ unsigned int ptp_skbs_in_flight; /* 32 4 */ u8 ptp_cmd; /* 36 1 */ /* XXX 3 bytes hole, try to pack */ struct sk_buff_head tx_skbs; /* 40 96 */ /* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */ u8 ts_id; /* 136 1 */ /* XXX 3 bytes hole, try to pack */ phy_interface_t phy_mode; /* 140 4 */ bool is_dsa_8021q_cpu; /* 144 1 */ bool learn_ena; /* 145 1 */ /* XXX 6 bytes hole, try to pack */ struct net_device * bond; /* 152 8 */ bool lag_tx_active; /* 160 1 */ /* XXX 1 byte hole, try to pack */ u16 mrp_ring_id; /* 162 2 */ /* XXX 4 bytes hole, try to pack */ struct net_device * bridge; /* 168 8 */ int bridge_num; /* 176 4 */ u8 stp_state; /* 180 1 */ /* XXX 3 bytes hole, try to pack */ int speed; /* 184 4 */ /* size: 192, cachelines: 3, members: 18 */ /* sum members: 161, holes: 7, sum holes: 27 */ /* padding: 4 */ }; After: struct ocelot_port { struct ocelot * ocelot; /* 0 8 */ struct regmap * target; /* 8 8 */ struct net_device * bond; /* 16 8 */ struct net_device * bridge; /* 24 8 */ const struct ocelot_bridge_vlan * pvid_vlan; /* 32 8 */ phy_interface_t phy_mode; /* 40 4 */ unsigned int ptp_skbs_in_flight; /* 44 4 */ struct sk_buff_head tx_skbs; /* 48 96 */ /* --- cacheline 2 boundary (128 bytes) was 16 bytes ago --- */ u16 mrp_ring_id; /* 144 2 */ u8 ptp_cmd; /* 146 1 */ u8 ts_id; /* 147 1 */ u8 stp_state; /* 148 1 */ bool vlan_aware; /* 149 1 */ bool is_dsa_8021q_cpu; /* 150 1 */ bool learn_ena; /* 151 1 */ bool lag_tx_active; /* 152 1 */ /* XXX 3 bytes hole, try to pack */ int bridge_num; /* 156 4 */ int speed; /* 160 4 */ /* size: 168, cachelines: 3, members: 18 */ /* sum members: 161, holes: 1, sum holes: 3 */ /* padding: 4 */ /* last cacheline: 40 bytes */ }; Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 919be1989c7c..904c15ca145e 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -659,28 +659,30 @@ struct ocelot_port { struct regmap *target; - bool vlan_aware; + struct net_device *bond; + struct net_device *bridge; + /* VLAN that untagged frames are classified to, on ingress */ const struct ocelot_bridge_vlan *pvid_vlan; + phy_interface_t phy_mode; + unsigned int ptp_skbs_in_flight; - u8 ptp_cmd; struct sk_buff_head tx_skbs; - u8 ts_id; - phy_interface_t phy_mode; + u16 mrp_ring_id; + u8 ptp_cmd; + u8 ts_id; + + u8 stp_state; + bool vlan_aware; bool is_dsa_8021q_cpu; bool learn_ena; - struct net_device *bond; bool lag_tx_active; - u16 mrp_ring_id; - - struct net_device *bridge; int bridge_num; - u8 stp_state; int speed; }; -- cgit v1.2.3 From 7e708760fc114f049df9dccb994e23d20866b310 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 13:06:37 +0300 Subject: net: mscc: ocelot: move ocelot_port_private :: chip_port to ocelot_port :: index Currently the ocelot switch lib is unaware of the index of a struct ocelot_port, since that is kept in the encapsulating structures of outer drivers (struct dsa_port :: index, struct ocelot_port_private :: chip_port). With the upcoming increase in complexity associated with assigning DSA tag_8021q CPU ports to certain user ports, it becomes necessary for the switch lib to be able to retrieve the index of a certain ocelot_port. Therefore, introduce a new u8 to ocelot_port (same size as the chip_port used by the ocelot switchdev driver) and rework the existing code to populate and use it. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 904c15ca145e..3b8c5a54fb00 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -675,6 +675,8 @@ struct ocelot_port { u8 ptp_cmd; u8 ts_id; + u8 index; + u8 stp_state; bool vlan_aware; bool is_dsa_8021q_cpu; -- cgit v1.2.3 From 8ea1eebb49a2dfee1dce621a638cc1626e542392 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 11 May 2022 17:05:52 -0700 Subject: net: inet: Remove count from inet_listen_hashbucket After commit 0ee58dad5b06 ("net: tcp6: prefer listeners bound to an address") and commit d9fbc7f6431f ("net: tcp: prefer listeners bound to an address"), the count is no longer used. This patch removes it. Signed-off-by: Martin KaFai Lau Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 98e1ec1a14f0..103fc7a30e60 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -111,7 +111,6 @@ struct inet_bind_hashbucket { #define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; - unsigned int count; union { struct hlist_head head; struct hlist_nulls_head nulls_head; -- cgit v1.2.3 From cae3873c5b3a4fcd9706fb461ff4e91bdf1f0120 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 11 May 2022 17:06:05 -0700 Subject: net: inet: Retire port only listening_hash The listen sk is currently stored in two hash tables, listening_hash (hashed by port) and lhash2 (hashed by port and address). After commit 0ee58dad5b06 ("net: tcp6: prefer listeners bound to an address") and commit d9fbc7f6431f ("net: tcp: prefer listeners bound to an address"), the TCP-SYN lookup fast path does not use listening_hash. The commit 05c0b35709c5 ("tcp: seq_file: Replace listening_hash with lhash2") also moved the seq_file (/proc/net/tcp) iteration usage from listening_hash to lhash2. There are still a few listening_hash usages left. One of them is inet_reuseport_add_sock() which uses the listening_hash to search a listen sk during the listen() system call. This turns out to be very slow on use cases that listen on many different VIPs at a popular port (e.g. 443). [ On top of the slowness in adding to the tail in the IPv6 case ]. The latter patch has a selftest to demonstrate this case. This patch takes this chance to move all remaining listening_hash usages to lhash2 and then retire listening_hash. Since most changes need to be done together, it is hard to cut the listening_hash to lhash2 switch into small patches. The changes in this patch is highlighted here for the review purpose. 1. Because of the listening_hash removal, lhash2 can use the sk->sk_nulls_node instead of the icsk->icsk_listen_portaddr_node. This will also keep the sk_unhashed() check to work as is after stop adding sk to listening_hash. The union is removed from inet_listen_hashbucket because only nulls_head is needed. 2. icsk->icsk_listen_portaddr_node and its helpers are removed. 3. The current lhash2 users needs to iterate with sk_nulls_node instead of icsk_listen_portaddr_node. One case is in the inet[6]_lhash2_lookup(). Another case is the seq_file iterator in tcp_ipv4.c. One thing to note is sk_nulls_next() is needed because the old inet_lhash2_for_each_icsk_continue() does a "next" first before iterating. 4. Move the remaining listening_hash usage to lhash2 inet_reuseport_add_sock() which this series is trying to improve. inet_diag.c and mptcp_diag.c are the final two remaining use cases and is moved to lhash2 now also. Signed-off-by: Martin KaFai Lau Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 2 -- include/net/inet_hashtables.h | 41 +------------------------------------- 2 files changed, 1 insertion(+), 42 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3908296d103f..85cd695e7fd1 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -66,7 +66,6 @@ struct inet_connection_sock_af_ops { * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data * @icsk_clean_acked Clean acked data hook - * @icsk_listen_portaddr_node hash to the portaddr listener hashtable * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event @@ -96,7 +95,6 @@ struct inet_connection_sock { const struct tcp_ulp_ops *icsk_ulp_ops; void __rcu *icsk_ulp_data; void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq); - struct hlist_node icsk_listen_portaddr_node; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:5, icsk_ca_initialized:1, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 103fc7a30e60..1b8706719d4f 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -111,10 +111,7 @@ struct inet_bind_hashbucket { #define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; - union { - struct hlist_head head; - struct hlist_nulls_head nulls_head; - }; + struct hlist_nulls_head nulls_head; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ @@ -142,32 +139,8 @@ struct inet_hashinfo { /* The 2nd listener table hashed by local port and address */ unsigned int lhash2_mask; struct inet_listen_hashbucket *lhash2; - - /* All the above members are written once at bootup and - * never written again _or_ are predominantly read-access. - * - * Now align to a new cache line as all the following members - * might be often dirty. - */ - /* All sockets in TCP_LISTEN state will be in listening_hash. - * This is the only table where wildcard'd TCP sockets can - * exist. listening_hash is only hashed by local port number. - * If lhash2 is initialized, the same socket will also be hashed - * to lhash2 by port and address. - */ - struct inet_listen_hashbucket listening_hash[INET_LHTABLE_SIZE] - ____cacheline_aligned_in_smp; }; -#define inet_lhash2_for_each_icsk_continue(__icsk) \ - hlist_for_each_entry_continue(__icsk, icsk_listen_portaddr_node) - -#define inet_lhash2_for_each_icsk(__icsk, list) \ - hlist_for_each_entry(__icsk, list, icsk_listen_portaddr_node) - -#define inet_lhash2_for_each_icsk_rcu(__icsk, list) \ - hlist_for_each_entry_rcu(__icsk, list, icsk_listen_portaddr_node) - static inline struct inet_listen_hashbucket * inet_lhash2_bucket(struct inet_hashinfo *h, u32 hash) { @@ -229,23 +202,11 @@ static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, const unsigned short snum); -/* These can have wildcards, don't try too hard. */ -static inline u32 inet_lhashfn(const struct net *net, const unsigned short num) -{ - return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1); -} - -static inline int inet_sk_listen_hashfn(const struct sock *sk) -{ - return inet_lhashfn(sock_net(sk), inet_sk(sk)->inet_num); -} - /* Caller must disable local BH processing. */ int __inet_inherit_port(const struct sock *sk, struct sock *child); void inet_put_port(struct sock *sk); -void inet_hashinfo_init(struct inet_hashinfo *h); void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, unsigned long numentries, int scale, unsigned long low_limit, -- cgit v1.2.3 From c9b516f16be5896a3d798f8efb03acbd2ceec715 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 12 May 2022 20:38:36 -0700 Subject: ELF, uapi: fixup ELF_ST_TYPE definition This is very theoretical compile failure: ELF_ST_TYPE(st_info = A) Cast will bind first and st_info will stop being lvalue: error: lvalue required as left operand of assignment Given that the only use of this macro is ELF_ST_TYPE(sym->st_info) where st_info is "unsigned char" I've decided to remove cast especially given that companion macro ELF_ST_BIND doesn't use cast. Link: https://lkml.kernel.org/r/Ymv7G1BeX4kt3obz@localhost.localdomain Signed-off-by: Alexey Dobriyan Acked-by: Kees Cook Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton --- include/uapi/linux/elf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..237f21a5e0f6 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -134,7 +134,7 @@ typedef __s64 Elf64_Sxword; #define STT_TLS 6 #define ELF_ST_BIND(x) ((x) >> 4) -#define ELF_ST_TYPE(x) (((unsigned int) x) & 0xf) +#define ELF_ST_TYPE(x) ((x) & 0xf) #define ELF32_ST_BIND(x) ELF_ST_BIND(x) #define ELF32_ST_TYPE(x) ELF_ST_TYPE(x) #define ELF64_ST_BIND(x) ELF_ST_BIND(x) -- cgit v1.2.3 From 58e4a2d27d3255e4e8c507fdc13734dccc9fc4c7 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 17 Dec 2021 09:28:46 +0300 Subject: extcon: Fix extcon_get_extcon_dev() error handling The extcon_get_extcon_dev() function returns error pointers on error, NULL when it's a -EPROBE_DEFER defer situation, and ERR_PTR(-ENODEV) when the CONFIG_EXTCON option is disabled. This is very complicated for the callers to handle and a number of them had bugs that would lead to an Oops. In real life, there are two things which prevented crashes. First, error pointers would only be returned if there was bug in the caller where they passed a NULL "extcon_name" and none of them do that. Second, only two out of the eight drivers will build when CONFIG_EXTCON is disabled. The normal way to write this would be to return -EPROBE_DEFER directly when appropriate and return NULL when CONFIG_EXTCON is disabled. Then the error handling is simple and just looks like: dev->edev = extcon_get_extcon_dev(acpi_dev_name(adev)); if (IS_ERR(dev->edev)) return PTR_ERR(dev->edev); For the two drivers which can build with CONFIG_EXTCON disabled, then extcon_get_extcon_dev() will now return NULL which is not treated as an error and the probe will continue successfully. Those two drivers are "typec_fusb302" and "max8997-battery". In the original code, the typec_fusb302 driver had an 800ms hang in tcpm_get_current_limit() but now that function is a no-op. For the max8997-battery driver everything should continue working as is. Signed-off-by: Dan Carpenter Reviewed-by: Hans de Goede Reviewed-by: Heikki Krogerus Reviewed-by: Guenter Roeck Acked-by: Sebastian Reichel Signed-off-by: Chanwoo Choi --- include/linux/extcon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/extcon.h b/include/linux/extcon.h index 0c19010da77f..685401d94d39 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -296,7 +296,7 @@ static inline void devm_extcon_unregister_notifier_all(struct device *dev, static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) { - return ERR_PTR(-ENODEV); + return NULL; } static inline struct extcon_dev *extcon_find_edev_by_node(struct device_node *node) -- cgit v1.2.3 From 783eb354fb3dcd598e8e7e8a2ed88c0fb6ce5d2f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 4 Apr 2022 15:19:41 +0900 Subject: agpgart.h: do not include from exported header Commit 35d0f1d54ecd ("include/uapi/linux/agpgart.h: include stdlib.h in userspace") included to fix the unknown size_t error, but I do not think it is the right fix. This header already uses __kernel_size_t a few lines below. Replace the remaining size_t, and stop including . Signed-off-by: Masahiro Yamada Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Reviewed-by: Nick Desaulniers --- include/uapi/linux/agpgart.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/agpgart.h b/include/uapi/linux/agpgart.h index f5251045181a..9cc3448c0b5b 100644 --- a/include/uapi/linux/agpgart.h +++ b/include/uapi/linux/agpgart.h @@ -52,7 +52,6 @@ #ifndef __KERNEL__ #include -#include struct agp_version { __u16 major; @@ -64,10 +63,10 @@ typedef struct _agp_info { __u32 bridge_id; /* bridge vendor/device */ __u32 agp_mode; /* mode info of bridge */ unsigned long aper_base;/* base of aperture */ - size_t aper_size; /* size of aperture */ - size_t pg_total; /* max pages (swap + system) */ - size_t pg_system; /* max pages (system) */ - size_t pg_used; /* current pages used */ + __kernel_size_t aper_size; /* size of aperture */ + __kernel_size_t pg_total; /* max pages (swap + system) */ + __kernel_size_t pg_system; /* max pages (system) */ + __kernel_size_t pg_used; /* current pages used */ } agp_info; typedef struct _agp_setup { -- cgit v1.2.3 From 7101d1279917e5c7fe897c275c5a0727fe90f3e3 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 18 Mar 2022 18:44:35 +0100 Subject: media: videobuf2-v4l2: Expose vb2_queue_is_busy() to drivers vb2 queue ownership is managed by the ioctl handler helpers (vb2_ioctl_*). There are however use cases where drivers can benefit from checking queue ownership, for instance when open-coding an ioctl handler that needs to perform additional checks before calling the corresponding vb2 operation. Expose the vb2_queue_is_busy() function in the videobuf2-v4l2.h header, and change its first argument to a struct vb2_queue pointer as the function name implies it operates on a queue, not a video_device. Signed-off-by: Laurent Pinchart Reviewed-by: Kieran Bingham Signed-off-by: Mauro Carvalho Chehab --- include/media/videobuf2-v4l2.h | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/videobuf2-v4l2.h b/include/media/videobuf2-v4l2.h index b66585e304e2..d818d9707695 100644 --- a/include/media/videobuf2-v4l2.h +++ b/include/media/videobuf2-v4l2.h @@ -302,10 +302,29 @@ __poll_t vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait); * The following functions are not part of the vb2 core API, but are simple * helper functions that you can use in your struct v4l2_file_operations, * struct v4l2_ioctl_ops and struct vb2_ops. They will serialize if vb2_queue->lock - * or video_device->lock is set, and they will set and test vb2_queue->owner - * to check if the calling filehandle is permitted to do the queuing operation. + * or video_device->lock is set, and they will set and test the queue owner + * (vb2_queue->owner) to check if the calling filehandle is permitted to do the + * queuing operation. */ +/** + * vb2_queue_is_busy() - check if the queue is busy + * @q: pointer to &struct vb2_queue with videobuf2 queue. + * @file: file through which the vb2 queue access is performed + * + * The queue is considered busy if it has an owner and the owner is not the + * @file. + * + * Queue ownership is acquired and checked by some of the v4l2_ioctl_ops helpers + * below. Drivers can also use this function directly when they need to + * open-code ioctl handlers, for instance to add additional checks between the + * queue ownership test and the call to the corresponding vb2 operation. + */ +static inline bool vb2_queue_is_busy(struct vb2_queue *q, struct file *file) +{ + return q->owner && q->owner != file->private_data; +} + /* struct v4l2_ioctl_ops helpers */ int vb2_ioctl_reqbufs(struct file *file, void *priv, -- cgit v1.2.3 From e3891b36364e85914fcb7a535656695a67e876a7 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 6 May 2022 14:46:46 +0200 Subject: media: cec-adap.c: reconfigure if the PA changes during configuration If the physical address changes (i.e. becomes invalid, then valid again) while the adapter is still claiming free logical addresses, then trigger a reconfiguration since any claimed LAs may now be stale. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 6f13b0222aa3..6c9b41fe9802 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -184,6 +184,7 @@ struct cec_adap_ops { * in order to transmit or receive CEC messages. This is usually a HW * limitation. * @is_configuring: the CEC adapter is configuring (i.e. claiming LAs) + * @must_reconfigure: while configuring, the PA changed, so reclaim LAs * @is_configured: the CEC adapter is configured (i.e. has claimed LAs) * @cec_pin_is_high: if true then the CEC pin is high. Only used with the * CEC pin framework. @@ -243,6 +244,7 @@ struct cec_adapter { u16 phys_addr; bool needs_hpd; bool is_configuring; + bool must_reconfigure; bool is_configured; bool cec_pin_is_high; bool adap_controls_phys_addr; -- cgit v1.2.3 From f9222f8ca18bcb1d55dd749b493b29fd8092fb82 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 10 May 2022 10:53:05 +0200 Subject: media: cec-adap.c: drop activate_cnt, use state info instead Using an activation counter to decide when the enable or disable the cec adapter is not the best approach and can lead to race conditions. Change this to determining the current status of the adapter, and enable or disable the adapter accordingly. It now only needs to be called whenever there is a chance that the state changes, and it can handle enabling/disabling monitoring as well if needed. This simplifies the code and it should be a more robust approach as well. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 6c9b41fe9802..abee41ae02d0 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -183,6 +183,7 @@ struct cec_adap_ops { * @needs_hpd: if true, then the HDMI HotPlug Detect pin must be high * in order to transmit or receive CEC messages. This is usually a HW * limitation. + * @is_enabled: the CEC adapter is enabled * @is_configuring: the CEC adapter is configuring (i.e. claiming LAs) * @must_reconfigure: while configuring, the PA changed, so reclaim LAs * @is_configured: the CEC adapter is configured (i.e. has claimed LAs) @@ -194,7 +195,6 @@ struct cec_adap_ops { * Drivers that need this can set this field to true after the * cec_allocate_adapter() call. * @last_initiator: the initiator of the last transmitted message. - * @activate_cnt: number of times that CEC is activated * @monitor_all_cnt: number of filehandles monitoring all msgs * @monitor_pin_cnt: number of filehandles monitoring pin changes * @follower_cnt: number of filehandles in follower mode @@ -243,13 +243,13 @@ struct cec_adapter { u16 phys_addr; bool needs_hpd; + bool is_enabled; bool is_configuring; bool must_reconfigure; bool is_configured; bool cec_pin_is_high; bool adap_controls_phys_addr; u8 last_initiator; - u32 activate_cnt; u32 monitor_all_cnt; u32 monitor_pin_cnt; u32 follower_cnt; -- cgit v1.2.3 From 05abad857277dda198063017b00ba5b9fed2c0cb Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 1 Apr 2022 16:38:23 -0700 Subject: Bluetooth: HCI: Add HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN quirk This adds HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN quirk which can be used to mark HCI_Enhanced_Setup_Synchronous_Connection as broken even if its support command bit are set since some controller report it as supported but the command don't work properly with some configurations (e.g. BT_VOICE_TRANSPARENT/mSBC). Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 9 +++++++++ include/net/bluetooth/hci_core.h | 8 ++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 69ef31cea582..62a9bb022aed 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -265,6 +265,15 @@ enum { * runtime suspend, because event filtering takes place there. */ HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL, + + /* + * When this quirk is set, disables the use of + * HCI_OP_ENHANCED_SETUP_SYNC_CONN command to setup SCO connections. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, }; /* HCI device flags */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 62d7b81b1cb7..5a52a2018b56 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1495,8 +1495,12 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define privacy_mode_capable(dev) (use_ll_privacy(dev) && \ (hdev->commands[39] & 0x04)) -/* Use enhanced synchronous connection if command is supported */ -#define enhanced_sco_capable(dev) ((dev)->commands[29] & 0x08) +/* Use enhanced synchronous connection if command is supported and its quirk + * has not been set. + */ +#define enhanced_sync_conn_capable(dev) \ + (((dev)->commands[29] & 0x08) && \ + !test_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &(dev)->quirks)) /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ -- cgit v1.2.3 From 4915d50e300e96929d2462041d6f6c6f061167fd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 May 2022 09:56:01 -0700 Subject: inet: add READ_ONCE(sk->sk_bound_dev_if) in INET_MATCH() INET_MATCH() runs without holding a lock on the socket. We probably need to annotate most reads. This patch makes INET_MATCH() an inline function to ease our changes. v2: We remove the 32bit version of it, as modern compilers should generate the same code really, no need to try to be smarter. Also make 'struct net *net' the first argument. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 35 ++++++++++++++++------------------- include/net/sock.h | 3 --- 2 files changed, 16 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 1b8706719d4f..59d72024ad1d 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -255,7 +255,6 @@ static inline struct sock *inet_lookup_listener(struct net *net, ((__force __portpair)(((__u32)(__dport) << 16) | (__force __u32)(__be16)(__sport))) #endif -#if (BITS_PER_LONG == 64) #ifdef __BIG_ENDIAN #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ const __addrpair __name = (__force __addrpair) ( \ @@ -267,24 +266,22 @@ static inline struct sock *inet_lookup_listener(struct net *net, (((__force __u64)(__be32)(__daddr)) << 32) | \ ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ -#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \ - (((__sk)->sk_portpair == (__ports)) && \ - ((__sk)->sk_addrpair == (__cookie)) && \ - (((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ - net_eq(sock_net(__sk), (__net))) -#else /* 32-bit arch */ -#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ - const int __name __deprecated __attribute__((unused)) - -#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \ - (((__sk)->sk_portpair == (__ports)) && \ - ((__sk)->sk_daddr == (__saddr)) && \ - ((__sk)->sk_rcv_saddr == (__daddr)) && \ - (((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ - net_eq(sock_net(__sk), (__net))) -#endif /* 64-bit arch */ + +static inline bool INET_MATCH(struct net *net, const struct sock *sk, + const __addrpair cookie, const __portpair ports, + int dif, int sdif) +{ + int bound_dev_if; + + if (!net_eq(sock_net(sk), net) || + sk->sk_portpair != ports || + sk->sk_addrpair != cookie) + return false; + + /* Paired with WRITE_ONCE() from sock_bindtoindex_locked() */ + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + return bound_dev_if == dif || bound_dev_if == sdif; +} /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need * not check it for lookups anymore, thanks Alexey. -DaveM diff --git a/include/net/sock.h b/include/net/sock.h index 73063c88a249..01edfde4257d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -161,9 +161,6 @@ typedef __u64 __bitwise __addrpair; * for struct sock and struct inet_timewait_sock. */ struct sock_common { - /* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned - * address on 64bit arches : cf INET_MATCH() - */ union { __addrpair skc_addrpair; struct { -- cgit v1.2.3 From 04c494e68a1340cb5c70d4704ac32d863dc64293 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 May 2022 14:14:56 -0700 Subject: Revert "tcp/dccp: get rid of inet_twsk_purge()" This reverts commits: 0dad4087a86a2cbe177404dc73f18ada26a2c390 ("tcp/dccp: get rid of inet_twsk_purge()") d507204d3c5cc57d9a8bdf0a477615bb59ea1611 ("tcp/dccp: add tw->tw_bslot") As Leonard pointed out, a newly allocated netns can happen to reuse a freed 'struct net'. While TCP TW timers were covered by my patches, other things were not: 1) Lookups in rx path (INET_MATCH() and INET6_MATCH()), as they look at 4-tuple plus the 'struct net' pointer. 2) /proc/net/tcp[6] and inet_diag, same reason. 3) hashinfo->bhash[], same reason. Fixing all this seems risky, lets instead revert. In the future, we might have a per netns tcp hash table, or a per netns list of timewait sockets... Fixes: 0dad4087a86a ("tcp/dccp: get rid of inet_twsk_purge()") Signed-off-by: Eric Dumazet Reported-by: Leonard Crestez Tested-by: Leonard Crestez Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 463ae5d33eb0..5b47545f22d3 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -71,7 +71,6 @@ struct inet_timewait_sock { tw_tos : 8; u32 tw_txhash; u32 tw_priority; - u32 tw_bslot; /* bind bucket slot */ struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; @@ -110,6 +109,8 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); +void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); + static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { -- cgit v1.2.3 From 1339f24b336db5ded9811f3fe7b948e0de207785 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 7 May 2022 14:18:44 -0600 Subject: io_uring: allow allocated fixed files for openat/openat2 If the application passes in IORING_FILE_INDEX_ALLOC as the file_slot, then that's a hint to allocate a fixed file descriptor rather than have one be passed in directly. This can be useful for having io_uring manage the direct descriptor space. Normal open direct requests will complete with 0 for success, and < 0 in case of error. If io_uring is asked to allocated the direct descriptor, then the direct descriptor is returned in case of success. Reviewed-by: Hao Xu Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 06621a278cb6..b7f02a55032a 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -63,6 +63,15 @@ struct io_uring_sqe { __u64 __pad2[2]; }; +/* + * If sqe->file_index is set to this for opcodes that instantiate a new + * direct descriptor (like openat/openat2/accept), then io_uring will allocate + * an available direct descriptor instead of having the application pass one + * in. The picked direct descriptor will be returned in cqe->res, or -ENFILE + * if the space is full. + */ +#define IORING_FILE_INDEX_ALLOC (~0U) + enum { IOSQE_FIXED_FILE_BIT, IOSQE_IO_DRAIN_BIT, -- cgit v1.2.3 From a8da73a32b6e9271a613e5a0e90a8c35f40abeb8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 9 May 2022 09:29:14 -0600 Subject: io_uring: add flag for allocating a fully sparse direct descriptor space Currently to setup a fully sparse descriptor space upfront, the app needs to alloate an array of the full size and memset it to -1 and then pass that in. Make this a bit easier by allowing a flag that simply does this internally rather than needing to copy each slot separately. This works with IORING_REGISTER_FILES2 as the flag is set in struct io_uring_rsrc_register, and is only allow when the type is IORING_RSRC_FILE as this doesn't make sense for registered buffers. Reviewed-by: Hao Xu Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index b7f02a55032a..36ec43dc7bf9 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -396,9 +396,15 @@ struct io_uring_files_update { __aligned_u64 /* __s32 * */ fds; }; +/* + * Register a fully sparse file space, rather than pass in an array of all + * -1 file descriptors. + */ +#define IORING_RSRC_REGISTER_SPARSE (1U << 0) + struct io_uring_rsrc_register { __u32 nr; - __u32 resv; + __u32 flags; __u64 resv2; __aligned_u64 data; __aligned_u64 tags; -- cgit v1.2.3 From 59fba9eed5a736caa257df4738c57ff72492365f Mon Sep 17 00:00:00 2001 From: Yunfei Dong Date: Thu, 12 May 2022 04:19:47 +0200 Subject: media: mediatek: vcodec: support stateless H.264 decoding for mt8192 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adds h264 lat and core architecture driver for mt8192, and the decode mode is frame based for stateless decoder. Signed-off-by: Yunfei Dong Tested-by: Nícolas F. R. A. Prado Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/remoteproc/mtk_scp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/remoteproc/mtk_scp.h b/include/linux/remoteproc/mtk_scp.h index b47416f7aeb8..7c2b7cc9fe6c 100644 --- a/include/linux/remoteproc/mtk_scp.h +++ b/include/linux/remoteproc/mtk_scp.h @@ -41,6 +41,8 @@ enum scp_ipi_id { SCP_IPI_ISP_FRAME, SCP_IPI_FD_CMD, SCP_IPI_CROS_HOST_CMD, + SCP_IPI_VDEC_LAT, + SCP_IPI_VDEC_CORE, SCP_IPI_NS_SERVICE = 0xFF, SCP_IPI_MAX = 0x100, }; -- cgit v1.2.3 From ea661ad6e1573d5b08c27444ff2ed403bf39ff66 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 10 May 2022 10:34:03 +0800 Subject: iommu/vt-d: Size Page Request Queue to avoid overflow condition PRQ overflow may cause I/O throughput congestion, resulting in unnecessary degradation of I/O performance. Appropriately increasing the length of PRQ can greatly reduce the occurrence of PRQ overflow. The count of maximum page requests that can be generated in parallel by a PCIe device is statically defined in the Outstanding Page Request Capacity field of the PCIe ATS configure space. The new length of PRQ is calculated by summing up the value of Outstanding Page Request Capacity register across all devices where Page Requests are supported on the real PR-capable platform (Intel Sapphire Rapids). The result is round to the nearest higher power of 2. The PRQ length is also double sized as the VT-d IOMMU driver only updates the Page Request Queue Head Register (PQH_REG) after processing the entire queue. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20220421113558.3504874-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20220510023407.2759143-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-svm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index b3b125b332aa..207ef06ba3e1 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -9,7 +9,7 @@ #define __INTEL_SVM_H__ /* Page Request Queue depth */ -#define PRQ_ORDER 2 +#define PRQ_ORDER 4 #define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) #define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) -- cgit v1.2.3 From fc0051cb95909ab56bd8c929f24d48c9870c3e3a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 10 May 2022 10:34:05 +0800 Subject: iommu/vt-d: Check domain force_snooping against attached devices As domain->force_snooping only impacts the devices attached with the domain, there's no need to check against all IOMMU units. On the other hand, force_snooping could be set on a domain no matter whether it has been attached or not, and once set it is an immutable flag. If no device attached, the operation always succeeds. Then this empty domain can be only attached to a device of which the IOMMU supports snoop control. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20220508123525.1973626-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20220510023407.2759143-7-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 72e5d7900e71..4f29139bbfc3 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -540,6 +540,7 @@ struct dmar_domain { u8 has_iotlb_device: 1; u8 iommu_coherency: 1; /* indicate coherency of iommu access */ u8 force_snooping : 1; /* Create IOPTEs with snoop control */ + u8 set_pte_snp:1; struct list_head devices; /* all devices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ -- cgit v1.2.3 From 4a18419f71cdf9155d2d2a6c79546f720978b990 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Mon, 9 May 2022 18:20:50 -0700 Subject: mm/mprotect: use mmu_gather Patch series "mm/mprotect: avoid unnecessary TLB flushes", v6. This patchset is intended to remove unnecessary TLB flushes during mprotect() syscalls. Once this patch-set make it through, similar and further optimizations for MADV_COLD and userfaultfd would be possible. Basically, there are 3 optimizations in this patch-set: 1. Use TLB batching infrastructure to batch flushes across VMAs and do better/fewer flushes. This would also be handy for later userfaultfd enhancements. 2. Avoid unnecessary TLB flushes. This optimization is the one that provides most of the performance benefits. Unlike previous versions, we now only avoid flushes that would not result in spurious page-faults. 3. Avoiding TLB flushes on change_huge_pmd() that are only needed to prevent the A/D bits from changing. Andrew asked for some benchmark numbers. I do not have an easy determinate macrobenchmark in which it is easy to show benefit. I therefore ran a microbenchmark: a loop that does the following on anonymous memory, just as a sanity check to see that time is saved by avoiding TLB flushes. The loop goes: mprotect(p, PAGE_SIZE, PROT_READ) mprotect(p, PAGE_SIZE, PROT_READ|PROT_WRITE) *p = 0; // make the page writable The test was run in KVM guest with 1 or 2 threads (the second thread was busy-looping). I measured the time (cycles) of each operation: 1 thread 2 threads mmots +patch mmots +patch PROT_READ 3494 2725 (-22%) 8630 7788 (-10%) PROT_READ|WRITE 3952 2724 (-31%) 9075 2865 (-68%) [ mmots = v5.17-rc6-mmots-2022-03-06-20-38 ] The exact numbers are really meaningless, but the benefit is clear. There are 2 interesting results though. (1) PROT_READ is cheaper, while one can expect it not to be affected. This is presumably due to TLB miss that is saved (2) Without memory access (*p = 0), the speedup of the patch is even greater. In that scenario mprotect(PROT_READ) also avoids the TLB flush. As a result both operations on the patched kernel take roughly ~1500 cycles (with either 1 or 2 threads), whereas on mmotm their cost is as high as presented in the table. This patch (of 3): change_pXX_range() currently does not use mmu_gather, but instead implements its own deferred TLB flushes scheme. This both complicates the code, as developers need to be aware of different invalidation schemes, and prevents opportunities to avoid TLB flushes or perform them in finer granularity. The use of mmu_gather for modified PTEs has benefits in various scenarios even if pages are not released. For instance, if only a single page needs to be flushed out of a range of many pages, only that page would be flushed. If a THP page is flushed, on x86 a single TLB invlpg instruction can be used instead of 512 instructions (or a full TLB flush, which would Linux would actually use by default). mprotect() over multiple VMAs requires a single flush. Use mmu_gather in change_pXX_range(). As the pages are not released, only record the flushed range using tlb_flush_pXX_range(). Handle THP similarly and get rid of flush_cache_range() which becomes redundant since tlb_start_vma() calls it when needed. Link: https://lkml.kernel.org/r/20220401180821.1986781-1-namit@vmware.com Link: https://lkml.kernel.org/r/20220401180821.1986781-2-namit@vmware.com Signed-off-by: Nadav Amit Acked-by: Peter Zijlstra (Intel) Cc: Andrea Arcangeli Cc: Andrew Cooper Cc: Andy Lutomirski Cc: Dave Hansen Cc: Peter Xu Cc: Thomas Gleixner Cc: Will Deacon Cc: Yu Zhao Cc: Nick Piggin Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 5 +++-- include/linux/mm.h | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 2999190adc22..9a26bd10e083 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -36,8 +36,9 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); -int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, - pgprot_t newprot, unsigned long cp_flags); +int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags); vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write); diff --git a/include/linux/mm.h b/include/linux/mm.h index 5dc5005ccc9b..d63ba0e0e068 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1967,10 +1967,11 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) -extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, +extern unsigned long change_protection(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, unsigned long cp_flags); -extern int mprotect_fixup(struct vm_area_struct *vma, +extern int mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); -- cgit v1.2.3 From c9fe66560bf2dc7d109754414e309888cb8c9ba9 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Mon, 9 May 2022 18:20:50 -0700 Subject: mm/mprotect: do not flush when not required architecturally Currently, using mprotect() to unprotect a memory region or uffd to unprotect a memory region causes a TLB flush. However, in such cases the PTE is often not modified (i.e., remain RO) and therefore not TLB flush is needed. Add an arch-specific pte_needs_flush() which tells whether a TLB flush is needed based on the old PTE and the new one. Implement an x86 pte_needs_flush(). Always flush the TLB when it is architecturally needed even when skipping a TLB flush might only result in a spurious page-faults by skipping the flush. Even with such conservative manner, we can in the future further refine the checks to test whether a PTE is present by only considering the architectural _PAGE_PRESENT flag instead of {pte|pmd}_preesnt(). For not be careful and use the latter. Link: https://lkml.kernel.org/r/20220401180821.1986781-3-namit@vmware.com Signed-off-by: Nadav Amit Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Dave Hansen Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: Yu Zhao Cc: Nick Piggin Cc: Andrew Cooper Cc: Peter Xu Signed-off-by: Andrew Morton --- include/asm-generic/tlb.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index eee6f7763a39..ff3e82553a76 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -658,6 +658,20 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, } while (0) #endif +#ifndef pte_needs_flush +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) +{ + return true; +} +#endif + +#ifndef huge_pmd_needs_flush +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) +{ + return true; +} +#endif + #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ -- cgit v1.2.3 From 4f83145721f362c2f4d312edc4755269a2069488 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Mon, 9 May 2022 18:20:50 -0700 Subject: mm: avoid unnecessary flush on change_huge_pmd() Calls to change_protection_range() on THP can trigger, at least on x86, two TLB flushes for one page: one immediately, when pmdp_invalidate() is called by change_huge_pmd(), and then another one later (that can be batched) when change_protection_range() finishes. The first TLB flush is only necessary to prevent the dirty bit (and with a lesser importance the access bit) from changing while the PTE is modified. However, this is not necessary as the x86 CPUs set the dirty-bit atomically with an additional check that the PTE is (still) present. One caveat is Intel's Knights Landing that has a bug and does not do so. Leverage this behavior to eliminate the unnecessary TLB flush in change_huge_pmd(). Introduce a new arch specific pmdp_invalidate_ad() that only invalidates the access and dirty bit from further changes. Link: https://lkml.kernel.org/r/20220401180821.1986781-4-namit@vmware.com Signed-off-by: Nadav Amit Cc: Andrea Arcangeli Cc: Andrew Cooper Cc: Andy Lutomirski Cc: Dave Hansen Cc: Peter Xu Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: Yu Zhao Cc: Nick Piggin Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 53750224e176..530b1817b58c 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -570,6 +570,26 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif +#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD + +/* + * pmdp_invalidate_ad() invalidates the PMD while changing a transparent + * hugepage mapping in the page tables. This function is similar to + * pmdp_invalidate(), but should only be used if the access and dirty bits would + * not be cleared by the software in the new PMD value. The function ensures + * that hardware changes of the access and dirty bits updates would not be lost. + * + * Doing so can allow in certain architectures to avoid a TLB flush in most + * cases. Yet, another TLB flush might be necessary later if the PMD update + * itself requires such flush (e.g., if protection was set to be stricter). Yet, + * even when a TLB flush is needed because of the update, the caller may be able + * to batch these TLB flushing operations, so fewer TLB flush operations are + * needed. + */ +extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#endif + #ifndef __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { -- cgit v1.2.3 From f38adfef7e6bfe681d6602b6668be31fe1310ed0 Mon Sep 17 00:00:00 2001 From: "Fabio M. De Francesco" Date: Mon, 9 May 2022 18:20:51 -0700 Subject: mm/highmem: VM_BUG_ON() if offset + len > PAGE_SIZE Add VM_BUG_ON() bounds checking to make sure that, if "offset + len> PAGE_SIZE", memset() does not corrupt data in adjacent pages. Mainly to match all the similar functions in highmem.h. Link: https://lkml.kernel.org/r/20220426193020.8710-1-fmdefrancesco@gmail.com Signed-off-by: Fabio M. De Francesco Reviewed-by: Andrew Morton Cc: Ira Weiny Cc: Catalin Marinas Cc: "Matthew Wilcox (Oracle)" Cc: Peter Collingbourne Signed-off-by: Andrew Morton --- include/linux/highmem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 39bb9b47fa9c..67720bfd6ade 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -358,6 +358,8 @@ static inline void memcpy_to_page(struct page *page, size_t offset, static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_local_page(page); + + VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, 0, len); flush_dcache_page(page); kunmap_local(addr); -- cgit v1.2.3 From 152e56178ad72037bc6a2f08d4a608543bc67cdf Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 9 May 2022 18:20:51 -0700 Subject: mm/damon/core: add a function for damon_operations registration checks Patch series "mm/damon: allow users know which monitoring ops are available". DAMON users can configure it for vaious address spaces including virtual address spaces and the physical address space by setting its monitoring operations set with appropriate one for their purpose. However, there is no celan and simple way to know exactly which monitoring operations sets are available on the currently running kernel. This patchset adds functions for the purpose on DAMON's kernel API ('damon_is_registered_ops()') and sysfs interface ('avail_operations' file under each context directory). This patch (of 4): To know if a specific 'damon_operations' is registered, users need to check the kernel config or try 'damon_select_ops()' with the ops of the question, and then see if it successes. In the latter case, the user should also revert the change. To make the process simple and convenient, this commit adds a function for checking if a specific 'damon_operations' is registered or not. Link: https://lkml.kernel.org/r/20220426203843.45238-1-sj@kernel.org Link: https://lkml.kernel.org/r/20220426203843.45238-2-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index f23cbfa4248d..73ff0e2d2a4d 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -509,6 +509,7 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); +bool damon_is_registered_ops(enum damon_ops_id id); int damon_register_ops(struct damon_operations *ops); int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id); -- cgit v1.2.3 From de6d01542a5c4f6fe6f0c65c14694b760f896acc Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 9 May 2022 18:20:52 -0700 Subject: mm/damon/vaddr: register a damon_operations for fixed virtual address ranges monitoring Patch series "support fixed virtual address ranges monitoring". The monitoring operations set for virtual address spaces automatically updates the monitoring target regions to cover entire mappings of the virtual address spaces as much as possible. Some users could have more information about their programs than kernel and therefore have interest in not entire regions but only specific regions. For such cases, the automatic monitoring target regions updates are only unnecessary overhead or distractions. This patchset adds supports for the use case on DAMON's kernel API (DAMON_OPS_FVADDR) and sysfs interface ('fvaddr' keyword for 'operations' sysfs file). This patch (of 3): The monitoring operations set for virtual address spaces automatically updates the monitoring target regions to cover entire mappings of the virtual address spaces as much as possible. Some users could have more information about their programs than kernel and therefore have interest in not entire regions but only specific regions. For such cases, the automatic monitoring target regions updates are only unnecessary overheads or distractions. For such cases, DAMON's API users can simply set the '->init()' and '->update()' of the DAMON context's '->ops' NULL, and set the target monitoring regions when creating the context. But, that would be a dirty hack. Worse yet, the hack is unavailable for DAMON user space interface users. To support the use case in a clean way that can easily exported to the user space, this commit adds another monitoring operations set called 'fvaddr', which is same to 'vaddr' but does not automatically update the monitoring regions. Instead, it will only respect the virtual address regions which have explicitly passed at the initial context creation. Note that this commit leave sysfs interface not supporting the feature yet. The support will be made in a following commit. Link: https://lkml.kernel.org/r/20220426231750.48822-1-sj@kernel.org Link: https://lkml.kernel.org/r/20220426231750.48822-2-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index 73ff0e2d2a4d..09a5d0d02c00 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -261,10 +261,13 @@ struct damos { * enum damon_ops_id - Identifier for each monitoring operations implementation * * @DAMON_OPS_VADDR: Monitoring operations for virtual address spaces + * @DAMON_OPS_FVADDR: Monitoring operations for only fixed ranges of virtual + * address spaces * @DAMON_OPS_PADDR: Monitoring operations for the physical address space */ enum damon_ops_id { DAMON_OPS_VADDR, + DAMON_OPS_FVADDR, DAMON_OPS_PADDR, NR_DAMON_OPS, }; -- cgit v1.2.3 From 534aa1dc975ac883ad89110534585a96630802a0 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Mon, 9 May 2022 18:20:53 -0700 Subject: printk: stop including cache.h from printk.h An inclusion of cache.h in printk.h was added in 2014 in commit c28aa1f0a847 ("printk/cache: mark printk_once test variable __read_mostly") in order to bring in the definition of __read_mostly. The usage of __read_mostly was later removed in commit 3ec25826ae33 ("printk: Tie printk_once / printk_deferred_once into .data.once for reset") which made the inclusion of cache.h unnecessary, so remove it. We have a small amount of code that depended on the inclusion of cache.h from printk.h; fix that code to include the appropriate header. This fixes a circular inclusion on arm64 (linux/printk.h -> linux/cache.h -> asm/cache.h -> linux/kasan-enabled.h -> linux/static_key.h -> linux/jump_label.h -> linux/bug.h -> asm/bug.h -> linux/printk.h) that would otherwise be introduced by the next patch. Build tested using {allyesconfig,defconfig} x {arm64,x86_64}. Link: https://linux-review.googlesource.com/id/I8fd51f72c9ef1f2d6afd3b2cbc875aa4792c1fba Link: https://lkml.kernel.org/r/20220427195820.1716975-1-pcc@google.com Signed-off-by: Peter Collingbourne Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric W. Biederman Cc: Herbert Xu Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Joonsoo Kim Cc: Kees Cook Cc: Pekka Enberg Cc: Roman Gushchin Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/printk.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 1522df223c0f..8e8d74edf121 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -6,7 +6,6 @@ #include #include #include -#include #include #include -- cgit v1.2.3 From d949a8155d139aa890795b802004a196b7f00598 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Mon, 9 May 2022 18:20:53 -0700 Subject: mm: make minimum slab alignment a runtime property When CONFIG_KASAN_HW_TAGS is enabled we currently increase the minimum slab alignment to 16. This happens even if MTE is not supported in hardware or disabled via kasan=off, which creates an unnecessary memory overhead in those cases. Eliminate this overhead by making the minimum slab alignment a runtime property and only aligning to 16 if KASAN is enabled at runtime. On a DragonBoard 845c (non-MTE hardware) with a kernel built with CONFIG_KASAN_HW_TAGS, waiting for quiescence after a full Android boot I see the following Slab measurements in /proc/meminfo (median of 3 reboots): Before: 169020 kB After: 167304 kB [akpm@linux-foundation.org: make slab alignment type `unsigned int' to avoid casting] Link: https://linux-review.googlesource.com/id/I752e725179b43b144153f4b6f584ceb646473ead Link: https://lkml.kernel.org/r/20220427195820.1716975-2-pcc@google.com Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Acked-by: David Rientjes Reviewed-by: Catalin Marinas Acked-by: Vlastimil Babka Cc: Pekka Enberg Cc: Roman Gushchin Cc: Joonsoo Kim Cc: Herbert Xu Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Eric W. Biederman Cc: Kees Cook Signed-off-by: Andrew Morton --- include/linux/slab.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 373b3ef99f4e..3d2f2a3ca17e 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -209,6 +209,18 @@ void kmem_dump_obj(void *object); #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif +/* + * Arches can define this function if they want to decide the minimum slab + * alignment at runtime. The value returned by the function must be a power + * of two and >= ARCH_SLAB_MINALIGN. + */ +#ifndef arch_slab_minalign +static inline unsigned int arch_slab_minalign(void) +{ + return ARCH_SLAB_MINALIGN; +} +#endif + /* * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN -- cgit v1.2.3 From b304c6f0d39d927a87e72a8ac6c89b96ac25f355 Mon Sep 17 00:00:00 2001 From: Hongchen Zhang Date: Mon, 9 May 2022 18:20:53 -0700 Subject: mm/swapops: make is_pmd_migration_entry more strict A pmd migration entry should first be a swap pmd,so use is_swap_pmd(pmd) instead of !pmd_present(pmd). On the other hand, some architecture (MIPS for example) may misjudge a pmd_none entry as a pmd migration entry. Link: https://lkml.kernel.org/r/1651131333-6386-1-git-send-email-zhanghongchen@loongson.cn Signed-off-by: Hongchen Zhang Acked-by: Peter Xu Cc: Alistair Popple Cc: Ralph Campbell Cc: Naoya Horiguchi Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/swapops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index d1b728904d4e..82265b055a0d 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -331,7 +331,7 @@ static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) static inline int is_pmd_migration_entry(pmd_t pmd) { - return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); + return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, -- cgit v1.2.3 From 6e74d2bf5a265113ca54a8323783d2f3fdde96b7 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 9 May 2022 18:20:54 -0700 Subject: mm/damon/core: add a new callback for watermarks checks Patch series "mm/damon: Support online tuning". Effects of DAMON and DAMON-based Operation Schemes highly depends on the configurations. Wrong configurations could even result in unexpected efficiency degradations. For finding a best configuration, repeating incremental configuration changes and results measurements, in other words, online tuning, could be helpful. Nevertheless, DAMON kernel API supports only restrictive online tuning. Worse yet, the sysfs-based DAMON user interface doesn't support online tuning at all. DAMON_RECLAIM also doesn't support online tuning. This patchset makes the DAMON kernel API, DAMON sysfs interface, and DAMON_RECLAIM supports online tuning. Sequence of patches ------------------- First two patches enhance DAMON online tuning for kernel API users. Specifically, patch 1 let kernel API users to be able to do DAMON online tuning without a restriction, and patch 2 makes error handling easier. Following seven patches (patches 3-9) refactor code for better readability and easier reuse of code fragments that will be useful for online tuning support. Patch 10 introduces DAMON callback based user request handling structure for DAMON sysfs interface, and patch 11 enables DAMON online tuning via DAMON sysfs interface. Documentation patch (patch 12) for usage of it follows. Patch 13 enables online tuning of DAMON_RECLAIM and finally patch 14 documents the DAMON_RECLAIM online tuning usage. This patch (of 14): For updating input parameters for running DAMON contexts, DAMON kernel API users can use the contexts' callbacks, as it is the safe place for context internal data accesses. When the context has DAMON-based operation schemes and all schemes are deactivated due to their watermarks, however, DAMON does nothing but only watermarks checks. As a result, no callbacks will be called back, and therefore the kernel API users cannot update the input parameters including monitoring attributes, DAMON-based operation schemes, and watermarks. To let users easily update such DAMON input parameters in such a case, this commit adds a new callback, 'after_wmarks_check()'. It will be called after each watermarks check. Users can do the online input parameters update in the callback even under the schemes deactivated case. Link: https://lkml.kernel.org/r/20220429160606.127307-2-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index 09a5d0d02c00..6cb5ab5d8e9d 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -343,6 +343,7 @@ struct damon_operations { * struct damon_callback - Monitoring events notification callbacks. * * @before_start: Called before starting the monitoring. + * @after_wmarks_check: Called after each schemes' watermarks check. * @after_sampling: Called after each sampling. * @after_aggregation: Called after each aggregation. * @before_terminate: Called before terminating the monitoring. @@ -353,6 +354,11 @@ struct damon_operations { * respectively. Therefore, those are good places for installing and cleaning * @private. * + * The monitoring thread calls @after_wmarks_check after each DAMON-based + * operation schemes' watermarks check. If users need to make changes to the + * attributes of the monitoring context while it's deactivated due to the + * watermarks, this is the good place to do. + * * The monitoring thread calls @after_sampling and @after_aggregation for each * of the sampling intervals and aggregation intervals, respectively. * Therefore, users can safely access the monitoring results without additional @@ -365,6 +371,7 @@ struct damon_callback { void *private; int (*before_start)(struct damon_ctx *context); + int (*after_wmarks_check)(struct damon_ctx *context); int (*after_sampling)(struct damon_ctx *context); int (*after_aggregation)(struct damon_ctx *context); void (*before_terminate)(struct damon_ctx *context); -- cgit v1.2.3 From d0723bc04185b15ed96ade0a0bf9277ef00008db Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 9 May 2022 18:20:55 -0700 Subject: mm/damon/vaddr: move 'damon_set_regions()' to core This commit moves 'damon_set_regions()' from vaddr to core, as it is aimed to be used by not only 'vaddr' but also other parts of DAMON. Link: https://lkml.kernel.org/r/20220429160606.127307-5-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index 6cb5ab5d8e9d..d1e6ee28a2ff 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -494,6 +494,8 @@ static inline void damon_insert_region(struct damon_region *r, void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); +int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, + unsigned int nr_ranges); struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, -- cgit v1.2.3 From 679d103319101800567c8bb7e341b5eee39f6685 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:52 -0700 Subject: mm: introduce PTE_MARKER swap entry Patch series "userfaultfd-wp: Support shmem and hugetlbfs", v8. Overview ======== Userfaultfd-wp anonymous support was merged two years ago. There're quite a few applications that started to leverage this capability either to take snapshots for user-app memory, or use it for full user controled swapping. This series tries to complete the feature for uffd-wp so as to cover all the RAM-based memory types. So far uffd-wp is the only missing piece of the rest features (uffd-missing & uffd-minor mode). One major reason to do so is that anonymous pages are sometimes not satisfying the need of applications, and there're growing users of either shmem and hugetlbfs for either sharing purpose (e.g., sharing guest mem between hypervisor process and device emulation process, shmem local live migration for upgrades), or for performance on tlb hits. All these mean that if a uffd-wp app wants to switch to any of the memory types, it'll stop working. I think it's worthwhile to have the kernel to cover all these aspects. This series chose to protect pages in pte level not page level. One major reason is safety. I have no idea how we could make it safe if any of the uffd-privileged app can wr-protect a page that any other application can use. It means this app can block any process potentially for any time it wants. The other reason is that it aligns very well with not only the anonymous uffd-wp solution, but also uffd as a whole. For example, userfaultfd is implemented fundamentally based on VMAs. We set flags to VMAs showing the status of uffd tracking. For another per-page based protection solution, it'll be crossing the fundation line on VMA-based, and it could simply be too far away already from what's called userfaultfd. PTE markers =========== The patchset is based on the idea called PTE markers. It was discussed in one of the mm alignment sessions, proposed starting from v6, and this is the 2nd version of it using PTE marker idea. PTE marker is a new type of swap entry that is ony applicable to file backed memories like shmem and hugetlbfs. It's used to persist some pte-level information even if the original present ptes in pgtable are zapped. Logically pte markers can store more than uffd-wp information, but so far only one bit is used for uffd-wp purpose. When the pte marker is installed with uffd-wp bit set, it means this pte is wr-protected by uffd. It solves the problem on e.g. file-backed memory mapped ptes got zapped due to any reason (e.g. thp split, or swapped out), we can still keep the wr-protect information in the ptes. Then when the page fault triggers again, we'll know this pte is wr-protected so we can treat the pte the same as a normal uffd wr-protected pte. The extra information is encoded into the swap entry, or swp_offset to be explicit, with the swp_type being PTE_MARKER. So far uffd-wp only uses one bit out of the swap entry, the rest bits of swp_offset are still reserved for other purposes. There're two configs to enable/disable PTE markers: CONFIG_PTE_MARKER CONFIG_PTE_MARKER_UFFD_WP We can set !PTE_MARKER to completely disable all the PTE markers, along with uffd-wp support. I made two config so we can also enable PTE marker but disable uffd-wp file-backed for other purposes. At the end of current series, I'll enable CONFIG_PTE_MARKER by default, but that patch is standalone and if anyone worries about having it by default, we can also consider turn it off by dropping that oneliner patch. So far I don't see a huge risk of doing so, so I kept that patch. In most cases, PTE markers should be treated as none ptes. It is because that unlike most of the other swap entry types, there's no PFN or block offset information encoded into PTE markers but some extra well-defined bits showing the status of the pte. These bits should only be used as extra data when servicing an upcoming page fault, and then we behave as if it's a none pte. I did spend a lot of time observing all the pte_none() users this time. It is indeed a challenge because there're a lot, and I hope I didn't miss a single of them when we should take care of pte markers. Luckily, I don't think it'll need to be considered in many cases, for example: boot code, arch code (especially non-x86), kernel-only page handlings (e.g. CPA), or device driver codes when we're tackling with pure PFN mappings. I introduced pte_none_mostly() in this series when we need to handle pte markers the same as none pte, the "mostly" is the other way to write "either none pte or a pte marker". I didn't replace pte_none() to cover pte markers for below reasons: - Very rare case of pte_none() callers will handle pte markers. E.g., all the kernel pages do not require knowledge of pte markers. So we don't pollute the major use cases. - Unconditionally change pte_none() semantics could confuse people, because pte_none() existed for so long a time. - Unconditionally change pte_none() semantics could make pte_none() slower even if in many cases pte markers do not exist. - There're cases where we'd like to handle pte markers differntly from pte_none(), so a full replace is also impossible. E.g. khugepaged should still treat pte markers as normal swap ptes rather than none ptes, because pte markers will always need a fault-in to merge the marker with a valid pte. Or the smap code will need to parse PTE markers not none ptes. Patch Layout ============ Introducing PTE marker and uffd-wp bit in PTE marker: mm: Introduce PTE_MARKER swap entry mm: Teach core mm about pte markers mm: Check against orig_pte for finish_fault() mm/uffd: PTE_MARKER_UFFD_WP Adding support for shmem uffd-wp: mm/shmem: Take care of UFFDIO_COPY_MODE_WP mm/shmem: Handle uffd-wp special pte in page fault handler mm/shmem: Persist uffd-wp bit across zapping for file-backed mm/shmem: Allow uffd wr-protect none pte for file-backed mem mm/shmem: Allows file-back mem to be uffd wr-protected on thps mm/shmem: Handle uffd-wp during fork() Adding support for hugetlbfs uffd-wp: mm/hugetlb: Introduce huge pte version of uffd-wp helpers mm/hugetlb: Hook page faults for uffd write protection mm/hugetlb: Take care of UFFDIO_COPY_MODE_WP mm/hugetlb: Handle UFFDIO_WRITEPROTECT mm/hugetlb: Handle pte markers in page faults mm/hugetlb: Allow uffd wr-protect none ptes mm/hugetlb: Only drop uffd-wp special pte if required mm/hugetlb: Handle uffd-wp during fork() Misc handling on the rest mm for uffd-wp file-backed: mm/khugepaged: Don't recycle vma pgtable if uffd-wp registered mm/pagemap: Recognize uffd-wp bit for shmem/hugetlbfs Enabling of uffd-wp on file-backed memory: mm/uffd: Enable write protection for shmem & hugetlbfs mm: Enable PTE markers by default selftests/uffd: Enable uffd-wp for shmem/hugetlbfs Tests ===== - Compile test on x86_64 and aarch64 on different configs - Kernel selftests - uffd-test [0] - Umapsort [1,2] test for shmem/hugetlb, with swap on/off [0] https://github.com/xzpeter/clibs/tree/master/uffd-test [1] https://github.com/xzpeter/umap-apps/tree/peter [2] https://github.com/xzpeter/umap/tree/peter-shmem-hugetlbfs This patch (of 23): Introduces a new swap entry type called PTE_MARKER. It can be installed for any pte that maps a file-backed memory when the pte is temporarily zapped, so as to maintain per-pte information. The information that kept in the pte is called a "marker". Here we define the marker as "unsigned long" just to match pgoff_t, however it will only work if it still fits in swp_offset(), which is e.g. currently 58 bits on x86_64. A new config CONFIG_PTE_MARKER is introduced too; it's by default off. A bunch of helpers are defined altogether to service the rest of the pte marker code. [peterx@redhat.com: fixup] Link: https://lkml.kernel.org/r/Yk2rdB7SXZf+2BDF@xz-m1.local Link: https://lkml.kernel.org/r/20220405014646.13522-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220405014646.13522-2-peterx@redhat.com Signed-off-by: Peter Xu Cc: Mike Kravetz Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Alistair Popple Cc: Nadav Amit Cc: Axel Rasmussen Cc: Andrea Arcangeli Cc: "Kirill A . Shutemov" Cc: Hugh Dickins Cc: Jerome Glisse Cc: Mike Rapoport Signed-off-by: Andrew Morton --- include/asm-generic/hugetlb.h | 9 +++++ include/linux/swap.h | 15 ++++++++- include/linux/swapops.h | 78 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 101 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 8e1e6244a89d..f39cad20ffc6 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -2,6 +2,9 @@ #ifndef _ASM_GENERIC_HUGETLB_H #define _ASM_GENERIC_HUGETLB_H +#include +#include + static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) { return mk_pte(page, pgprot); @@ -80,6 +83,12 @@ static inline int huge_pte_none(pte_t pte) } #endif +/* Please refer to comments above pte_none_mostly() for the usage */ +static inline int huge_pte_none_mostly(pte_t pte) +{ + return huge_pte_none(pte) || is_pte_marker(pte); +} + #ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT static inline pte_t huge_pte_wrprotect(pte_t pte) { diff --git a/include/linux/swap.h b/include/linux/swap.h index 7daae5a4b3e1..5553189d0215 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -55,6 +55,19 @@ static inline int current_is_kswapd(void) * actions on faults. */ +/* + * PTE markers are used to persist information onto PTEs that are mapped with + * file-backed memories. As its name "PTE" hints, it should only be applied to + * the leaves of pgtables. + */ +#ifdef CONFIG_PTE_MARKER +#define SWP_PTE_MARKER_NUM 1 +#define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ + SWP_MIGRATION_NUM + SWP_DEVICE_NUM) +#else +#define SWP_PTE_MARKER_NUM 0 +#endif + /* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/vm/hmm.rst. Short description is we need struct pages for @@ -107,7 +120,7 @@ static inline int current_is_kswapd(void) #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) + SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - SWP_PTE_MARKER_NUM) /* * Magic header for a swap area. The first part of the union is diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 82265b055a0d..bb70da461b7d 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -274,6 +274,84 @@ static inline int is_readable_migration_entry(swp_entry_t entry) #endif +typedef unsigned long pte_marker; + +#define PTE_MARKER_MASK (0) + +#ifdef CONFIG_PTE_MARKER + +static inline swp_entry_t make_pte_marker_entry(pte_marker marker) +{ + return swp_entry(SWP_PTE_MARKER, marker); +} + +static inline bool is_pte_marker_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_PTE_MARKER; +} + +static inline pte_marker pte_marker_get(swp_entry_t entry) +{ + return swp_offset(entry) & PTE_MARKER_MASK; +} + +static inline bool is_pte_marker(pte_t pte) +{ + return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte)); +} + +#else /* CONFIG_PTE_MARKER */ + +static inline swp_entry_t make_pte_marker_entry(pte_marker marker) +{ + /* This should never be called if !CONFIG_PTE_MARKER */ + WARN_ON_ONCE(1); + return swp_entry(0, 0); +} + +static inline bool is_pte_marker_entry(swp_entry_t entry) +{ + return false; +} + +static inline pte_marker pte_marker_get(swp_entry_t entry) +{ + return 0; +} + +static inline bool is_pte_marker(pte_t pte) +{ + return false; +} + +#endif /* CONFIG_PTE_MARKER */ + +static inline pte_t make_pte_marker(pte_marker marker) +{ + return swp_entry_to_pte(make_pte_marker_entry(marker)); +} + +/* + * This is a special version to check pte_none() just to cover the case when + * the pte is a pte marker. It existed because in many cases the pte marker + * should be seen as a none pte; it's just that we have stored some information + * onto the none pte so it becomes not-none any more. + * + * It should be used when the pte is file-backed, ram-based and backing + * userspace pages, like shmem. It is not needed upon pgtables that do not + * support pte markers at all. For example, it's not needed on anonymous + * memory, kernel-only memory (including when the system is during-boot), + * non-ram based generic file-system. It's fine to be used even there, but the + * extra pte marker check will be pure overhead. + * + * For systems configured with !CONFIG_PTE_MARKER this will be automatically + * optimized to pte_none(). + */ +static inline int pte_none_mostly(pte_t pte) +{ + return pte_none(pte) || is_pte_marker(pte); +} + static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { struct page *p = pfn_to_page(swp_offset(entry)); -- cgit v1.2.3 From f46f2adecdcc1ba0799383e67fe98f65f41fea5c Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:52 -0700 Subject: mm: check against orig_pte for finish_fault() This patch allows do_fault() to trigger on !pte_none() cases too. This prepares for the pte markers to be handled by do_fault() just like none pte. To achieve this, instead of unconditionally check against pte_none() in finish_fault(), we may hit the case that the orig_pte was some pte marker so what we want to do is to replace the pte marker with some valid pte entry. Then if orig_pte was set we'd want to check the current *pte (under pgtable lock) against orig_pte rather than none pte. Right now there's no solid way to safely reference orig_pte because when pmd is not allocated handle_pte_fault() will not initialize orig_pte, so it's not safe to reference it. There's another solution proposed before this patch to do pte_clear() for vmf->orig_pte for pmd==NULL case, however it turns out it'll break arm32 because arm32 could have assumption that pte_t* pointer will always reside on a real ram32 pgtable, not any kernel stack variable. To solve this, we add a new flag FAULT_FLAG_ORIG_PTE_VALID, and it'll be set along with orig_pte when there is valid orig_pte, or it'll be cleared when orig_pte was not initialized. It'll be updated every time we call handle_pte_fault(), so e.g. if a page fault retry happened it'll be properly updated along with orig_pte. [1] https://lore.kernel.org/lkml/710c48c9-406d-e4c5-a394-10501b951316@samsung.com/ [akpm@linux-foundation.org: coding-style cleanups] [peterx@redhat.com: fix crash reported by Marek] Link: https://lkml.kernel.org/r/Ylb9rXJyPm8/ao8f@xz-m1.local Link: https://lkml.kernel.org/r/20220405014836.14077-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Alistair Popple Tested-by: Marek Szyprowski Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7216d77a5884..dd382270ae40 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -822,6 +822,8 @@ typedef struct { * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to unshare (and mark * exclusive) a possibly shared anonymous page that is * mapped R/O. + * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. + * We should only access orig_pte if this flag set. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -858,6 +860,7 @@ enum fault_flag { FAULT_FLAG_INSTRUCTION = 1 << 8, FAULT_FLAG_INTERRUPTIBLE = 1 << 9, FAULT_FLAG_UNSHARE = 1 << 10, + FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, }; #endif /* _LINUX_MM_TYPES_H */ -- cgit v1.2.3 From 1db9dbc2ef05205bf1022f9b14aa29b1dd8efd7e Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:52 -0700 Subject: mm/uffd: PTE_MARKER_UFFD_WP This patch introduces the 1st user of pte marker: the uffd-wp marker. When the pte marker is installed with the uffd-wp bit set, it means this pte was wr-protected by uffd. We will use this special pte to arm the ptes that got either unmapped or swapped out for a file-backed region that was previously wr-protected. This special pte could trigger a page fault just like swap entries. This idea is greatly inspired by Hugh and Andrea in the discussion, which is referenced in the links below. Some helpers are introduced to detect whether a swap pte is uffd wr-protected. After the pte marker introduced, one swap pte can be wr-protected in two forms: either it is a normal swap pte and it has _PAGE_SWP_UFFD_WP set, or it's a pte marker that has PTE_MARKER_UFFD_WP set. [peterx@redhat.com: fixup] Link: https://lkml.kernel.org/r/YkzKiM8tI4+qOfXF@xz-m1.local Link: https://lore.kernel.org/lkml/20201126222359.8120-1-peterx@redhat.com/ Link: https://lore.kernel.org/lkml/20201130230603.46187-1-peterx@redhat.com/ Link: https://lkml.kernel.org/r/20220405014838.14131-1-peterx@redhat.com Signed-off-by: Peter Xu Suggested-by: Andrea Arcangeli Suggested-by: Hugh Dickins Cc: Alistair Popple Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/swapops.h | 3 ++- include/linux/userfaultfd_k.h | 47 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index bb70da461b7d..09945342bf76 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -276,7 +276,8 @@ static inline int is_readable_migration_entry(swp_entry_t entry) typedef unsigned long pte_marker; -#define PTE_MARKER_MASK (0) +#define PTE_MARKER_UFFD_WP BIT(0) +#define PTE_MARKER_MASK (PTE_MARKER_UFFD_WP) #ifdef CONFIG_PTE_MARKER diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 33cea484d1ad..3354d9ddc35f 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -15,6 +15,8 @@ #include #include +#include +#include #include /* The set of all possible UFFD-related VM flags. */ @@ -236,4 +238,49 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, #endif /* CONFIG_USERFAULTFD */ +static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + return is_pte_marker_entry(entry) && + (pte_marker_get(entry) & PTE_MARKER_UFFD_WP); +#else + return false; +#endif +} + +static inline bool pte_marker_uffd_wp(pte_t pte) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + swp_entry_t entry; + + if (!is_swap_pte(pte)) + return false; + + entry = pte_to_swp_entry(pte); + + return pte_marker_entry_uffd_wp(entry); +#else + return false; +#endif +} + +/* + * Returns true if this is a swap pte and was uffd-wp wr-protected in either + * forms (pte marker or a normal swap pte), false otherwise. + */ +static inline bool pte_swp_uffd_wp_any(pte_t pte) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + if (!is_swap_pte(pte)) + return false; + + if (pte_swp_uffd_wp(pte)) + return true; + + if (pte_marker_uffd_wp(pte)) + return true; +#endif + return false; +} + #endif /* _LINUX_USERFAULTFD_K_H */ -- cgit v1.2.3 From 8ee79edff6d3b43b2d0c1e41f92b32e128988b22 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:52 -0700 Subject: mm/shmem: take care of UFFDIO_COPY_MODE_WP Pass wp_copy into shmem_mfill_atomic_pte() through the stack, then apply the UFFD_WP bit properly when the UFFDIO_COPY on shmem is with UFFDIO_COPY_MODE_WP. wp_copy lands mfill_atomic_install_pte() finally. Note: we must do pte_wrprotect() if !writable in mfill_atomic_install_pte(), as mk_pte() could return a writable pte (e.g., when VM_SHARED on a shmem file). Link: https://lkml.kernel.org/r/20220405014841.14185-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 3e915cc550bc..a68f982f22d1 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -145,11 +145,11 @@ extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - bool zeropage, + bool zeropage, bool wp_copy, struct page **pagep); #else /* !CONFIG_SHMEM */ #define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ - src_addr, zeropage, pagep) ({ BUG(); 0; }) + src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ -- cgit v1.2.3 From 9c28a205c06123b9f0a0c4d819ece9f5f552d004 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:53 -0700 Subject: mm/shmem: handle uffd-wp special pte in page fault handler File-backed memories are prone to unmap/swap so the ptes are always unstable, because they can be easily faulted back later using the page cache. This could lead to uffd-wp getting lost when unmapping or swapping out such memory. One example is shmem. PTE markers are needed to store those information. This patch prepares it by handling uffd-wp pte markers first it is applied elsewhere, so that the page fault handler can recognize uffd-wp pte markers. The handling of uffd-wp pte markers is similar to missing fault, it's just that we'll handle this "missing fault" when we see the pte markers, meanwhile we need to make sure the marker information is kept during processing the fault. This is a slow path of uffd-wp handling, because zapping of wr-protected shmem ptes should be rare. So far it should only trigger in two conditions: (1) When trying to punch holes in shmem_fallocate(), there is an optimization to zap the pgtables before evicting the page. (2) When swapping out shmem pages. Because of this, the page fault handling is simplifed too by not sending the wr-protect message in the 1st page fault, instead the page will be installed read-only, so the uffd-wp message will be generated in the next fault, which will trigger the do_wp_page() path of general uffd-wp handling. Disable fault-around for all uffd-wp registered ranges for extra safety just like uffd-minor fault, and clean the code up. Link: https://lkml.kernel.org/r/20220405014844.14239-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 3354d9ddc35f..e7afcdfd4b46 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -96,6 +96,18 @@ static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } +/* + * Don't do fault around for either WP or MINOR registered uffd range. For + * MINOR registered range, fault around will be a total disaster and ptes can + * be installed without notifications; for WP it should mostly be fine as long + * as the fault around checks for pte_none() before the installation, however + * to be super safe we just forbid it. + */ +static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); +} + static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MISSING; @@ -236,6 +248,11 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, { } +static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) -- cgit v1.2.3 From 999dad824c39ed14dee7c4412aae531ba9e74a90 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:53 -0700 Subject: mm/shmem: persist uffd-wp bit across zapping for file-backed File-backed memory is prone to being unmapped at any time. It means all information in the pte will be dropped, including the uffd-wp flag. To persist the uffd-wp flag, we'll use the pte markers. This patch teaches the zap code to understand uffd-wp and know when to keep or drop the uffd-wp bit. Add a new flag ZAP_FLAG_DROP_MARKER and set it in zap_details when we don't want to persist such an information, for example, when destroying the whole vma, or punching a hole in a shmem file. For the rest cases we should never drop the uffd-wp bit, or the wr-protect information will get lost. The new ZAP_FLAG_DROP_MARKER needs to be put into mm.h rather than memory.c because it'll be further referenced in hugetlb files later. Link: https://lkml.kernel.org/r/20220405014847.14295-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/mm.h | 10 ++++++++++ include/linux/mm_inline.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index d63ba0e0e068..61786259e52a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3428,4 +3428,14 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, } #endif +typedef unsigned int __bitwise zap_flags_t; + +/* + * Whether to drop the pte markers, for example, the uffd-wp information for + * file-backed memory. This should only be specified when we will completely + * drop the page in the mm, either by truncation or unmapping of the vma. By + * default, the flag is not set. + */ +#define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index ac32125745ab..7b25b53c474a 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -6,6 +6,8 @@ #include #include #include +#include +#include /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? @@ -316,5 +318,46 @@ static inline bool mm_tlb_flush_nested(struct mm_struct *mm) return atomic_read(&mm->tlb_flush_pending) > 1; } +/* + * If this pte is wr-protected by uffd-wp in any form, arm the special pte to + * replace a none pte. NOTE! This should only be called when *pte is already + * cleared so we will never accidentally replace something valuable. Meanwhile + * none pte also means we are not demoting the pte so tlb flushed is not needed. + * E.g., when pte cleared the caller should have taken care of the tlb flush. + * + * Must be called with pgtable lock held so that no thread will see the none + * pte, and if they see it, they'll fault and serialize at the pgtable lock. + * + * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled. + */ +static inline void +pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, + pte_t *pte, pte_t pteval) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + bool arm_uffd_pte = false; + + /* The current status of the pte should be "cleared" before calling */ + WARN_ON_ONCE(!pte_none(*pte)); + + if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) + return; + + /* A uffd-wp wr-protected normal pte */ + if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) + arm_uffd_pte = true; + + /* + * A uffd-wp wr-protected swap pte. Note: this should even cover an + * existing pte marker with uffd-wp bit set. + */ + if (unlikely(pte_swp_uffd_wp_any(pteval))) + arm_uffd_pte = true; + + if (unlikely(arm_uffd_pte)) + set_pte_at(vma->vm_mm, addr, pte, + make_pte_marker(PTE_MARKER_UFFD_WP)); +#endif +} #endif -- cgit v1.2.3 From 229f3fa778c50edf12b34bd91b2025645a11bb94 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:54 -0700 Subject: mm/hugetlb: introduce huge pte version of uffd-wp helpers They will be used in the follow up patches to either check/set/clear uffd-wp bit of a huge pte. So far it reuses all the small pte helpers. Archs can overwrite these versions when necessary (with __HAVE_ARCH_HUGE_PTE_UFFD_WP* macros) in the future. Link: https://lkml.kernel.org/r/20220405014858.14531-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/asm-generic/hugetlb.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index f39cad20ffc6..896f341f614d 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -35,6 +35,21 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) return pte_modify(pte, newprot); } +static inline pte_t huge_pte_mkuffd_wp(pte_t pte) +{ + return pte_mkuffd_wp(pte); +} + +static inline pte_t huge_pte_clear_uffd_wp(pte_t pte) +{ + return pte_clear_uffd_wp(pte); +} + +static inline int huge_pte_uffd_wp(pte_t pte) +{ + return pte_uffd_wp(pte); +} + #ifndef __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) -- cgit v1.2.3 From 6041c69179034278ac6d57f90a55b09e588f4b90 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:54 -0700 Subject: mm/hugetlb: take care of UFFDIO_COPY_MODE_WP Pass the wp_copy variable into hugetlb_mcopy_atomic_pte() thoughout the stack. Apply the UFFD_WP bit if UFFDIO_COPY_MODE_WP is with UFFDIO_COPY. Hugetlb pages are only managed by hugetlbfs, so we're safe even without setting dirty bit in the huge pte if the page is installed as read-only. However we'd better still keep the dirty bit set for a read-only UFFDIO_COPY pte (when UFFDIO_COPY_MODE_WP bit is set), not only to match what we do with shmem, but also because the page does contain dirty data that the kernel just copied from the userspace. Link: https://lkml.kernel.org/r/20220405014904.14643-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ac2ece9e9c79..159b253e523d 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -160,7 +160,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, enum mcopy_atomic_mode mode, - struct page **pagep); + struct page **pagep, + bool wp_copy); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, @@ -356,7 +357,8 @@ static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, unsigned long dst_addr, unsigned long src_addr, enum mcopy_atomic_mode mode, - struct page **pagep) + struct page **pagep, + bool wp_copy) { BUG(); return 0; -- cgit v1.2.3 From 5a90d5a103c2badfcf12d48e2fec350969e3f486 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:54 -0700 Subject: mm/hugetlb: handle UFFDIO_WRITEPROTECT This starts from passing cp_flags into hugetlb_change_protection() so hugetlb will be able to handle MM_CP_UFFD_WP[_RESOLVE] requests. huge_pte_clear_uffd_wp() is introduced to handle the case where the UFFDIO_WRITEPROTECT is requested upon migrating huge page entries. Link: https://lkml.kernel.org/r/20220405014906.14708-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 159b253e523d..f1143f1fb444 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -211,7 +211,8 @@ struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, int pmd_huge(pmd_t pmd); int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot); + unsigned long address, unsigned long end, pgprot_t newprot, + unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); @@ -397,7 +398,8 @@ static inline void move_hugetlb_state(struct page *oldpage, static inline unsigned long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, - unsigned long end, pgprot_t newprot) + unsigned long end, pgprot_t newprot, + unsigned long cp_flags) { return 0; } -- cgit v1.2.3 From 05e90bd05eea33fc77d6b11e121e2da01fee379f Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:55 -0700 Subject: mm/hugetlb: only drop uffd-wp special pte if required As with shmem uffd-wp special ptes, only drop the uffd-wp special swap pte if unmapping an entire vma or synchronized such that faults can not race with the unmap operation. This requires passing zap_flags all the way to the lowest level hugetlb unmap routine: __unmap_hugepage_range. In general, unmap calls originated in hugetlbfs code will pass the ZAP_FLAG_DROP_MARKER flag as synchronization is in place to prevent faults. The exception is hole punch which will first unmap without any synchronization. Later when hole punch actually removes the page from the file, it will check to see if there was a subsequent fault and if so take the hugetlb fault mutex while unmapping again. This second unmap will pass in ZAP_FLAG_DROP_MARKER. The justification of "whether to apply ZAP_FLAG_DROP_MARKER flag when unmap a hugetlb range" is (IMHO): we should never reach a state when a page fault could errornously fault in a page-cache page that was wr-protected to be writable, even in an extremely short period. That could happen if e.g. we pass ZAP_FLAG_DROP_MARKER when hugetlbfs_punch_hole() calls hugetlb_vmdelete_list(), because if a page faults after that call and before remove_inode_hugepages() is executed, the page cache can be mapped writable again in the small racy window, that can cause unexpected data overwritten. [peterx@redhat.com: fix sparse warning] Link: https://lkml.kernel.org/r/Ylcdw8I1L5iAoWhb@xz-m1.local [akpm@linux-foundation.org: move zap_flags_t from mm.h to mm_types.h to fix build issues] Link: https://lkml.kernel.org/r/20220405014915.14873-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 8 +++++--- include/linux/mm.h | 2 -- include/linux/mm_types.h | 2 ++ 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index f1143f1fb444..19cec415f546 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -143,11 +143,12 @@ long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, unsigned long *, unsigned long *, long, unsigned int, int *); void unmap_hugepage_range(struct vm_area_struct *, - unsigned long, unsigned long, struct page *); + unsigned long, unsigned long, struct page *, + zap_flags_t); void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, - struct page *ref_page); + struct page *ref_page, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo(void); @@ -406,7 +407,8 @@ static inline unsigned long hugetlb_change_protection( static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) + unsigned long end, struct page *ref_page, + zap_flags_t zap_flags) { BUG(); } diff --git a/include/linux/mm.h b/include/linux/mm.h index 61786259e52a..de32c0383387 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3428,8 +3428,6 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, } #endif -typedef unsigned int __bitwise zap_flags_t; - /* * Whether to drop the pte markers, for example, the uffd-wp information for * file-backed memory. This should only be specified when we will completely diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index dd382270ae40..b34ff2cdbc4f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -863,4 +863,6 @@ enum fault_flag { FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, }; +typedef unsigned int __bitwise zap_flags_t; + #endif /* _LINUX_MM_TYPES_H */ -- cgit v1.2.3 From bc70fbf269fdff410b0b6d75c3770b9f59117b90 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:55 -0700 Subject: mm/hugetlb: handle uffd-wp during fork() Firstly, we'll need to pass in dst_vma into copy_hugetlb_page_range() because for uffd-wp it's the dst vma that matters on deciding how we should treat uffd-wp protected ptes. We should recognize pte markers during fork and do the pte copy if needed. [lkp@intel.com: vma_needs_copy can be static] Link: https://lkml.kernel.org/r/Ylb0CGeFJlc4EzLk@7ec4ff11d4ae Link: https://lkml.kernel.org/r/20220405014918.14932-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 19cec415f546..04f0186b089b 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -137,7 +137,8 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len); -int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); +int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, + struct vm_area_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, unsigned long *, long, unsigned int, @@ -269,7 +270,9 @@ static inline struct page *follow_huge_addr(struct mm_struct *mm, } static inline int copy_hugetlb_page_range(struct mm_struct *dst, - struct mm_struct *src, struct vm_area_struct *vma) + struct mm_struct *src, + struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma) { BUG(); return 0; -- cgit v1.2.3 From b1f9e876862d8f7176299ec4fb2108bc1045cbc8 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:56 -0700 Subject: mm/uffd: enable write protection for shmem & hugetlbfs We've had all the necessary changes ready for both shmem and hugetlbfs. Turn on all the shmem/hugetlbfs switches for userfaultfd-wp. We can expand UFFD_API_RANGE_IOCTLS_BASIC with _UFFDIO_WRITEPROTECT too because all existing types now support write protection mode. Since vma_can_userfault() will be used elsewhere, move into userfaultfd_k.h. Link: https://lkml.kernel.org/r/20220405014926.15101-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 20 ++++++++++++++++++++ include/uapi/linux/userfaultfd.h | 10 ++++++++-- 2 files changed, 28 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index e7afcdfd4b46..732b522bacb7 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -18,6 +18,7 @@ #include #include #include +#include /* The set of all possible UFFD-related VM flags. */ #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) @@ -140,6 +141,25 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) return vma->vm_flags & __VM_UFFD_FLAGS; } +static inline bool vma_can_userfault(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + if (vm_flags & VM_UFFD_MINOR) + return is_vm_hugetlb_page(vma) || vma_is_shmem(vma); + +#ifndef CONFIG_PTE_MARKER_UFFD_WP + /* + * If user requested uffd-wp but not enabled pte markers for + * uffd-wp, then shmem & hugetlbfs are not supported but only + * anonymous. + */ + if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma)) + return false; +#endif + return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || + vma_is_shmem(vma); +} + extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index ef739054cb1c..7d32b1e797fb 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -33,7 +33,8 @@ UFFD_FEATURE_THREAD_ID | \ UFFD_FEATURE_MINOR_HUGETLBFS | \ UFFD_FEATURE_MINOR_SHMEM | \ - UFFD_FEATURE_EXACT_ADDRESS) + UFFD_FEATURE_EXACT_ADDRESS | \ + UFFD_FEATURE_WP_HUGETLBFS_SHMEM) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -47,7 +48,8 @@ #define UFFD_API_RANGE_IOCTLS_BASIC \ ((__u64)1 << _UFFDIO_WAKE | \ (__u64)1 << _UFFDIO_COPY | \ - (__u64)1 << _UFFDIO_CONTINUE) + (__u64)1 << _UFFDIO_CONTINUE | \ + (__u64)1 << _UFFDIO_WRITEPROTECT) /* * Valid ioctl command number range with this API is from 0x00 to @@ -194,6 +196,9 @@ struct uffdio_api { * UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page * faults would be provided and the offset within the page would not be * masked. + * + * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd + * write-protection mode is supported on both shmem and hugetlbfs. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -207,6 +212,7 @@ struct uffdio_api { #define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) #define UFFD_FEATURE_MINOR_SHMEM (1<<10) #define UFFD_FEATURE_EXACT_ADDRESS (1<<11) +#define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12) __u64 features; __u64 ioctls; -- cgit v1.2.3 From b48d8a8e5ce53e3114a1ffe96563e3555b51d40b Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Thu, 12 May 2022 20:22:57 -0700 Subject: mm: page_isolation: move has_unmovable_pages() to mm/page_isolation.c Patch series "Use pageblock_order for cma and alloc_contig_range alignment", v11. This patchset tries to remove the MAX_ORDER-1 alignment requirement for CMA and alloc_contig_range(). It prepares for my upcoming changes to make MAX_ORDER adjustable at boot time[1]. The MAX_ORDER - 1 alignment requirement comes from that alloc_contig_range() isolates pageblocks to remove free memory from buddy allocator but isolating only a subset of pageblocks within a page spanning across multiple pageblocks causes free page accounting issues. Isolated page might not be put into the right free list, since the code assumes the migratetype of the first pageblock as the whole free page migratetype. This is based on the discussion at [2]. To remove the requirement, this patchset: 1. isolates pages at pageblock granularity instead of max(MAX_ORDER_NR_PAEGS, pageblock_nr_pages); 2. splits free pages across the specified range or migrates in-use pages across the specified range then splits the freed page to avoid free page accounting issues (it happens when multiple pageblocks within a single page have different migratetypes); 3. only checks unmovable pages within the range instead of MAX_ORDER - 1 aligned range during isolation to avoid alloc_contig_range() failure when pageblocks within a MAX_ORDER - 1 aligned range are allocated separately. 4. returns pages not in the range as it did before. One optimization might come later: 1. make MIGRATE_ISOLATE a separate bit to be able to restore the original migratetypes when isolation fails in the middle of the range. [1] https://lore.kernel.org/linux-mm/20210805190253.2795604-1-zi.yan@sent.com/ [2] https://lore.kernel.org/linux-mm/d19fb078-cb9b-f60f-e310-fdeea1b947d2@redhat.com/ This patch (of 6): has_unmovable_pages() is only used in mm/page_isolation.c. Move it from mm/page_alloc.c and make it static. Link: https://lkml.kernel.org/r/20220425143118.2850746-2-zi.yan@sent.com Signed-off-by: Zi Yan Reviewed-by: Oscar Salvador Reviewed-by: Mike Rapoport Acked-by: David Hildenbrand Cc: Vlastimil Babka Cc: Mel Gorman Cc: Eric Ren Cc: Christophe Leroy Cc: Minchan Kim Cc: kernel test robot Signed-off-by: Andrew Morton --- include/linux/page-isolation.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 572458016331..e14eddf6741a 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -33,8 +33,6 @@ static inline bool is_migrate_isolate(int migratetype) #define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 -struct page *has_unmovable_pages(struct zone *zone, struct page *page, - int migratetype, int flags); void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable); -- cgit v1.2.3 From b2c9e2fbba32539626522b6aed30d1dde7b7e971 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Thu, 12 May 2022 20:22:58 -0700 Subject: mm: make alloc_contig_range work at pageblock granularity alloc_contig_range() worked at MAX_ORDER_NR_PAGES granularity to avoid merging pageblocks with different migratetypes. It might unnecessarily convert extra pageblocks at the beginning and at the end of the range. Change alloc_contig_range() to work at pageblock granularity. Special handling is needed for free pages and in-use pages across the boundaries of the range specified by alloc_contig_range(). Because these= Partially isolated pages causes free page accounting issues. The free pages will be split and freed into separate migratetype lists; the in-use= Pages will be migrated then the freed pages will be handled in the aforementioned way. [ziy@nvidia.com: fix deadlock/crash] Link: https://lkml.kernel.org/r/23A7297E-6C84-4138-A9FE-3598234004E6@nvidia.com Link: https://lkml.kernel.org/r/20220425143118.2850746-4-zi.yan@sent.com Signed-off-by: Zi Yan Reported-by: kernel test robot Cc: Christophe Leroy Cc: David Hildenbrand Cc: Eric Ren Cc: Mel Gorman Cc: Mike Rapoport Cc: Minchan Kim Cc: Oscar Salvador Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/page-isolation.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index e14eddf6741a..5456b7be38ae 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -42,7 +42,7 @@ int move_freepages_block(struct zone *zone, struct page *page, */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - unsigned migratetype, int flags); + int migratetype, int flags, gfp_t gfp_flags); /* * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE. @@ -50,7 +50,7 @@ start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, */ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - unsigned migratetype); + int migratetype); /* * Test all pages in [start_pfn, end_pfn) are isolated or not. -- cgit v1.2.3 From 11ac3e87ce09c27f4587a8c4fe0829d814021a82 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Thu, 12 May 2022 20:22:58 -0700 Subject: mm: cma: use pageblock_order as the single alignment Now alloc_contig_range() works at pageblock granularity. Change CMA allocation, which uses alloc_contig_range(), to use pageblock_nr_pages alignment. Link: https://lkml.kernel.org/r/20220425143118.2850746-6-zi.yan@sent.com Signed-off-by: Zi Yan Cc: Christophe Leroy Cc: David Hildenbrand Cc: Eric Ren Cc: kernel test robot Cc: Mel Gorman Cc: Mike Rapoport Cc: Minchan Kim Cc: Oscar Salvador Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/cma.h | 4 ++-- include/linux/mmzone.h | 5 +---- 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/cma.h b/include/linux/cma.h index a6f637342740..63873b93deaa 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -17,11 +17,11 @@ #define CMA_MAX_NAME 64 /* - * TODO: once the buddy -- especially pageblock merging and alloc_contig_range() + * the buddy -- especially pageblock merging and alloc_contig_range() * -- can deal with only some pageblocks of a higher-order page being * MIGRATE_CMA, we can use pageblock_nr_pages. */ -#define CMA_MIN_ALIGNMENT_PAGES MAX_ORDER_NR_PAGES +#define CMA_MIN_ALIGNMENT_PAGES pageblock_nr_pages #define CMA_MIN_ALIGNMENT_BYTES (PAGE_SIZE * CMA_MIN_ALIGNMENT_PAGES) struct cma; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 46ffab808f03..aab70355d64f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -54,10 +54,7 @@ enum migratetype { * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by - * __free_pageblock_cma() function. What is important though - * is that a range of pageblocks must be aligned to - * MAX_ORDER_NR_PAGES should biggest page be bigger than - * a single pageblock. + * __free_pageblock_cma() function. */ MIGRATE_CMA, #endif -- cgit v1.2.3 From adf88aa8ea7ff143825a2a8a7193f92e0e6fc79b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:01 -0700 Subject: mm: remove alloc_pages_vma() All callers have now been converted to use vma_alloc_folio(), so convert the body of alloc_pages_vma() to allocate folios instead. Link: https://lkml.kernel.org/r/20220504182857.4013401-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/gfp.h | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 3e3d36fc2109..2a08a3c4ba95 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -613,13 +613,8 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); -struct page *alloc_pages_vma(gfp_t gfp_mask, int order, - struct vm_area_struct *vma, unsigned long addr, - bool hugepage); struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, true) #else static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { @@ -629,16 +624,17 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, hugepage) \ - alloc_pages(gfp_mask, order) #define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ folio_alloc(gfp, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) -#define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, false) +static inline struct page *alloc_page_vma(gfp_t gfp, + struct vm_area_struct *vma, unsigned long addr) +{ + struct folio *folio = vma_alloc_folio(gfp, 0, vma, addr, false); + + return &folio->page; +} extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); -- cgit v1.2.3 From e2e3fdc7d4afdb8e7ba981eba7827993f2d390a8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:02 -0700 Subject: swap: turn get_swap_page() into folio_alloc_swap() This removes an assumption that a large folio is HPAGE_PMD_NR pages in size. Link: https://lkml.kernel.org/r/20220504182857.4013401-8-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/swap.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 5553189d0215..252c23a6667f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -470,7 +470,7 @@ static inline long get_nr_swap_pages(void) } extern void si_swapinfo(struct sysinfo *); -extern swp_entry_t get_swap_page(struct page *page); +swp_entry_t folio_alloc_swap(struct folio *folio); extern void put_swap_page(struct page *page, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); @@ -583,7 +583,7 @@ static inline int try_to_free_swap(struct page *page) return 0; } -static inline swp_entry_t get_swap_page(struct page *page) +static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; entry.val = 0; @@ -643,12 +643,13 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) #ifdef CONFIG_MEMCG_SWAP void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); -extern int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); -static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) +int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); +static inline int mem_cgroup_try_charge_swap(struct folio *folio, + swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; - return __mem_cgroup_try_charge_swap(page, entry); + return __mem_cgroup_try_charge_swap(folio, entry); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); @@ -666,7 +667,7 @@ static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } -static inline int mem_cgroup_try_charge_swap(struct page *page, +static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; -- cgit v1.2.3 From 64daa5d818ae3430f0785206b0af13ef528cb9ef Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:03 -0700 Subject: vmscan: convert lazy freeing to folios Remove a hidden call to compound_head(), and account nr_pages instead of a single page. This matches the code in lru_lazyfree_fn() that accounts nr_pages to PGLAZYFREE. Link: https://lkml.kernel.org/r/20220504182857.4013401-12-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index fe580cb96683..8ea4b541c31e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1057,6 +1057,15 @@ static inline void count_memcg_page_event(struct page *page, count_memcg_events(memcg, idx, 1); } +static inline void count_memcg_folio_events(struct folio *folio, + enum vm_event_item idx, unsigned long nr) +{ + struct mem_cgroup *memcg = folio_memcg(folio); + + if (memcg) + count_memcg_events(memcg, idx, nr); +} + static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { @@ -1494,6 +1503,11 @@ static inline void count_memcg_page_event(struct page *page, { } +static inline void count_memcg_folio_events(struct folio *folio, + enum vm_event_item idx, unsigned long nr) +{ +} + static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { -- cgit v1.2.3 From dc786690a6a1d9a680e6872821291ad7ca9f520d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:03 -0700 Subject: mm: allow can_split_folio() to be called when THP are disabled The call to can_split_folio() in vmscan is currently guarded by a test of PageTransHuge() so the BUILD_BUG() is eliminated if THP are disabled. The next patch replaces that test with folio_test_large() which may be true, even when THP are disabled. However, if THP are disabled, we cannot split, so an unconditional return of false is appropriate. Link: https://lkml.kernel.org/r/20220504182857.4013401-15-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 9a26bd10e083..fbf36bb1be22 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -348,7 +348,6 @@ static inline void prep_transhuge_page(struct page *page) {} static inline bool can_split_folio(struct folio *folio, int *pextra_pins) { - BUILD_BUG(); return false; } static inline int -- cgit v1.2.3 From 039bc1240165c99b932fb4be2f784948d1038eea Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:04 -0700 Subject: mm/swap: add folio_throttle_swaprate The only use of the page argument to cgroup_throttle_swaprate() is to get the node ID, and this will be the same for all pages in the folio, so just pass in the first page of the folio. Link: https://lkml.kernel.org/r/20220504182857.4013401-18-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/swap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 252c23a6667f..6bf1506e5080 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -640,6 +640,10 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { } #endif +static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) +{ + cgroup_throttle_swaprate(&folio->page, gfp); +} #ifdef CONFIG_MEMCG_SWAP void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); -- cgit v1.2.3 From da08e9b7932345aff0a748c55f8a25709505f2a3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:05 -0700 Subject: mm/shmem: convert shmem_swapin_page() to shmem_swapin_folio() shmem_swapin_page() only brings in order-0 pages, which are folios by definition. Link: https://lkml.kernel.org/r/20220504182857.4013401-24-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 530b1817b58c..39fa93e94b80 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -758,7 +758,7 @@ static inline void arch_swap_invalidate_area(int type) #endif #ifndef __HAVE_ARCH_SWAP_RESTORE -static inline void arch_swap_restore(swp_entry_t entry, struct page *page) +static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) { } #endif -- cgit v1.2.3 From a9595b305c0f6cbbf9505325509d95637f6a7062 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:05 -0700 Subject: mm: add folio_mapping_flags() This is the equivalent of PageMappingFlags and is needed for converting mm/migrate.c to folios. Link: https://lkml.kernel.org/r/20220504182857.4013401-25-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b70124b9c7c1..97eb88dbcbbc 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -650,6 +650,11 @@ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) +static __always_inline bool folio_mapping_flags(struct folio *folio) +{ + return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; +} + static __always_inline int PageMappingFlags(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; -- cgit v1.2.3 From 8b463be3a0241558071e6ba9bf11e4bf42ccc856 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:05 -0700 Subject: mm: add folio_test_movable() This is the folio equivalent of PageMovable() which is needed to convert mm/migrate.c to folios. Link: https://lkml.kernel.org/r/20220504182857.4013401-26-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/migrate.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 2707bfd43a0d..069a89e847f3 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -105,6 +105,11 @@ static inline void __ClearPageMovable(struct page *page) } #endif +static inline bool folio_test_movable(struct folio *folio) +{ + return PageMovable(&folio->page); +} + #ifdef CONFIG_NUMA_BALANCING extern int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node); -- cgit v1.2.3 From de8c8e52836d0082188508548d0b939f49f7f0e6 Mon Sep 17 00:00:00 2001 From: Tong Tiangen Date: Thu, 12 May 2022 20:23:06 -0700 Subject: mm: page_table_check: add hooks to public helpers Move ptep_clear() to the include/linux/pgtable.h and add page table check relate hooks to some helpers, it's prepare for support page table check feature on new architecture. Optimize the implementation of ptep_clear(), page table hooks added page table check stubs, the interface control should be at stubs, there is no rationale for doing a IS_ENABLED() check here. For architectures that do not enable CONFIG_PAGE_TABLE_CHECK, they will call a fallback page table check stubs[1] when getting their page table helpers[2] in include/linux/pgtable.h. [1] page table check stubs defined in include/linux/page_table_check.h [2] ptep_clear() ptep_get_and_clear() pmdp_huge_get_and_clear() pudp_huge_get_and_clear() Link: https://lkml.kernel.org/r/20220507110114.4128854-4-tongtiangen@huawei.com Signed-off-by: Tong Tiangen Acked-by: Pasha Tatashin Cc: Anshuman Khandual Cc: Borislav Petkov Cc: Catalin Marinas Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Kefeng Wang Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 39fa93e94b80..e0a449b477c5 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -12,6 +12,7 @@ #include #include #include +#include #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS @@ -259,14 +260,6 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif -#ifndef __HAVE_ARCH_PTEP_CLEAR -static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - pte_clear(mm, addr, ptep); -} -#endif - #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, @@ -274,10 +267,19 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = *ptep; pte_clear(mm, address, ptep); + page_table_check_pte_clear(mm, address, pte); return pte; } #endif +#ifndef __HAVE_ARCH_PTEP_CLEAR +static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + ptep_get_and_clear(mm, addr, ptep); +} +#endif + #ifndef __HAVE_ARCH_PTEP_GET static inline pte_t ptep_get(pte_t *ptep) { @@ -347,7 +349,10 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, pmd_t *pmdp) { pmd_t pmd = *pmdp; + pmd_clear(pmdp); + page_table_check_pmd_clear(mm, address, pmd); + return pmd; } #endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ @@ -359,6 +364,8 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, pud_t pud = *pudp; pud_clear(pudp); + page_table_check_pud_clear(mm, address, pud); + return pud; } #endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ -- cgit v1.2.3 From 2e7dc2b632a324c670ff11dd6c84d711043c683f Mon Sep 17 00:00:00 2001 From: Tong Tiangen Date: Thu, 12 May 2022 20:23:06 -0700 Subject: mm: remove __HAVE_ARCH_PTEP_CLEAR in pgtable.h Currently, there is no architecture definition __HAVE_ARCH_PTEP_CLEAR, Generic ptep_clear() is the only definition for all architecture, So drop the "#ifndef __HAVE_ARCH_PTEP_CLEAR". Link: https://lkml.kernel.org/r/20220507110114.4128854-5-tongtiangen@huawei.com Signed-off-by: Tong Tiangen Suggested-by: Anshuman Khandual Cc: Borislav Petkov Cc: Catalin Marinas Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Kefeng Wang Cc: Palmer Dabbelt Cc: Pasha Tatashin Cc: Paul Walmsley Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e0a449b477c5..ecb4c762d760 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -272,13 +272,11 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #endif -#ifndef __HAVE_ARCH_PTEP_CLEAR static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { ptep_get_and_clear(mm, addr, ptep); } -#endif #ifndef __HAVE_ARCH_PTEP_GET static inline pte_t ptep_get(pte_t *ptep) -- cgit v1.2.3 From c8db8c2628afc7088a43de3f7cfbcc2ef1f182f7 Mon Sep 17 00:00:00 2001 From: Li kunyu Date: Thu, 12 May 2022 20:23:07 -0700 Subject: mm: functions may simplify the use of return values p4d_clear_huge may be optimized for void return type and function usage. vunmap_p4d_range function saves a few steps here. Link: https://lkml.kernel.org/r/20220507150630.90399-1-kunyu@nfschina.com Signed-off-by: Li kunyu Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index ecb4c762d760..3cdc16cfd867 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1448,16 +1448,13 @@ static inline int pmd_protnone(pmd_t pmd) #ifndef __PAGETABLE_P4D_FOLDED int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); -int p4d_clear_huge(p4d_t *p4d); +void p4d_clear_huge(p4d_t *p4d); #else static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } -static inline int p4d_clear_huge(p4d_t *p4d) -{ - return 0; -} +static inline void p4d_clear_huge(p4d_t *p4d) { } #endif /* !__PAGETABLE_P4D_FOLDED */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); @@ -1480,10 +1477,7 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { return 0; } -static inline int p4d_clear_huge(p4d_t *p4d) -{ - return 0; -} +static inline void p4d_clear_huge(p4d_t *p4d) { } static inline int pud_clear_huge(pud_t *pud) { return 0; -- cgit v1.2.3 From f67bed134a053663852a1a3ab1b3223bfc2104a2 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 12 May 2022 20:23:07 -0700 Subject: percpu: improve percpu_alloc_percpu event trace Add call_site, bytes_alloc and gfp_flags fields to the output of the percpu_alloc_percpu ftrace event: mkdir-4393 [001] 169.334788: percpu_alloc_percpu: call_site=mem_cgroup_css_alloc+0xa6 reserved=0 is_atomic=0 size=2408 align=8 base_addr=0xffffc7117fc00000 off=402176 ptr=0x3dc867a62300 bytes_alloc=14448 gfp_flags=GFP_KERNEL_ACCOUNT This is required to track memcg-accounted percpu allocations. Link: https://lkml.kernel.org/r/a07be858-c8a3-7851-9086-e3262cbcf707@openvz.org Signed-off-by: Vasily Averin Acked-by: Roman Gushchin Cc: Shakeel Butt Cc: Steven Rostedt Cc: Ingo Molnar Cc: Vlastimil Babka Cc: Michal Hocko Cc: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Signed-off-by: Andrew Morton --- include/trace/events/percpu.h | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/trace/events/percpu.h b/include/trace/events/percpu.h index df112a64f6c9..e989cefc0def 100644 --- a/include/trace/events/percpu.h +++ b/include/trace/events/percpu.h @@ -6,15 +6,20 @@ #define _TRACE_PERCPU_H #include +#include TRACE_EVENT(percpu_alloc_percpu, - TP_PROTO(bool reserved, bool is_atomic, size_t size, - size_t align, void *base_addr, int off, void __percpu *ptr), + TP_PROTO(unsigned long call_site, + bool reserved, bool is_atomic, size_t size, + size_t align, void *base_addr, int off, + void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), - TP_ARGS(reserved, is_atomic, size, align, base_addr, off, ptr), + TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, + ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( + __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) @@ -22,9 +27,11 @@ TRACE_EVENT(percpu_alloc_percpu, __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) + __field( size_t, bytes_alloc ) + __field( gfp_t, gfp_flags ) ), - TP_fast_assign( + __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; @@ -32,12 +39,16 @@ TRACE_EVENT(percpu_alloc_percpu, __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; + __entry->bytes_alloc = bytes_alloc; + __entry->gfp_flags = gfp_flags; ), - TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p", + TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", + (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, - __entry->base_addr, __entry->off, __entry->ptr) + __entry->base_addr, __entry->off, __entry->ptr, + __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, -- cgit v1.2.3 From fe573327ffb1deba802c91dd1d4ff41dafa97a0e Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 12 May 2022 20:23:08 -0700 Subject: tracing: incorrect gfp_t conversion Fixes the following sparse warnings: include/trace/events/*: sparse: cast to restricted gfp_t include/trace/events/*: sparse: restricted gfp_t degrades to integer gfp_t type is bitwise and requires __force attributes for any casts. Link: https://lkml.kernel.org/r/331d88fe-f4f7-657c-02a2-d977f15fbff6@openvz.org Signed-off-by: Vasily Averin Cc: Steven Rostedt Cc: Ingo Molnar Signed-off-by: Andrew Morton --- include/linux/gfp.h | 2 +- include/trace/events/btrfs.h | 4 +- include/trace/events/compaction.h | 4 +- include/trace/events/kmem.h | 12 +++--- include/trace/events/mmflags.h | 78 +++++++++++++++++++-------------------- include/trace/events/vmscan.h | 16 ++++---- 6 files changed, 58 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 2a08a3c4ba95..2d2ccae933c2 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -367,7 +367,7 @@ static inline int gfp_migratetype(const gfp_t gfp_flags) return MIGRATE_UNMOVABLE; /* Group based on mobility */ - return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; + return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index f068ff30d654..ed92c80331ea 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -1344,13 +1344,13 @@ TRACE_EVENT(alloc_extent_state, TP_STRUCT__entry( __field(const struct extent_state *, state) - __field(gfp_t, mask) + __field(unsigned long, mask) __field(const void*, ip) ), TP_fast_assign( __entry->state = state, - __entry->mask = mask, + __entry->mask = (__force unsigned long)mask, __entry->ip = (const void *)IP ), diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index c6d5d70dc7a5..3313eb83c117 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -162,13 +162,13 @@ TRACE_EVENT(mm_compaction_try_to_compact_pages, TP_STRUCT__entry( __field(int, order) - __field(gfp_t, gfp_mask) + __field(unsigned long, gfp_mask) __field(int, prio) ), TP_fast_assign( __entry->order = order; - __entry->gfp_mask = gfp_mask; + __entry->gfp_mask = (__force unsigned long)gfp_mask; __entry->prio = prio; ), diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index ddc8c944f417..71c141804222 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -24,7 +24,7 @@ DECLARE_EVENT_CLASS(kmem_alloc, __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( @@ -32,7 +32,7 @@ DECLARE_EVENT_CLASS(kmem_alloc, __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s", @@ -75,7 +75,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) __field( int, node ) ), @@ -84,7 +84,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), @@ -208,14 +208,14 @@ TRACE_EVENT(mm_page_alloc, TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 6532119a6bf1..fcb1ffb2cc8d 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -14,48 +14,48 @@ */ #define __def_gfpflag_names \ - {(unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ - {(unsigned long)GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"}, \ - {(unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"},\ - {(unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ - {(unsigned long)GFP_USER, "GFP_USER"}, \ - {(unsigned long)GFP_KERNEL_ACCOUNT, "GFP_KERNEL_ACCOUNT"}, \ - {(unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ - {(unsigned long)GFP_NOFS, "GFP_NOFS"}, \ - {(unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ - {(unsigned long)GFP_NOIO, "GFP_NOIO"}, \ - {(unsigned long)GFP_NOWAIT, "GFP_NOWAIT"}, \ - {(unsigned long)GFP_DMA, "GFP_DMA"}, \ - {(unsigned long)__GFP_HIGHMEM, "__GFP_HIGHMEM"}, \ - {(unsigned long)GFP_DMA32, "GFP_DMA32"}, \ - {(unsigned long)__GFP_HIGH, "__GFP_HIGH"}, \ - {(unsigned long)__GFP_ATOMIC, "__GFP_ATOMIC"}, \ - {(unsigned long)__GFP_IO, "__GFP_IO"}, \ - {(unsigned long)__GFP_FS, "__GFP_FS"}, \ - {(unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ - {(unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ - {(unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ - {(unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ - {(unsigned long)__GFP_COMP, "__GFP_COMP"}, \ - {(unsigned long)__GFP_ZERO, "__GFP_ZERO"}, \ - {(unsigned long)__GFP_NOMEMALLOC, "__GFP_NOMEMALLOC"}, \ - {(unsigned long)__GFP_MEMALLOC, "__GFP_MEMALLOC"}, \ - {(unsigned long)__GFP_HARDWALL, "__GFP_HARDWALL"}, \ - {(unsigned long)__GFP_THISNODE, "__GFP_THISNODE"}, \ - {(unsigned long)__GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"}, \ - {(unsigned long)__GFP_MOVABLE, "__GFP_MOVABLE"}, \ - {(unsigned long)__GFP_ACCOUNT, "__GFP_ACCOUNT"}, \ - {(unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ - {(unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ - {(unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ - {(unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ - {(unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ + {(__force unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ + {(__force unsigned long)GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"}, \ + {(__force unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"},\ + {(__force unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ + {(__force unsigned long)GFP_USER, "GFP_USER"}, \ + {(__force unsigned long)GFP_KERNEL_ACCOUNT, "GFP_KERNEL_ACCOUNT"}, \ + {(__force unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ + {(__force unsigned long)GFP_NOFS, "GFP_NOFS"}, \ + {(__force unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ + {(__force unsigned long)GFP_NOIO, "GFP_NOIO"}, \ + {(__force unsigned long)GFP_NOWAIT, "GFP_NOWAIT"}, \ + {(__force unsigned long)GFP_DMA, "GFP_DMA"}, \ + {(__force unsigned long)__GFP_HIGHMEM, "__GFP_HIGHMEM"}, \ + {(__force unsigned long)GFP_DMA32, "GFP_DMA32"}, \ + {(__force unsigned long)__GFP_HIGH, "__GFP_HIGH"}, \ + {(__force unsigned long)__GFP_ATOMIC, "__GFP_ATOMIC"}, \ + {(__force unsigned long)__GFP_IO, "__GFP_IO"}, \ + {(__force unsigned long)__GFP_FS, "__GFP_FS"}, \ + {(__force unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ + {(__force unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ + {(__force unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ + {(__force unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ + {(__force unsigned long)__GFP_COMP, "__GFP_COMP"}, \ + {(__force unsigned long)__GFP_ZERO, "__GFP_ZERO"}, \ + {(__force unsigned long)__GFP_NOMEMALLOC, "__GFP_NOMEMALLOC"}, \ + {(__force unsigned long)__GFP_MEMALLOC, "__GFP_MEMALLOC"}, \ + {(__force unsigned long)__GFP_HARDWALL, "__GFP_HARDWALL"}, \ + {(__force unsigned long)__GFP_THISNODE, "__GFP_THISNODE"}, \ + {(__force unsigned long)__GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"}, \ + {(__force unsigned long)__GFP_MOVABLE, "__GFP_MOVABLE"}, \ + {(__force unsigned long)__GFP_ACCOUNT, "__GFP_ACCOUNT"}, \ + {(__force unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ + {(__force unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ + {(__force unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ + {(__force unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ + {(__force unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ #ifdef CONFIG_KASAN_HW_TAGS #define __def_gfpflag_names_kasan , \ - {(unsigned long)__GFP_SKIP_ZERO, "__GFP_SKIP_ZERO"}, \ - {(unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ - {(unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} + {(__force unsigned long)__GFP_SKIP_ZERO, "__GFP_SKIP_ZERO"}, \ + {(__force unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ + {(__force unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} #else #define __def_gfpflag_names_kasan #endif diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index de136dbd623a..408c86244d64 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -96,14 +96,14 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd, __field( int, nid ) __field( int, zid ) __field( int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->nid = nid; __entry->zid = zid; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", @@ -120,12 +120,12 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template, TP_STRUCT__entry( __field( int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("order=%d gfp_flags=%s", @@ -210,7 +210,7 @@ TRACE_EVENT(mm_shrink_slab_start, __field(void *, shrink) __field(int, nid) __field(long, nr_objects_to_shrink) - __field(gfp_t, gfp_flags) + __field(unsigned long, gfp_flags) __field(unsigned long, cache_items) __field(unsigned long long, delta) __field(unsigned long, total_scan) @@ -222,7 +222,7 @@ TRACE_EVENT(mm_shrink_slab_start, __entry->shrink = shr->scan_objects; __entry->nid = sc->nid; __entry->nr_objects_to_shrink = nr_objects_to_shrink; - __entry->gfp_flags = sc->gfp_mask; + __entry->gfp_flags = (__force unsigned long)sc->gfp_mask; __entry->cache_items = cache_items; __entry->delta = delta; __entry->total_scan = total_scan; @@ -446,13 +446,13 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin, TP_STRUCT__entry( __field(int, nid) __field(int, order) - __field(gfp_t, gfp_flags) + __field(unsigned long, gfp_flags) ), TP_fast_assign( __entry->nid = nid; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", -- cgit v1.2.3 From 50d63b5bbfd12262069ad062611cd5e69c5e9e05 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 4 May 2022 16:14:41 -0300 Subject: vfio: Change vfio_external_user_iommu_id() to vfio_file_iommu_group() The only caller wants to get a pointer to the struct iommu_group associated with the VFIO group file. Instead of returning the group ID then searching sysfs for that string to get the struct iommu_group just directly return the iommu_group pointer already held by the vfio_group struct. It already has a safe lifetime due to the struct file kref, the vfio_group and thus the iommu_group cannot be destroyed while the group file is open. Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Reviewed-by: Yi Liu Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/3-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index be1e7db4a314..d8c34c8490cb 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -140,7 +140,7 @@ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); extern bool vfio_external_group_match_file(struct vfio_group *group, struct file *filep); -extern int vfio_external_user_iommu_id(struct vfio_group *group); +extern struct iommu_group *vfio_file_iommu_group(struct file *file); extern long vfio_external_check_extension(struct vfio_group *group, unsigned long arg); -- cgit v1.2.3 From c38ff5b0c373fbbd6a249eb461ffd4ae0f9dbfa0 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 4 May 2022 16:14:42 -0300 Subject: vfio: Remove vfio_external_group_match_file() vfio_group_fops_open() ensures there is only ever one struct file open for any struct vfio_group at any time: /* Do we need multiple instances of the group open? Seems not. */ opened = atomic_cmpxchg(&group->opened, 0, 1); if (opened) { vfio_group_put(group); return -EBUSY; Therefor the struct file * can be used directly to search the list of VFIO groups that KVM keeps instead of using the vfio_external_group_match_file() callback to try to figure out if the passed in FD matches the list or not. Delete vfio_external_group_match_file(). Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Reviewed-by: Yi Liu Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/4-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index d8c34c8490cb..df0adecdf1ea 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -138,8 +138,6 @@ int vfio_mig_get_next_state(struct vfio_device *device, */ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); -extern bool vfio_external_group_match_file(struct vfio_group *group, - struct file *filep); extern struct iommu_group *vfio_file_iommu_group(struct file *file); extern long vfio_external_check_extension(struct vfio_group *group, unsigned long arg); -- cgit v1.2.3 From a905ad043f32bbb0c35d4325036397f20f30c8a9 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 4 May 2022 16:14:43 -0300 Subject: vfio: Change vfio_external_check_extension() to vfio_file_enforced_coherent() Instead of a general extension check change the function into a limited test if the iommu_domain has enforced coherency, which is the only thing kvm needs to query. Make the new op self contained by properly refcounting the container before touching it. Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/5-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index df0adecdf1ea..7cc374da4839 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -139,8 +139,7 @@ int vfio_mig_get_next_state(struct vfio_device *device, extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); extern struct iommu_group *vfio_file_iommu_group(struct file *file); -extern long vfio_external_check_extension(struct vfio_group *group, - unsigned long arg); +extern bool vfio_file_enforced_coherent(struct file *file); #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) -- cgit v1.2.3 From ba70a89f3c2a8279809ea0fc7684857c91938b8a Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 4 May 2022 16:14:44 -0300 Subject: vfio: Change vfio_group_set_kvm() to vfio_file_set_kvm() Just change the argument from struct vfio_group to struct file *. Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/6-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 7cc374da4839..b298a26c4f07 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -15,6 +15,8 @@ #include #include +struct kvm; + /* * VFIO devices can be placed in a set, this allows all devices to share this * structure and the VFIO core will provide a lock that is held around @@ -140,6 +142,7 @@ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); extern struct iommu_group *vfio_file_iommu_group(struct file *file); extern bool vfio_file_enforced_coherent(struct file *file); +extern void vfio_file_set_kvm(struct file *file, struct kvm *kvm); #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) @@ -170,8 +173,6 @@ extern int vfio_unregister_notifier(struct vfio_device *device, enum vfio_notify_type type, struct notifier_block *nb); -struct kvm; -extern void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm); /* * Sub-module helpers -- cgit v1.2.3 From 6a985ae80befcf2c00e7c889336bfe9e9739e2ef Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 4 May 2022 16:14:46 -0300 Subject: vfio/pci: Use the struct file as the handle not the vfio_group VFIO PCI does a security check as part of hot reset to prove that the user has permission to manipulate all the devices that will be impacted by the reset. Use a new API vfio_file_has_dev() to perform this security check against the struct file directly and remove the vfio_group from VFIO PCI. Since VFIO PCI was the last user of vfio_group_get_external_user() and vfio_group_put_external_user() remove it as well. Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/8-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index b298a26c4f07..45b287826ce6 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -138,11 +138,10 @@ int vfio_mig_get_next_state(struct vfio_device *device, /* * External user API */ -extern struct vfio_group *vfio_group_get_external_user(struct file *filep); -extern void vfio_group_put_external_user(struct vfio_group *group); extern struct iommu_group *vfio_file_iommu_group(struct file *file); extern bool vfio_file_enforced_coherent(struct file *file); extern void vfio_file_set_kvm(struct file *file, struct kvm *kvm); +extern bool vfio_file_has_dev(struct file *file, struct vfio_device *device); #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) -- cgit v1.2.3 From 2ed3bf188b33630cf9d93b996ebf001847a00b5a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:16 +0200 Subject: netfilter: ecache: use dedicated list for event redelivery This disentangles event redelivery and the percpu dying list. Because entries are now stored on a dedicated list, all entries are in NFCT_ECACHE_DESTROY_FAIL state and all entries still have confirmed bit set -- the reference count is at least 1. The 'struct net' back-pointer can be removed as well. The pcpu dying list will be removed eventually, it has no functionality. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 3 ++- include/net/netfilter/nf_conntrack_ecache.h | 2 -- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 69e6c6a218be..28672a944499 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -45,7 +45,8 @@ union nf_conntrack_expect_proto { struct nf_conntrack_net_ecache { struct delayed_work dwork; - struct netns_ct *ct_net; + spinlock_t dying_lock; + struct hlist_nulls_head dying_list; }; struct nf_conntrack_net { diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 6c4c490a3e34..a6135b5030dd 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -14,7 +14,6 @@ #include enum nf_ct_ecache_state { - NFCT_ECACHE_UNKNOWN, /* destroy event not sent */ NFCT_ECACHE_DESTROY_FAIL, /* tried but failed to send destroy event */ NFCT_ECACHE_DESTROY_SENT, /* sent destroy event after failure */ }; @@ -23,7 +22,6 @@ struct nf_conntrack_ecache { unsigned long cache; /* bitops want long */ u16 ctmask; /* bitmask of ct events to be delivered */ u16 expmask; /* bitmask of expect events to be delivered */ - enum nf_ct_ecache_state state:8;/* ecache state */ u32 missed; /* missed events */ u32 portid; /* netlink portid of destroyer */ }; -- cgit v1.2.3 From 0d3cc504ba9cdcff76346306c37eb1ea01e60a86 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:17 +0200 Subject: netfilter: conntrack: include ecache dying list in dumps The new pernet dying list includes conntrack entries that await delivery of the 'destroy' event via ctnetlink. The old percpu dying list will be removed soon. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_ecache.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index a6135b5030dd..b57d73785e4d 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -164,6 +164,8 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state); void nf_conntrack_ecache_pernet_init(struct net *net); void nf_conntrack_ecache_pernet_fini(struct net *net); +struct nf_conntrack_net_ecache *nf_conn_pernet_ecache(const struct net *net); + static inline bool nf_conntrack_ecache_dwork_pending(const struct net *net) { return net->ct.ecache_dwork_pending; -- cgit v1.2.3 From 1397af5bfd7d32b0cf2adb70a78c9a9e8f11d912 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:18 +0200 Subject: netfilter: conntrack: remove the percpu dying list Its no longer needed. Entries that need event redelivery are placed on the new pernet dying list. The advantage is that there is no need to take additional spinlock on conntrack removal unless event redelivery failed or the conntrack entry was never added to the table in the first place (confirmed bit not set). The IPS_CONFIRMED bit now needs to be set as soon as the entry has been unlinked from the unconfirmed list, else the destroy function may attempt to unlink it a second time. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netns/conntrack.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 0294f3d473af..e985a3010b89 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -96,7 +96,6 @@ struct nf_ip_net { struct ct_pcpu { spinlock_t lock; struct hlist_nulls_head unconfirmed; - struct hlist_nulls_head dying; }; struct netns_ct { -- cgit v1.2.3 From 78222bacfca97cb18505df1ba5f3591864498a7e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:19 +0200 Subject: netfilter: cttimeout: decouple unlink and free on netns destruction Make it so netns pre_exit unlinks the objects from the pernet list, so they cannot be found anymore. netns core issues a synchronize_rcu() before calling the exit hooks so any the time the exit hooks run unconfirmed nf_conn entries have been free'd or they have been committed to the hashtable. The exit hook still tags unconfirmed entries as dying, this can now be removed in a followup change. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_timeout.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 3ea94f6f3844..fea258983d23 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -17,14 +17,6 @@ struct nf_ct_timeout { char data[]; }; -struct ctnl_timeout { - struct list_head head; - struct rcu_head rcu_head; - refcount_t refcnt; - char name[CTNL_TIMEOUT_NAME_MAX]; - struct nf_ct_timeout timeout; -}; - struct nf_conn_timeout { struct nf_ct_timeout __rcu *timeout; }; -- cgit v1.2.3 From 17438b42ce14cb60ceda9ae62ad5dd022d55a216 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:20 +0200 Subject: netfilter: remove nf_ct_unconfirmed_destroy helper This helper tags connections not yet in the conntrack table as dying. These nf_conn entries will be dropped instead when the core attempts to insert them from the input or postrouting 'confirm' hook. After the previous change, the entries get unlinked from the list earlier, so that by the time the actual exit hook runs, new connections no longer have a timeout policy assigned. Its enough to walk the hashtable instead. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 28672a944499..f60212244b13 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -237,9 +237,6 @@ static inline bool nf_ct_kill(struct nf_conn *ct) return nf_ct_delete(ct, 0, 0); } -/* Set all unconfirmed conntrack as dying */ -void nf_ct_unconfirmed_destroy(struct net *); - /* Iterate over all conntracks: if iter returns true, it's deleted. */ void nf_ct_iterate_cleanup_net(struct net *net, int (*iter)(struct nf_conn *i, void *data), -- cgit v1.2.3 From c56716c69ce1ac320432fb1ea5654196ba24d2f8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:21 +0200 Subject: netfilter: extensions: introduce extension genid count Multiple netfilter extensions store pointers to external data in their extension area struct. Examples: 1. Timeout policies 2. Connection tracking helpers. No references are taken for these. When a helper or timeout policy is removed, the conntrack table gets traversed and affected extensions are cleared. Conntrack entries not yet in the hashtable are referenced via a special list, the unconfirmed list. On removal of a policy or connection tracking helper, the unconfirmed list gets traversed an all entries are marked as dying, this prevents them from getting committed to the table at insertion time: core checks for dying bit, if set, the conntrack entry gets destroyed at confirm time. The disadvantage is that each new conntrack has to be added to the percpu unconfirmed list, and each insertion needs to remove it from this list. The list is only ever needed when a policy or helper is removed -- a rare occurrence. Add a generation ID count: Instead of adding to the list and then traversing that list on policy/helper removal, increment a counter that is stored in the extension area. For unconfirmed conntracks, the extension has the genid valid at ct allocation time. Removal of a helper/policy etc. increments the counter. At confirmation time, validate that ext->genid == global_id. If the stored number is not the same, do not allow the conntrack insertion, just like as if a confirmed-list traversal would have flagged the entry as dying. After insertion, the genid is no longer relevant (conntrack entries are now reachable via the conntrack table iterators and is set to 0. This allows removal of the percpu unconfirmed list. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_extend.h | 31 +++++++++++++++-------------- include/net/netfilter/nf_conntrack_labels.h | 10 +++++++++- 2 files changed, 25 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 96635ad2acc7..0b247248b032 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -34,21 +34,11 @@ enum nf_ct_ext_id { NF_CT_EXT_NUM, }; -#define NF_CT_EXT_HELPER_TYPE struct nf_conn_help -#define NF_CT_EXT_NAT_TYPE struct nf_conn_nat -#define NF_CT_EXT_SEQADJ_TYPE struct nf_conn_seqadj -#define NF_CT_EXT_ACCT_TYPE struct nf_conn_acct -#define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache -#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp -#define NF_CT_EXT_TIMEOUT_TYPE struct nf_conn_timeout -#define NF_CT_EXT_LABELS_TYPE struct nf_conn_labels -#define NF_CT_EXT_SYNPROXY_TYPE struct nf_conn_synproxy -#define NF_CT_EXT_ACT_CT_TYPE struct nf_conn_act_ct_ext - /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { u8 offset[NF_CT_EXT_NUM]; u8 len; + unsigned int gen_id; char data[] __aligned(8); }; @@ -62,17 +52,28 @@ static inline bool nf_ct_ext_exist(const struct nf_conn *ct, u8 id) return (ct->ext && __nf_ct_ext_exist(ct->ext, id)); } -static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id) +void *__nf_ct_ext_find(const struct nf_ct_ext *ext, u8 id); + +static inline void *nf_ct_ext_find(const struct nf_conn *ct, u8 id) { - if (!nf_ct_ext_exist(ct, id)) + struct nf_ct_ext *ext = ct->ext; + + if (!ext || !__nf_ct_ext_exist(ext, id)) return NULL; + if (unlikely(ext->gen_id)) + return __nf_ct_ext_find(ext, id); + return (void *)ct->ext + ct->ext->offset[id]; } -#define nf_ct_ext_find(ext, id) \ - ((id##_TYPE *)__nf_ct_ext_find((ext), (id))) /* Add this type, returns pointer to data or NULL. */ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp); +/* ext genid. if ext->id != ext_genid, extensions cannot be used + * anymore unless conntrack has CONFIRMED bit set. + */ +extern atomic_t nf_conntrack_ext_genid; +void nf_ct_ext_bump_genid(void); + #endif /* _NF_CONNTRACK_EXTEND_H */ diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index 3c23298e68ca..66bab6c60d12 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -17,10 +17,18 @@ struct nf_conn_labels { unsigned long bits[NF_CT_LABELS_MAX_SIZE / sizeof(long)]; }; +/* Can't use nf_ct_ext_find(), flow dissector cannot use symbols + * exported by nf_conntrack module. + */ static inline struct nf_conn_labels *nf_ct_labels_find(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_LABELS - return nf_ct_ext_find(ct, NF_CT_EXT_LABELS); + struct nf_ct_ext *ext = ct->ext; + + if (!ext || !__nf_ct_ext_exist(ext, NF_CT_EXT_LABELS)) + return NULL; + + return (void *)ct->ext + ct->ext->offset[NF_CT_EXT_LABELS]; #else return NULL; #endif -- cgit v1.2.3 From 8a75a2c1741073f0c2d7bee146648e717527e048 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:24 +0200 Subject: netfilter: conntrack: remove unconfirmed list It has no function anymore and can be removed. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 1 - include/net/netns/conntrack.h | 6 ------ 2 files changed, 7 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index f60212244b13..3ce9a5b42fe5 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -101,7 +101,6 @@ struct nf_conn { /* Have we seen traffic both ways yet? (bitset) */ unsigned long status; - u16 cpu; possible_net_t ct_net; #if IS_ENABLED(CONFIG_NF_NAT) diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index e985a3010b89..a71cfd4e2f21 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -93,11 +93,6 @@ struct nf_ip_net { #endif }; -struct ct_pcpu { - spinlock_t lock; - struct hlist_nulls_head unconfirmed; -}; - struct netns_ct { #ifdef CONFIG_NF_CONNTRACK_EVENTS bool ecache_dwork_pending; @@ -109,7 +104,6 @@ struct netns_ct { u8 sysctl_tstamp; u8 sysctl_checksum; - struct ct_pcpu __percpu *pcpu_lists; struct ip_conntrack_stat __percpu *stat; struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; struct nf_ip_net nf_ct_proto; -- cgit v1.2.3 From 8169ff584003c871a226719e998bb034231954d6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 8 Apr 2022 13:10:19 +0200 Subject: netfilter: conntrack: add nf_ct_iter_data object for nf_ct_iterate_cleanup*() This patch adds a structure to collect all the context data that is passed to the cleanup iterator. struct nf_ct_iter_data { struct net *net; void *data; u32 portid; int report; }; There is a netns field that allows to clean up conntrack entries specifically owned by the specified netns. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 3ce9a5b42fe5..a32be8aa7ed2 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -236,10 +236,16 @@ static inline bool nf_ct_kill(struct nf_conn *ct) return nf_ct_delete(ct, 0, 0); } +struct nf_ct_iter_data { + struct net *net; + void *data; + u32 portid; + int report; +}; + /* Iterate over all conntracks: if iter returns true, it's deleted. */ -void nf_ct_iterate_cleanup_net(struct net *net, - int (*iter)(struct nf_conn *i, void *data), - void *data, u32 portid, int report); +void nf_ct_iterate_cleanup_net(int (*iter)(struct nf_conn *i, void *data), + const struct nf_ct_iter_data *iter_data); /* also set unconfirmed conntracks as dying. Only use in module exit path. */ void nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), -- cgit v1.2.3 From 2794cdb0b97bfe62d25c996c8afe4832207e78bc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Apr 2022 15:15:41 +0200 Subject: netfilter: nfnetlink: allow to detect if ctnetlink listeners exist At this time, every new conntrack gets the 'event cache extension' enabled for it. This is because the 'net.netfilter.nf_conntrack_events' sysctl defaults to 1. Changing the default to 0 means that commands that rely on the event notification extension, e.g. 'conntrack -E' or conntrackd, stop working. We COULD detect if there is a listener by means of 'nfnetlink_has_listeners()' and only add the extension if this is true. The downside is a dependency from conntrack module to nfnetlink module. This adds a different way: inc/dec a counter whenever a ctnetlink group is being (un)subscribed and toggle a flag in struct net. Next patches will take advantage of this and will only add the event extension if the flag is set. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netns/conntrack.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index a71cfd4e2f21..0677cd3de034 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -95,6 +95,7 @@ struct nf_ip_net { struct netns_ct { #ifdef CONFIG_NF_CONNTRACK_EVENTS + bool ctnetlink_has_listener; bool ecache_dwork_pending; #endif u8 sysctl_log_invalid; /* Log invalid packets */ -- cgit v1.2.3 From b0a7ab4a776583b4344e8313638dc795f7589209 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Apr 2022 15:15:42 +0200 Subject: netfilter: conntrack: un-inline nf_ct_ecache_ext_add Only called when new ct is allocated or the extension isn't present. This function will be extended, place this in the conntrack module instead of inlining. The callers already depend on nf_conntrack module. Return value is changed to bool, noone used the returned pointer. Make sure that the core drops the newly allocated conntrack if the extension is requested but can't be added. This makes it necessary to ifdef the section, as the stub always returns false we'd drop every new conntrack if the the ecache extension is disabled in kconfig. Add from data path (xt_CT, nft_ct) is unchanged. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_ecache.h | 30 +++++------------------------ 1 file changed, 5 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index b57d73785e4d..2e3d58439e34 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -36,31 +36,6 @@ nf_ct_ecache_find(const struct nf_conn *ct) #endif } -static inline struct nf_conntrack_ecache * -nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) -{ -#ifdef CONFIG_NF_CONNTRACK_EVENTS - struct net *net = nf_ct_net(ct); - struct nf_conntrack_ecache *e; - - if (!ctmask && !expmask && net->ct.sysctl_events) { - ctmask = ~0; - expmask = ~0; - } - if (!ctmask && !expmask) - return NULL; - - e = nf_ct_ext_add(ct, NF_CT_EXT_ECACHE, gfp); - if (e) { - e->ctmask = ctmask; - e->expmask = expmask; - } - return e; -#else - return NULL; -#endif -} - #ifdef CONFIG_NF_CONNTRACK_EVENTS /* This structure is passed to event handler */ @@ -89,6 +64,7 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct); int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct, u32 portid, int report); +bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp); #else static inline void nf_ct_deliver_cached_events(const struct nf_conn *ct) @@ -103,6 +79,10 @@ static inline int nf_conntrack_eventmask_report(unsigned int eventmask, return 0; } +static inline bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) +{ + return false; +} #endif static inline void -- cgit v1.2.3 From 8edc813111001e9be3cce066d3d4091d2ef04a1d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Apr 2022 15:15:44 +0200 Subject: netfilter: prefer extension check to pointer check The pointer check usually results in a 'false positive': its likely that the ctnetlink module is loaded but no event monitoring is enabled. After recent change to autodetect ctnetlink usage and only allocate the ecache extension if a listener is active, check if the extension is present on a given conntrack. If its not there, there is nothing to report and calls to the notification framework can be elided. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 2 +- include/net/netfilter/nf_conntrack_ecache.h | 31 ++++++++++++++--------------- 2 files changed, 16 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 13807ea94cd2..6406cfee34c2 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -60,7 +60,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) if (ct) { if (!nf_ct_is_confirmed(ct)) ret = __nf_conntrack_confirm(skb); - if (likely(ret == NF_ACCEPT)) + if (ret == NF_ACCEPT && nf_ct_ecache_exist(ct)) nf_ct_deliver_cached_events(ct); } return ret; diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 2e3d58439e34..0c1dac318e02 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -36,6 +36,15 @@ nf_ct_ecache_find(const struct nf_conn *ct) #endif } +static inline bool nf_ct_ecache_exist(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_EVENTS + return nf_ct_ext_exist(ct, NF_CT_EXT_ECACHE); +#else + return false; +#endif +} + #ifdef CONFIG_NF_CONNTRACK_EVENTS /* This structure is passed to event handler */ @@ -108,30 +117,20 @@ nf_conntrack_event_report(enum ip_conntrack_events event, struct nf_conn *ct, u32 portid, int report) { #ifdef CONFIG_NF_CONNTRACK_EVENTS - const struct net *net = nf_ct_net(ct); - - if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb)) - return 0; - - return nf_conntrack_eventmask_report(1 << event, ct, portid, report); -#else - return 0; + if (nf_ct_ecache_exist(ct)) + return nf_conntrack_eventmask_report(1 << event, ct, portid, report); #endif + return 0; } static inline int nf_conntrack_event(enum ip_conntrack_events event, struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_EVENTS - const struct net *net = nf_ct_net(ct); - - if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb)) - return 0; - - return nf_conntrack_eventmask_report(1 << event, ct, 0, 0); -#else - return 0; + if (nf_ct_ecache_exist(ct)) + return nf_conntrack_eventmask_report(1 << event, ct, 0, 0); #endif + return 0; } #ifdef CONFIG_NF_CONNTRACK_EVENTS -- cgit v1.2.3 From 4f9bd53084d18c2f9f1ec68fa56587b99a2cef00 Mon Sep 17 00:00:00 2001 From: Kevin Mitchell Date: Fri, 29 Apr 2022 20:40:27 -0700 Subject: netfilter: conntrack: skip verification of zero UDP checksum The checksum is optional for UDP packets. However nf_reject would previously require a valid checksum to elicit a response such as ICMP_DEST_UNREACH. Add some logic to nf_reject_verify_csum to determine if a UDP packet has a zero checksum and should therefore not be verified. Signed-off-by: Kevin Mitchell Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_reject.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_reject.h b/include/net/netfilter/nf_reject.h index 9051c3a0c8e7..7c669792fb9c 100644 --- a/include/net/netfilter/nf_reject.h +++ b/include/net/netfilter/nf_reject.h @@ -5,12 +5,28 @@ #include #include -static inline bool nf_reject_verify_csum(__u8 proto) +static inline bool nf_reject_verify_csum(struct sk_buff *skb, int dataoff, + __u8 proto) { /* Skip protocols that don't use 16-bit one's complement checksum * of the entire payload. */ switch (proto) { + /* Protocols with optional checksums. */ + case IPPROTO_UDP: { + const struct udphdr *udp_hdr; + struct udphdr _udp_hdr; + + udp_hdr = skb_header_pointer(skb, dataoff, + sizeof(_udp_hdr), + &_udp_hdr); + if (!udp_hdr || udp_hdr->check) + return true; + + return false; + } + case IPPROTO_GRE: + /* Protocols with other integrity checks. */ case IPPROTO_AH: case IPPROTO_ESP: @@ -19,9 +35,6 @@ static inline bool nf_reject_verify_csum(__u8 proto) /* Protocols with partial checksums. */ case IPPROTO_UDPLITE: case IPPROTO_DCCP: - - /* Protocols with optional checksums. */ - case IPPROTO_GRE: return false; } return true; -- cgit v1.2.3 From 1af0e4a0233fea7e8226cb977d379dc20f9bbe11 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20G=C3=B6ttsche?= Date: Thu, 17 Feb 2022 15:18:57 +0100 Subject: security: declare member holding string literal const MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The struct security_hook_list member lsm is assigned in security_add_hooks() with string literals passed from the individual security modules. Declare the function parameter and the struct member const to signal their immutability. Reported by Clang [-Wwrite-strings]: security/selinux/hooks.c:7388:63: error: passing 'const char [8]' to parameter of type 'char *' discards qualifiers [-Werror,-Wincompatible-pointer-types-discards-qualifiers] security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), selinux); ^~~~~~~~~ ./include/linux/lsm_hooks.h:1629:11: note: passing argument to parameter 'lsm' here char *lsm); ^ Signed-off-by: Christian Göttsche Reviewed-by: Paul Moore Reviewed-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 419b5febc3ca..47cdf3fbecef 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1595,7 +1595,7 @@ struct security_hook_list { struct hlist_node list; struct hlist_head *head; union security_list_options hook; - char *lsm; + const char *lsm; } __randomize_layout; /* @@ -1630,7 +1630,7 @@ extern struct security_hook_heads security_hook_heads; extern char *lsm_names; extern void security_add_hooks(struct security_hook_list *hooks, int count, - char *lsm); + const char *lsm); #define LSM_FLAG_LEGACY_MAJOR BIT(0) #define LSM_FLAG_EXCLUSIVE BIT(1) -- cgit v1.2.3 From 1366992e16bddd5e2d9a561687f367f9f802e2e4 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sun, 10 Apr 2022 16:49:50 +0200 Subject: timekeeping: Add raw clock fallback for random_get_entropy() The addition of random_get_entropy_fallback() provides access to whichever time source has the highest frequency, which is useful for gathering entropy on platforms without available cycle counters. It's not necessarily as good as being able to quickly access a cycle counter that the CPU has, but it's still something, even when it falls back to being jiffies-based. In the event that a given arch does not define get_cycles(), falling back to the get_cycles() default implementation that returns 0 is really not the best we can do. Instead, at least calling random_get_entropy_fallback() would be preferable, because that always needs to return _something_, even falling back to jiffies eventually. It's not as though random_get_entropy_fallback() is super high precision or guaranteed to be entropic, but basically anything that's not zero all the time is better than returning zero all the time. Finally, since random_get_entropy_fallback() is used during extremely early boot when randomizing freelists in mm_init(), it can be called before timekeeping has been initialized. In that case there really is nothing we can do; jiffies hasn't even started ticking yet. So just give up and return 0. Suggested-by: Thomas Gleixner Signed-off-by: Jason A. Donenfeld Reviewed-by: Thomas Gleixner Cc: Arnd Bergmann Cc: Theodore Ts'o --- include/linux/timex.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/timex.h b/include/linux/timex.h index 5745c90c8800..3871b06bd302 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -62,6 +62,8 @@ #include #include +unsigned long random_get_entropy_fallback(void); + #include #ifndef random_get_entropy @@ -74,8 +76,14 @@ * * By default we use get_cycles() for this purpose, but individual * architectures may override this in their asm/timex.h header file. + * If a given arch does not have get_cycles(), then we fallback to + * using random_get_entropy_fallback(). */ +#ifdef get_cycles #define random_get_entropy() ((unsigned long)get_cycles()) +#else +#define random_get_entropy() random_get_entropy_fallback() +#endif #endif /* -- cgit v1.2.3 From 16d1e00c7e8a4950e914223b3112144289a82913 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 9 May 2022 15:42:52 -0700 Subject: bpf: Add MEM_UNINIT as a bpf_type_flag Instead of having uninitialized versions of arguments as separate bpf_arg_types (eg ARG_PTR_TO_UNINIT_MEM as the uninitialized version of ARG_PTR_TO_MEM), we can instead use MEM_UNINIT as a bpf_type_flag modifier to denote that the argument is uninitialized. Doing so cleans up some of the logic in the verifier. We no longer need to do two checks against an argument type (eg "if (base_type(arg_type) == ARG_PTR_TO_MEM || base_type(arg_type) == ARG_PTR_TO_UNINIT_MEM)"), since uninitialized and initialized versions of the same argument type will now share the same base type. In the near future, MEM_UNINIT will be used by dynptr helper functions as well. Signed-off-by: Joanne Koong Acked-by: Andrii Nakryiko Acked-by: David Vernet Link: https://lore.kernel.org/r/20220509224257.3222614-2-joannelkoong@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5061ccd8b2dc..c107392b0ba7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -390,7 +390,10 @@ enum bpf_type_flag { */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = PTR_UNTRUSTED, + MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_FLAG_MAX, + __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; /* Max number of base types. */ @@ -409,16 +412,11 @@ enum bpf_arg_type { ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ - ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ - /* the following constraints used to prototype bpf_memcmp() and other - * functions that access data on eBPF program stack + /* Used to prototype bpf_memcmp() and other functions that access data + * on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ - ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized, - * helper function must fill all bytes or clear - * them in error case. - */ ARG_CONST_SIZE, /* number of bytes accessed from memory */ ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ @@ -450,6 +448,10 @@ enum bpf_arg_type { ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, + /* pointer to memory does not need to be initialized, helper function must fill + * all bytes or clear them in error case. + */ + ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. -- cgit v1.2.3 From e7392b4eca84e86718a7b73aea8fa5573b06ba76 Mon Sep 17 00:00:00 2001 From: "Fabio M. De Francesco" Date: Fri, 13 May 2022 16:48:55 -0700 Subject: mm/highmem: fix kernel-doc warnings in highmem*.h Patch series "Extend and reorganize Highmem's documentation", v4. This series has the purpose to extend and reorganize Highmem's documentation. This is a work in progress because some information should still be moved from highmem.rst to highmem.h and highmem-internal.h. Specifically I'm talking about moving the "how to" information to the relevant headers, as it as been suggested by Ira Weiny (Intel). Also, this is a work in progress because some kdocs in highmem.h and highmem-internal.h should be improved. This patch (of 4): `scripts/kernel-doc -v -none include/linux/highmem*` reports the following warnings: include/linux/highmem.h:160: warning: expecting prototype for kunmap_atomic(). Prototype was for nr_free_highpages() instead include/linux/highmem.h:204: warning: No description found for return value of 'alloc_zeroed_user_highpage_movable' include/linux/highmem-internal.h:256: warning: Function parameter or member '__addr' not described in 'kunmap_atomic' include/linux/highmem-internal.h:256: warning: Excess function parameter 'addr' description in 'kunmap_atomic' Fix these warnings by (1) moving the kernel-doc comments from highmem.h to highmem-internal.h (which is the file were the kunmap_atomic() macro is actually defined), (2) extending and merging it with the comment which was already in highmem-internal.h, and (3) using correct parameter names (4) correcting a few technical inaccuracies in comments, and (5) adding a deprecation notice in kunmap_atomic() for consistency with kmap_atomic(). Link: https://lkml.kernel.org/r/20220428212455.892-1-fmdefrancesco@gmail.com Link: https://lkml.kernel.org/r/20220428212455.892-2-fmdefrancesco@gmail.com Signed-off-by: Fabio M. De Francesco Reviewed-by: Sebastian Andrzej Siewior Reviewed-by: Ira Weiny Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Catalin Marinas Cc: Will Deacon Cc: Peter Collingbourne Cc: Vlastimil Babka Cc: Jonathan Corbet Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Jonathan Corbet Signed-off-by: Andrew Morton --- include/linux/highmem-internal.h | 18 +++++++++++++++--- include/linux/highmem.h | 22 ++++++++-------------- 2 files changed, 23 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index a77be5630209..a694ca95c4ed 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -236,9 +236,21 @@ static inline unsigned long totalhigh_pages(void) { return 0UL; } #endif /* CONFIG_HIGHMEM */ -/* - * Prevent people trying to call kunmap_atomic() as if it were kunmap() - * kunmap_atomic() should get the return value of kmap_atomic, not the page. +/** + * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - deprecated! + * @__addr: Virtual address to be unmapped + * + * Unmaps an address previously mapped by kmap_atomic() and re-enables + * pagefaults. Depending on PREEMP_RT configuration, re-enables also + * migration and preemption. Users should not count on these side effects. + * + * Mappings should be unmapped in the reverse order that they were mapped. + * See kmap_local_page() for details on nesting. + * + * @__addr can be any address within the mapped page, so there is no need + * to subtract any offset that has been added. In contrast to kunmap(), + * this function takes the address returned from kmap_atomic(), not the + * page passed to it. The compiler will warn you if you pass the page. */ #define kunmap_atomic(__addr) \ do { \ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 67720bfd6ade..c05ae395898a 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -37,7 +37,7 @@ static inline void *kmap(struct page *page); /** * kunmap - Unmap the virtual address mapped by kmap() - * @addr: Virtual address to be unmapped + * @page: Pointer to the page which was mapped by kmap() * * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. @@ -138,24 +138,16 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * * Returns: The virtual address of the mapping * - * Effectively a wrapper around kmap_local_page() which disables pagefaults - * and preemption. + * In fact a wrapper around kmap_local_page() which also disables pagefaults + * and, depending on PREEMPT_RT configuration, also CPU migration and + * preemption. Therefore users should not count on the latter two side effects. + * + * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. */ static inline void *kmap_atomic(struct page *page); -/** - * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - * @addr: Virtual address to be unmapped - * - * Counterpart to kmap_atomic(). - * - * Effectively a wrapper around kunmap_local() which additionally undoes - * the side effects of kmap_atomic(), i.e. reenabling pagefaults and - * preemption. - */ - /* Highmem related interfaces for management code */ static inline unsigned int nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); @@ -191,6 +183,8 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr) * @vma: The VMA the page is to be allocated for * @vaddr: The virtual address the page will be inserted into * + * Returns: The allocated and zeroed HIGHMEM page + * * This function will allocate a page for a VMA that the caller knows will * be able to migrate in the future using move_pages() or reclaimed * -- cgit v1.2.3 From 85a85e7601263f2b4edc86136dd0172c2cfbfaa1 Mon Sep 17 00:00:00 2001 From: "Fabio M. De Francesco" Date: Fri, 13 May 2022 16:48:55 -0700 Subject: Documentation/vm: move "Using kmap-atomic" to highmem.h The use of kmap_atomic() is new code is being deprecated in favor of kmap_local_page(). For this reason the "Using kmap_atomic" section in highmem.rst is obsolete and unnecessary, but it can still help developers if it were moved to kdocs in highmem.h. Therefore, move the relevant parts of this section from highmem.rst and merge them with the kdocs in highmem.h. Link: https://lkml.kernel.org/r/20220428212455.892-4-fmdefrancesco@gmail.com Signed-off-by: Fabio M. De Francesco Suggested-by: Ira Weiny Reviewed-by: Sebastian Andrzej Siewior Reviewed-by: Ira Weiny Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Catalin Marinas Cc: Mike Rapoport Cc: Peter Collingbourne Cc: Vlastimil Babka Cc: Will Deacon Cc: Jonathan Corbet Signed-off-by: Andrew Morton --- include/linux/highmem.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index c05ae395898a..3af34de54330 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -145,6 +145,37 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. + * + * It is used in atomic context when code wants to access the contents of a + * page that might be allocated from high memory (see __GFP_HIGHMEM), for + * example a page in the pagecache. The API has two functions, and they + * can be used in a manner similar to the following: + * + * -- Find the page of interest. -- + * struct page *page = find_get_page(mapping, offset); + * + * -- Gain access to the contents of that page. -- + * void *vaddr = kmap_atomic(page); + * + * -- Do something to the contents of that page. -- + * memset(vaddr, 0, PAGE_SIZE); + * + * -- Unmap that page. -- + * kunmap_atomic(vaddr); + * + * Note that the kunmap_atomic() call takes the result of the kmap_atomic() + * call, not the argument. + * + * If you need to map two pages because you want to copy from one page to + * another you need to keep the kmap_atomic calls strictly nested, like: + * + * vaddr1 = kmap_atomic(page1); + * vaddr2 = kmap_atomic(page2); + * + * memcpy(vaddr1, vaddr2, PAGE_SIZE); + * + * kunmap_atomic(vaddr2); + * kunmap_atomic(vaddr1); */ static inline void *kmap_atomic(struct page *page); -- cgit v1.2.3 From ae07562909f3dfcdff40f87e51965728dab50485 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 13 May 2022 16:48:55 -0700 Subject: mm: change huge_ptep_clear_flush() to return the original pte Patch series "Fix CONT-PTE/PMD size hugetlb issue when unmapping or migrating", v4. presently, migrating a hugetlb page or unmapping a poisoned hugetlb page, we'll use ptep_clear_flush() and set_pte_at() to nuke the page table entry and remap it, and this is incorrect for CONT-PTE or CONT-PMD size hugetlb page, which will cause potential data consistent issue. This patch set will change to use hugetlb related APIs to fix this issue. Note: Mike pointed out the huge_ptep_get() will only return the one specific value, and it would not take into account the dirty or young bits of CONT-PTE/PMDs like the huge_ptep_get_and_clear() [1]. This inconsistent issue is not introduced by this patch set, and this issue will be addressed in another thread [2]. Meanwhile the uffd for hugetlb case [3] pointed out by Gerald also needs another patch to address. [1] https://lore.kernel.org/linux-mm/85bd80b4-b4fd-0d3f-a2e5-149559f2f387@oracle.com/ [2] https://lore.kernel.org/all/cover.1651998586.git.baolin.wang@linux.alibaba.com/ [3] https://lore.kernel.org/linux-mm/20220503120343.6264e126@thinkpad/ This patch (of 3): It is incorrect to use ptep_clear_flush() to nuke a hugetlb page table when unmapping or migrating a hugetlb page, and will change to use huge_ptep_clear_flush() instead in the following patches. So this is a preparation patch, which changes the huge_ptep_clear_flush() to return the original pte to help to nuke a hugetlb page table. [baolin.wang@linux.alibaba.com: fix build in several more architectures] Link: https://lkml.kernel.org/r/0009a4cd-2826-e8be-e671-f050d4f18d5d@linux.alibaba.com [sfr@canb.auug.org.au: fixup] Link: https://lkml.kernel.org/r/20220511181531.7f27a5c1@canb.auug.org.au Link: https://lkml.kernel.org/r/cover.1652270205.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/20f77ddab90baa249bd24504c413189b82acde69.1652270205.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/cover.1652147571.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/dcf065868cce35bceaf138613ad27f17bb7c0c19.1652147571.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Signed-off-by: Stephen Rothwell Acked-by: Mike Kravetz Reviewed-by: Muchun Song Cc: Catalin Marinas Cc: Will Deacon Cc: Thomas Bogendoerfer Cc: James Bottomley Cc: Helge Deller Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Yoshinori Sato Cc: Rich Felker Cc: David S. Miller Cc: Arnd Bergmann Cc: Gerald Schaefer Signed-off-by: Andrew Morton --- include/asm-generic/hugetlb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 896f341f614d..a57d667addd2 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -84,10 +84,10 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, #endif #ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - ptep_clear_flush(vma, addr, ptep); + return ptep_clear_flush(vma, addr, ptep); } #endif -- cgit v1.2.3 From 5d4af6195c87c6b162b7963e0ad00a214b80d764 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 13 May 2022 16:48:55 -0700 Subject: mm: rmap: fix CONT-PTE/PMD size hugetlb issue when migration On some architectures (like ARM64), it can support CONT-PTE/PMD size hugetlb, which means it can support not only PMD/PUD size hugetlb: 2M and 1G, but also CONT-PTE/PMD size: 64K and 32M if a 4K page size specified. When migrating a hugetlb page, we will get the relevant page table entry by huge_pte_offset() only once to nuke it and remap it with a migration pte entry. This is correct for PMD or PUD size hugetlb, since they always contain only one pmd entry or pud entry in the page table. However this is incorrect for CONT-PTE and CONT-PMD size hugetlb, since they can contain several continuous pte or pmd entry with same page table attributes. So we will nuke or remap only one pte or pmd entry for this CONT-PTE/PMD size hugetlb page, which is not expected for hugetlb migration. The problem is we can still continue to modify the subpages' data of a hugetlb page during migrating a hugetlb page, which can cause a serious data consistent issue, since we did not nuke the page table entry and set a migration pte for the subpages of a hugetlb page. To fix this issue, we should change to use huge_ptep_clear_flush() to nuke a hugetlb page table, and remap it with set_huge_pte_at() and set_huge_swap_pte_at() when migrating a hugetlb page, which already considered the CONT-PTE or CONT-PMD size hugetlb. [akpm@linux-foundation.org: fix nommu build] [baolin.wang@linux.alibaba.com: fix build errors for !CONFIG_MMU] Link: https://lkml.kernel.org/r/a4baca670aca637e7198d9ae4543b8873cb224dc.1652270205.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/ea5abf529f0997b5430961012bfda6166c1efc8c.1652147571.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Muchun Song Reviewed-by: Mike Kravetz Acked-by: David Hildenbrand Cc: Alexander Gordeev Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Christian Borntraeger Cc: David S. Miller Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Helge Deller Cc: James Bottomley Cc: Michael Ellerman Cc: Paul Mackerras Cc: Rich Felker Cc: Sven Schnelle Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 04f0186b089b..0f2894d01333 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -1093,6 +1093,17 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr pte_t *ptep, pte_t pte, unsigned long sz) { } + +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + return *ptep; +} + +static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, -- cgit v1.2.3 From 78f39084b41d287aedb2ea55f2c1895cfa11d61a Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 13 May 2022 16:48:56 -0700 Subject: mm: hugetlb_vmemmap: add hugetlb_optimize_vmemmap sysctl We must add hugetlb_free_vmemmap=on (or "off") to the boot cmdline and reboot the server to enable or disable the feature of optimizing vmemmap pages associated with HugeTLB pages. However, rebooting usually takes a long time. So add a sysctl to enable or disable the feature at runtime without rebooting. Why we need this? There are 3 use cases. 1) The feature of minimizing overhead of struct page associated with each HugeTLB is disabled by default without passing "hugetlb_free_vmemmap=on" to the boot cmdline. When we (ByteDance) deliver the servers to the users who want to enable this feature, they have to configure the grub (change boot cmdline) and reboot the servers, whereas rebooting usually takes a long time (we have thousands of servers). It's a very bad experience for the users. So we need a approach to enable this feature after rebooting. This is a use case in our practical environment. 2) Some use cases are that HugeTLB pages are allocated 'on the fly' instead of being pulled from the HugeTLB pool, those workloads would be affected with this feature enabled. Those workloads could be identified by the characteristics of they never explicitly allocating huge pages with 'nr_hugepages' but only set 'nr_overcommit_hugepages' and then let the pages be allocated from the buddy allocator at fault time. We can confirm it is a real use case from the commit 099730d67417. For those workloads, the page fault time could be ~2x slower than before. We suspect those users want to disable this feature if the system has enabled this before and they don't think the memory savings benefit is enough to make up for the performance drop. 3) If the workload which wants vmemmap pages to be optimized and the workload which wants to set 'nr_overcommit_hugepages' and does not want the extera overhead at fault time when the overcommitted pages be allocated from the buddy allocator are deployed in the same server. The user could enable this feature and set 'nr_hugepages' and 'nr_overcommit_hugepages', then disable the feature. In this case, the overcommited HugeTLB pages will not encounter the extra overhead at fault time. Link: https://lkml.kernel.org/r/20220512041142.39501-5-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Mike Kravetz Cc: Jonathan Corbet Cc: Luis Chamberlain Cc: Kees Cook Cc: Iurii Zaikin Cc: Oscar Salvador Cc: David Hildenbrand Cc: Masahiro Yamada Cc: Xiongchun Duan Signed-off-by: Andrew Morton --- include/linux/memory_hotplug.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index e0b2209ab71c..20d7edf62a6a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -351,4 +351,13 @@ void arch_remove_linear_mapping(u64 start, u64 size); extern bool mhp_supports_memmap_on_memory(unsigned long size); #endif /* CONFIG_MEMORY_HOTPLUG */ +#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY +bool mhp_memmap_on_memory(void); +#else +static inline bool mhp_memmap_on_memory(void) +{ + return false; +} +#endif + #endif /* __LINUX_MEMORY_HOTPLUG_H */ -- cgit v1.2.3 From d4a157f5a26fbf1f1fd5da47a4772a738306348f Mon Sep 17 00:00:00 2001 From: Gautam Menghani Date: Fri, 13 May 2022 16:48:57 -0700 Subject: mm/damon: add documentation for Enum value Fix the warning - "Enum value 'NR_DAMON_OPS' not described in enum 'damon_ops_id'" generated by the command "make pdfdocs" Link: https://lkml.kernel.org/r/20220508073316.141401-1-gautammenghani201@gmail.com Signed-off-by: Gautam Menghani Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index d1e6ee28a2ff..7c62da31ce4b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -264,6 +264,7 @@ struct damos { * @DAMON_OPS_FVADDR: Monitoring operations for only fixed ranges of virtual * address spaces * @DAMON_OPS_PADDR: Monitoring operations for the physical address space + * @NR_DAMON_OPS: Number of monitoring operations implementations */ enum damon_ops_id { DAMON_OPS_VADDR, -- cgit v1.2.3 From 390ed29b5e425ba00da2b6113b74a14949f71b02 Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Sat, 14 May 2022 22:20:43 +0800 Subject: io_uring: add IORING_ACCEPT_MULTISHOT for accept add an accept_flag IORING_ACCEPT_MULTISHOT for accept, which is to support multishot. Signed-off-by: Hao Xu Link: https://lore.kernel.org/r/20220514142046.58072-2-haoxu.linux@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 36ec43dc7bf9..15f821af9242 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -232,6 +232,11 @@ enum { */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) +/* + * accept flags stored in sqe->ioprio + */ +#define IORING_ACCEPT_MULTISHOT (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ -- cgit v1.2.3 From 81132a39c152ca09832b9e4cb748129cee5f55ec Mon Sep 17 00:00:00 2001 From: Gou Hao Date: Tue, 2 Nov 2021 10:46:48 +0800 Subject: fs: remove fget_many and fput_many interface These two interface were added in 091141a42 commit, but now there is no place to call them. The only user of fput/fget_many() was removed in commit 62906e89e63b ("io_uring: remove file batch-get optimisation"). A user of get_file_rcu_many() were removed in commit f073531070d2 ("init: add an init_dup helper"). And replace atomic_long_sub/add to atomic_long_dec/inc can improve performance. Here are the test results of unixbench: Cmd: ./Run -c 64 context1 Without patch: System Benchmarks Partial Index BASELINE RESULT INDEX Pipe-based Context Switching 4000.0 2798407.0 6996.0 ======== System Benchmarks Index Score (Partial Only) 6996.0 With patch: System Benchmarks Partial Index BASELINE RESULT INDEX Pipe-based Context Switching 4000.0 3486268.8 8715.7 ======== System Benchmarks Index Score (Partial Only) 8715.7 Signed-off-by: Gou Hao Signed-off-by: Al Viro --- include/linux/file.h | 2 -- include/linux/fs.h | 4 +--- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/file.h b/include/linux/file.h index 51e830b4fe3a..39704eae83e2 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -14,7 +14,6 @@ struct file; extern void fput(struct file *); -extern void fput_many(struct file *, unsigned int); struct file_operations; struct task_struct; @@ -47,7 +46,6 @@ static inline void fdput(struct fd fd) } extern struct file *fget(unsigned int fd); -extern struct file *fget_many(unsigned int fd, unsigned int refs); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern unsigned long __fdget(unsigned int fd); diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..3660c338bb16 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -981,9 +981,7 @@ static inline struct file *get_file(struct file *f) atomic_long_inc(&f->f_count); return f; } -#define get_file_rcu_many(x, cnt) \ - atomic_long_add_unless(&(x)->f_count, (cnt), 0) -#define get_file_rcu(x) get_file_rcu_many((x), 1) +#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count) #define file_count(x) atomic_long_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) -- cgit v1.2.3 From 6319194ec57b0452dcda4589d24c4e7db299c5bf Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 12 May 2022 17:08:03 -0400 Subject: Unify the primitives for file descriptor closing Currently we have 3 primitives for removing an opened file from descriptor table - pick_file(), __close_fd_get_file() and close_fd_get_file(). Their calling conventions are rather odd and there's a code duplication for no good reason. They can be unified - 1) have __range_close() cap max_fd in the very beginning; that way we don't need separate way for pick_file() to report being past the end of descriptor table. 2) make {__,}close_fd_get_file() return file (or NULL) directly, rather than returning it via struct file ** argument. Don't bother with (bogus) return value - nobody wants that -ENOENT. 3) make pick_file() return NULL on unopened descriptor - the only caller that used to care about the distinction between descriptor past the end of descriptor table and finding NULL in descriptor table doesn't give a damn after (1). 4) lift ->files_lock out of pick_file() That actually simplifies the callers, as well as the primitives themselves. Code duplication is also gone... Reviewed-by: Christian Brauner (Microsoft) Signed-off-by: Al Viro --- include/linux/fdtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index d0e78174874a..e066816f3519 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -125,7 +125,7 @@ int iterate_fd(struct files_struct *, unsigned, extern int close_fd(unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); -extern int close_fd_get_file(unsigned int fd, struct file **res); +extern struct file *close_fd_get_file(unsigned int fd); extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp); -- cgit v1.2.3 From e987a4c60f9755b2f7a19bf1b5ef2eb74c90579b Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Tue, 10 May 2022 09:57:08 +0000 Subject: KVM: arm64: Repack struct kvm_pmu to reduce size struct kvm_pmu has 2 holes using 10 bytes. This is instantiated in all vcpus, so it adds up. Repack the structures to remove the holes. No functional change intended. Reviewed-by: Oliver Upton Signed-off-by: Fuad Tabba Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220510095710.148178-3-tabba@google.com --- include/kvm/arm_pmu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 20193416d214..eaa8290b116f 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -21,12 +21,12 @@ struct kvm_pmc { }; struct kvm_pmu { - int irq_num; + struct irq_work overflow_work; struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS]; DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS); + int irq_num; bool created; bool irq_level; - struct irq_work overflow_work; }; struct arm_pmu_entry { -- cgit v1.2.3 From 84d751a019a9792f5b4884e1d598b603c360ec22 Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Tue, 10 May 2022 09:57:09 +0000 Subject: KVM: arm64: Pass pmu events to hyp via vcpu Instead of the host accessing hyp data directly, pass the pmu events of the current cpu to hyp via the vcpu. This adds 64 bits (in two fields) to the vcpu that need to be synced before every vcpu run in nvhe and protected modes. However, it isolates the hypervisor from the host, which allows us to use pmu in protected mode in a subsequent patch. No visible side effects in behavior intended. Signed-off-by: Fuad Tabba Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220510095710.148178-4-tabba@google.com --- include/kvm/arm_pmu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index eaa8290b116f..35a0903cae32 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -20,8 +20,14 @@ struct kvm_pmc { struct perf_event *perf_event; }; +struct kvm_pmu_events { + u32 events_host; + u32 events_guest; +}; + struct kvm_pmu { struct irq_work overflow_work; + struct kvm_pmu_events events; struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS]; DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS); int irq_num; -- cgit v1.2.3 From 03fea699b050805ad6ee111f9db04f223f3e835e Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 15 May 2022 21:58:30 +0100 Subject: cdrom: remove the unused driver specific disc change ioctl This was only used by the ide-cd driver, which went away in commit b7fb14d3ac63 ("ide: remove the legacy ide driver") so we might as well take advantage of that and get rid of this hook as well. Cc: Christoph Hellwig Cc: Jens Axboe Cc: Phillip Potter Signed-off-by: Paul Gortmaker Link: https://lore.kernel.org/all/20220427132436.12795-2-paul.gortmaker@windriver.com Signed-off-by: Phillip Potter Link: https://lore.kernel.org/r/20220515205833.944139-3-phil@philpotter.co.uk Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 0a89f111e00e..67caa909e3e6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,6 @@ struct cdrom_device_ops { int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); int (*select_speed) (struct cdrom_device_info *, int); - int (*select_disc) (struct cdrom_device_info *, int); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, -- cgit v1.2.3 From 8fa10ee183c3a1ecb53e81c95895ed5bc2a5530a Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 15 May 2022 21:58:31 +0100 Subject: cdrom: mark CDROMGETSPINDOWN/CDROMSETSPINDOWN obsolete These were only implemented by the IDE CD driver, which has since been removed. Given that nobody is likely to create new CD/DVD hardware (and associated drivers) we can mark these appropriately. Cc: Jens Axboe Cc: Christoph Hellwig Cc: Phillip Potter Signed-off-by: Paul Gortmaker Link: https://lore.kernel.org/all/20220427132436.12795-3-paul.gortmaker@windriver.com Signed-off-by: Phillip Potter Link: https://lore.kernel.org/r/20220515205833.944139-4-phil@philpotter.co.uk Signed-off-by: Jens Axboe --- include/uapi/linux/cdrom.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h index 804ff8d98f71..011e594e4a0d 100644 --- a/include/uapi/linux/cdrom.h +++ b/include/uapi/linux/cdrom.h @@ -103,7 +103,7 @@ #define CDROMREADALL 0x5318 /* read all 2646 bytes */ /* - * These ioctls are (now) only in ide-cd.c for controlling + * These ioctls were only in (now removed) ide-cd.c for controlling * drive spindown time. They should be implemented in the * Uniform driver, via generic packet commands, GPCMD_MODE_SELECT_10, * GPCMD_MODE_SENSE_10 and the GPMODE_POWER_PAGE... -- cgit v1.2.3 From ca2d89925ae3f3d5c65182ff75e58bc9b484e69c Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 28 Apr 2022 12:19:35 +0300 Subject: nvme: add missing status values to verbose logging Log a few more path related status codes. Signed-off-by: Max Gurtovoy Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f626a445d1a8..bbabdc7600da 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1679,9 +1679,11 @@ enum { /* * Path-related Errors: */ + NVME_SC_INTERNAL_PATH_ERROR = 0x300, NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, + NVME_SC_CTRL_PATH_ERROR = 0x360, NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_HOST_ABORTED_CMD = 0x371, -- cgit v1.2.3 From 4273d3fa8aa594e37c295bef3e73073608644241 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 10 May 2022 13:37:59 +0200 Subject: mac80211: fix typo in documentation This is called offload_flags, remove the extra 'a'. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 75880fc70700..7b74c695a83a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1701,7 +1701,7 @@ enum ieee80211_offload_flags { * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed * at runtime, mac80211 will never touch this field - * @offloaad_flags: hardware offload capabilities/flags for this interface. + * @offload_flags: hardware offload capabilities/flags for this interface. * These are initialized by mac80211 before calling .add_interface, * .change_interface or .update_vif_offload and updated by the driver * within these ops, based on supported features or runtime change -- cgit v1.2.3 From f5bf586aadddd9803a1f16bc18621fd819377130 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 10 May 2022 16:38:19 +0200 Subject: mac80211: remove stray multi_sta_back_32bit docs This field doesn't exist, remove the docs for it. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7b74c695a83a..944b31f0eb0d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -514,7 +514,6 @@ struct ieee80211_fils_discovery { * to that BSS) that can change during the lifetime of the BSS. * * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE - * @multi_sta_back_32bit: supports BA bitmap of 32-bits in Multi-STA BACK * @uora_exists: is the UORA element advertised by AP * @ack_enabled: indicates support to receive a multi-TID that solicits either * ACK, BACK or both -- cgit v1.2.3 From e6175a2ed1f18bf2f649625bf725e07adcfa6a28 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Fri, 13 May 2022 23:34:02 +0300 Subject: xfrm: fix "disable_policy" flag use when arriving from different devices In IPv4 setting the "disable_policy" flag on a device means no policy should be enforced for traffic originating from the device. This was implemented by seting the DST_NOPOLICY flag in the dst based on the originating device. However, dsts are cached in nexthops regardless of the originating devices, in which case, the DST_NOPOLICY flag value may be incorrect. Consider the following setup: +------------------------------+ | ROUTER | +-------------+ | +-----------------+ | | ipsec src |----|-|ipsec0 | | +-------------+ | |disable_policy=0 | +----+ | | +-----------------+ |eth1|-|----- +-------------+ | +-----------------+ +----+ | | noipsec src |----|-|eth0 | | +-------------+ | |disable_policy=1 | | | +-----------------+ | +------------------------------+ Where ROUTER has a default route towards eth1. dst entries for traffic arriving from eth0 would have DST_NOPOLICY and would be cached and therefore can be reused by traffic originating from ipsec0, skipping policy check. Fix by setting a IPSKB_NOPOLICY flag in IPCB and observing it instead of the DST in IN/FWD IPv4 policy checks. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Shmulik Ladkani Signed-off-by: Eyal Birger Signed-off-by: Steffen Klassert --- include/net/ip.h | 1 + include/net/xfrm.h | 14 +++++++++++++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 3984f2c39c4b..0161137914cf 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -56,6 +56,7 @@ struct inet_skb_parm { #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) #define IPSKB_L3SLAVE BIT(7) +#define IPSKB_NOPOLICY BIT(8) u16 frag_max_size; }; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6fb899ff5afc..d2efddce65d4 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1093,6 +1093,18 @@ static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb, return false; } +static inline bool __xfrm_check_dev_nopolicy(struct sk_buff *skb, + int dir, unsigned short family) +{ + if (dir != XFRM_POLICY_OUT && family == AF_INET) { + /* same dst may be used for traffic originating from + * devices with different policy settings. + */ + return IPCB(skb)->flags & IPSKB_NOPOLICY; + } + return skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY); +} + static inline int __xfrm_policy_check2(struct sock *sk, int dir, struct sk_buff *skb, unsigned int family, int reverse) @@ -1104,7 +1116,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, return __xfrm_policy_check(sk, ndir, skb, family); return __xfrm_check_nopolicy(net, skb, dir) || - (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || + __xfrm_check_dev_nopolicy(skb, dir, family) || __xfrm_policy_check(sk, ndir, skb, family); } -- cgit v1.2.3 From 3d48cb74816d8468f0235ce9a867a2d7b9832693 Mon Sep 17 00:00:00 2001 From: Rameshkumar Sundaram Date: Wed, 13 Apr 2022 21:58:14 +0530 Subject: nl80211: Parse NL80211_ATTR_HE_BSS_COLOR as a part of nl80211_parse_beacon NL80211_ATTR_HE_BSS_COLOR attribute can be included in both NL80211_CMD_START_AP and NL80211_CMD_SET_BEACON commands. Move he_bss_color from cfg80211_ap_settings to cfg80211_beacon_data and parse NL80211_ATTR_HE_BSS_COLOR as a part of nl80211_parse_beacon() to have bss color settings parsed for both start ap and set beacon commands. Add a new flag he_bss_color_valid to indicate whether NL80211_ATTR_HE_BSS_COLOR attribute is included. Signed-off-by: Rameshkumar Sundaram Link: https://lore.kernel.org/r/1649867295-7204-2-git-send-email-quic_ramess@quicinc.com [fix build ...] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6a3e3f0a8615..97a5804ccdcf 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1183,6 +1183,9 @@ struct cfg80211_mbssid_elems { * Token (measurement type 11) * @lci_len: LCI data length * @civicloc_len: Civic location data length + * @he_bss_color: BSS Color settings + * @he_bss_color_valid: indicates whether bss color + attribute is present in beacon data or not. */ struct cfg80211_beacon_data { const u8 *head, *tail; @@ -1202,6 +1205,8 @@ struct cfg80211_beacon_data { size_t probe_resp_len; size_t lci_len; size_t civicloc_len; + struct cfg80211_he_bss_color he_bss_color; + bool he_bss_color_valid; }; struct mac_address { @@ -1292,7 +1297,6 @@ struct cfg80211_unsol_bcast_probe_resp { * @sae_h2e_required: stations must support direct H2E technique in SAE * @flags: flags, as defined in enum cfg80211_ap_settings_flags * @he_obss_pd: OBSS Packet Detection settings - * @he_bss_color: BSS Color settings * @he_oper: HE operation IE (or %NULL if HE isn't enabled) * @fils_discovery: FILS discovery transmission parameters * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters @@ -1326,7 +1330,6 @@ struct cfg80211_ap_settings { bool twt_responder; u32 flags; struct ieee80211_he_obss_pd he_obss_pd; - struct cfg80211_he_bss_color he_bss_color; struct cfg80211_fils_discovery fils_discovery; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; struct cfg80211_mbssid_config mbssid_config; -- cgit v1.2.3 From aa4a38af97e9f117450bcafd25ef02f9f1a37215 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Mon, 9 May 2022 22:46:41 +0100 Subject: ALSA: hda: cs35l41: Add Support for Interrupts The CS35L41 can produce interrupts on error. When the interrupts occur, the driver will report the error, but errors will only be fixed after playback finishes. Signed-off-by: Stefan Binding Signed-off-by: Vitaly Rodionov Link: https://lore.kernel.org/r/20220509214703.4482-5-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 54 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index dbe8d9c0191b..8e4b125c81c8 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -691,6 +691,13 @@ #define CS35L41_TEMP_WARN_ERR_RLS 0x20 #define CS35L41_TEMP_ERR_RLS 0x40 +#define CS35L41_AMP_SHORT_ERR_RLS_SHIFT 1 +#define CS35L41_BST_SHORT_ERR_RLS_SHIFT 2 +#define CS35L41_BST_OVP_ERR_RLS_SHIFT 3 +#define CS35L41_BST_UVP_ERR_RLS_SHIFT 4 +#define CS35L41_TEMP_WARN_ERR_RLS_SHIFT 5 +#define CS35L41_TEMP_ERR_RLS_SHIFT 6 + #define CS35L41_INT1_MASK_DEFAULT 0x7FFCFE3F #define CS35L41_INT1_UNMASK_PUP 0xFEFFFFFF #define CS35L41_INT1_UNMASK_PDN 0xFF7FFFFF @@ -794,6 +801,53 @@ struct cs35l41_otp_map_element_t { u32 word_offset; }; +/* + * IRQs + */ +#define CS35L41_IRQ(_irq, _name, _hand) \ + { \ + .irq = CS35L41_ ## _irq ## _IRQ,\ + .name = _name, \ + .handler = _hand, \ + } + +struct cs35l41_irq { + int irq; + const char *name; + irqreturn_t (*handler)(int irq, void *data); +}; + +#define CS35L41_REG_IRQ(_reg, _irq) \ + [CS35L41_ ## _irq ## _IRQ] = { \ + .reg_offset = (CS35L41_ ## _reg) - CS35L41_IRQ1_STATUS1,\ + .mask = CS35L41_ ## _irq ## _MASK \ + } + +/* (0x0000E010) CS35L41_IRQ1_STATUS1 */ +#define CS35L41_BST_OVP_ERR_SHIFT 6 +#define CS35L41_BST_OVP_ERR_MASK BIT(CS35L41_BST_OVP_ERR_SHIFT) +#define CS35L41_BST_DCM_UVP_ERR_SHIFT 7 +#define CS35L41_BST_DCM_UVP_ERR_MASK BIT(CS35L41_BST_DCM_UVP_ERR_SHIFT) +#define CS35L41_BST_SHORT_ERR_SHIFT 8 +#define CS35L41_BST_SHORT_ERR_MASK BIT(CS35L41_BST_SHORT_ERR_SHIFT) +#define CS35L41_TEMP_WARN_SHIFT 15 +#define CS35L41_TEMP_WARN_MASK BIT(CS35L41_TEMP_WARN_SHIFT) +#define CS35L41_TEMP_ERR_SHIFT 17 +#define CS35L41_TEMP_ERR_MASK BIT(CS35L41_TEMP_ERR_SHIFT) +#define CS35L41_AMP_SHORT_ERR_SHIFT 31 +#define CS35L41_AMP_SHORT_ERR_MASK BIT(CS35L41_AMP_SHORT_ERR_SHIFT) + +enum cs35l41_irq_list { + CS35L41_BST_OVP_ERR_IRQ, + CS35L41_BST_DCM_UVP_ERR_IRQ, + CS35L41_BST_SHORT_ERR_IRQ, + CS35L41_TEMP_WARN_IRQ, + CS35L41_TEMP_ERR_IRQ, + CS35L41_AMP_SHORT_ERR_IRQ, + + CS35L41_NUM_IRQ +}; + extern struct regmap_config cs35l41_regmap_i2c; extern struct regmap_config cs35l41_regmap_spi; -- cgit v1.2.3 From caf7c1f1de9f011ea0e6494fcb1b2ba203bd3422 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Mon, 9 May 2022 22:46:43 +0100 Subject: ASoC: cs35l41: Move cs35l41_set_cspl_mbox_cmd to shared code This function is used to control the DSP Firmware for cs35l41, and will be needed by the cs35l41 hda driver, when firmware support is added. Signed-off-by: Stefan Binding Signed-off-by: Vitaly Rodionov Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220509214703.4482-7-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index 8e4b125c81c8..2271471225b1 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -801,6 +801,24 @@ struct cs35l41_otp_map_element_t { u32 word_offset; }; +enum cs35l41_cspl_mbox_status { + CSPL_MBOX_STS_RUNNING = 0, + CSPL_MBOX_STS_PAUSED = 1, + CSPL_MBOX_STS_RDY_FOR_REINIT = 2, +}; + +enum cs35l41_cspl_mbox_cmd { + CSPL_MBOX_CMD_NONE = 0, + CSPL_MBOX_CMD_PAUSE = 1, + CSPL_MBOX_CMD_RESUME = 2, + CSPL_MBOX_CMD_REINIT = 3, + CSPL_MBOX_CMD_STOP_PRE_REINIT = 4, + CSPL_MBOX_CMD_HIBERNATE = 5, + CSPL_MBOX_CMD_OUT_OF_HIBERNATE = 6, + CSPL_MBOX_CMD_UNKNOWN_CMD = -1, + CSPL_MBOX_CMD_INVALID_SEQUENCE = -2, +}; + /* * IRQs */ @@ -859,6 +877,8 @@ int cs35l41_set_channels(struct device *dev, struct regmap *reg, unsigned int tx_num, unsigned int *tx_slot, unsigned int rx_num, unsigned int *rx_slot); int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); +int cs35l41_set_cspl_mbox_cmd(struct device *dev, struct regmap *regmap, + enum cs35l41_cspl_mbox_cmd cmd); int cs35l41_init_boost(struct device *dev, struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); bool cs35l41_safe_reset(struct regmap *regmap, enum cs35l41_boost_type b_type); -- cgit v1.2.3 From ff8aad072e6388243fb0c76db4154d0883988384 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Mon, 9 May 2022 22:46:44 +0100 Subject: ASoC: cs35l41: Move cs35l41 fs errata into shared code This sequence is required to setup firmware, and will be needed for hda driver. Signed-off-by: Stefan Binding Signed-off-by: Vitaly Rodionov Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220509214703.4482-8-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index 2271471225b1..d0cfb41495b0 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -879,6 +879,7 @@ int cs35l41_set_channels(struct device *dev, struct regmap *reg, int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); int cs35l41_set_cspl_mbox_cmd(struct device *dev, struct regmap *regmap, enum cs35l41_cspl_mbox_cmd cmd); +int cs35l41_write_fs_errata(struct device *dev, struct regmap *regmap); int cs35l41_init_boost(struct device *dev, struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); bool cs35l41_safe_reset(struct regmap *regmap, enum cs35l41_boost_type b_type); -- cgit v1.2.3 From 0db99577c4cddc45447701aeb7b4d7d7b03d626f Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Mon, 9 May 2022 22:46:45 +0100 Subject: ASoC: cs35l41: Move cs_dsp config struct into shared code This can then be used by HDA code to configure cs_dsp. Signed-off-by: Stefan Binding Signed-off-by: Vitaly Rodionov Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220509214703.4482-9-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index d0cfb41495b0..dd70fb8dd860 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -11,6 +11,7 @@ #define __CS35L41_H #include +#include #define CS35L41_FIRSTREG 0x00000000 #define CS35L41_LASTREG 0x03804FE8 @@ -877,6 +878,7 @@ int cs35l41_set_channels(struct device *dev, struct regmap *reg, unsigned int tx_num, unsigned int *tx_slot, unsigned int rx_num, unsigned int *rx_slot); int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); +void cs35l41_configure_cs_dsp(struct device *dev, struct regmap *reg, struct cs_dsp *dsp); int cs35l41_set_cspl_mbox_cmd(struct device *dev, struct regmap *regmap, enum cs35l41_cspl_mbox_cmd cmd); int cs35l41_write_fs_errata(struct device *dev, struct regmap *regmap); -- cgit v1.2.3 From 44fa75f207d8a106bc75e6230db61e961fdbf8a8 Mon Sep 17 00:00:00 2001 From: Jonas Jelonek Date: Mon, 9 May 2022 19:39:57 +0200 Subject: mac80211: extend current rate control tx status API This patch adds the new struct ieee80211_rate_status and replaces 'struct rate_info *rate' in ieee80211_tx_status with pointer and length annotation. The struct ieee80211_rate_status allows to: (1) receive tx power status feedback for transmit power control (TPC) per packet or packet retry (2) dynamic mapping of wifi chip specific multi-rate retry (mrr) chains with different lengths (3) increase the limit of annotatable rate indices to support IEEE802.11ac rate sets and beyond ieee80211_tx_info, control and status buffer, and ieee80211_tx_rate cannot be used to achieve these goals due to fixed size limitations. Our new struct contains a struct rate_info to annotate the rate that was used, retry count of the rate and tx power. It is intended for all information related to RC and TPC that needs to be passed from driver to mac80211 and its RC/TPC algorithms like Minstrel_HT. It corresponds to one stage in an mrr. Multiple subsequent instances of this struct can be included in struct ieee80211_tx_status via a pointer and a length variable. Those instances can be allocated on-stack. The former reference to a single instance of struct rate_info is replaced with our new annotation. An extension is introduced to struct ieee80211_hw. There are two new members called 'tx_power_levels' and 'max_txpwr_levels_idx' acting as a tx power level table. When a wifi device is registered, the driver shall supply all supported power levels in this list. This allows to support several quirks like differing power steps in power level ranges or alike. TPC can use this for algorithm and thus be designed more abstract instead of handling all possible step widths individually. Further mandatory changes in status.c, mt76 and ath11k drivers due to the removal of 'struct rate_info *rate' are also included. status.c already uses the information in ieee80211_tx_status->rate in radiotap, this is now changed to use ieee80211_rate_status->rate_idx. mt76 driver already uses struct rate_info to pass the tx rate to status path. The new members of the ieee80211_tx_status are set to NULL and 0 because the previously passed rate is not relevant to rate control and accurate information is passed via tx_info->status.rates. For ath11k, the txrate can be passed via this struct because ath11k uses firmware RC and thus the information does not interfere with software RC. Compile-Tested: current wireless-next tree with all flags on Tested-on: Xiaomi 4A Gigabit (MediaTek MT7603E, MT7612E) with OpenWrt Linux 5.10.113 Signed-off-by: Jonas Jelonek Link: https://lore.kernel.org/r/20220509173958.1398201-2-jelonek.jonas@gmail.com Signed-off-by: Johannes Berg --- include/net/mac80211.h | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 944b31f0eb0d..ebadb2103968 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1143,20 +1143,41 @@ ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info) return info->tx_time_est << 2; } +/*** + * struct ieee80211_rate_status - mrr stage for status path + * + * This struct is used in struct ieee80211_tx_status to provide drivers a + * dynamic way to report about used rates and power levels per packet. + * + * @rate_idx The actual used rate. + * @try_count How often the rate was tried. + * @tx_power_idx An idx into the ieee80211_hw->tx_power_levels list of the + * corresponding wifi hardware. The idx shall point to the power level + * that was used when sending the packet. + */ +struct ieee80211_rate_status { + struct rate_info rate_idx; + u8 try_count; + u8 tx_power_idx; +}; + /** * struct ieee80211_tx_status - extended tx status info for rate control * * @sta: Station that the packet was transmitted for * @info: Basic tx status information * @skb: Packet skb (can be NULL if not provided by the driver) - * @rate: The TX rate that was used when sending the packet + * @rates: Mrr stages that were used when sending the packet + * @n_rates: Number of mrr stages (count of instances for @rates) * @free_list: list where processed skbs are stored to be free'd by the driver */ struct ieee80211_tx_status { struct ieee80211_sta *sta; struct ieee80211_tx_info *info; struct sk_buff *skb; - struct rate_info *rate; + struct ieee80211_rate_status *rates; + u8 n_rates; + struct list_head *free_list; }; @@ -2657,6 +2678,12 @@ enum ieee80211_hw_flags { * refilling deficit of each TXQ. * * @max_mtu: the max mtu could be set. + * + * @tx_power_levels: a list of power levels supported by the wifi hardware. + * The power levels can be specified either as integer or fractions. + * The power level at idx 0 shall be the maximum positive power level. + * + * @max_txpwr_levels_idx: the maximum valid idx of 'tx_power_levels' list. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -2695,6 +2722,8 @@ struct ieee80211_hw { u8 tx_sk_pacing_shift; u8 weight_multiplier; u32 max_mtu; + const s8 *tx_power_levels; + u8 max_txpwr_levels_idx; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, -- cgit v1.2.3 From 89527be8d8d672773eeaec910118a6e84fb597e3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:33:56 -0700 Subject: net: add IFLA_TSO_{MAX_SIZE|SEGS} attributes New netlink attributes IFLA_TSO_MAX_SIZE and IFLA_TSO_MAX_SEGS are used to report to user-space the device TSO limits. ip -d link sh dev eth1 ... tso_max_size 65536 tso_max_segs 65535 Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index d1e600816b82..5f58dcfe2787 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -368,6 +368,8 @@ enum { IFLA_PARENT_DEV_NAME, IFLA_PARENT_DEV_BUS_NAME, IFLA_GRO_MAX_SIZE, + IFLA_TSO_MAX_SIZE, + IFLA_TSO_MAX_SEGS, __IFLA_MAX }; -- cgit v1.2.3 From 7c4e983c4f3cf94fcd879730c6caa877e0768a4d Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 13 May 2022 11:33:57 -0700 Subject: net: allow gso_max_size to exceed 65536 The code for gso_max_size was added originally to allow for debugging and workaround of buggy devices that couldn't support TSO with blocks 64K in size. The original reason for limiting it to 64K was because that was the existing limits of IPv4 and non-jumbogram IPv6 length fields. With the addition of Big TCP we can remove this limit and allow the value to potentially go up to UINT_MAX and instead be limited by the tso_max_size value. So in order to support this we need to go through and clean up the remaining users of the gso_max_size value so that the values will cap at 64K for non-TCPv6 flows. In addition we can clean up the GSO_MAX_SIZE value so that 64K becomes GSO_LEGACY_MAX_SIZE and UINT_MAX will now be the upper limit for GSO_MAX_SIZE. v6: (edumazet) fixed a compile error if CONFIG_IPV6=n, in a new sk_trim_gso_size() helper. netif_set_tso_max_size() caps the requested TSO size with GSO_MAX_SIZE. Signed-off-by: Alexander Duyck Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 536321691c72..ce780e352f43 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2272,7 +2272,9 @@ struct net_device { const struct rtnl_link_ops *rtnl_link_ops; /* for setting kernel sock attribute on TCP connection setup */ -#define GSO_MAX_SIZE 65536 +#define GSO_LEGACY_MAX_SIZE 65536u +#define GSO_MAX_SIZE UINT_MAX + unsigned int gso_max_size; #define TSO_LEGACY_MAX_SIZE 65536 #define TSO_MAX_SIZE UINT_MAX -- cgit v1.2.3 From 34b92e8d19da1e44070dc0ecc2747871469ac534 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:33:58 -0700 Subject: net: limit GSO_MAX_SIZE to 524280 bytes Make sure we will not overflow shinfo->gso_segs Minimal TCP MSS size is 8 bytes, and shinfo->gso_segs is a 16bit field. TCP_MIN_GSO_SIZE is currently defined in include/net/tcp.h, it seems cleaner to not bring tcp details into include/linux/netdevice.h Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ce780e352f43..fd38847d0dc7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2272,14 +2272,17 @@ struct net_device { const struct rtnl_link_ops *rtnl_link_ops; /* for setting kernel sock attribute on TCP connection setup */ +#define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u -#define GSO_MAX_SIZE UINT_MAX +/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), + * and shinfo->gso_segs is a 16bit field. + */ +#define GSO_MAX_SIZE (8 * GSO_MAX_SEGS) unsigned int gso_max_size; #define TSO_LEGACY_MAX_SIZE 65536 #define TSO_MAX_SIZE UINT_MAX unsigned int tso_max_size; -#define GSO_MAX_SEGS 65535 u16 gso_max_segs; #define TSO_MAX_SEGS U16_MAX u16 tso_max_segs; -- cgit v1.2.3 From 7c96d8ec96bb71aac54c9f872aaa65d7411ab864 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:34:00 -0700 Subject: ipv6: add struct hop_jumbo_hdr definition Following patches will need to add and remove local IPv6 jumbogram options to enable BIG TCP. Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/ipv6.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 213612f1680c..63d019953c47 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -151,6 +151,17 @@ struct frag_hdr { __be32 identification; }; +/* + * Jumbo payload option, as described in RFC 2675 2. + */ +struct hop_jumbo_hdr { + u8 nexthdr; + u8 hdrlen; + u8 tlv_type; /* IPV6_TLV_JUMBO, 0xC2 */ + u8 tlv_len; /* 4 */ + __be32 jumbo_payload_len; +}; + #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 -- cgit v1.2.3 From 09f3d1a3a52c696208008618a67e2c7c3fb16d41 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:34:01 -0700 Subject: ipv6/gso: remove temporary HBH/jumbo header ipv6 tcp and gro stacks will soon be able to build big TCP packets, with an added temporary Hop By Hop header. If GSO is involved for these large packets, we need to remove the temporary HBH header before segmentation happens. v2: perform HBH removal from ipv6_gso_segment() instead of skb_segment() (Alexander feedback) Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/ipv6.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 63d019953c47..b6df0314aa02 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -467,6 +467,39 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt); +/* This helper is specialized for BIG TCP needs. + * It assumes the hop_jumbo_hdr will immediately follow the IPV6 header. + * It assumes headers are already in skb->head. + * Returns 0, or IPPROTO_TCP if a BIG TCP packet is there. + */ +static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) +{ + const struct hop_jumbo_hdr *jhdr; + const struct ipv6hdr *nhdr; + + if (likely(skb->len <= GRO_MAX_SIZE)) + return 0; + + if (skb->protocol != htons(ETH_P_IPV6)) + return 0; + + if (skb_network_offset(skb) + + sizeof(struct ipv6hdr) + + sizeof(struct hop_jumbo_hdr) > skb_headlen(skb)) + return 0; + + nhdr = ipv6_hdr(skb); + + if (nhdr->nexthdr != NEXTHDR_HOP) + return 0; + + jhdr = (const struct hop_jumbo_hdr *) (nhdr + 1); + if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 || + jhdr->nexthdr != IPPROTO_TCP) + return 0; + return jhdr->nexthdr; +} + static inline bool ipv6_accept_ra(struct inet6_dev *idev) { /* If forwarding is enabled, RA are not accepted unless the special -- cgit v1.2.3 From 0fe79f28bfaf73b66b7b1562d2468f94aa03bd12 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 13 May 2022 11:34:03 -0700 Subject: net: allow gro_max_size to exceed 65536 Allow the gro_max_size to exceed a value larger than 65536. There weren't really any external limitations that prevented this other than the fact that IPv4 only supports a 16 bit length field. Since we have the option of adding a hop-by-hop header for IPv6 we can allow IPv6 to exceed this value and for IPv4 and non-TCP flows we can cap things at 65536 via a constant rather than relying on gro_max_size. [edumazet] limit GRO_MAX_SIZE to (8 * 65535) to avoid overflows. Signed-off-by: Alexander Duyck Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +++++- include/net/ipv6.h | 2 +- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fd38847d0dc7..d57ce248004c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2161,7 +2161,11 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; int napi_defer_hard_irqs; -#define GRO_MAX_SIZE 65536 +#define GRO_LEGACY_MAX_SIZE 65536u +/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), + * and shinfo->gso_segs is a 16bit field. + */ +#define GRO_MAX_SIZE (8 * 65535u) unsigned int gro_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index b6df0314aa02..5b38bf1a586b 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -477,7 +477,7 @@ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) const struct hop_jumbo_hdr *jhdr; const struct ipv6hdr *nhdr; - if (likely(skb->len <= GRO_MAX_SIZE)) + if (likely(skb->len <= GRO_LEGACY_MAX_SIZE)) return 0; if (skb->protocol != htons(ETH_P_IPV6)) -- cgit v1.2.3 From 80e425b613421911f89664663a7060216abcaed2 Mon Sep 17 00:00:00 2001 From: Coco Li Date: Fri, 13 May 2022 11:34:04 -0700 Subject: ipv6: Add hop-by-hop header to jumbograms in ip6_output Instead of simply forcing a 0 payload_len in IPv6 header, implement RFC 2675 and insert a custom extension header. Note that only TCP stack is currently potentially generating jumbograms, and that this extension header is purely local, it wont be sent on a physical link. This is needed so that packet capture (tcpdump and friends) can properly dissect these large packets. Signed-off-by: Coco Li Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ec5ca392eaa3..38c8203d52cb 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -145,6 +145,7 @@ struct inet6_skb_parm { #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 #define IP6SKB_SEG6 256 +#define IP6SKB_FAKEJUMBO 512 }; #if defined(CONFIG_NET_L3_MASTER_DEV) -- cgit v1.2.3 From 4c971d2f3548e4f11b1460ac048f5307e4b39fdb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:55:41 -0700 Subject: net: annotate races around sk->sk_bound_dev_if UDP sendmsg() is lockless, and reads sk->sk_bound_dev_if while this field can be changed by another thread. Adds minimal annotations to avoid KCSAN splats for UDP. Following patches will add more annotations to potential lockless readers. BUG: KCSAN: data-race in __ip6_datagram_connect / udpv6_sendmsg write to 0xffff888136d47a94 of 4 bytes by task 7681 on cpu 0: __ip6_datagram_connect+0x6e2/0x930 net/ipv6/datagram.c:221 ip6_datagram_connect+0x2a/0x40 net/ipv6/datagram.c:272 inet_dgram_connect+0x107/0x190 net/ipv4/af_inet.c:576 __sys_connect_file net/socket.c:1900 [inline] __sys_connect+0x197/0x1b0 net/socket.c:1917 __do_sys_connect net/socket.c:1927 [inline] __se_sys_connect net/socket.c:1924 [inline] __x64_sys_connect+0x3d/0x50 net/socket.c:1924 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x50 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888136d47a94 of 4 bytes by task 7670 on cpu 1: udpv6_sendmsg+0xc60/0x16e0 net/ipv6/udp.c:1436 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:652 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmmsg+0x267/0x4c0 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x50 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x00000000 -> 0xffffff9b Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 7670 Comm: syz-executor.3 Tainted: G W 5.18.0-rc1-syzkaller-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 I chose to not add Fixes: tag because race has minor consequences and stable teams busy enough. Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- include/net/sock.h | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 3984f2c39c4b..8ad04f60b413 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -93,7 +93,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->sockc.mark = inet->sk.sk_mark; ipcm->sockc.tsflags = inet->sk.sk_tsflags; - ipcm->oif = inet->sk.sk_bound_dev_if; + ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; } diff --git a/include/net/sock.h b/include/net/sock.h index 01edfde4257d..72ca97ccb460 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2875,13 +2875,14 @@ static inline void sk_pacing_shift_update(struct sock *sk, int val) */ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) { + int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); int mdif; - if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif) + if (!bound_dev_if || bound_dev_if == dif) return true; mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); - if (mdif && mdif == sk->sk_bound_dev_if) + if (mdif && mdif == bound_dev_if) return true; return false; -- cgit v1.2.3 From fdb5fd7f736ec7ae9fb36d2842ea6d9ebc4e7269 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:55:43 -0700 Subject: tcp: sk->sk_bound_dev_if once in inet_request_bound_dev_if() inet_request_bound_dev_if() reads sk->sk_bound_dev_if twice while listener socket is not locked. Another cpu could change this field under us. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 234d70ae5f4c..c1b5dcd6597c 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -116,14 +116,15 @@ static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) static inline int inet_request_bound_dev_if(const struct sock *sk, struct sk_buff *skb) { + int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); - if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) + if (!bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) return l3mdev_master_ifindex_by_index(net, skb->skb_iif); #endif - return sk->sk_bound_dev_if; + return bound_dev_if; } static inline int inet_sk_bound_l3mdev(const struct sock *sk) -- cgit v1.2.3 From 5d368f03280d3678433a7f119efe15dfbbb87bc8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:55:49 -0700 Subject: ipv6: add READ_ONCE(sk->sk_bound_dev_if) in INET6_MATCH() INET6_MATCH() runs without holding a lock on the socket. We probably need to annotate most reads. This patch makes INET6_MATCH() an inline function to ease our changes. v2: inline function only defined if IS_ENABLED(CONFIG_IPV6) Change the name to inet6_match(), this is no longer a macro. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_hashtables.h | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 81b965953036..f259e1ae14ba 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -103,15 +103,25 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, const int dif); int inet6_hash(struct sock *sk); -#endif /* IS_ENABLED(CONFIG_IPV6) */ -#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif, __sdif) \ - (((__sk)->sk_portpair == (__ports)) && \ - ((__sk)->sk_family == AF_INET6) && \ - ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \ - ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \ - (((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ - net_eq(sock_net(__sk), (__net))) +static inline bool inet6_match(struct net *net, const struct sock *sk, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + const __portpair ports, + const int dif, const int sdif) +{ + int bound_dev_if; + + if (!net_eq(sock_net(sk), net) || + sk->sk_family != AF_INET6 || + sk->sk_portpair != ports || + !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) || + !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) + return false; + + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + return bound_dev_if == dif || bound_dev_if == sdif; +} +#endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _INET6_HASHTABLES_H */ -- cgit v1.2.3 From eda090c31fe923ab9463b884469744ec903ab0cc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:55:50 -0700 Subject: inet: rename INET_MATCH() This is no longer a macro, but an inlined function. INET_MATCH() -> inet_match() Signed-off-by: Eric Dumazet Suggested-by: Olivier Hartkopp Suggested-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 59d72024ad1d..ebfa3df6f8dc 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -267,7 +267,7 @@ static inline struct sock *inet_lookup_listener(struct net *net, ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ -static inline bool INET_MATCH(struct net *net, const struct sock *sk, +static inline bool inet_match(struct net *net, const struct sock *sk, const __addrpair cookie, const __portpair ports, int dif, int sdif) { -- cgit v1.2.3 From 7ebd3f3ee51a9e02994cd0a1be44fbd325d1e0dc Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 13 May 2022 11:03:38 +0800 Subject: net: skb: change the definition SKB_DR_SET() The SKB_DR_OR() is used to set the drop reason to a value when it is not set or specified yet. SKB_NOT_DROPPED_YET should also be considered as not set. Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9d82a8b6c8f1..5a2b29df6cab 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -510,7 +510,8 @@ enum skb_drop_reason { (name = SKB_DROP_REASON_##reason) #define SKB_DR_OR(name, reason) \ do { \ - if (name == SKB_DROP_REASON_NOT_SPECIFIED) \ + if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ + name == SKB_NOT_DROPPED_YET) \ SKB_DR_SET(name, reason); \ } while (0) -- cgit v1.2.3 From 97e719a82b43c6c2bb5eebdb3c5d479a332ac2ac Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 15 May 2022 21:24:53 -0700 Subject: net: fix possible race in skb_attempt_defer_free() A cpu can observe sd->defer_count reaching 128, and call smp_call_function_single_async() Problem is that the remote CPU can clear sd->defer_count before the IPI is run/acknowledged. Other cpus can queue more packets and also decide to call smp_call_function_single_async() while the pending IPI was not yet delivered. This is a common issue with smp_call_function_single_async(). Callers must ensure correct synchronization and serialization. I triggered this issue while experimenting smaller threshold. Performing the call to smp_call_function_single_async() under sd->defer_lock protection did not solve the problem. Commit 5a18ceca6350 ("smp: Allow smp_call_function_single_async() to insert locked csd") replaced an informative WARN_ON_ONCE() with a return of -EBUSY, which is often ignored. Test of CSD_FLAG_LOCK presence is racy anyway. Fixes: 68822bdf76f1 ("net: generalize skb freeing deferral to per-cpu lists") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d57ce248004c..cbaf312e365b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3136,6 +3136,7 @@ struct softnet_data { /* Another possibly contended cache line */ spinlock_t defer_lock ____cacheline_aligned_in_smp; int defer_count; + int defer_ipi_scheduled; struct sk_buff *defer_list; call_single_data_t defer_csd; }; -- cgit v1.2.3 From cf2df74e202d81b09f09d84c2d8903e0e87e9274 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 9 May 2022 14:26:15 +0200 Subject: net: fix dev_fill_forward_path with pppoe + bridge When calling dev_fill_forward_path on a pppoe device, the provided destination address is invalid. In order for the bridge fdb lookup to succeed, the pppoe code needs to update ctx->daddr to the correct value. Fix this by storing the address inside struct net_device_path_ctx Fixes: f6efc675c9dd ("net: ppp: resolve forwarding path for bridge pppoe devices") Signed-off-by: Felix Fietkau Signed-off-by: Pablo Neira Ayuso --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b1fbe21650bb..f736c020cde2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -900,7 +900,7 @@ struct net_device_path_stack { struct net_device_path_ctx { const struct net_device *dev; - const u8 *daddr; + u8 daddr[ETH_ALEN]; int num_vlans; struct { -- cgit v1.2.3 From d265929930e2ffafc744c0ae05fb70acd53be1ee Mon Sep 17 00:00:00 2001 From: William Tu Date: Wed, 4 May 2022 08:35:59 -0700 Subject: netfilter: nf_conncount: reduce unnecessary GC Currently nf_conncount can trigger garbage collection (GC) at multiple places. Each GC process takes a spin_lock_bh to traverse the nf_conncount_list. We found that when testing port scanning use two parallel nmap, because the number of connection increase fast, the nf_conncount_count and its subsequent call to __nf_conncount_add take too much time, causing several CPU lockup. This happens when user set the conntrack limit to +20,000, because the larger the limit, the longer the list that GC has to traverse. The patch mitigate the performance issue by avoiding unnecessary GC with a timestamp. Whenever nf_conncount has done a GC, a timestamp is updated, and beforce the next time GC is triggered, we make sure it's more than a jiffies. By doin this we can greatly reduce the CPU cycles and avoid the softirq lockup. To reproduce it in OVS, $ ovs-appctl dpctl/ct-set-limits zone=1,limit=20000 $ ovs-appctl dpctl/ct-get-limits At another machine, runs two nmap $ nmap -p1- $ nmap -p1- Signed-off-by: William Tu Co-authored-by: Yifeng Sun Reported-by: Greg Rose Suggested-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_count.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index 9645b47fa7e4..e227d997fc71 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -10,6 +10,7 @@ struct nf_conncount_data; struct nf_conncount_list { spinlock_t list_lock; + u32 last_gc; /* jiffies at most recent gc */ struct list_head head; /* connections with the same filtering key */ unsigned int count; /* length of list */ }; -- cgit v1.2.3 From 9db69df4bdd37eb1f65b6931ee067fb15b9a4d5c Mon Sep 17 00:00:00 2001 From: TingHan Shen Date: Thu, 12 May 2022 16:22:13 +0800 Subject: firmware: mediatek: Add adsp ipc protocol interface Some of mediatek processors contain the Tensilica HiFix DSP for audio processing. The communication between Host CPU and DSP firmware is taking place using a shared memory area for message passing. ADSP IPC protocol offers (send/recv) interfaces using mediatek-mailbox APIs. We use two mbox channels to implement a request-reply protocol. Signed-off-by: Allen-KH Cheng Signed-off-by: TingHan Shen Reviewed-by: Pierre-Louis Bossart Reviewed-by: Curtis Malainey Reviewed-by: Tzung-Bi Shih Reviewed-by: YC Hung Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20220512082215.3018-2-tinghan.shen@mediatek.com Signed-off-by: Mark Brown --- include/linux/firmware/mediatek/mtk-adsp-ipc.h | 65 ++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) create mode 100644 include/linux/firmware/mediatek/mtk-adsp-ipc.h (limited to 'include') diff --git a/include/linux/firmware/mediatek/mtk-adsp-ipc.h b/include/linux/firmware/mediatek/mtk-adsp-ipc.h new file mode 100644 index 000000000000..28fd313340b8 --- /dev/null +++ b/include/linux/firmware/mediatek/mtk-adsp-ipc.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 MediaTek Inc. + */ + +#ifndef MTK_ADSP_IPC_H +#define MTK_ADSP_IPC_H + +#include +#include +#include +#include + +#define MTK_ADSP_IPC_REQ 0 +#define MTK_ADSP_IPC_RSP 1 +#define MTK_ADSP_IPC_OP_REQ 0x1 +#define MTK_ADSP_IPC_OP_RSP 0x2 + +enum { + MTK_ADSP_MBOX_REPLY, + MTK_ADSP_MBOX_REQUEST, + MTK_ADSP_MBOX_NUM, +}; + +struct mtk_adsp_ipc; + +struct mtk_adsp_ipc_ops { + void (*handle_reply)(struct mtk_adsp_ipc *ipc); + void (*handle_request)(struct mtk_adsp_ipc *ipc); +}; + +struct mtk_adsp_chan { + struct mtk_adsp_ipc *ipc; + struct mbox_client cl; + struct mbox_chan *ch; + char *name; + int idx; +}; + +struct mtk_adsp_ipc { + struct mtk_adsp_chan chans[MTK_ADSP_MBOX_NUM]; + struct device *dev; + struct mtk_adsp_ipc_ops *ops; + void *private_data; +}; + +static inline void mtk_adsp_ipc_set_data(struct mtk_adsp_ipc *ipc, void *data) +{ + if (!ipc) + return; + + ipc->private_data = data; +} + +static inline void *mtk_adsp_ipc_get_data(struct mtk_adsp_ipc *ipc) +{ + if (!ipc) + return NULL; + + return ipc->private_data; +} + +int mtk_adsp_ipc_send(struct mtk_adsp_ipc *ipc, unsigned int idx, uint32_t op); + +#endif /* MTK_ADSP_IPC_H */ -- cgit v1.2.3 From 64c917d1cfd70ff827c9ea37277a97762ea372d4 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Fri, 13 May 2022 10:05:30 +0100 Subject: ASoC: core: Correct spelling fliped -> flipped Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20220513090532.1450944-1-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index f906e5a70830..f20f5f890794 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1259,7 +1259,7 @@ int snd_soc_of_parse_audio_routing(struct snd_soc_card *card, const char *propname); int snd_soc_of_parse_aux_devs(struct snd_soc_card *card, const char *propname); -unsigned int snd_soc_daifmt_clock_provider_fliped(unsigned int dai_fmt); +unsigned int snd_soc_daifmt_clock_provider_flipped(unsigned int dai_fmt); unsigned int snd_soc_daifmt_clock_provider_from_bitmap(unsigned int bit_frame); unsigned int snd_soc_daifmt_parse_format(struct device_node *np, const char *prefix); -- cgit v1.2.3 From 20492a62b99bd4367b79a76ca288d018f11980db Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 16 May 2022 13:02:24 +0100 Subject: KVM: arm64: pmu: Restore compilation when HW_PERF_EVENTS isn't selected Moving kvm_pmu_events into the vcpu (and refering to it) broke the somewhat unusual case where the kernel has no support for a PMU at all. In order to solve this, move things around a bit so that we can easily avoid refering to the pmu structure outside of PMU-aware code. As a bonus, pmu.c isn't compiled in when HW_PERF_EVENTS isn't selected. Reported-by: kernel test robot Reviewed-by: Fuad Tabba Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/202205161814.KQHpOzsJ-lkp@intel.com --- include/kvm/arm_pmu.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 35a0903cae32..c0b868ce6a8f 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -72,6 +72,25 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu); + +struct kvm_pmu_events *kvm_get_pmu_events(void); +void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu); +void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu); + +#define kvm_vcpu_has_pmu(vcpu) \ + (test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features)) + +/* + * Updates the vcpu's view of the pmu events for this cpu. + * Must be called before every vcpu run after disabling interrupts, to ensure + * that an interrupt cannot fire and update the structure. + */ +#define kvm_pmu_update_vcpu_events(vcpu) \ + do { \ + if (!has_vhe() && kvm_vcpu_has_pmu(vcpu)) \ + vcpu->arch.pmu.events = *kvm_get_pmu_events(); \ + } while (0) + #else struct kvm_pmu { }; @@ -133,6 +152,11 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) return 0; } +#define kvm_vcpu_has_pmu(vcpu) ({ false; }) +static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {} +static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} +static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} + #endif #endif -- cgit v1.2.3 From 7f8d12ea96352275c2850c24a1367166179392d2 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Tue, 29 Mar 2022 15:55:59 +0900 Subject: fs: add a lockdep check function for sb_start_write() Add a function sb_write_started() to allow callers to verify if sb_start_write() is properly called. It will be used for assertion in btrfs. Reviewed-by: Filipe Manana Signed-off-by: Naohiro Aota Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..01d61984ce7a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1708,6 +1708,11 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) +static inline bool sb_write_started(const struct super_block *sb) +{ + return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1); +} + /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to -- cgit v1.2.3 From a31b4a4368d28c5e780f0906588fbd1dcfe4ad54 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 18 Apr 2022 06:43:09 +0200 Subject: btrfs: simplify WQ_HIGHPRI handling in struct btrfs_workqueue Just let the one caller that wants optional WQ_HIGHPRI handling allocate a separate btrfs_workqueue for that. This allows to rename struct __btrfs_workqueue to btrfs_workqueue, remove a pointer indirection and separate allocation for all btrfs_workqueue users and generally simplify the code. Reviewed-by: Qu Wenruo Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index f068ff30d654..290f07eb050a 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -24,7 +24,7 @@ struct btrfs_free_cluster; struct map_lookup; struct extent_buffer; struct btrfs_work; -struct __btrfs_workqueue; +struct btrfs_workqueue; struct btrfs_qgroup_extent_record; struct btrfs_qgroup; struct extent_io_tree; @@ -1457,42 +1457,36 @@ DEFINE_EVENT(btrfs__work, btrfs_ordered_sched, TP_ARGS(work) ); -DECLARE_EVENT_CLASS(btrfs__workqueue, +DECLARE_EVENT_CLASS(btrfs_workqueue, - TP_PROTO(const struct __btrfs_workqueue *wq, - const char *name, int high), + TP_PROTO(const struct btrfs_workqueue *wq, const char *name), - TP_ARGS(wq, name, high), + TP_ARGS(wq, name), TP_STRUCT__entry_btrfs( __field( const void *, wq ) __string( name, name ) - __field( int , high ) ), TP_fast_assign_btrfs(btrfs_workqueue_owner(wq), __entry->wq = wq; __assign_str(name, name); - __entry->high = high; ), - TP_printk_btrfs("name=%s%s wq=%p", __get_str(name), - __print_flags(__entry->high, "", - {(WQ_HIGHPRI), "-high"}), + TP_printk_btrfs("name=%s wq=%p", __get_str(name), __entry->wq) ); -DEFINE_EVENT(btrfs__workqueue, btrfs_workqueue_alloc, +DEFINE_EVENT(btrfs_workqueue, btrfs_workqueue_alloc, - TP_PROTO(const struct __btrfs_workqueue *wq, - const char *name, int high), + TP_PROTO(const struct btrfs_workqueue *wq, const char *name), - TP_ARGS(wq, name, high) + TP_ARGS(wq, name) ); -DECLARE_EVENT_CLASS(btrfs__workqueue_done, +DECLARE_EVENT_CLASS(btrfs_workqueue_done, - TP_PROTO(const struct __btrfs_workqueue *wq), + TP_PROTO(const struct btrfs_workqueue *wq), TP_ARGS(wq), @@ -1507,9 +1501,9 @@ DECLARE_EVENT_CLASS(btrfs__workqueue_done, TP_printk_btrfs("wq=%p", __entry->wq) ); -DEFINE_EVENT(btrfs__workqueue_done, btrfs_workqueue_destroy, +DEFINE_EVENT(btrfs_workqueue_done, btrfs_workqueue_destroy, - TP_PROTO(const struct __btrfs_workqueue *wq), + TP_PROTO(const struct btrfs_workqueue *wq), TP_ARGS(wq) ); -- cgit v1.2.3 From f04fbcc64e4be16185151f9fca44ea1b3d074bd0 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 20 Apr 2022 16:08:27 +0800 Subject: btrfs: move definition of btrfs_raid_types to volumes.h It's only internally used as another way to represent btrfs profiles, it's not exposed through any on-disk format, in fact this btrfs_raid_types is diverted from the on-disk format values. Furthermore, since it's internal structure, its definition can change in the future. Reviewed-by: Johannes Thumshirn Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index b069752a8ecf..d4117152d907 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -880,19 +880,6 @@ struct btrfs_dev_replace_item { #define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ BTRFS_SPACE_INFO_GLOBAL_RSV) -enum btrfs_raid_types { - BTRFS_RAID_RAID10, - BTRFS_RAID_RAID1, - BTRFS_RAID_DUP, - BTRFS_RAID_RAID0, - BTRFS_RAID_SINGLE, - BTRFS_RAID_RAID5, - BTRFS_RAID_RAID6, - BTRFS_RAID_RAID1C3, - BTRFS_RAID_RAID1C4, - BTRFS_NR_RAID_TYPES -}; - #define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \ BTRFS_BLOCK_GROUP_SYSTEM | \ BTRFS_BLOCK_GROUP_METADATA) -- cgit v1.2.3 From 908c54909ae72dcbf1d7e1440f7297187d06c275 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 5 May 2022 15:11:10 -0500 Subject: iomap: allow the file system to provide a bio_set for direct I/O Allow the file system to provide a specific bio_set for allocating direct I/O bios. This will allow file systems that use the ->submit_io hook to stash away additional information for file system use. To make use of this additional space for information in the completion path, the file system needs to override the ->bi_end_io callback and then call back into iomap, so export iomap_dio_bio_end_io for that. Reviewed-by: Darrick J. Wong Reviewed-by: Nikolay Borisov Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/iomap.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index b76f0dd149fb..cf903f1a230f 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -320,6 +320,16 @@ struct iomap_dio_ops { unsigned flags); void (*submit_io)(const struct iomap_iter *iter, struct bio *bio, loff_t file_offset); + + /* + * Filesystems wishing to attach private information to a direct io bio + * must provide a ->submit_io method that attaches the additional + * information to the bio and changes the ->bi_end_io callback to a + * custom function. This function should, at a minimum, perform any + * relevant post-processing of the bio and end with a call to + * iomap_dio_bio_end_io. + */ + struct bio_set *bio_set; }; /* @@ -349,6 +359,7 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, size_t done_before); ssize_t iomap_dio_complete(struct iomap_dio *dio); +void iomap_dio_bio_end_io(struct bio *bio); #ifdef CONFIG_SWAP struct file; -- cgit v1.2.3 From 786f847f43a54e63161474fe85a4f1764d871a35 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 5 May 2022 15:11:11 -0500 Subject: iomap: add per-iomap_iter private data Allow the file system to keep state for all iterations. For now only wire it up for direct I/O as there is an immediate need for it there. Reviewed-by: Darrick J. Wong Reviewed-by: Nikolay Borisov Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/iomap.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index cf903f1a230f..5b6f64f4d771 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -188,6 +188,7 @@ struct iomap_iter { unsigned flags; struct iomap iomap; struct iomap srcmap; + void *private; }; int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); @@ -354,10 +355,10 @@ struct iomap_dio_ops { ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags, size_t done_before); + unsigned int dio_flags, void *private, size_t done_before); struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags, size_t done_before); + unsigned int dio_flags, void *private, size_t done_before); ssize_t iomap_dio_complete(struct iomap_dio *dio); void iomap_dio_bio_end_io(struct bio *bio); -- cgit v1.2.3 From 1c05bb947f6464756174830b778aabf8f9d6ed0e Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Mon, 16 May 2022 12:12:02 +0200 Subject: include/uapi/linux/vfio.h: Fix trivial typo - _IORW should be _IOWR instead There is no macro called _IORW, so use _IOWR in the comment instead. Signed-off-by: Thomas Huth Reviewed-by: Cornelia Huck Link: https://lore.kernel.org/r/20220516101202.88373-1-thuth@redhat.com Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index fea86061b44e..733a1cddde30 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -643,7 +643,7 @@ enum { }; /** - * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IORW(VFIO_TYPE, VFIO_BASE + 12, + * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 12, * struct vfio_pci_hot_reset_info) * * Return: 0 on success, -errno on failure: @@ -770,7 +770,7 @@ struct vfio_device_ioeventfd { #define VFIO_DEVICE_IOEVENTFD _IO(VFIO_TYPE, VFIO_BASE + 16) /** - * VFIO_DEVICE_FEATURE - _IORW(VFIO_TYPE, VFIO_BASE + 17, + * VFIO_DEVICE_FEATURE - _IOWR(VFIO_TYPE, VFIO_BASE + 17, * struct vfio_device_feature) * * Get, set, or probe feature data of the device. The feature is selected -- cgit v1.2.3 From b3fdf9398a16f01dc013967a4ab25e99c3f4fc12 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Mon, 16 May 2022 11:21:46 -0700 Subject: x86/mce: relocate set{clear}_mce_nospec() functions Relocate the twin mce functions to arch/x86/mm/pat/set_memory.c file where they belong. While at it, fixup a function name in a comment. Reviewed-by: Christoph Hellwig Reviewed-by: Dan Williams Signed-off-by: Jane Chu Acked-by: Borislav Petkov Cc: Stephen Rothwell [sfr: gate {set,clear}_mce_nospec() by CONFIG_X86_64] Link: https://lore.kernel.org/r/165272527328.90175.8336008202048685278.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/set_memory.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index f36be5166c19..683a6c3f7179 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -42,14 +42,14 @@ static inline bool can_set_direct_map(void) #endif #endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */ -#ifndef set_mce_nospec +#ifdef CONFIG_X86_64 +int set_mce_nospec(unsigned long pfn, bool unmap); +int clear_mce_nospec(unsigned long pfn); +#else static inline int set_mce_nospec(unsigned long pfn, bool unmap) { return 0; } -#endif - -#ifndef clear_mce_nospec static inline int clear_mce_nospec(unsigned long pfn) { return 0; -- cgit v1.2.3 From 5898b43af954b83c4a4ee4ab85c4dbafa395822a Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Mon, 16 May 2022 11:38:10 -0700 Subject: mce: fix set_mce_nospec to always unmap the whole page The set_memory_uc() approach doesn't work well in all cases. As Dan pointed out when "The VMM unmapped the bad page from guest physical space and passed the machine check to the guest." "The guest gets virtual #MC on an access to that page. When the guest tries to do set_memory_uc() and instructs cpa_flush() to do clean caches that results in taking another fault / exception perhaps because the VMM unmapped the page from the guest." Since the driver has special knowledge to handle NP or UC, mark the poisoned page with NP and let driver handle it when it comes down to repair. Please refer to discussions here for more details. https://lore.kernel.org/all/CAPcyv4hrXPb1tASBZUg-GgdVs0OOFKXMXLiHmktg_kFi7YBMyQ@mail.gmail.com/ Now since poisoned page is marked as not-present, in order to avoid writing to a not-present page and trigger kernel Oops, also fix pmem_do_write(). Fixes: 284ce4011ba6 ("x86/memory_failure: Introduce {set, clear}_mce_nospec()") Reviewed-by: Christoph Hellwig Reviewed-by: Dan Williams Signed-off-by: Jane Chu Acked-by: Tony Luck Link: https://lore.kernel.org/r/165272615484.103830.2563950688772226611.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/set_memory.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index 683a6c3f7179..369769ce7399 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -43,10 +43,10 @@ static inline bool can_set_direct_map(void) #endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */ #ifdef CONFIG_X86_64 -int set_mce_nospec(unsigned long pfn, bool unmap); +int set_mce_nospec(unsigned long pfn); int clear_mce_nospec(unsigned long pfn); #else -static inline int set_mce_nospec(unsigned long pfn, bool unmap) +static inline int set_mce_nospec(unsigned long pfn) { return 0; } -- cgit v1.2.3 From 7466886b400b1904ce30fa311904849e314a2cf4 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 2 May 2022 11:36:25 +0200 Subject: kunit: take `kunit_assert` as `const` The `kunit_do_failed_assertion` function passes its `struct kunit_assert` argument to `kunit_fail`. This one, in turn, calls its `format` field passing the assert again as a `const` pointer. Therefore, the whole chain may be made `const`. Signed-off-by: Miguel Ojeda Reviewed-by: Daniel Latypov Reviewed-by: Kees Cook Signed-off-by: Shuah Khan --- include/kunit/test.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 607e02b8e167..8ffcd7de9607 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -508,7 +508,7 @@ void __printf(2, 3) kunit_log_append(char *log, const char *fmt, ...); void kunit_do_failed_assertion(struct kunit *test, const struct kunit_loc *loc, enum kunit_assert_type type, - struct kunit_assert *assert, + const struct kunit_assert *assert, const char *fmt, ...); #define KUNIT_ASSERTION(test, assert_type, pass, assert_class, INITIALIZER, fmt, ...) do { \ -- cgit v1.2.3 From 9f39d36530e5678d092d53c5c2c60d82b4dcc169 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Sat, 7 May 2022 13:55:58 +0200 Subject: can: isotp: add support for transmission without flow control Usually the ISO 15765-2 protocol is a point-to-point protocol to transfer segmented PDUs to a dedicated receiver. This receiver sends a flow control message to specify protocol options and timings (e.g. block size / STmin). The so called functional addressing communication allows a 1:N communication but is limited to a single frame length. This new CAN_ISOTP_CF_BROADCAST allows an unconfirmed 1:N communication with PDU length that would not fit into a single frame. This feature is not covered by the ISO 15765-2 standard. Link: https://lore.kernel.org/all/20220507115558.19065-1-socketcan@hartkopp.net Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/isotp.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h index 590f8aea2b6d..439c982f7e81 100644 --- a/include/uapi/linux/can/isotp.h +++ b/include/uapi/linux/can/isotp.h @@ -124,18 +124,19 @@ struct can_isotp_ll_options { /* flags for isotp behaviour */ -#define CAN_ISOTP_LISTEN_MODE 0x001 /* listen only (do not send FC) */ -#define CAN_ISOTP_EXTEND_ADDR 0x002 /* enable extended addressing */ -#define CAN_ISOTP_TX_PADDING 0x004 /* enable CAN frame padding tx path */ -#define CAN_ISOTP_RX_PADDING 0x008 /* enable CAN frame padding rx path */ -#define CAN_ISOTP_CHK_PAD_LEN 0x010 /* check received CAN frame padding */ -#define CAN_ISOTP_CHK_PAD_DATA 0x020 /* check received CAN frame padding */ -#define CAN_ISOTP_HALF_DUPLEX 0x040 /* half duplex error state handling */ -#define CAN_ISOTP_FORCE_TXSTMIN 0x080 /* ignore stmin from received FC */ -#define CAN_ISOTP_FORCE_RXSTMIN 0x100 /* ignore CFs depending on rx stmin */ -#define CAN_ISOTP_RX_EXT_ADDR 0x200 /* different rx extended addressing */ -#define CAN_ISOTP_WAIT_TX_DONE 0x400 /* wait for tx completion */ -#define CAN_ISOTP_SF_BROADCAST 0x800 /* 1-to-N functional addressing */ +#define CAN_ISOTP_LISTEN_MODE 0x0001 /* listen only (do not send FC) */ +#define CAN_ISOTP_EXTEND_ADDR 0x0002 /* enable extended addressing */ +#define CAN_ISOTP_TX_PADDING 0x0004 /* enable CAN frame padding tx path */ +#define CAN_ISOTP_RX_PADDING 0x0008 /* enable CAN frame padding rx path */ +#define CAN_ISOTP_CHK_PAD_LEN 0x0010 /* check received CAN frame padding */ +#define CAN_ISOTP_CHK_PAD_DATA 0x0020 /* check received CAN frame padding */ +#define CAN_ISOTP_HALF_DUPLEX 0x0040 /* half duplex error state handling */ +#define CAN_ISOTP_FORCE_TXSTMIN 0x0080 /* ignore stmin from received FC */ +#define CAN_ISOTP_FORCE_RXSTMIN 0x0100 /* ignore CFs depending on rx stmin */ +#define CAN_ISOTP_RX_EXT_ADDR 0x0200 /* different rx extended addressing */ +#define CAN_ISOTP_WAIT_TX_DONE 0x0400 /* wait for tx completion */ +#define CAN_ISOTP_SF_BROADCAST 0x0800 /* 1-to-N functional addressing */ +#define CAN_ISOTP_CF_BROADCAST 0x1000 /* 1-to-N transmission w/o FC */ /* protocol machine default values */ -- cgit v1.2.3 From e511c4a3d2a1f64aafc1f5df37a2ffcf7ef91b55 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Fri, 13 May 2022 15:10:58 -0700 Subject: dax: introduce DAX_RECOVERY_WRITE dax access mode Up till now, dax_direct_access() is used implicitly for normal access, but for the purpose of recovery write, dax range with poison is requested. To make the interface clear, introduce enum dax_access_mode { DAX_ACCESS, DAX_RECOVERY_WRITE, } where DAX_ACCESS is used for normal dax access, and DAX_RECOVERY_WRITE is used for dax recovery write. Suggested-by: Dan Williams Signed-off-by: Jane Chu Reviewed-by: Christoph Hellwig Cc: Mike Snitzer Reviewed-by: Vivek Goyal Link: https://lore.kernel.org/r/165247982851.52965.11024212198889762949.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/dax.h | 9 +++++++-- include/linux/device-mapper.h | 4 +++- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dax.h b/include/linux/dax.h index 9fc5f99a0ae2..3f1339bce3c0 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,6 +14,11 @@ struct iomap_ops; struct iomap_iter; struct iomap; +enum dax_access_mode { + DAX_ACCESS, + DAX_RECOVERY_WRITE, +}; + struct dax_operations { /* * direct_access: translate a device-relative @@ -21,7 +26,7 @@ struct dax_operations { * number of pages available for DAX at that pfn. */ long (*direct_access)(struct dax_device *, pgoff_t, long, - void **, pfn_t *); + enum dax_access_mode, void **, pfn_t *); /* * Validate whether this device is usable as an fsdax backing * device. @@ -178,7 +183,7 @@ static inline void dax_read_unlock(int id) bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, - void **kaddr, pfn_t *pfn); + enum dax_access_mode mode, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index c2a3758c4aaa..acdedda0d12b 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -20,6 +20,7 @@ struct dm_table; struct dm_report_zones_args; struct mapped_device; struct bio_vec; +enum dax_access_mode; /* * Type of table, mapped_device's mempool and request_queue @@ -146,7 +147,8 @@ typedef int (*dm_busy_fn) (struct dm_target *ti); * >= 0 : the number of bytes accessible at the address */ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, - long nr_pages, void **kaddr, pfn_t *pfn); + long nr_pages, enum dax_access_mode node, void **kaddr, + pfn_t *pfn); typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); -- cgit v1.2.3 From 047218ec904da19c45c4a70274fc3f818a1fcba1 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Fri, 22 Apr 2022 16:45:06 -0600 Subject: dax: add .recovery_write dax_operation Introduce dax_recovery_write() operation. The function is used to recover a dax range that contains poison. Typical use case is when a user process receives a SIGBUS with si_code BUS_MCEERR_AR indicating poison(s) in a dax range, in response, the user process issues a pwrite() to the page-aligned dax range, thus clears the poison and puts valid data in the range. Reviewed-by: Christoph Hellwig Signed-off-by: Jane Chu Link: https://lore.kernel.org/r/20220422224508.440670-6-jane.chu@oracle.com Signed-off-by: Dan Williams --- include/linux/dax.h | 13 +++++++++++++ include/linux/device-mapper.h | 9 +++++++++ 2 files changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/dax.h b/include/linux/dax.h index 3f1339bce3c0..e7b81634c52a 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -35,6 +35,12 @@ struct dax_operations { sector_t, sector_t); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); + /* + * recovery_write: recover a poisoned range by DAX device driver + * capable of clearing poison. + */ + size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *iter); }; #if IS_ENABLED(CONFIG_DAX) @@ -45,6 +51,8 @@ void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); bool dax_synchronous(struct dax_device *dax_dev); void set_dax_synchronous(struct dax_device *dax_dev); +size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); /* * Check if given mapping is supported by the file / underlying device. */ @@ -92,6 +100,11 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, { return !(vma->vm_flags & VM_SYNC); } +static inline size_t dax_recovery_write(struct dax_device *dax_dev, + pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) +{ + return 0; +} #endif void set_dax_nocache(struct dax_device *dax_dev); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index acdedda0d12b..47a01c7cffdf 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -152,6 +152,14 @@ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); +/* + * Returns: + * != 0 : number of bytes transferred + * 0 : recovery write failed + */ +typedef size_t (*dm_dax_recovery_write_fn)(struct dm_target *ti, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); + void dm_error(const char *message); struct dm_dev { @@ -201,6 +209,7 @@ struct target_type { dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; dm_dax_zero_page_range_fn dax_zero_page_range; + dm_dax_recovery_write_fn dax_recovery_write; /* For internal device-mapper use. */ struct list_head list; -- cgit v1.2.3 From 89af2ce2d95c80f6da9388d9da2e35c84c2573b1 Mon Sep 17 00:00:00 2001 From: Ricardo Martinez Date: Fri, 13 May 2022 10:34:00 -0700 Subject: net: skb: Remove skb_data_area_size() skb_data_area_size() is not needed. As Jakub pointed out [1]: For Rx, drivers can use the size passed during skb allocation or use skb_tailroom(). For Tx, drivers should use skb_headlen(). [1] https://lore.kernel.org/netdev/CAHNKnsTmH-rGgWi3jtyC=ktM1DW2W1VJkYoTMJV2Z_Bt498bsg@mail.gmail.com/ Signed-off-by: Ricardo Martinez Reviewed-by: Andy Shevchenko Reviewed-by: Sergey Ryazanov Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5a2b29df6cab..da96f0d3e753 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1765,11 +1765,6 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif -static inline unsigned int skb_data_area_size(struct sk_buff *skb) -{ - return skb_end_pointer(skb) - skb->data; -} - struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); -- cgit v1.2.3 From 848b89778ed53e6c9f9e3ed01c90109ee970b3d1 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Fri, 6 May 2022 12:57:55 +0200 Subject: scsi: fcoe: Add a local_lock to fcoe_percpu fcoe_get_paged_crc_eof() relies on the caller having preemption disabled to ensure the per-CPU fcoe_percpu context remains valid throughout the call. This is done by either holding spinlocks (such as bnx2fc_global_lock or qedf_global_lock) or the get_cpu() from fcoe_alloc_paged_crc_eof(). This last one breaks PREEMPT_RT semantics as there can be memory allocation and end up sleeping in atomic contexts. Introduce a local_lock_t to struct fcoe_percpu that will keep the non-RT case the same, mapping to preempt_disable/enable, while RT will use a per-CPU spinlock allowing the region to be preemptible but still maintain CPU locality. The other users of fcoe_percpu are already safe in this regard and do not require local_lock()ing. Link: https://lore.kernel.org/r/20211117025956.79616-3-dave@stgolabs.net Link: https://lore.kernel.org/r/20220506105758.283887-2-bigeasy@linutronix.de Acked-by: Sebastian Andrzej Siewior Signed-off-by: Davidlohr Bueso Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Martin K. Petersen --- include/scsi/libfcoe.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index fac8e89aed81..6e79fb87fea2 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -326,6 +327,7 @@ struct fcoe_percpu_s { struct sk_buff_head fcoe_rx_list; struct page *crc_eof_page; int crc_eof_offset; + local_lock_t lock; }; /** -- cgit v1.2.3 From e626f37e657adbab2a7abe51480925891662a5f3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 May 2022 14:29:43 +0200 Subject: nvme: split the enum used for various register constants Instead of having one big enum add one for each register or field. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Chaitanya Kulkarni --- include/linux/nvme.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index bbabdc7600da..5f6d432fa06a 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -204,8 +204,9 @@ enum { NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, - NVME_CAP_CSS_NVM = 1 << 0, - NVME_CAP_CSS_CSI = 1 << 6, +}; + +enum { NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, @@ -214,10 +215,18 @@ enum { NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, NVME_CSTS_SHST_MASK = 3 << 2, +}; + +enum { NVME_CMBMSC_CRE = 1 << 0, NVME_CMBMSC_CMSE = 1 << 1, }; +enum { + NVME_CAP_CSS_NVM = 1 << 0, + NVME_CAP_CSS_CSI = 1 << 6, +}; + struct nvme_id_power_state { __le16 max_power; /* centiwatts */ __u8 rsvd2; -- cgit v1.2.3 From 5e052a4d2a47eec3ac1e707ed415b2948bba54ef Mon Sep 17 00:00:00 2001 From: Xin Ji Date: Fri, 22 Apr 2022 10:47:15 +0200 Subject: media: media/v4l2-core: Add enum V4L2_FWNODE_BUS_TYPE_DPI As V4L2_FWNODE_BUS_TYPE_PARALLEL is not used for DPI interface, this patch add V4L2_FWNODE_BUS_TYPE_DPI for video DPI interface. Signed-off-by: Xin Ji Reviewed-by: Robert Foss Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-fwnode.h | 2 ++ include/media/v4l2-mediabus.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h index feb132df45a3..15e4ab672223 100644 --- a/include/media/v4l2-fwnode.h +++ b/include/media/v4l2-fwnode.h @@ -173,6 +173,7 @@ struct v4l2_fwnode_connector { * @V4L2_FWNODE_BUS_TYPE_CSI2_DPHY: MIPI CSI-2 bus, D-PHY physical layer * @V4L2_FWNODE_BUS_TYPE_PARALLEL: Camera Parallel Interface bus * @V4L2_FWNODE_BUS_TYPE_BT656: BT.656 video format bus-type + * @V4L2_FWNODE_BUS_TYPE_DPI: Video Parallel Interface bus * @NR_OF_V4L2_FWNODE_BUS_TYPE: Number of bus-types */ enum v4l2_fwnode_bus_type { @@ -183,6 +184,7 @@ enum v4l2_fwnode_bus_type { V4L2_FWNODE_BUS_TYPE_CSI2_DPHY, V4L2_FWNODE_BUS_TYPE_PARALLEL, V4L2_FWNODE_BUS_TYPE_BT656, + V4L2_FWNODE_BUS_TYPE_DPI, NR_OF_V4L2_FWNODE_BUS_TYPE }; diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index e0db3bcff9ed..f67a74daf799 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -129,6 +129,7 @@ struct v4l2_mbus_config_mipi_csi1 { * @V4L2_MBUS_CCP2: CCP2 (Compact Camera Port 2) * @V4L2_MBUS_CSI2_DPHY: MIPI CSI-2 serial interface, with D-PHY * @V4L2_MBUS_CSI2_CPHY: MIPI CSI-2 serial interface, with C-PHY + * @V4L2_MBUS_DPI: MIPI VIDEO DPI interface * @V4L2_MBUS_INVALID: invalid bus type (keep as last) */ enum v4l2_mbus_type { @@ -139,6 +140,7 @@ enum v4l2_mbus_type { V4L2_MBUS_CCP2, V4L2_MBUS_CSI2_DPHY, V4L2_MBUS_CSI2_CPHY, + V4L2_MBUS_DPI, V4L2_MBUS_INVALID, }; -- cgit v1.2.3 From a34cc79c9623ea2c12eca22c16e70047fbd7c26e Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 26 Apr 2022 09:02:38 +0200 Subject: media: Add bus type to frame descriptors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the media bus type to the frame descriptor. CSI-2 specific information will be added in next patch to the frame descriptor. - Make the bus type a named enum Signed-off-by: Sakari Ailus Reviewed-by: Niklas Söderlund Signed-off-by: Jacopo Mondi Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 33a7201edb61..544ddd1bdcbe 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -344,12 +344,32 @@ struct v4l2_mbus_frame_desc_entry { #define V4L2_FRAME_DESC_ENTRY_MAX 4 +/** + * enum v4l2_mbus_frame_desc_type - media bus frame description type + * + * @V4L2_MBUS_FRAME_DESC_TYPE_UNDEFINED: + * Undefined frame desc type. Drivers should not use this, it is + * for backwards compatibility. + * @V4L2_MBUS_FRAME_DESC_TYPE_PARALLEL: + * Parallel media bus. + * @V4L2_MBUS_FRAME_DESC_TYPE_CSI2: + * CSI-2 media bus. Frame desc parameters must be set in + * &struct v4l2_mbus_frame_desc_entry->csi2. + */ +enum v4l2_mbus_frame_desc_type { + V4L2_MBUS_FRAME_DESC_TYPE_UNDEFINED = 0, + V4L2_MBUS_FRAME_DESC_TYPE_PARALLEL, + V4L2_MBUS_FRAME_DESC_TYPE_CSI2, +}; + /** * struct v4l2_mbus_frame_desc - media bus data frame description + * @type: type of the bus (enum v4l2_mbus_frame_desc_type) * @entry: frame descriptors array * @num_entries: number of entries in @entry array */ struct v4l2_mbus_frame_desc { + enum v4l2_mbus_frame_desc_type type; struct v4l2_mbus_frame_desc_entry entry[V4L2_FRAME_DESC_ENTRY_MAX]; unsigned short num_entries; }; -- cgit v1.2.3 From 897c45df291ff063d6a0acb20b3a0c276c6adf6a Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 26 Apr 2022 09:02:39 +0200 Subject: media: Add CSI-2 bus configuration to frame descriptors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add CSI-2 bus specific configuration to the frame descriptors. This allows obtaining the virtual channel and data type information for each stream the transmitter is sending. Signed-off-by: Sakari Ailus Reviewed-by: Niklas Söderlund Reviewed-by: Jacopo Mondi Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 544ddd1bdcbe..b661e1817470 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -312,6 +312,17 @@ struct v4l2_subdev_audio_ops { int (*s_stream)(struct v4l2_subdev *sd, int enable); }; +/** + * struct v4l2_mbus_frame_desc_entry_csi2 + * + * @vc: CSI-2 virtual channel + * @dt: CSI-2 data type ID + */ +struct v4l2_mbus_frame_desc_entry_csi2 { + u8 vc; + u8 dt; +}; + /** * enum v4l2_mbus_frame_desc_flags - media bus frame description flags * @@ -335,11 +346,16 @@ enum v4l2_mbus_frame_desc_flags { * %FRAME_DESC_FL_BLOB is not set. * @length: number of octets per frame, valid if @flags * %V4L2_MBUS_FRAME_DESC_FL_LEN_MAX is set. + * @bus: Bus-specific frame descriptor parameters + * @bus.csi2: CSI-2-specific bus configuration */ struct v4l2_mbus_frame_desc_entry { enum v4l2_mbus_frame_desc_flags flags; u32 pixelcode; u32 length; + union { + struct v4l2_mbus_frame_desc_entry_csi2 csi2; + } bus; }; #define V4L2_FRAME_DESC_ENTRY_MAX 4 -- cgit v1.2.3 From e74e476834f810d99261988e501d460235269158 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 29 Apr 2022 00:52:06 +0200 Subject: media: Add MIPI CSI-2 28 bits per pixel raw data type Add CSI-2 data type for 28 bits per pixel data. Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/mipi-csi2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/mipi-csi2.h b/include/media/mipi-csi2.h index 392794e5badd..c3d8f12234b1 100644 --- a/include/media/mipi-csi2.h +++ b/include/media/mipi-csi2.h @@ -31,6 +31,7 @@ #define MIPI_CSI2_DT_RGB565 0x22 #define MIPI_CSI2_DT_RGB666 0x23 #define MIPI_CSI2_DT_RGB888 0x24 +#define MIPI_CSI2_DT_RAW28 0x26 #define MIPI_CSI2_DT_RAW24 0x27 #define MIPI_CSI2_DT_RAW6 0x28 #define MIPI_CSI2_DT_RAW7 0x29 -- cgit v1.2.3 From b87f5e25b2f9deb503a61c6957c7b1680d91cfea Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Fri, 6 May 2022 01:03:48 +0200 Subject: media: uapi: Add IPU3 packed Y10 format Some platforms with an Intel IPU3 have an IR sensor producing 10 bit greyscale format data that is transmitted over a CSI-2 bus to a CIO2 device - this packs the data into 32 bytes per 25 pixels. Add an entry to the uAPI header defining that format. Signed-off-by: Daniel Scally Acked-by: Andy Shevchenko Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 6d465dc443b7..343b95107fce 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -569,6 +569,7 @@ struct v4l2_pix_format { /* Grey bit-packed formats */ #define V4L2_PIX_FMT_Y10BPACK v4l2_fourcc('Y', '1', '0', 'B') /* 10 Greyscale bit-packed */ #define V4L2_PIX_FMT_Y10P v4l2_fourcc('Y', '1', '0', 'P') /* 10 Greyscale, MIPI RAW10 packed */ +#define V4L2_PIX_FMT_IPU3_Y10 v4l2_fourcc('i', 'p', '3', 'y') /* IPU3 packed 10-bit greyscale */ /* Palette formats */ #define V4L2_PIX_FMT_PAL8 v4l2_fourcc('P', 'A', 'L', '8') /* 8 8-bit palette */ @@ -749,7 +750,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_QC08C v4l2_fourcc('Q', '0', '8', 'C') /* Qualcomm 8-bit compressed */ #define V4L2_PIX_FMT_QC10C v4l2_fourcc('Q', '1', '0', 'C') /* Qualcomm 10-bit compressed */ -/* 10bit raw bayer packed, 32 bytes for every 25 pixels, last LSB 6 bits unused */ +/* 10bit raw packed, 32 bytes for every 25 pixels, last LSB 6 bits unused */ #define V4L2_PIX_FMT_IPU3_SBGGR10 v4l2_fourcc('i', 'p', '3', 'b') /* IPU3 packed 10-bit BGGR bayer */ #define V4L2_PIX_FMT_IPU3_SGBRG10 v4l2_fourcc('i', 'p', '3', 'g') /* IPU3 packed 10-bit GBRG bayer */ #define V4L2_PIX_FMT_IPU3_SGRBG10 v4l2_fourcc('i', 'p', '3', 'G') /* IPU3 packed 10-bit GRBG bayer */ -- cgit v1.2.3 From 2e2c3d6c0ef88ffac0d6b5079ee88cf8408f5f3b Mon Sep 17 00:00:00 2001 From: Nicolas Dufresne Date: Fri, 13 May 2022 22:29:03 +0200 Subject: media: h264: Use v4l2_h264_reference for reflist In preparation for adding field decoding support, convert the byte arrays for reflist into array of struct v4l2_h264_reference. That struct will allow us to mark which field of the reference picture is being referenced. [hverkuil: top_field_order_cnt -> pic_order_count] Signed-off-by: Nicolas Dufresne Reviewed-by: Ezequiel Garcia Tested-by: Dmitry Osipenko Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-h264.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index 4b1c71c935e0..ef9a894e3c32 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -37,7 +37,7 @@ struct v4l2_h264_reflist_builder { u16 longterm : 1; } refs[V4L2_H264_NUM_DPB_ENTRIES]; s32 cur_pic_order_count; - u8 unordered_reflist[V4L2_H264_NUM_DPB_ENTRIES]; + struct v4l2_h264_reference unordered_reflist[V4L2_H264_NUM_DPB_ENTRIES]; u8 num_valid; }; @@ -51,10 +51,10 @@ v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b, * v4l2_h264_build_b_ref_lists() - Build the B0/B1 reference lists * * @builder: reference list builder context - * @b0_reflist: 16-bytes array used to store the B0 reference list. Each entry - * is an index in the DPB - * @b1_reflist: 16-bytes array used to store the B1 reference list. Each entry - * is an index in the DPB + * @b0_reflist: 16 sized array used to store the B0 reference list. Each entry + * is a v4l2_h264_reference structure + * @b1_reflist: 16 sized array used to store the B1 reference list. Each entry + * is a v4l2_h264_reference structure * * This functions builds the B0/B1 reference lists. This procedure is described * in section '8.2.4 Decoding process for reference picture lists construction' @@ -63,14 +63,15 @@ v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b, */ void v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, - u8 *b0_reflist, u8 *b1_reflist); + struct v4l2_h264_reference *b0_reflist, + struct v4l2_h264_reference *b1_reflist); /** * v4l2_h264_build_p_ref_list() - Build the P reference list * * @builder: reference list builder context - * @reflist: 16-bytes array used to store the P reference list. Each entry - * is an index in the DPB + * @reflist: 16 sized array used to store the P reference list. Each entry + * is a v4l2_h264_reference structure * * This functions builds the P reference lists. This procedure is describe in * section '8.2.4 Decoding process for reference picture lists construction' @@ -79,6 +80,6 @@ v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, */ void v4l2_h264_build_p_ref_list(const struct v4l2_h264_reflist_builder *builder, - u8 *reflist); + struct v4l2_h264_reference *reflist); #endif /* _MEDIA_V4L2_H264_H */ -- cgit v1.2.3 From 26e4520509ffa4bec3d679f7cb3de9adfabef4b3 Mon Sep 17 00:00:00 2001 From: Nicolas Dufresne Date: Fri, 13 May 2022 22:29:04 +0200 Subject: media: h264: Increase reference lists size to 32 This is to accommodate support for field decoding, which splits the top and the bottom references into the reference list. Signed-off-by: Nicolas Dufresne Reviewed-by: Sebastian Fricke Reviewed-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-h264.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index ef9a894e3c32..e282fb16ac58 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -37,7 +37,7 @@ struct v4l2_h264_reflist_builder { u16 longterm : 1; } refs[V4L2_H264_NUM_DPB_ENTRIES]; s32 cur_pic_order_count; - struct v4l2_h264_reference unordered_reflist[V4L2_H264_NUM_DPB_ENTRIES]; + struct v4l2_h264_reference unordered_reflist[V4L2_H264_REF_LIST_LEN]; u8 num_valid; }; @@ -51,9 +51,9 @@ v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b, * v4l2_h264_build_b_ref_lists() - Build the B0/B1 reference lists * * @builder: reference list builder context - * @b0_reflist: 16 sized array used to store the B0 reference list. Each entry + * @b0_reflist: 32 sized array used to store the B0 reference list. Each entry * is a v4l2_h264_reference structure - * @b1_reflist: 16 sized array used to store the B1 reference list. Each entry + * @b1_reflist: 32 sized array used to store the B1 reference list. Each entry * is a v4l2_h264_reference structure * * This functions builds the B0/B1 reference lists. This procedure is described @@ -70,7 +70,7 @@ v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, * v4l2_h264_build_p_ref_list() - Build the P reference list * * @builder: reference list builder context - * @reflist: 16 sized array used to store the P reference list. Each entry + * @reflist: 32 sized array used to store the P reference list. Each entry * is a v4l2_h264_reference structure * * This functions builds the P reference lists. This procedure is describe in -- cgit v1.2.3 From adc8a8d6c98a5c996aad41bf1625d87829bd76ba Mon Sep 17 00:00:00 2001 From: Nicolas Dufresne Date: Fri, 13 May 2022 22:29:05 +0200 Subject: media: h264: Store current picture fields This information, also called picture structure, is required in field decoding mode to construct reference lists. Signed-off-by: Nicolas Dufresne Reviewed-by: Sebastian Fricke Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-h264.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index e282fb16ac58..e165a54c68fa 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -21,6 +21,7 @@ * @refs.longterm: set to true for a long term reference * @refs: array of references * @cur_pic_order_count: picture order count of the frame being decoded + * @cur_pic_fields: fields present in the frame being decoded * @unordered_reflist: unordered list of references. Will be used to generate * ordered P/B0/B1 lists * @num_valid: number of valid references in the refs array @@ -36,7 +37,10 @@ struct v4l2_h264_reflist_builder { u32 pic_num; u16 longterm : 1; } refs[V4L2_H264_NUM_DPB_ENTRIES]; + s32 cur_pic_order_count; + u8 cur_pic_fields; + struct v4l2_h264_reference unordered_reflist[V4L2_H264_REF_LIST_LEN]; u8 num_valid; }; -- cgit v1.2.3 From e5991e1fd90295b1eb8326a4a6c09012d6c5fc8d Mon Sep 17 00:00:00 2001 From: Nicolas Dufresne Date: Fri, 13 May 2022 22:29:06 +0200 Subject: media: h264: Store all fields into the unordered list When the current picture is a field, store each field into the unordered_list and preserve both top and bottom picture order count. Signed-off-by: Nicolas Dufresne Reviewed-by: Sebastian Fricke Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-h264.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index e165a54c68fa..4cef717b3f18 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -15,7 +15,8 @@ /** * struct v4l2_h264_reflist_builder - Reference list builder object * - * @refs.pic_order_count: reference picture order count + * @refs.top_field_order_cnt: top field order count + * @refs.bottom_field_order_cnt: bottom field order count * @refs.frame_num: reference frame number * @refs.pic_num: reference picture number * @refs.longterm: set to true for a long term reference @@ -32,7 +33,8 @@ */ struct v4l2_h264_reflist_builder { struct { - s32 pic_order_count; + s32 top_field_order_cnt; + s32 bottom_field_order_cnt; int frame_num; u32 pic_num; u16 longterm : 1; -- cgit v1.2.3 From 6cafdc8cc0da0ddffad25ca9c70bab990ab9130f Mon Sep 17 00:00:00 2001 From: Nicolas Dufresne Date: Fri, 13 May 2022 22:29:08 +0200 Subject: media: h264: Sort p/b reflist using frame_num In the reference list builder, frame_num refers to FrameNumWrap in the spec, which is the same as the pic_num for frame decoding. The same applies for long_term_pic_num and long_term_frame_idx. Sort all type of references by frame_num so the sort can be reused for fields reflist were the sorting is done using frame_num instead. In short, pic_num is never actually used for building reference lists. Signed-off-by: Nicolas Dufresne Reviewed-by: Sebastian Fricke Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-h264.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index 4cef717b3f18..0d9eaa956123 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -18,7 +18,6 @@ * @refs.top_field_order_cnt: top field order count * @refs.bottom_field_order_cnt: bottom field order count * @refs.frame_num: reference frame number - * @refs.pic_num: reference picture number * @refs.longterm: set to true for a long term reference * @refs: array of references * @cur_pic_order_count: picture order count of the frame being decoded @@ -36,7 +35,6 @@ struct v4l2_h264_reflist_builder { s32 top_field_order_cnt; s32 bottom_field_order_cnt; int frame_num; - u32 pic_num; u16 longterm : 1; } refs[V4L2_H264_NUM_DPB_ENTRIES]; -- cgit v1.2.3 From a03dacb0316f74400846aaf144d6c73f4217ca08 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Tue, 2 Mar 2021 15:58:21 +0900 Subject: PM / devfreq: Add cpu based scaling support to passive governor Many CPU architectures have caches that can scale independent of the CPUs. Frequency scaling of the caches is necessary to make sure that the cache is not a performance bottleneck that leads to poor performance and power. The same idea applies for RAM/DDR. To achieve this, this patch adds support for cpu based scaling to the passive governor. This is accomplished by taking the current frequency of each CPU frequency domain and then adjust the frequency of the cache (or any devfreq device) based on the frequency of the CPUs. It listens to CPU frequency transition notifiers to keep itself up to date on the current CPU frequency. To decide the frequency of the device, the governor does one of the following: * Derives the optimal devfreq device opp from required-opps property of the parent cpu opp_table. * Scales the device frequency in proportion to the CPU frequency. So, if the CPUs are running at their max frequency, the device runs at its max frequency. If the CPUs are running at their min frequency, the device runs at its min frequency. It is interpolated for frequencies in between. Tested-by: Chen-Yu Tsai Tested-by: Johnson Wang Signed-off-by: Saravana Kannan [Sibi: Integrated cpu-freqmap governor into passive_governor] Signed-off-by: Sibi Sankar [Chanwoo: Fix conflict with latest code and cleanup code] Signed-off-by: Chanwoo Choi --- include/linux/devfreq.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 142474b4af96..b1e4a6f796ce 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -38,6 +38,7 @@ enum devfreq_timer { struct devfreq; struct devfreq_governor; +struct devfreq_cpu_data; struct thermal_cooling_device; /** @@ -288,6 +289,11 @@ struct devfreq_simple_ondemand_data { #endif #if IS_ENABLED(CONFIG_DEVFREQ_GOV_PASSIVE) +enum devfreq_parent_dev_type { + DEVFREQ_PARENT_DEV, + CPUFREQ_PARENT_DEV, +}; + /** * struct devfreq_passive_data - ``void *data`` fed to struct devfreq * and devfreq_add_device @@ -299,8 +305,11 @@ struct devfreq_simple_ondemand_data { * using governors except for passive governor. * If the devfreq device has the specific method to decide * the next frequency, should use this callback. - * @this: the devfreq instance of own device. - * @nb: the notifier block for DEVFREQ_TRANSITION_NOTIFIER list + * @parent_type: the parent type of the device. + * @this: the devfreq instance of own device. + * @nb: the notifier block for DEVFREQ_TRANSITION_NOTIFIER or + * CPUFREQ_TRANSITION_NOTIFIER list. + * @parent_cpu_data: the state min/max/current frequency of all online cpu's. * * The devfreq_passive_data have to set the devfreq instance of parent * device with governors except for the passive governor. But, don't need to @@ -314,9 +323,13 @@ struct devfreq_passive_data { /* Optional callback to decide the next frequency of passvice device */ int (*get_target_freq)(struct devfreq *this, unsigned long *freq); + /* Should set the type of parent device */ + enum devfreq_parent_dev_type parent_type; + /* For passive governor's internal use. Don't need to set them */ struct devfreq *this; struct notifier_block nb; + struct devfreq_cpu_data *parent_cpu_data[NR_CPUS]; }; #endif -- cgit v1.2.3 From 26984d9d581e5049bd75091d2e789b9cc3ea12e0 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Wed, 27 Apr 2022 03:49:19 +0900 Subject: PM / devfreq: passive: Keep cpufreq_policy for possible cpus The passive governor requires the cpu data to get the next target frequency of devfreq device if depending on cpu. In order to reduce the unnecessary memory data, keep cpufreq_policy data for possible cpus instead of NR_CPU. Tested-by: Chen-Yu Tsai Tested-by: Johnson Wang Signed-off-by: Chanwoo Choi --- include/linux/devfreq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index b1e4a6f796ce..dc10bee75a72 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -309,7 +309,7 @@ enum devfreq_parent_dev_type { * @this: the devfreq instance of own device. * @nb: the notifier block for DEVFREQ_TRANSITION_NOTIFIER or * CPUFREQ_TRANSITION_NOTIFIER list. - * @parent_cpu_data: the state min/max/current frequency of all online cpu's. + * @cpu_data_list: the list of cpu frequency data for all cpufreq_policy. * * The devfreq_passive_data have to set the devfreq instance of parent * device with governors except for the passive governor. But, don't need to @@ -329,7 +329,7 @@ struct devfreq_passive_data { /* For passive governor's internal use. Don't need to set them */ struct devfreq *this; struct notifier_block nb; - struct devfreq_cpu_data *parent_cpu_data[NR_CPUS]; + struct list_head cpu_data_list; }; #endif -- cgit v1.2.3 From ee0e2f51e2115c2578d40e5a8ac33737984fe477 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 17 May 2022 12:43:46 +0200 Subject: cfg80211: fix kernel-doc for cfg80211_beacon_data The kernel-doc comment is formatted badly, resulting in a warning: include/net/cfg80211.h:1188: warning: bad line: [...] Fix that. Reported-by: Stephen Rothwell Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 97a5804ccdcf..cc8a9880b9d6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1185,7 +1185,7 @@ struct cfg80211_mbssid_elems { * @civicloc_len: Civic location data length * @he_bss_color: BSS Color settings * @he_bss_color_valid: indicates whether bss color - attribute is present in beacon data or not. + * attribute is present in beacon data or not. */ struct cfg80211_beacon_data { const u8 *head, *tail; -- cgit v1.2.3 From f1b3b320bd6519b16e3480f74f2926d106e3bcba Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 16 May 2022 12:11:03 +0200 Subject: ASoC: Intel: avs: Generic soc component driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Prepare for concrete PCM operations over HDA, DMIC and I2S interfaces by providing generic soc component implementation. Interface-specific components re-use this code as majority of flow is shared. Signed-off-by: Amadeusz Sławiński Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220516101116.190192-3-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/sound/soc-acpi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index d33cf8df14b1..b38fd25c5729 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -156,6 +156,7 @@ struct snd_soc_acpi_link_adr { * @links: array of link _ADR descriptors, null terminated. * @drv_name: machine driver name * @fw_filename: firmware file name. Used when SOF is not enabled. + * @tplg_filename: topology file name. Used when SOF is not enabled. * @board: board name * @machine_quirk: pointer to quirk, usually based on DMI information when * ACPI ID alone is not sufficient, wrong or misleading @@ -174,6 +175,7 @@ struct snd_soc_acpi_mach { const struct snd_soc_acpi_link_adr *links; const char *drv_name; const char *fw_filename; + const char *tplg_filename; const char *board; struct snd_soc_acpi_mach * (*machine_quirk)(void *arg); const void *quirk_data; -- cgit v1.2.3 From 1affc44ea5dd554c103e0ce1e809f3aa5d942349 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 16 May 2022 12:11:13 +0200 Subject: ASoC: Intel: avs: PCI driver implementation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit HD-Audio bus is a PCI device. Add all functions necessary to probe such device along with its removal sequence. Behaviour implemented for all standard operations is similar to existing solutions: sound/pci/hda and sound/soc/intel/skylake. Signed-off-by: Amadeusz Sławiński Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220516101116.190192-13-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/sound/intel-dsp-config.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/intel-dsp-config.h b/include/sound/intel-dsp-config.h index d4609077c258..34c975910574 100644 --- a/include/sound/intel-dsp-config.h +++ b/include/sound/intel-dsp-config.h @@ -15,7 +15,8 @@ enum { SND_INTEL_DSP_DRIVER_LEGACY, SND_INTEL_DSP_DRIVER_SST, SND_INTEL_DSP_DRIVER_SOF, - SND_INTEL_DSP_DRIVER_LAST = SND_INTEL_DSP_DRIVER_SOF + SND_INTEL_DSP_DRIVER_AVS, + SND_INTEL_DSP_DRIVER_LAST = SND_INTEL_DSP_DRIVER_AVS }; #if IS_ENABLED(CONFIG_SND_INTEL_DSP_CONFIG) -- cgit v1.2.3 From 7c3e9fcad9c7d8bb5d69a576044fb16b1d2e8a01 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Pouiller?= Date: Tue, 17 May 2022 09:27:08 +0200 Subject: dma-buf: fix use of DMA_BUF_SET_NAME_{A,B} in userspace MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The typedefs u32 and u64 are not available in userspace. Thus user get an error he try to use DMA_BUF_SET_NAME_A or DMA_BUF_SET_NAME_B: $ gcc -Wall -c -MMD -c -o ioctls_list.o ioctls_list.c In file included from /usr/include/x86_64-linux-gnu/asm/ioctl.h:1, from /usr/include/linux/ioctl.h:5, from /usr/include/asm-generic/ioctls.h:5, from ioctls_list.c:11: ioctls_list.c:463:29: error: ‘u32’ undeclared here (not in a function) 463 | { "DMA_BUF_SET_NAME_A", DMA_BUF_SET_NAME_A, -1, -1 }, // linux/dma-buf.h | ^~~~~~~~~~~~~~~~~~ ioctls_list.c:464:29: error: ‘u64’ undeclared here (not in a function) 464 | { "DMA_BUF_SET_NAME_B", DMA_BUF_SET_NAME_B, -1, -1 }, // linux/dma-buf.h | ^~~~~~~~~~~~~~~~~~ The issue was initially reported here[1]. [1]: https://github.com/jerome-pouiller/ioctl/pull/14 Signed-off-by: Jérôme Pouiller Reviewed-by: Christian König Fixes: a5bff92eaac4 ("dma-buf: Fix SET_NAME ioctl uapi") CC: stable@vger.kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20220517072708.245265-1-Jerome.Pouiller@silabs.com Signed-off-by: Christian König --- include/uapi/linux/dma-buf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 8e4a2ca0bcbf..b1523cb8ab30 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -92,7 +92,7 @@ struct dma_buf_sync { * between them in actual uapi, they're just different numbers. */ #define DMA_BUF_SET_NAME _IOW(DMA_BUF_BASE, 1, const char *) -#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, u32) -#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, u64) +#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, __u32) +#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, __u64) #endif -- cgit v1.2.3 From 1ad6c3b7ef132e1d8c5d606008069724625c8daf Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 5 Apr 2022 11:24:51 +0200 Subject: hwmon: introduce hwmon_sanitize_name() More and more drivers will check for bad characters in the hwmon name and all are using the same code snippet. Consolidate that code by adding a new hwmon_sanitize_name() function. Signed-off-by: Michael Walle Reviewed-by: Tom Rix Link: https://lore.kernel.org/r/20220405092452.4033674-2-michael@walle.cc Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index eba380b76d15..4efaf06fd2b8 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -461,6 +461,9 @@ void devm_hwmon_device_unregister(struct device *dev); int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel); +char *hwmon_sanitize_name(const char *name); +char *devm_hwmon_sanitize_name(struct device *dev, const char *name); + /** * hwmon_is_bad_char - Is the char invalid in a hwmon name * @ch: the char to be considered -- cgit v1.2.3 From c8383054506c77b814489c09877b5db83fd4abf2 Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 25 Apr 2022 20:21:24 +0800 Subject: cachefiles: notify the user daemon when looking up cookie Fscache/CacheFiles used to serve as a local cache for a remote networking fs. A new on-demand read mode will be introduced for CacheFiles, which can boost the scenario where on-demand read semantics are needed, e.g. container image distribution. The essential difference between these two modes is seen when a cache miss occurs: In the original mode, the netfs will fetch the data from the remote server and then write it to the cache file; in on-demand read mode, fetching the data and writing it into the cache is delegated to a user daemon. As the first step, notify the user daemon when looking up cookie. In this case, an anonymous fd is sent to the user daemon, through which the user daemon can write the fetched data to the cache file. Since the user daemon may move the anonymous fd around, e.g. through dup(), an object ID uniquely identifying the cache file is also attached. Also add one advisory flag (FSCACHE_ADV_WANT_CACHE_SIZE) suggesting that the cache file size shall be retrieved at runtime. This helps the scenario where one cache file contains multiple netfs files, e.g. for the purpose of deduplication. In this case, netfs itself has no idea the size of the cache file, whilst the user daemon should give the hint on it. Signed-off-by: Jeffle Xu Link: https://lore.kernel.org/r/20220509074028.74954-3-jefflexu@linux.alibaba.com Acked-by: David Howells Signed-off-by: Gao Xiang --- include/linux/fscache.h | 1 + include/trace/events/cachefiles.h | 2 ++ include/uapi/linux/cachefiles.h | 50 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 53 insertions(+) create mode 100644 include/uapi/linux/cachefiles.h (limited to 'include') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index e25539072463..72585c9729a2 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -39,6 +39,7 @@ struct fscache_cookie; #define FSCACHE_ADV_SINGLE_CHUNK 0x01 /* The object is a single chunk of data */ #define FSCACHE_ADV_WRITE_CACHE 0x00 /* Do cache if written to locally */ #define FSCACHE_ADV_WRITE_NOCACHE 0x02 /* Don't cache if written to locally */ +#define FSCACHE_ADV_WANT_CACHE_SIZE 0x04 /* Retrieve cache size at runtime */ #define FSCACHE_INVAL_DIO_WRITE 0x01 /* Invalidate due to DIO write */ diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 311c14a20e70..93df9391bd7f 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -31,6 +31,8 @@ enum cachefiles_obj_ref_trace { cachefiles_obj_see_lookup_failed, cachefiles_obj_see_withdraw_cookie, cachefiles_obj_see_withdrawal, + cachefiles_obj_get_ondemand_fd, + cachefiles_obj_put_ondemand_fd, }; enum fscache_why_object_killed { diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h new file mode 100644 index 000000000000..521f2fe4fe9c --- /dev/null +++ b/include/uapi/linux/cachefiles.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_CACHEFILES_H +#define _LINUX_CACHEFILES_H + +#include + +/* + * Fscache ensures that the maximum length of cookie key is 255. The volume key + * is controlled by netfs, and generally no bigger than 255. + */ +#define CACHEFILES_MSG_MAX_SIZE 1024 + +enum cachefiles_opcode { + CACHEFILES_OP_OPEN, +}; + +/* + * Message Header + * + * @msg_id a unique ID identifying this message + * @opcode message type, CACHEFILE_OP_* + * @len message length, including message header and following data + * @object_id a unique ID identifying a cache file + * @data message type specific payload + */ +struct cachefiles_msg { + __u32 msg_id; + __u32 opcode; + __u32 len; + __u32 object_id; + __u8 data[]; +}; + +/* + * @data contains the volume_key followed directly by the cookie_key. volume_key + * is a NUL-terminated string; @volume_key_size indicates the size of the volume + * key in bytes. cookie_key is binary data, which is netfs specific; + * @cookie_key_size indicates the size of the cookie key in bytes. + * + * @fd identifies an anon_fd referring to the cache file. + */ +struct cachefiles_open { + __u32 volume_key_size; + __u32 cookie_key_size; + __u32 fd; + __u32 flags; + __u8 data[]; +}; + +#endif -- cgit v1.2.3 From 324b954ac80cff0d11ddb6bde9b6631e45e98620 Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 25 Apr 2022 20:21:26 +0800 Subject: cachefiles: notify the user daemon when withdrawing cookie Notify the user daemon that cookie is going to be withdrawn, providing a hint that the associated anonymous fd can be closed. Be noted that this is only a hint. The user daemon may close the associated anonymous fd when receiving the CLOSE request, then it will receive another anonymous fd when the cookie gets looked up. Or it may ignore the CLOSE request, and keep writing data through the anonymous fd. However the next time the cookie gets looked up, the user daemon will still receive another new anonymous fd. Signed-off-by: Jeffle Xu Acked-by: David Howells Link: https://lore.kernel.org/r/20220425122143.56815-5-jefflexu@linux.alibaba.com Signed-off-by: Gao Xiang --- include/uapi/linux/cachefiles.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h index 521f2fe4fe9c..37a0071037c8 100644 --- a/include/uapi/linux/cachefiles.h +++ b/include/uapi/linux/cachefiles.h @@ -12,6 +12,7 @@ enum cachefiles_opcode { CACHEFILES_OP_OPEN, + CACHEFILES_OP_CLOSE, }; /* -- cgit v1.2.3 From 9032b6e8589f269743984aac53e82e4835be16dc Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 25 Apr 2022 20:21:27 +0800 Subject: cachefiles: implement on-demand read Implement the data plane of on-demand read mode. The early implementation [1] place the entry to cachefiles_ondemand_read() in fscache_read(). However, fscache_read() can only detect if the requested file range is fully cache miss, whilst we need to notify the user daemon as long as there's a hole inside the requested file range. Thus the entry is now placed in cachefiles_prepare_read(). When working in on-demand read mode, once a hole detected, the read routine will send a READ request to the user daemon. The user daemon needs to fetch the data and write it to the cache file. After sending the READ request, the read routine will hang there, until the READ request is handled by the user daemon. Then it will retry to read from the same file range. If no progress encountered, the read routine will fail then. A new NETFS_SREQ_ONDEMAND flag is introduced to indicate that on-demand read should be done when a cache miss encountered. [1] https://lore.kernel.org/all/20220406075612.60298-6-jefflexu@linux.alibaba.com/ #v8 Signed-off-by: Jeffle Xu Acked-by: David Howells Link: https://lore.kernel.org/r/20220425122143.56815-6-jefflexu@linux.alibaba.com Signed-off-by: Gao Xiang --- include/linux/netfs.h | 1 + include/uapi/linux/cachefiles.h | 17 +++++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c7bf1eaf51d5..057d04efaf79 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -159,6 +159,7 @@ struct netfs_io_subrequest { #define NETFS_SREQ_SHORT_IO 2 /* Set if the I/O was short */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ +#define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ }; enum netfs_io_origin { diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h index 37a0071037c8..78caa73e5343 100644 --- a/include/uapi/linux/cachefiles.h +++ b/include/uapi/linux/cachefiles.h @@ -3,6 +3,7 @@ #define _LINUX_CACHEFILES_H #include +#include /* * Fscache ensures that the maximum length of cookie key is 255. The volume key @@ -13,6 +14,7 @@ enum cachefiles_opcode { CACHEFILES_OP_OPEN, CACHEFILES_OP_CLOSE, + CACHEFILES_OP_READ, }; /* @@ -48,4 +50,19 @@ struct cachefiles_open { __u8 data[]; }; +/* + * @off indicates the starting offset of the requested file range + * @len indicates the length of the requested file range + */ +struct cachefiles_read { + __u64 off; + __u64 len; +}; + +/* + * Reply for READ request + * @arg for this ioctl is the @id field of READ request. + */ +#define CACHEFILES_IOC_READ_COMPLETE _IOW(0x98, 1, int) + #endif -- cgit v1.2.3 From 1519670e4fecc6063fa2f0c10f0666d3331f219b Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 25 Apr 2022 20:21:29 +0800 Subject: cachefiles: add tracepoints for on-demand read mode Add tracepoints for on-demand read mode. Currently following tracepoints are added: OPEN request / COPEN reply CLOSE request READ request / CREAD reply write through anonymous fd release of anonymous fd Signed-off-by: Jeffle Xu Acked-by: David Howells Link: https://lore.kernel.org/r/20220425122143.56815-8-jefflexu@linux.alibaba.com Signed-off-by: Gao Xiang --- include/trace/events/cachefiles.h | 174 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 174 insertions(+) (limited to 'include') diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 93df9391bd7f..d8d4d73fe7b6 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -673,6 +673,180 @@ TRACE_EVENT(cachefiles_io_error, __entry->error) ); +TRACE_EVENT(cachefiles_ondemand_open, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg, + struct cachefiles_open *load), + + TP_ARGS(obj, msg, load), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + __field(unsigned int, fd ) + __field(unsigned int, flags ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + __entry->fd = load->fd; + __entry->flags = load->flags; + ), + + TP_printk("o=%08x mid=%x oid=%x fd=%d f=%x", + __entry->obj, + __entry->msg_id, + __entry->object_id, + __entry->fd, + __entry->flags) + ); + +TRACE_EVENT(cachefiles_ondemand_copen, + TP_PROTO(struct cachefiles_object *obj, unsigned int msg_id, + long len), + + TP_ARGS(obj, msg_id, len), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(long, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg_id; + __entry->len = len; + ), + + TP_printk("o=%08x mid=%x l=%lx", + __entry->obj, + __entry->msg_id, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_close, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg), + + TP_ARGS(obj, msg), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + ), + + TP_printk("o=%08x mid=%x oid=%x", + __entry->obj, + __entry->msg_id, + __entry->object_id) + ); + +TRACE_EVENT(cachefiles_ondemand_read, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg, + struct cachefiles_read *load), + + TP_ARGS(obj, msg, load), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + __field(loff_t, start ) + __field(size_t, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + __entry->start = load->off; + __entry->len = load->len; + ), + + TP_printk("o=%08x mid=%x oid=%x s=%llx l=%zx", + __entry->obj, + __entry->msg_id, + __entry->object_id, + __entry->start, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_cread, + TP_PROTO(struct cachefiles_object *obj, unsigned int msg_id), + + TP_ARGS(obj, msg_id), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg_id; + ), + + TP_printk("o=%08x mid=%x", + __entry->obj, + __entry->msg_id) + ); + +TRACE_EVENT(cachefiles_ondemand_fd_write, + TP_PROTO(struct cachefiles_object *obj, struct inode *backer, + loff_t start, size_t len), + + TP_ARGS(obj, backer, start, len), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, backer ) + __field(loff_t, start ) + __field(size_t, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->backer = backer->i_ino; + __entry->start = start; + __entry->len = len; + ), + + TP_printk("o=%08x iB=%x s=%llx l=%zx", + __entry->obj, + __entry->backer, + __entry->start, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_fd_release, + TP_PROTO(struct cachefiles_object *obj, int object_id), + + TP_ARGS(obj, object_id), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, object_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->object_id = object_id; + ), + + TP_printk("o=%08x oid=%x", + __entry->obj, + __entry->object_id) + ); + #endif /* _TRACE_CACHEFILES_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 7b8b44eb7710e34a1ea5278392417993a549fabf Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 14 May 2022 10:36:58 -0400 Subject: NFSv4: Specify the type of ACL to cache When caching a NFSv4 ACL, we want to specify whether we are caching an NFSv4.0 type acl, the NFSv4.1 dacl or the NFSv4.1 sacl. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs4.h | 2 ++ include/linux/nfs_xdr.h | 7 +++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 5662d8be04eb..8d04b6a5964c 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -451,6 +451,8 @@ enum lock_type4 { #define FATTR4_WORD1_TIME_MODIFY (1UL << 21) #define FATTR4_WORD1_TIME_MODIFY_SET (1UL << 22) #define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23) +#define FATTR4_WORD1_DACL (1UL << 26) +#define FATTR4_WORD1_SACL (1UL << 27) #define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30) #define FATTR4_WORD2_LAYOUT_TYPES (1UL << 0) #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2863e5a69c6a..13d068c57d8d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -800,6 +800,13 @@ struct nfs_setattrargs { const struct nfs4_label *label; }; +enum nfs4_acl_type { + NFS4ACL_NONE = 0, + NFS4ACL_ACL, + NFS4ACL_DACL, + NFS4ACL_SACL, +}; + struct nfs_setaclargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; -- cgit v1.2.3 From db145db021abf75aa1a5810e631425055cfbed47 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 14 May 2022 10:36:59 -0400 Subject: NFSv4: Add encoders/decoders for the NFSv4.1 dacl and sacl attributes Add the ability to set or retrieve the acl using the NFSv4.1 'dacl' and 'sacl' attributes to the NFSv4 xdr encoders/decoders. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 13d068c57d8d..4a8ba84f848e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -810,6 +810,7 @@ enum nfs4_acl_type { struct nfs_setaclargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; + enum nfs4_acl_type acl_type; size_t acl_len; struct page ** acl_pages; }; @@ -821,6 +822,7 @@ struct nfs_setaclres { struct nfs_getaclargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; + enum nfs4_acl_type acl_type; size_t acl_len; struct page ** acl_pages; }; @@ -829,6 +831,7 @@ struct nfs_getaclargs { #define NFS4_ACL_TRUNC 0x0001 /* ACL was truncated */ struct nfs_getaclres { struct nfs4_sequence_res seq_res; + enum nfs4_acl_type acl_type; size_t acl_len; size_t acl_data_offset; int acl_flags; -- cgit v1.2.3 From c81d5bae404abc6b257667e84d39b9b50c7063d4 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 6 May 2022 13:34:41 -0700 Subject: f2fs: do not stop GC when requiring a free section The f2fs_gc uses a bitmap to indicate pinned sections, but when disabling chckpoint, we call f2fs_gc() with NULL_SEGNO which selects the same dirty segment as a victim all the time, resulting in checkpoint=disable failure, for example. Let's pick another one, if we fail to collect it. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 54ec9e543f09..16c67ede85b6 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -645,18 +645,21 @@ TRACE_EVENT(f2fs_background_gc, TRACE_EVENT(f2fs_gc_begin, TP_PROTO(struct super_block *sb, int gc_type, bool no_bg_gc, + unsigned int nr_free_secs, long long dirty_nodes, long long dirty_dents, long long dirty_imeta, unsigned int free_sec, unsigned int free_seg, int reserved_seg, unsigned int prefree_seg), - TP_ARGS(sb, gc_type, no_bg_gc, dirty_nodes, dirty_dents, dirty_imeta, + TP_ARGS(sb, gc_type, no_bg_gc, nr_free_secs, dirty_nodes, + dirty_dents, dirty_imeta, free_sec, free_seg, reserved_seg, prefree_seg), TP_STRUCT__entry( __field(dev_t, dev) __field(int, gc_type) __field(bool, no_bg_gc) + __field(unsigned int, nr_free_secs) __field(long long, dirty_nodes) __field(long long, dirty_dents) __field(long long, dirty_imeta) @@ -670,6 +673,7 @@ TRACE_EVENT(f2fs_gc_begin, __entry->dev = sb->s_dev; __entry->gc_type = gc_type; __entry->no_bg_gc = no_bg_gc; + __entry->nr_free_secs = nr_free_secs; __entry->dirty_nodes = dirty_nodes; __entry->dirty_dents = dirty_dents; __entry->dirty_imeta = dirty_imeta; @@ -679,12 +683,13 @@ TRACE_EVENT(f2fs_gc_begin, __entry->prefree_seg = prefree_seg; ), - TP_printk("dev = (%d,%d), gc_type = %s, no_background_GC = %d, nodes = %lld, " - "dents = %lld, imeta = %lld, free_sec:%u, free_seg:%u, " + TP_printk("dev = (%d,%d), gc_type = %s, no_background_GC = %d, nr_free_secs = %u, " + "nodes = %lld, dents = %lld, imeta = %lld, free_sec:%u, free_seg:%u, " "rsv_seg:%d, prefree_seg:%u", show_dev(__entry->dev), show_gc_type(__entry->gc_type), (__entry->gc_type == BG_GC) ? __entry->no_bg_gc : -1, + __entry->nr_free_secs, __entry->dirty_nodes, __entry->dirty_dents, __entry->dirty_imeta, -- cgit v1.2.3 From 69e9cd66ae1392437234a63a3a1d60b6655f92ef Mon Sep 17 00:00:00 2001 From: Julian Orth Date: Tue, 17 May 2022 12:32:53 +0200 Subject: audit,io_uring,io-wq: call __audit_uring_exit for dummy contexts Not calling the function for dummy contexts will cause the context to not be reset. During the next syscall, this will cause an error in __audit_syscall_entry: WARN_ON(context->context != AUDIT_CTX_UNUSED); WARN_ON(context->name_count); if (context->context != AUDIT_CTX_UNUSED || context->name_count) { audit_panic("unrecoverable error in audit_syscall_entry()"); return; } These problematic dummy contexts are created via the following call chain: exit_to_user_mode_prepare -> arch_do_signal_or_restart -> get_signal -> task_work_run -> tctx_task_work -> io_req_task_submit -> io_issue_sqe -> audit_uring_entry Cc: stable@vger.kernel.org Fixes: 5bd2182d58e9 ("audit,io_uring,io-wq: add some basic audit support to io_uring") Signed-off-by: Julian Orth [PM: subject line tweaks] Signed-off-by: Paul Moore --- include/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index d06134ac6245..cece70231138 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -339,7 +339,7 @@ static inline void audit_uring_entry(u8 op) } static inline void audit_uring_exit(int success, long code) { - if (unlikely(!audit_dummy_context())) + if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, -- cgit v1.2.3 From 0aa7be05d83cc584da0782405e8007e351dfb6cc Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Sun, 15 May 2022 20:42:03 +0200 Subject: locking/atomic: Add generic try_cmpxchg64 support Add generic support for try_cmpxchg64{,_acquire,_release,_relaxed} and their falbacks involving cmpxchg64. Signed-off-by: Uros Bizjak Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220515184205.103089-2-ubizjak@gmail.com --- include/linux/atomic/atomic-arch-fallback.h | 72 ++++++++++++++++++++++++++++- include/linux/atomic/atomic-instrumented.h | 40 +++++++++++++++- 2 files changed, 110 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 6db58d180866..77bc5522e61c 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -147,6 +147,76 @@ #endif /* arch_try_cmpxchg_relaxed */ +#ifndef arch_try_cmpxchg64_relaxed +#ifdef arch_try_cmpxchg64 +#define arch_try_cmpxchg64_acquire arch_try_cmpxchg64 +#define arch_try_cmpxchg64_release arch_try_cmpxchg64 +#define arch_try_cmpxchg64_relaxed arch_try_cmpxchg64 +#endif /* arch_try_cmpxchg64 */ + +#ifndef arch_try_cmpxchg64 +#define arch_try_cmpxchg64(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64 */ + +#ifndef arch_try_cmpxchg64_acquire +#define arch_try_cmpxchg64_acquire(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_acquire((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_acquire */ + +#ifndef arch_try_cmpxchg64_release +#define arch_try_cmpxchg64_release(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_release((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_release */ + +#ifndef arch_try_cmpxchg64_relaxed +#define arch_try_cmpxchg64_relaxed(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_relaxed((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_relaxed */ + +#else /* arch_try_cmpxchg64_relaxed */ + +#ifndef arch_try_cmpxchg64_acquire +#define arch_try_cmpxchg64_acquire(...) \ + __atomic_op_acquire(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg64_release +#define arch_try_cmpxchg64_release(...) \ + __atomic_op_release(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg64 +#define arch_try_cmpxchg64(...) \ + __atomic_op_fence(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#endif /* arch_try_cmpxchg64_relaxed */ + #ifndef arch_atomic_read_acquire static __always_inline int arch_atomic_read_acquire(const atomic_t *v) @@ -2386,4 +2456,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 8e2cc06bc0d2c0967d2f8424762bd48555ee40ae +// b5e87bdd5ede61470c29f7a7e4de781af3770f09 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 5d69b143c28e..7a139ec030b0 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -2006,6 +2006,44 @@ atomic_long_dec_if_positive(atomic_long_t *v) arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) +#define try_cmpxchg64(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + kcsan_mb(); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_acquire(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_release(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + kcsan_release(); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_relaxed(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + #define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ @@ -2045,4 +2083,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 87c974b93032afd42143613434d1a7788fa598f9 +// 764f741eb77a7ad565dc8d99ce2837d5542e8aee -- cgit v1.2.3 From 42c4e3f670b97df0c9e23ca2f7080ff7cd591837 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 3 May 2022 14:19:24 -0700 Subject: interconnect: qcom: sc8180x: Fix QUP0 nodes The QUP0 BCM relates to some internal property of the QUPs, and should be configured independently of the path to the QUP. In line with other platforms expose QUP_CORE endpoints in order allow this configuration. Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220503211925.1022169-4-bjorn.andersson@linaro.org Signed-off-by: Georgi Djakov --- include/dt-bindings/interconnect/qcom,sc8180x.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/interconnect/qcom,sc8180x.h b/include/dt-bindings/interconnect/qcom,sc8180x.h index 235b525d2803..e84cfec5afdd 100644 --- a/include/dt-bindings/interconnect/qcom,sc8180x.h +++ b/include/dt-bindings/interconnect/qcom,sc8180x.h @@ -182,4 +182,11 @@ #define SLAVE_MNOC_SF_MEM_NOC_DISPLAY 3 #define SLAVE_MNOC_HF_MEM_NOC_DISPLAY 4 +#define MASTER_QUP_CORE_0 0 +#define MASTER_QUP_CORE_1 1 +#define MASTER_QUP_CORE_2 2 +#define SLAVE_QUP_CORE_0 3 +#define SLAVE_QUP_CORE_1 4 +#define SLAVE_QUP_CORE_2 5 + #endif -- cgit v1.2.3 From bec67592521ec816371f5f072b1a340e1c2ad434 Mon Sep 17 00:00:00 2001 From: Min Li Date: Mon, 16 May 2022 10:47:06 -0400 Subject: ptp: ptp_clockmatrix: Add PTP_CLK_REQ_EXTTS support Use TOD_READ_SECONDARY for extts to keep TOD_READ_PRIMARY for gettime and settime exclusively. Before this change, TOD_READ_PRIMARY was used for both extts and gettime/settime, which would result in changing TOD read/write triggers between operations. Using TOD_READ_SECONDARY would make extts independent of gettime/settime operation Signed-off-by: Min Li Acked-by: Richard Cochran Link: https://lore.kernel.org/r/1652712427-14703-1-git-send-email-min.li.xe@renesas.com Signed-off-by: Jakub Kicinski --- include/linux/mfd/idt8a340_reg.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h index a18c1539a152..0c706085c205 100644 --- a/include/linux/mfd/idt8a340_reg.h +++ b/include/linux/mfd/idt8a340_reg.h @@ -407,7 +407,7 @@ #define TOD_READ_PRIMARY_0 0xcc40 #define TOD_READ_PRIMARY_0_V520 0xcc50 /* 8-bit subns, 32-bit ns, 48-bit seconds */ -#define TOD_READ_PRIMARY 0x0000 +#define TOD_READ_PRIMARY_BASE 0x0000 /* Counter increments after TOD write is completed */ #define TOD_READ_PRIMARY_COUNTER 0x000b /* Read trigger configuration */ @@ -424,6 +424,16 @@ #define TOD_READ_SECONDARY_0 0xcc90 #define TOD_READ_SECONDARY_0_V520 0xcca0 +/* 8-bit subns, 32-bit ns, 48-bit seconds */ +#define TOD_READ_SECONDARY_BASE 0x0000 +/* Counter increments after TOD write is completed */ +#define TOD_READ_SECONDARY_COUNTER 0x000b +/* Read trigger configuration */ +#define TOD_READ_SECONDARY_SEL_CFG_0 0x000c +/* Read trigger selection */ +#define TOD_READ_SECONDARY_CMD 0x000e +#define TOD_READ_SECONDARY_CMD_V520 0x000f + #define TOD_READ_SECONDARY_1 0xcca0 #define TOD_READ_SECONDARY_1_V520 0xccb0 #define TOD_READ_SECONDARY_2 0xccb0 -- cgit v1.2.3 From 1d2c717bc7f7fd3c9cf38d4a0d5d7ede06adf05b Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Fri, 13 May 2022 06:19:31 +0300 Subject: net/mlx5: Add last command failure syndrome to debugfs Add syndrome of last command failure per command type to debugfs to ease debugging of such failure. last_failed_syndrome - last command failed syndrome returned by FW. Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d6bac3976913..74c8cfb771a2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -272,6 +272,8 @@ struct mlx5_cmd_stats { u32 last_failed_errno; /* last bad status returned by FW */ u8 last_failed_mbox_status; + /* last command failed syndrome returned by FW */ + u32 last_failed_syndrome; struct dentry *root; /* protect command average calculations */ spinlock_t lock; -- cgit v1.2.3 From 9b45bde82c229fda94618896ff530dcba9d66fe0 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 25 Jan 2022 14:47:36 +0200 Subject: net/mlx5: Inline db alloc API function Take the wrapper version which picks default node into a header file. This reduces the number of exported functions. Signed-off-by: Tariq Toukan Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 74c8cfb771a2..b064bc278f52 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1053,9 +1053,14 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); -int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db); int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, int node); + +static inline int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db) +{ + return mlx5_db_alloc_node(dev, db, dev->priv.numa_node); +} + void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db); const char *mlx5_command_str(int command); -- cgit v1.2.3 From 94db3317781922ba52722c58061e0e8517d4d80d Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Mon, 31 Jan 2022 07:49:51 +0200 Subject: net/mlx5: Support multiport eswitch mode Multiport eswitch mode is a LAG mode that allows to add rules that forward traffic to a specific physical port without being affected by LAG affinity configuration. This mode of operation is mutual exclusive with the other LAG modes used by multipath and bonding. To make the transition between the modes, we maintain a counter on the number of rules specifying one of the uplink representors as the target of mirred egress redirect action. An example of such rule would be: $ tc filter add dev enp8s0f0_0 prot all root flower dst_mac \ 00:11:22:33:44:55 action mirred egress redirect dev enp8s0f0 If the reference count just grows to one and LAG is not in use, we create the LAG in multiport eswitch mode. Other mode changes are not allowed while in this mode. When the reference count reaches zero, we destroy the LAG and let other modes be used if needed. logic also changed such that if forwarding to some uplink destination cannot be guaranteed, we fail the operation so the rule will eventually be in software and not in hardware. Signed-off-by: Eli Cohen Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 7bab3e51c61e..78b3d3465dd7 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1359,7 +1359,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vhca_resource_manager[0x1]; u8 hca_cap_2[0x1]; - u8 reserved_at_21[0x1]; + u8 create_lag_when_not_master_up[0x1]; u8 dtor[0x1]; u8 event_on_vhca_state_teardown_request[0x1]; u8 event_on_vhca_state_in_use[0x1]; @@ -10816,7 +10816,8 @@ struct mlx5_ifc_dcbx_param_bits { enum { MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY = 0, - MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT, + MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT = 1, + MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_MPESW = 2, }; struct mlx5_ifc_lagc_bits { -- cgit v1.2.3 From 41929c9f628b9990d33a200c54bb0c919e089aa8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 6 Apr 2022 22:55:05 +0200 Subject: clocksource/drivers/ixp4xx: Drop boardfile probe path The boardfiles for IXP4xx have been deleted. Delete all the quirks and code dealing with that boot path and rely solely on device tree boot. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220406205505.2332821-1-linus.walleij@linaro.org Signed-off-by: Daniel Lezcano --- include/linux/platform_data/timer-ixp4xx.h | 11 ----------- 1 file changed, 11 deletions(-) delete mode 100644 include/linux/platform_data/timer-ixp4xx.h (limited to 'include') diff --git a/include/linux/platform_data/timer-ixp4xx.h b/include/linux/platform_data/timer-ixp4xx.h deleted file mode 100644 index ee92ae7edaed..000000000000 --- a/include/linux/platform_data/timer-ixp4xx.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __TIMER_IXP4XX_H -#define __TIMER_IXP4XX_H - -#include - -void __init ixp4xx_timer_setup(resource_size_t timerbase, - int timer_irq, - unsigned int timer_freq); - -#endif -- cgit v1.2.3 From c7fb19428d67dd0a2a78a4f237af01d39c78dc5a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 30 Apr 2022 14:38:53 -0600 Subject: io_uring: add support for ring mapped supplied buffers Provided buffers allow an application to supply io_uring with buffers that can then be grabbed for a read/receive request, when the data source is ready to deliver data. The existing scheme relies on using IORING_OP_PROVIDE_BUFFERS to do that, but it can be difficult to use in real world applications. It's pretty efficient if the application is able to supply back batches of provided buffers when they have been consumed and the application is ready to recycle them, but if fragmentation occurs in the buffer space, it can become difficult to supply enough buffers at the time. This hurts efficiency. Add a register op, IORING_REGISTER_PBUF_RING, which allows an application to setup a shared queue for each buffer group of provided buffers. The application can then supply buffers simply by adding them to this ring, and the kernel can consume then just as easily. The ring shares the head with the application, the tail remains private in the kernel. Provided buffers setup with IORING_REGISTER_PBUF_RING cannot use IORING_OP_{PROVIDE,REMOVE}_BUFFERS for adding or removing entries to the ring, they must use the mapped ring. Mapped provided buffer rings can co-exist with normal provided buffers, just not within the same group ID. To gauge overhead of the existing scheme and evaluate the mapped ring approach, a simple NOP benchmark was written. It uses a ring of 128 entries, and submits/completes 32 at the time. 'Replenish' is how many buffers are provided back at the time after they have been consumed: Test Replenish NOPs/sec ================================================================ No provided buffers NA ~30M Provided buffers 32 ~16M Provided buffers 1 ~10M Ring buffers 32 ~27M Ring buffers 1 ~27M The ring mapped buffers perform almost as well as not using provided buffers at all, and they don't care if you provided 1 or more back at the same time. This means application can just replenish as they go, rather than need to batch and compact, further reducing overhead in the application. The NOP benchmark above doesn't need to do any compaction, so that overhead isn't even reflected in the above test. Co-developed-by: Dylan Yudaken Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 15f821af9242..ddf969ae5a79 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -384,6 +384,10 @@ enum { IORING_REGISTER_RING_FDS = 20, IORING_UNREGISTER_RING_FDS = 21, + /* register ring based provide buffer group */ + IORING_REGISTER_PBUF_RING = 22, + IORING_UNREGISTER_PBUF_RING = 23, + /* this goes last */ IORING_REGISTER_LAST }; @@ -461,6 +465,38 @@ struct io_uring_restriction { __u32 resv2[3]; }; +struct io_uring_buf { + __u64 addr; + __u32 len; + __u16 bid; + __u16 resv; +}; + +struct io_uring_buf_ring { + union { + /* + * To avoid spilling into more pages than we need to, the + * ring tail is overlaid with the io_uring_buf->resv field. + */ + struct { + __u64 resv1; + __u32 resv2; + __u16 resv3; + __u16 tail; + }; + struct io_uring_buf bufs[0]; + }; +}; + +/* argument for IORING_(UN)REGISTER_PBUF_RING */ +struct io_uring_buf_reg { + __u64 ring_addr; + __u32 ring_entries; + __u16 bgid; + __u16 pad; + __u64 resv[3]; +}; + /* * io_uring_restriction->opcode values */ -- cgit v1.2.3 From 14362a2541797cf9df0e86fb12dcd7950baf566e Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 11 May 2022 22:02:12 +0300 Subject: fsnotify: introduce mark type iterator fsnotify_foreach_iter_mark_type() is used to reduce boilerplate code of iterating all marks of a specific group interested in an event by consulting the iterator report_mask. Use an open coded version of that iterator in fsnotify_iter_next() that collects all marks of the current iteration group without consulting the iterator report_mask. At the moment, the two iterator variants are the same, but this decoupling will allow us to exclude some of the group's marks from reporting the event, for example for event on child and inode marks on parent did not request to watch events on children. Fixes: 2f02fd3fa13e ("fanotify: fix ignore mask logic for events on child and on dir") Reported-by: Jan Kara Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20220511190213.831646-2-amir73il@gmail.com --- include/linux/fsnotify_backend.h | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 9a1a9e78f69f..9560734759fa 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -399,6 +399,7 @@ static inline bool fsnotify_valid_obj_type(unsigned int obj_type) struct fsnotify_iter_info { struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; + struct fsnotify_group *current_group; unsigned int report_mask; int srcu_idx; }; @@ -415,20 +416,31 @@ static inline void fsnotify_iter_set_report_type( iter_info->report_mask |= (1U << iter_type); } -static inline void fsnotify_iter_set_report_type_mark( - struct fsnotify_iter_info *iter_info, int iter_type, - struct fsnotify_mark *mark) +static inline struct fsnotify_mark *fsnotify_iter_mark( + struct fsnotify_iter_info *iter_info, int iter_type) { - iter_info->marks[iter_type] = mark; - iter_info->report_mask |= (1U << iter_type); + if (fsnotify_iter_should_report_type(iter_info, iter_type)) + return iter_info->marks[iter_type]; + return NULL; +} + +static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type, + struct fsnotify_mark **markp) +{ + while (type < FSNOTIFY_ITER_TYPE_COUNT) { + *markp = fsnotify_iter_mark(iter, type); + if (*markp) + break; + type++; + } + return type; } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ - return (iter_info->report_mask & (1U << FSNOTIFY_ITER_TYPE_##NAME)) ? \ - iter_info->marks[FSNOTIFY_ITER_TYPE_##NAME] : NULL; \ + return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \ } FSNOTIFY_ITER_FUNCS(inode, INODE) @@ -438,6 +450,11 @@ FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_iter_type(type) \ for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) +#define fsnotify_foreach_iter_mark_type(iter, mark, type) \ + for (type = 0; \ + type = fsnotify_iter_step(iter, type, &mark), \ + type < FSNOTIFY_ITER_TYPE_COUNT; \ + type++) /* * fsnotify_connp_t is what we embed in objects which connector can be attached -- cgit v1.2.3 From e73aaae2fa9024832e1f42e30c787c7baf61d014 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sat, 7 May 2022 14:03:46 +0200 Subject: siphash: use one source of truth for siphash permutations The SipHash family of permutations is currently used in three places: - siphash.c itself, used in the ordinary way it was intended. - random32.c, in a construction from an anonymous contributor. - random.c, as part of its fast_mix function. Each one of these places reinvents the wheel with the same C code, same rotation constants, and same symmetry-breaking constants. This commit tidies things up a bit by placing macros for the permutations and constants into siphash.h, where each of the three .c users can access them. It also leaves a note dissuading more users of them from emerging. Signed-off-by: Jason A. Donenfeld --- include/linux/prandom.h | 23 +++++++---------------- include/linux/siphash.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/prandom.h b/include/linux/prandom.h index 056d31317e49..a4aadd2dc153 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -10,6 +10,7 @@ #include #include +#include u32 prandom_u32(void); void prandom_bytes(void *buf, size_t nbytes); @@ -27,15 +28,10 @@ DECLARE_PER_CPU(unsigned long, net_rand_noise); * The core SipHash round function. Each line can be executed in * parallel given enough CPU resources. */ -#define PRND_SIPROUND(v0, v1, v2, v3) ( \ - v0 += v1, v1 = rol64(v1, 13), v2 += v3, v3 = rol64(v3, 16), \ - v1 ^= v0, v0 = rol64(v0, 32), v3 ^= v2, \ - v0 += v3, v3 = rol64(v3, 21), v2 += v1, v1 = rol64(v1, 17), \ - v3 ^= v0, v1 ^= v2, v2 = rol64(v2, 32) \ -) +#define PRND_SIPROUND(v0, v1, v2, v3) SIPHASH_PERMUTATION(v0, v1, v2, v3) -#define PRND_K0 (0x736f6d6570736575 ^ 0x6c7967656e657261) -#define PRND_K1 (0x646f72616e646f6d ^ 0x7465646279746573) +#define PRND_K0 (SIPHASH_CONST_0 ^ SIPHASH_CONST_2) +#define PRND_K1 (SIPHASH_CONST_1 ^ SIPHASH_CONST_3) #elif BITS_PER_LONG == 32 /* @@ -43,14 +39,9 @@ DECLARE_PER_CPU(unsigned long, net_rand_noise); * This is weaker, but 32-bit machines are not used for high-traffic * applications, so there is less output for an attacker to analyze. */ -#define PRND_SIPROUND(v0, v1, v2, v3) ( \ - v0 += v1, v1 = rol32(v1, 5), v2 += v3, v3 = rol32(v3, 8), \ - v1 ^= v0, v0 = rol32(v0, 16), v3 ^= v2, \ - v0 += v3, v3 = rol32(v3, 7), v2 += v1, v1 = rol32(v1, 13), \ - v3 ^= v0, v1 ^= v2, v2 = rol32(v2, 16) \ -) -#define PRND_K0 0x6c796765 -#define PRND_K1 0x74656462 +#define PRND_SIPROUND(v0, v1, v2, v3) HSIPHASH_PERMUTATION(v0, v1, v2, v3) +#define PRND_K0 (HSIPHASH_CONST_0 ^ HSIPHASH_CONST_2) +#define PRND_K1 (HSIPHASH_CONST_1 ^ HSIPHASH_CONST_3) #else #error Unsupported BITS_PER_LONG diff --git a/include/linux/siphash.h b/include/linux/siphash.h index cce8a9acc76c..3af1428da559 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -138,4 +138,32 @@ static inline u32 hsiphash(const void *data, size_t len, return ___hsiphash_aligned(data, len, key); } +/* + * These macros expose the raw SipHash and HalfSipHash permutations. + * Do not use them directly! If you think you have a use for them, + * be sure to CC the maintainer of this file explaining why. + */ + +#define SIPHASH_PERMUTATION(a, b, c, d) ( \ + (a) += (b), (b) = rol64((b), 13), (b) ^= (a), (a) = rol64((a), 32), \ + (c) += (d), (d) = rol64((d), 16), (d) ^= (c), \ + (a) += (d), (d) = rol64((d), 21), (d) ^= (a), \ + (c) += (b), (b) = rol64((b), 17), (b) ^= (c), (c) = rol64((c), 32)) + +#define SIPHASH_CONST_0 0x736f6d6570736575ULL +#define SIPHASH_CONST_1 0x646f72616e646f6dULL +#define SIPHASH_CONST_2 0x6c7967656e657261ULL +#define SIPHASH_CONST_3 0x7465646279746573ULL + +#define HSIPHASH_PERMUTATION(a, b, c, d) ( \ + (a) += (b), (b) = rol32((b), 5), (b) ^= (a), (a) = rol32((a), 16), \ + (c) += (d), (d) = rol32((d), 8), (d) ^= (c), \ + (a) += (d), (d) = rol32((d), 7), (d) ^= (a), \ + (c) += (b), (b) = rol32((b), 13), (b) ^= (c), (c) = rol32((c), 16)) + +#define HSIPHASH_CONST_0 0U +#define HSIPHASH_CONST_1 0U +#define HSIPHASH_CONST_2 0x6c796765U +#define HSIPHASH_CONST_3 0x74656462U + #endif /* _LINUX_SIPHASH_H */ -- cgit v1.2.3 From d4150779e60fb6c49be25572596b2cdfc5d46a09 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 11 May 2022 16:11:29 +0200 Subject: random32: use real rng for non-deterministic randomness MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit random32.c has two random number generators in it: one that is meant to be used deterministically, with some predefined seed, and one that does the same exact thing as random.c, except does it poorly. The first one has some use cases. The second one no longer does and can be replaced with calls to random.c's proper random number generator. The relatively recent siphash-based bad random32.c code was added in response to concerns that the prior random32.c was too deterministic. Out of fears that random.c was (at the time) too slow, this code was anonymously contributed. Then out of that emerged a kind of shadow entropy gathering system, with its own tentacles throughout various net code, added willy nilly. Stop👏making👏bespoke👏random👏number👏generators👏. Fortunately, recent advances in random.c mean that we can stop playing with this sketchiness, and just use get_random_u32(), which is now fast enough. In micro benchmarks using RDPMC, I'm seeing the same median cycle count between the two functions, with the mean being _slightly_ higher due to batches refilling (which we can optimize further need be). However, when doing *real* benchmarks of the net functions that actually use these random numbers, the mean cycles actually *decreased* slightly (with the median still staying the same), likely because the additional prandom code means icache misses and complexity, whereas random.c is generally already being used by something else nearby. The biggest benefit of this is that there are many users of prandom who probably should be using cryptographically secure random numbers. This makes all of those accidental cases become secure by just flipping a switch. Later on, we can do a tree-wide cleanup to remove the static inline wrapper functions that this commit adds. There are also some low-ish hanging fruits for making this even faster in the future: a get_random_u16() function for use in the networking stack will give a 2x performance boost there, using SIMD for ChaCha20 will let us compute 4 or 8 or 16 blocks of output in parallel, instead of just one, giving us large buffers for cheap, and introducing a get_random_*_bh() function that assumes irqs are already disabled will shave off a few cycles for ordinary calls. These are things we can chip away at down the road. Acked-by: Jakub Kicinski Acked-by: Theodore Ts'o Signed-off-by: Jason A. Donenfeld --- include/linux/prandom.h | 52 +++++++------------------------------------------ 1 file changed, 7 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/linux/prandom.h b/include/linux/prandom.h index a4aadd2dc153..deace5fb4e62 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -10,53 +10,16 @@ #include #include -#include +#include -u32 prandom_u32(void); -void prandom_bytes(void *buf, size_t nbytes); -void prandom_seed(u32 seed); -void prandom_reseed_late(void); - -DECLARE_PER_CPU(unsigned long, net_rand_noise); - -#define PRANDOM_ADD_NOISE(a, b, c, d) \ - prandom_u32_add_noise((unsigned long)(a), (unsigned long)(b), \ - (unsigned long)(c), (unsigned long)(d)) - -#if BITS_PER_LONG == 64 -/* - * The core SipHash round function. Each line can be executed in - * parallel given enough CPU resources. - */ -#define PRND_SIPROUND(v0, v1, v2, v3) SIPHASH_PERMUTATION(v0, v1, v2, v3) - -#define PRND_K0 (SIPHASH_CONST_0 ^ SIPHASH_CONST_2) -#define PRND_K1 (SIPHASH_CONST_1 ^ SIPHASH_CONST_3) - -#elif BITS_PER_LONG == 32 -/* - * On 32-bit machines, we use HSipHash, a reduced-width version of SipHash. - * This is weaker, but 32-bit machines are not used for high-traffic - * applications, so there is less output for an attacker to analyze. - */ -#define PRND_SIPROUND(v0, v1, v2, v3) HSIPHASH_PERMUTATION(v0, v1, v2, v3) -#define PRND_K0 (HSIPHASH_CONST_0 ^ HSIPHASH_CONST_2) -#define PRND_K1 (HSIPHASH_CONST_1 ^ HSIPHASH_CONST_3) - -#else -#error Unsupported BITS_PER_LONG -#endif +static inline u32 prandom_u32(void) +{ + return get_random_u32(); +} -static inline void prandom_u32_add_noise(unsigned long a, unsigned long b, - unsigned long c, unsigned long d) +static inline void prandom_bytes(void *buf, size_t nbytes) { - /* - * This is not used cryptographically; it's just - * a convenient 4-word hash function. (3 xor, 2 add, 2 rol) - */ - a ^= raw_cpu_read(net_rand_noise); - PRND_SIPROUND(a, b, c, d); - raw_cpu_write(net_rand_noise, d); + return get_random_bytes(buf, nbytes); } struct rnd_state { @@ -108,7 +71,6 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) state->s2 = __seed(i, 8U); state->s3 = __seed(i, 16U); state->s4 = __seed(i, 128U); - PRANDOM_ADD_NOISE(state, i, 0, 0); } /* Pseudo random number generator from numerical recipes. */ -- cgit v1.2.3 From 2f14062bb14b0fcfcc21e6dc7d5b5c0d25966164 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Thu, 5 May 2022 02:20:22 +0200 Subject: random: handle latent entropy and command line from random_init() Currently, start_kernel() adds latent entropy and the command line to the entropy bool *after* the RNG has been initialized, deferring when it's actually used by things like stack canaries until the next time the pool is seeded. This surely is not intended. Rather than splitting up which entropy gets added where and when between start_kernel() and random_init(), just do everything in random_init(), which should eliminate these kinds of bugs in the future. While we're at it, rename the awkwardly titled "rand_initialize()" to the more standard "random_init()" nomenclature. Reviewed-by: Dominik Brodowski Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index f673fbb838b3..b52963955a99 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -14,22 +14,21 @@ struct notifier_block; extern void add_device_randomness(const void *, size_t); extern void add_bootloader_randomness(const void *, size_t); +extern void add_input_randomness(unsigned int type, unsigned int code, + unsigned int value) __latent_entropy; +extern void add_interrupt_randomness(int irq) __latent_entropy; +extern void add_hwgenerator_randomness(const void *buffer, size_t count, + size_t entropy); #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) { - add_device_randomness((const void *)&latent_entropy, - sizeof(latent_entropy)); + add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); } #else static inline void add_latent_entropy(void) {} #endif -extern void add_input_randomness(unsigned int type, unsigned int code, - unsigned int value) __latent_entropy; -extern void add_interrupt_randomness(int irq) __latent_entropy; -extern void add_hwgenerator_randomness(const void *buffer, size_t count, - size_t entropy); #if IS_ENABLED(CONFIG_VMGENID) extern void add_vmfork_randomness(const void *unique_vm_id, size_t size); extern int register_random_vmfork_notifier(struct notifier_block *nb); @@ -41,7 +40,7 @@ static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { extern void get_random_bytes(void *buf, size_t nbytes); extern int wait_for_random_bytes(void); -extern int __init rand_initialize(void); +extern int __init random_init(const char *command_line); extern bool rng_is_initialized(void); extern int register_random_ready_notifier(struct notifier_block *nb); extern int unregister_random_ready_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 354201c53e61e493017b15327294b0c8ab522d69 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 May 2022 15:09:21 +0200 Subject: nvme: add support for TP4084 - Time-to-Ready Enhancements Add support for using longer timeouts during controller initialization and letting the controller come up with namespaces that are not ready for I/O yet. We skip these not ready namespaces during scanning and only bring them online once anoter scan is kicked off by the AEN that is set when the NRDY bit gets set in the I/O Command Set Independent Identify Namespace Data Structure. This asynchronous probing avoids blocking the kernel boot when controllers take a very long time to recover after unclean shutdowns (up to minutes). Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Chaitanya Kulkarni Reviewed-by: Hannes Reinecke --- include/linux/nvme.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 5f6d432fa06a..29ec3e3481ff 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -137,6 +137,7 @@ enum { NVME_REG_CMBMSC = 0x0050, /* Controller Memory Buffer Memory * Space Control */ + NVME_REG_CRTO = 0x0068, /* Controller Ready Timeouts */ NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ @@ -161,6 +162,9 @@ enum { #define NVME_CMB_BIR(cmbloc) ((cmbloc) & 0x7) #define NVME_CMB_OFST(cmbloc) (((cmbloc) >> 12) & 0xfffff) +#define NVME_CRTO_CRIMT(crto) ((crto) >> 16) +#define NVME_CRTO_CRWMT(crto) ((crto) & 0xffff) + enum { NVME_CMBSZ_SQS = 1 << 0, NVME_CMBSZ_CQS = 1 << 1, @@ -204,6 +208,7 @@ enum { NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, + NVME_CC_CRIME = 1 << 24, }; enum { @@ -227,6 +232,11 @@ enum { NVME_CAP_CSS_CSI = 1 << 6, }; +enum { + NVME_CAP_CRMS_CRIMS = 1ULL << 59, + NVME_CAP_CRMS_CRWMS = 1ULL << 60, +}; + struct nvme_id_power_state { __le16 max_power; /* centiwatts */ __u8 rsvd2; @@ -414,6 +424,21 @@ struct nvme_id_ns { __u8 vs[3712]; }; +/* I/O Command Set Independent Identify Namespace Data Structure */ +struct nvme_id_ns_cs_indep { + __u8 nsfeat; + __u8 nmic; + __u8 rescap; + __u8 fpi; + __le32 anagrpid; + __u8 nsattr; + __u8 rsvd9; + __le16 nvmsetid; + __le16 endgid; + __u8 nstat; + __u8 rsvd15[4081]; +}; + struct nvme_zns_lbafe { __le64 zsze; __u8 zdes; @@ -478,6 +503,7 @@ enum { NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_CS_NS = 0x05, NVME_ID_CNS_CS_CTRL = 0x06, + NVME_ID_CNS_NS_CS_INDEP = 0x08, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, @@ -531,6 +557,10 @@ enum { NVME_NS_DPS_PI_TYPE3 = 3, }; +enum { + NVME_NSTAT_NRDY = 1 << 0, +}; + enum { NVME_NVM_NS_16B_GUARD = 0, NVME_NVM_NS_32B_GUARD = 1, @@ -1592,6 +1622,7 @@ enum { NVME_SC_NS_WRITE_PROTECTED = 0x20, NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_TRANSIENT_TR_ERR = 0x22, + NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY = 0x24, NVME_SC_INVALID_IO_CMD_SET = 0x2C, NVME_SC_LBA_RANGE = 0x80, -- cgit v1.2.3 From 75dbb685f4e8786c33ddef8279bab0eadfb0731f Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sat, 14 May 2022 12:16:47 +0200 Subject: libceph: fix potential use-after-free on linger ping and resends request_reinit() is not only ugly as the comment rightfully suggests, but also unsafe. Even though it is called with osdc->lock held for write in all cases, resetting the OSD request refcount can still race with handle_reply() and result in use-after-free. Taking linger ping as an example: handle_timeout thread handle_reply thread down_read(&osdc->lock) req = lookup_request(...) ... finish_request(req) # unregisters up_read(&osdc->lock) __complete_request(req) linger_ping_cb(req) # req->r_kref == 2 because handle_reply still holds its ref down_write(&osdc->lock) send_linger_ping(lreq) req = lreq->ping_req # same req # cancel_linger_request is NOT # called - handle_reply already # unregistered request_reinit(req) WARN_ON(req->r_kref != 1) # fires request_init(req) kref_init(req->r_kref) # req->r_kref == 1 after kref_init ceph_osdc_put_request(req) kref_put(req->r_kref) # req->r_kref == 0 after kref_put, req is freed !!! This happens because send_linger_ping() always (re)uses the same OSD request for watch ping requests, relying on cancel_linger_request() to unregister it from the OSD client and rip its messages out from the messenger. send_linger() does the same for watch/notify registration and watch reconnect requests. Unfortunately cancel_request() doesn't guarantee that after it returns the OSD client would be completely done with the OSD request -- a ref could still be held and the callback (if specified) could still be invoked too. The original motivation for request_reinit() was inability to deal with allocation failures in send_linger() and send_linger_ping(). Switching to using osdc->req_mempool (currently only used by CephFS) respects that and allows us to get rid of request_reinit(). Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Xiubo Li Acked-by: Jeff Layton --- include/linux/ceph/osd_client.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3431011f364d..cba8a6ffc329 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -287,6 +287,9 @@ struct ceph_osd_linger_request { rados_watcherrcb_t errcb; void *data; + struct ceph_pagelist *request_pl; + struct page **notify_id_pages; + struct page ***preply_pages; size_t *preply_len; }; -- cgit v1.2.3 From 3f68e69520d3d52d66a6ad872a75b7d8f2ea7665 Mon Sep 17 00:00:00 2001 From: Sunil V L Date: Thu, 19 May 2022 10:45:12 +0530 Subject: riscv/efi_stub: Add support for RISCV_EFI_BOOT_PROTOCOL Add support for getting the boot hart ID from the Linux EFI stub using RISCV_EFI_BOOT_PROTOCOL. This method is preferred over the existing DT based approach since it works irrespective of DT or ACPI. The specification of the protocol is hosted at: https://github.com/riscv-non-isa/riscv-uefi Signed-off-by: Sunil V L Acked-by: Palmer Dabbelt Reviewed-by: Heinrich Schuchardt Link: https://lore.kernel.org/r/20220519051512.136724-2-sunilvl@ventanamicro.com [ardb: minor tweaks for coding style and whitespace] Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index 580ce607d6f5..0412304ce34e 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -410,6 +410,8 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) #define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) +#define RISCV_EFI_BOOT_PROTOCOL_GUID EFI_GUID(0xccd15fec, 0x6f73, 0x4eec, 0x83, 0x95, 0x3e, 0x69, 0xe4, 0xb9, 0x40, 0xbf) + /* * This GUID may be installed onto the kernel image's handle as a NULL protocol * to signal to the stub that the placement of the image should be respected, -- cgit v1.2.3 From 238e34ad7d5ce36939ac1442c98c7cbb7771f4de Mon Sep 17 00:00:00 2001 From: Jishnu Prakash Date: Sun, 3 Apr 2022 18:47:47 +0530 Subject: iio: adc: qcom-vadc-common: add reverse scaling for PMIC5 Gen2 ADC_TM Add reverse scaling function for PMIC5 Gen2 ADC_TM, to convert temperature to raw ADC code, for setting thresholds for thermistor channels. Signed-off-by: Jishnu Prakash Acked-by: Jonathan Cameron Link: https://lore.kernel.org/r/1648991869-20899-3-git-send-email-quic_jprakash@quicinc.com Signed-off-by: Daniel Lezcano --- include/linux/iio/adc/qcom-vadc-common.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h index ce78d4804994..aa21b032e861 100644 --- a/include/linux/iio/adc/qcom-vadc-common.h +++ b/include/linux/iio/adc/qcom-vadc-common.h @@ -152,6 +152,8 @@ int qcom_adc5_hw_scale(enum vadc_scale_fn_type scaletype, u16 qcom_adc_tm5_temp_volt_scale(unsigned int prescale_ratio, u32 full_scale_code_volt, int temp); +u16 qcom_adc_tm5_gen2_temp_res_scale(int temp); + int qcom_adc5_prescaling_from_dt(u32 num, u32 den); int qcom_adc5_hw_settle_time_from_dt(u32 value, const unsigned int *hw_settle); -- cgit v1.2.3 From bf70c577516b8d9fbe703371aa98bbea13661cec Mon Sep 17 00:00:00 2001 From: Manaf Meethalavalappu Pallikunhi Date: Wed, 9 Mar 2022 00:56:26 +0530 Subject: thermal/drivers/thermal_of: Add change_mode ops support for thermal_of sensor The sensor driver which register through thermal_of interface doesn't have an option to get thermal zone mode change notification from thermal core. Add support for change_mode ops in thermal_of interface so that sensor driver can use this ops for mode change notification. Signed-off-by: Manaf Meethalavalappu Pallikunhi Link: https://lore.kernel.org/r/1646767586-31908-1-git-send-email-quic_manafm@quicinc.com Signed-off-by: Daniel Lezcano --- include/linux/thermal.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index c314893970b3..365733b428d8 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -299,6 +299,8 @@ struct thermal_zone_params { * temperature. * @set_trip_temp: a pointer to a function that sets the trip temperature on * hardware. + * @change_mode: a pointer to a function that notifies the thermal zone + * mode change. */ struct thermal_zone_of_device_ops { int (*get_temp)(void *, int *); @@ -306,6 +308,7 @@ struct thermal_zone_of_device_ops { int (*set_trips)(void *, int, int); int (*set_emul_temp)(void *, int); int (*set_trip_temp)(void *, int, int); + int (*change_mode) (void *, enum thermal_device_mode); }; /* Function declarations */ -- cgit v1.2.3 From c1318b39c7d36bd5139a9c71044ff2b2d3c6f9d8 Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Wed, 18 May 2022 12:27:31 +0300 Subject: tls: Add opt-in zerocopy mode of sendfile() TLS device offload copies sendfile data to a bounce buffer before transmitting. It allows to maintain the valid MAC on TLS records when the file contents change and a part of TLS record has to be retransmitted on TCP level. In many common use cases (like serving static files over HTTPS) the file contents are not changed on the fly. In many use cases breaking the connection is totally acceptable if the file is changed during transmission, because it would be received corrupted in any case. This commit allows to optimize performance for such use cases to providing a new optional mode of TLS sendfile(), in which the extra copy is skipped. Removing this copy improves performance significantly, as TLS and TCP sendfile perform the same operations, and the only overhead is TLS header/trailer insertion. The new mode can only be enabled with the new socket option named TLS_TX_ZEROCOPY_SENDFILE on per-socket basis. It preserves backwards compatibility with existing applications that rely on the copying behavior. The new mode is safe, meaning that unsolicited modifications of the file being sent can't break integrity of the kernel. The worst thing that can happen is sending a corrupted TLS record, which is in any case not forbidden when using regular TCP sockets. Sockets other than TLS device offload are not affected by the new socket option. The actual status of zerocopy sendfile can be queried with sock_diag. Performance numbers in a single-core test with 24 HTTPS streams on nginx, under 100% CPU load: * non-zerocopy: 33.6 Gbit/s * zerocopy: 79.92 Gbit/s CPU: Intel(R) Xeon(R) Platinum 8380 CPU @ 2.30GHz Signed-off-by: Boris Pismenny Signed-off-by: Tariq Toukan Signed-off-by: Maxim Mikityanskiy Reviewed-by: Jakub Kicinski Link: https://lore.kernel.org/r/20220518092731.1243494-1-maximmi@nvidia.com Signed-off-by: Paolo Abeni --- include/net/tls.h | 1 + include/uapi/linux/tls.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index b59f0a63292b..8017f1703447 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -238,6 +238,7 @@ struct tls_context { u8 tx_conf:3; u8 rx_conf:3; + u8 zerocopy_sendfile:1; int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index 5f38be0ec0f3..ac39328eabe7 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -39,6 +39,7 @@ /* TLS socket options */ #define TLS_TX 1 /* Set transmit parameters */ #define TLS_RX 2 /* Set receive parameters */ +#define TLS_TX_ZEROCOPY_SENDFILE 3 /* transmit zerocopy sendfile */ /* Supported versions */ #define TLS_VERSION_MINOR(ver) ((ver) & 0xFF) @@ -160,6 +161,7 @@ enum { TLS_INFO_CIPHER, TLS_INFO_TXCONF, TLS_INFO_RXCONF, + TLS_INFO_ZC_SENDFILE, __TLS_INFO_MAX, }; #define TLS_INFO_MAX (__TLS_INFO_MAX - 1) -- cgit v1.2.3 From 5ce9231c5b961596ebf948777c9c5a6981f067d9 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 28 Apr 2022 09:53:20 +0200 Subject: xen: update vscsiif.h Update include/xen/interface/io/vscsiif.h to its newest version. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20220428075323.12853-2-jgross@suse.com Signed-off-by: Juergen Gross --- include/xen/interface/io/vscsiif.h | 133 +++++++++++++++++++++++++++++++++++-- 1 file changed, 129 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/xen/interface/io/vscsiif.h b/include/xen/interface/io/vscsiif.h index 1f6047d3de44..7ea4dc9611c4 100644 --- a/include/xen/interface/io/vscsiif.h +++ b/include/xen/interface/io/vscsiif.h @@ -43,7 +43,7 @@ * * A string specifying the backend device: either a 4-tuple "h:c:t:l" * (host, controller, target, lun, all integers), or a WWN (e.g. - * "naa.60014054ac780582"). + * "naa.60014054ac780582:0"). * * v-dev * Values: string @@ -87,6 +87,75 @@ * response structures. */ +/* + * Xenstore format in practice + * =========================== + * + * The backend driver uses a single_host:many_devices notation to manage domU + * devices. Everything is stored in /local/domain//backend/vscsi/. + * The xenstore layout looks like this (dom0 is assumed to be the backend_domid): + * + * //feature-host = "0" + * //frontend = "/local/domain//device/vscsi/0" + * //frontend-id = "" + * //online = "1" + * //state = "4" + * //vscsi-devs/dev-0/p-dev = "8:0:2:1" or "naa.wwn:lun" + * //vscsi-devs/dev-0/state = "4" + * //vscsi-devs/dev-0/v-dev = "0:0:0:0" + * //vscsi-devs/dev-1/p-dev = "8:0:2:2" + * //vscsi-devs/dev-1/state = "4" + * //vscsi-devs/dev-1/v-dev = "0:0:1:0" + * + * The frontend driver maintains its state in + * /local/domain//device/vscsi/. + * + * /backend = "/local/domain/0/backend/vscsi//" + * /backend-id = "0" + * /event-channel = "20" + * /ring-ref = "43" + * /state = "4" + * /vscsi-devs/dev-0/state = "4" + * /vscsi-devs/dev-1/state = "4" + * + * In addition to the entries for backend and frontend these flags are stored + * for the toolstack: + * + * //vscsi-devs/dev-1/p-devname = "/dev/$device" + * //libxl_ctrl_index = "0" + * + * + * Backend/frontend protocol + * ========================= + * + * To create a vhost along with a device: + * //feature-host = "0" + * //frontend = "/local/domain//device/vscsi/0" + * //frontend-id = "" + * //online = "1" + * //state = "1" + * //vscsi-devs/dev-0/p-dev = "8:0:2:1" + * //vscsi-devs/dev-0/state = "1" + * //vscsi-devs/dev-0/v-dev = "0:0:0:0" + * Wait for //state + //vscsi-devs/dev-0/state become 4 + * + * To add another device to a vhost: + * //state = "7" + * //vscsi-devs/dev-1/p-dev = "8:0:2:2" + * //vscsi-devs/dev-1/state = "1" + * //vscsi-devs/dev-1/v-dev = "0:0:1:0" + * Wait for //state + //vscsi-devs/dev-1/state become 4 + * + * To remove a device from a vhost: + * //state = "7" + * //vscsi-devs/dev-1/state = "5" + * Wait for //state to become 4 + * Wait for //vscsi-devs/dev-1/state become 6 + * Remove //vscsi-devs/dev-1/{state,p-dev,v-dev,p-devname} + * Remove //vscsi-devs/dev-1/ + * + */ + /* Requests from the frontend to the backend */ /* @@ -117,7 +186,8 @@ * (plus the set VSCSIIF_SG_GRANT bit), the number of scsiif_request_segment * elements referencing the target data buffers is calculated from the lengths * of the seg[] elements (the sum of all valid seg[].length divided by the - * size of one scsiif_request_segment structure). + * size of one scsiif_request_segment structure). The frontend may use a mix of + * direct and indirect requests. */ #define VSCSIIF_ACT_SCSI_CDB 1 @@ -154,12 +224,14 @@ /* * based on Linux kernel 2.6.18, still valid + * * Changing these values requires support of multiple protocols via the rings * as "old clients" will blindly use these values and the resulting structure * sizes. */ #define VSCSIIF_MAX_COMMAND_SIZE 16 #define VSCSIIF_SENSE_BUFFERSIZE 96 +#define VSCSIIF_PAGE_SIZE 4096 struct scsiif_request_segment { grant_ref_t gref; @@ -167,7 +239,8 @@ struct scsiif_request_segment { uint16_t length; }; -#define VSCSIIF_SG_PER_PAGE (PAGE_SIZE / sizeof(struct scsiif_request_segment)) +#define VSCSIIF_SG_PER_PAGE (VSCSIIF_PAGE_SIZE / \ + sizeof(struct scsiif_request_segment)) /* Size of one request is 252 bytes */ struct vscsiif_request { @@ -207,6 +280,58 @@ struct vscsiif_response { uint32_t reserved[36]; }; +/* SCSI I/O status from vscsiif_response->rslt */ +#define XEN_VSCSIIF_RSLT_STATUS(x) ((x) & 0x00ff) + +/* Host I/O status from vscsiif_response->rslt */ +#define XEN_VSCSIIF_RSLT_HOST(x) (((x) & 0x00ff0000) >> 16) +#define XEN_VSCSIIF_RSLT_HOST_OK 0 +/* Couldn't connect before timeout */ +#define XEN_VSCSIIF_RSLT_HOST_NO_CONNECT 1 +/* Bus busy through timeout */ +#define XEN_VSCSIIF_RSLT_HOST_BUS_BUSY 2 +/* Timed out for other reason */ +#define XEN_VSCSIIF_RSLT_HOST_TIME_OUT 3 +/* Bad target */ +#define XEN_VSCSIIF_RSLT_HOST_BAD_TARGET 4 +/* Abort for some other reason */ +#define XEN_VSCSIIF_RSLT_HOST_ABORT 5 +/* Parity error */ +#define XEN_VSCSIIF_RSLT_HOST_PARITY 6 +/* Internal error */ +#define XEN_VSCSIIF_RSLT_HOST_ERROR 7 +/* Reset by somebody */ +#define XEN_VSCSIIF_RSLT_HOST_RESET 8 +/* Unexpected interrupt */ +#define XEN_VSCSIIF_RSLT_HOST_BAD_INTR 9 +/* Force command past mid-layer */ +#define XEN_VSCSIIF_RSLT_HOST_PASSTHROUGH 10 +/* Retry requested */ +#define XEN_VSCSIIF_RSLT_HOST_SOFT_ERROR 11 +/* Hidden retry requested */ +#define XEN_VSCSIIF_RSLT_HOST_IMM_RETRY 12 +/* Requeue command requested */ +#define XEN_VSCSIIF_RSLT_HOST_REQUEUE 13 +/* Transport error disrupted I/O */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_DISRUPTED 14 +/* Transport class fastfailed */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_FAILFAST 15 +/* Permanent target failure */ +#define XEN_VSCSIIF_RSLT_HOST_TARGET_FAILURE 16 +/* Permanent nexus failure on path */ +#define XEN_VSCSIIF_RSLT_HOST_NEXUS_FAILURE 17 +/* Space allocation on device failed */ +#define XEN_VSCSIIF_RSLT_HOST_ALLOC_FAILURE 18 +/* Medium error */ +#define XEN_VSCSIIF_RSLT_HOST_MEDIUM_ERROR 19 +/* Transport marginal errors */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_MARGINAL 20 + +/* Result values of reset operations */ +#define XEN_VSCSIIF_RSLT_RESET_SUCCESS 0x2002 +#define XEN_VSCSIIF_RSLT_RESET_FAILED 0x2003 + DEFINE_RING_TYPES(vscsiif, struct vscsiif_request, struct vscsiif_response); -#endif /*__XEN__PUBLIC_IO_SCSI_H__*/ + +#endif /*__XEN__PUBLIC_IO_SCSI_H__*/ -- cgit v1.2.3 From 79c22318f89f3e6cafeabddd5894cad13c7e5957 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 5 May 2022 08:49:52 +0200 Subject: xen: update grant_table.h Update include/xen/interface/grant_table.h to its newest version. This allows to drop some private definitions in grant-table.c and include/xen/grant_table.h. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- include/xen/grant_table.h | 2 - include/xen/interface/grant_table.h | 161 ++++++++++++++++++++++-------------- 2 files changed, 100 insertions(+), 63 deletions(-) (limited to 'include') diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index dfd5bf31cfb9..7d0f2f0037b8 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -57,8 +57,6 @@ #define INVALID_GRANT_REF ((grant_ref_t)-1) #define INVALID_GRANT_HANDLE ((grant_handle_t)-1) -#define GNTTAB_RESERVED_XENSTORE 1 - /* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */ #define NR_GRANT_FRAMES 4 diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h index 3eeabbc7ee09..cebbd99f1f84 100644 --- a/include/xen/interface/grant_table.h +++ b/include/xen/interface/grant_table.h @@ -19,7 +19,8 @@ /* Some rough guidelines on accessing and updating grant-table entries * in a concurrency-safe manner. For more information, Linux contains a - * reference implementation for guest OSes (arch/xen/kernel/grant_table.c). + * reference implementation for guest OSes (drivers/xen/grant_table.c, see + * http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=blob;f=drivers/xen/grant-table.c;hb=HEAD * * NB. WMB is a no-op on current-generation x86 processors. However, a * compiler barrier will still be required. @@ -80,8 +81,9 @@ typedef uint32_t grant_ref_t; */ /* - * Version 1 of the grant table entry structure is maintained purely - * for backwards compatibility. New guests should use version 2. + * Version 1 of the grant table entry structure is maintained largely for + * backwards compatibility. New guests are recommended to support using + * version 2 to overcome version 1 limitations, but to default to version 1. */ struct grant_entry_v1 { /* GTF_xxx: various type and flag information. [XEN,GST] */ @@ -89,12 +91,21 @@ struct grant_entry_v1 { /* The domain being granted foreign privileges. [GST] */ domid_t domid; /* - * GTF_permit_access: Frame that @domid is allowed to map and access. [GST] - * GTF_accept_transfer: Frame whose ownership transferred by @domid. [XEN] + * GTF_permit_access: GFN that @domid is allowed to map and access. [GST] + * GTF_accept_transfer: GFN that @domid is allowed to transfer into. [GST] + * GTF_transfer_completed: MFN whose ownership transferred by @domid + * (non-translated guests only). [XEN] */ uint32_t frame; }; +/* The first few grant table entries will be preserved across grant table + * version changes and may be pre-populated at domain creation by tools. + */ +#define GNTTAB_NR_RESERVED_ENTRIES 8 +#define GNTTAB_RESERVED_CONSOLE 0 +#define GNTTAB_RESERVED_XENSTORE 1 + /* * Type of grant entry. * GTF_invalid: This grant entry grants no privileges. @@ -111,10 +122,13 @@ struct grant_entry_v1 { #define GTF_type_mask (3U<<0) /* - * Subflags for GTF_permit_access. + * Subflags for GTF_permit_access and GTF_transitive. * GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST] * GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN] * GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN] + * Further subflags for GTF_permit_access only. + * GTF_PAT, GTF_PWT, GTF_PCD: (x86) cache attribute flags to be used for + * mappings of the grant [GST] * GTF_sub_page: Grant access to only a subrange of the page. @domid * will only be allowed to copy from the grant, and not * map it. [GST] @@ -125,6 +139,12 @@ struct grant_entry_v1 { #define GTF_reading (1U<<_GTF_reading) #define _GTF_writing (4) #define GTF_writing (1U<<_GTF_writing) +#define _GTF_PWT (5) +#define GTF_PWT (1U<<_GTF_PWT) +#define _GTF_PCD (6) +#define GTF_PCD (1U<<_GTF_PCD) +#define _GTF_PAT (7) +#define GTF_PAT (1U<<_GTF_PAT) #define _GTF_sub_page (8) #define GTF_sub_page (1U<<_GTF_sub_page) @@ -164,8 +184,7 @@ struct grant_entry_header { }; /* - * Version 2 of the grant entry structure, here is a union because three - * different types are suppotted: full_page, sub_page and transitive. + * Version 2 of the grant entry structure. */ union grant_entry_v2 { struct grant_entry_header hdr; @@ -180,9 +199,9 @@ union grant_entry_v2 { * field of the same name in the V1 entry structure. */ struct { - struct grant_entry_header hdr; - uint32_t pad0; - uint64_t frame; + struct grant_entry_header hdr; + uint32_t pad0; + uint64_t frame; } full_page; /* @@ -191,10 +210,10 @@ union grant_entry_v2 { * in frame @frame. */ struct { - struct grant_entry_header hdr; - uint16_t page_off; - uint16_t length; - uint64_t frame; + struct grant_entry_header hdr; + uint16_t page_off; + uint16_t length; + uint64_t frame; } sub_page; /* @@ -202,12 +221,15 @@ union grant_entry_v2 { * grant @gref in domain @trans_domid, as if it was the local * domain. Obviously, the transitive access must be compatible * with the original grant. + * + * The current version of Xen does not allow transitive grants + * to be mapped. */ struct { - struct grant_entry_header hdr; - domid_t trans_domid; - uint16_t pad0; - grant_ref_t gref; + struct grant_entry_header hdr; + domid_t trans_domid; + uint16_t pad0; + grant_ref_t gref; } transitive; uint32_t __spacer[4]; /* Pad to a power of two */ @@ -219,6 +241,21 @@ typedef uint16_t grant_status_t; * GRANT TABLE QUERIES AND USES */ +#define GNTTABOP_map_grant_ref 0 +#define GNTTABOP_unmap_grant_ref 1 +#define GNTTABOP_setup_table 2 +#define GNTTABOP_dump_table 3 +#define GNTTABOP_transfer 4 +#define GNTTABOP_copy 5 +#define GNTTABOP_query_size 6 +#define GNTTABOP_unmap_and_replace 7 +#define GNTTABOP_set_version 8 +#define GNTTABOP_get_status_frames 9 +#define GNTTABOP_get_version 10 +#define GNTTABOP_swap_grant_ref 11 +#define GNTTABOP_cache_flush 12 +/* ` } */ + /* * Handle to track a mapping created via a grant reference. */ @@ -227,7 +264,7 @@ typedef uint32_t grant_handle_t; /* * GNTTABOP_map_grant_ref: Map the grant entry (,) for access * by devices and/or host CPUs. If successful, is a tracking number - * that must be presented later to destroy the mapping(s). On error, + * that must be presented later to destroy the mapping(s). On error, * is a negative status code. * NOTES: * 1. If GNTMAP_device_map is specified then is the address @@ -241,7 +278,6 @@ typedef uint32_t grant_handle_t; * host mapping is destroyed by other means then it is *NOT* guaranteed * to be accounted to the correct grant reference! */ -#define GNTTABOP_map_grant_ref 0 struct gnttab_map_grant_ref { /* IN parameters. */ uint64_t host_addr; @@ -266,7 +302,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_map_grant_ref); * 3. After executing a batch of unmaps, it is guaranteed that no stale * mappings will remain in the device or host TLBs. */ -#define GNTTABOP_unmap_grant_ref 1 struct gnttab_unmap_grant_ref { /* IN parameters. */ uint64_t host_addr; @@ -286,7 +321,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_grant_ref); * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. * 3. Xen may not support more than a single grant-table page per domain. */ -#define GNTTABOP_setup_table 2 struct gnttab_setup_table { /* IN parameters. */ domid_t dom; @@ -301,7 +335,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_setup_table); * GNTTABOP_dump_table: Dump the contents of the grant table to the * xen console. Debugging use only. */ -#define GNTTABOP_dump_table 3 struct gnttab_dump_table { /* IN parameters. */ domid_t dom; @@ -311,17 +344,17 @@ struct gnttab_dump_table { DEFINE_GUEST_HANDLE_STRUCT(gnttab_dump_table); /* - * GNTTABOP_transfer_grant_ref: Transfer to a foreign domain. The - * foreign domain has previously registered its interest in the transfer via - * . + * GNTTABOP_transfer: Transfer to a foreign domain. The foreign domain + * has previously registered its interest in the transfer via . * * Note that, even if the transfer fails, the specified page no longer belongs * to the calling domain *unless* the error is GNTST_bad_page. + * + * Note further that only PV guests can use this operation. */ -#define GNTTABOP_transfer 4 struct gnttab_transfer { /* IN parameters. */ - xen_pfn_t mfn; + xen_pfn_t mfn; domid_t domid; grant_ref_t ref; /* OUT parameters. */ @@ -352,21 +385,20 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_transfer); #define _GNTCOPY_dest_gref (1) #define GNTCOPY_dest_gref (1<<_GNTCOPY_dest_gref) -#define GNTTABOP_copy 5 struct gnttab_copy { - /* IN parameters. */ - struct { - union { - grant_ref_t ref; - xen_pfn_t gmfn; - } u; - domid_t domid; - uint16_t offset; - } source, dest; - uint16_t len; - uint16_t flags; /* GNTCOPY_* */ - /* OUT parameters. */ - int16_t status; + /* IN parameters. */ + struct gnttab_copy_ptr { + union { + grant_ref_t ref; + xen_pfn_t gmfn; + } u; + domid_t domid; + uint16_t offset; + } source, dest; + uint16_t len; + uint16_t flags; /* GNTCOPY_* */ + /* OUT parameters. */ + int16_t status; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy); @@ -377,7 +409,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy); * 1. may be specified as DOMID_SELF. * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. */ -#define GNTTABOP_query_size 6 struct gnttab_query_size { /* IN parameters. */ domid_t dom; @@ -399,7 +430,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_query_size); * 2. After executing a batch of unmaps, it is guaranteed that no stale * mappings will remain in the device or host TLBs. */ -#define GNTTABOP_unmap_and_replace 7 struct gnttab_unmap_and_replace { /* IN parameters. */ uint64_t host_addr; @@ -412,14 +442,12 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_and_replace); /* * GNTTABOP_set_version: Request a particular version of the grant - * table shared table structure. This operation can only be performed - * once in any given domain. It must be performed before any grants - * are activated; otherwise, the domain will be stuck with version 1. - * The only defined versions are 1 and 2. + * table shared table structure. This operation may be used to toggle + * between different versions, but must be performed while no grants + * are active. The only defined versions are 1 and 2. */ -#define GNTTABOP_set_version 8 struct gnttab_set_version { - /* IN parameters */ + /* IN/OUT parameters */ uint32_t version; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version); @@ -436,7 +464,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version); * 1. may be specified as DOMID_SELF. * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. */ -#define GNTTABOP_get_status_frames 9 struct gnttab_get_status_frames { /* IN parameters. */ uint32_t nr_frames; @@ -451,7 +478,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_status_frames); * GNTTABOP_get_version: Get the grant table version which is in * effect for domain . */ -#define GNTTABOP_get_version 10 struct gnttab_get_version { /* IN parameters */ domid_t dom; @@ -461,27 +487,38 @@ struct gnttab_get_version { }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version); +/* + * GNTTABOP_swap_grant_ref: Swap the contents of two grant entries. + */ +struct gnttab_swap_grant_ref { + /* IN parameters */ + grant_ref_t ref_a; + grant_ref_t ref_b; + /* OUT parameters */ + int16_t status; /* GNTST_* */ +}; +DEFINE_GUEST_HANDLE_STRUCT(gnttab_swap_grant_ref); + /* * Issue one or more cache maintenance operations on a portion of a * page granted to the calling domain by a foreign domain. */ -#define GNTTABOP_cache_flush 12 struct gnttab_cache_flush { union { uint64_t dev_bus_addr; grant_ref_t ref; } a; - uint16_t offset; /* offset from start of grant */ - uint16_t length; /* size within the grant */ -#define GNTTAB_CACHE_CLEAN (1<<0) -#define GNTTAB_CACHE_INVAL (1<<1) -#define GNTTAB_CACHE_SOURCE_GREF (1<<31) + uint16_t offset; /* offset from start of grant */ + uint16_t length; /* size within the grant */ +#define GNTTAB_CACHE_CLEAN (1u<<0) +#define GNTTAB_CACHE_INVAL (1u<<1) +#define GNTTAB_CACHE_SOURCE_GREF (1u<<31) uint32_t op; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); /* - * Bitfield values for update_pin_status.flags. + * Bitfield values for gnttab_map_grant_ref.flags. */ /* Map the grant entry for access by I/O devices. */ #define _GNTMAP_device_map (0) @@ -531,6 +568,7 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); #define GNTST_bad_copy_arg (-10) /* copy arguments cross page boundary. */ #define GNTST_address_too_big (-11) /* transfer page address too large. */ #define GNTST_eagain (-12) /* Operation not done; try again. */ +#define GNTST_no_space (-13) /* Out of space (handles etc). */ #define GNTTABOP_error_msgs { \ "okay", \ @@ -545,7 +583,8 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); "bad page", \ "copy arguments cross page boundary", \ "page address size too large", \ - "operation not done; try again" \ + "operation not done; try again", \ + "out of space", \ } #endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */ -- cgit v1.2.3 From 6fac592cca60dca0b2a524c303c83e958c2003bb Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 28 Apr 2022 09:59:01 +0200 Subject: xen: update ring.h Update include/xen/interface/io/ring.h to its newest version. Switch the two improper use cases of RING_HAS_UNCONSUMED_RESPONSES() to XEN_RING_NR_UNCONSUMED_RESPONSES() in order to avoid the nasty XEN_RING_HAS_UNCONSUMED_IS_BOOL #define. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- include/xen/interface/io/ring.h | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index 2470ec45ebb2..ba4c4274b714 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -72,9 +72,8 @@ typedef unsigned int RING_IDX; * of the shared memory area (PAGE_SIZE, for instance). To initialise * the front half: * - * mytag_front_ring_t front_ring; - * SHARED_RING_INIT((mytag_sring_t *)shared_page); - * FRONT_RING_INIT(&front_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); + * mytag_front_ring_t ring; + * XEN_FRONT_RING_INIT(&ring, (mytag_sring_t *)shared_page, PAGE_SIZE); * * Initializing the back follows similarly (note that only the front * initializes the shared ring): @@ -146,6 +145,11 @@ struct __name##_back_ring { \ #define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size) +#define XEN_FRONT_RING_INIT(r, s, size) do { \ + SHARED_RING_INIT(s); \ + FRONT_RING_INIT(r, s, size); \ +} while (0) + #define BACK_RING_ATTACH(_r, _s, _i, __size) do { \ (_r)->rsp_prod_pvt = (_i); \ (_r)->req_cons = (_i); \ @@ -170,16 +174,21 @@ struct __name##_back_ring { \ (RING_FREE_REQUESTS(_r) == 0) /* Test if there are outstanding messages to be processed on a ring. */ -#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ +#define XEN_RING_NR_UNCONSUMED_RESPONSES(_r) \ ((_r)->sring->rsp_prod - (_r)->rsp_cons) -#define RING_HAS_UNCONSUMED_REQUESTS(_r) ({ \ +#define XEN_RING_NR_UNCONSUMED_REQUESTS(_r) ({ \ unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ unsigned int rsp = RING_SIZE(_r) - \ ((_r)->req_cons - (_r)->rsp_prod_pvt); \ req < rsp ? req : rsp; \ }) +#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ + (!!XEN_RING_NR_UNCONSUMED_RESPONSES(_r)) +#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ + (!!XEN_RING_NR_UNCONSUMED_REQUESTS(_r)) + /* Direct access to individual ring elements, by index. */ #define RING_GET_REQUEST(_r, _idx) \ (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req)) -- cgit v1.2.3 From 7050096d07755c53f71e486af18475050cc4e04b Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 28 Apr 2022 09:01:03 +0200 Subject: xen/xenbus: add xenbus_setup_ring() service function Most PV device frontends share very similar code for setting up shared ring buffers: - allocate page(s) - init the ring admin data - give the backend access to the ring via grants Tearing down the ring requires similar actions in all frontends again: - remove grants - free the page(s) Provide service functions xenbus_setup_ring() and xenbus_teardown_ring() for that purpose. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- include/xen/xenbus.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index b13eb86395e0..b533b4adc835 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -226,6 +226,10 @@ int xenbus_watch_pathfmt(struct xenbus_device *dev, struct xenbus_watch *watch, int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state new_state); int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, unsigned int nr_pages, grant_ref_t *grefs); +int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr, + unsigned int nr_pages, grant_ref_t *grefs); +void xenbus_teardown_ring(void **vaddr, unsigned int nr_pages, + grant_ref_t *grefs); int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs, unsigned int nr_grefs, void **vaddr); -- cgit v1.2.3 From 4573240f0764ee79d7558d74fc535baa1e110d20 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 28 Apr 2022 09:01:05 +0200 Subject: xen/xenbus: eliminate xenbus_grant_ring() There is no external user of xenbus_grant_ring() left, so merge it into the only caller xenbus_setup_ring(). Signed-off-by: Juergen Gross Reviewed-by: Oleksandr Tyshchenko Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- include/xen/xenbus.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index b533b4adc835..eaa932b99d8a 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -224,8 +224,6 @@ int xenbus_watch_pathfmt(struct xenbus_device *dev, struct xenbus_watch *watch, const char *pathfmt, ...); int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state new_state); -int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, - unsigned int nr_pages, grant_ref_t *grefs); int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr, unsigned int nr_pages, grant_ref_t *grefs); void xenbus_teardown_ring(void **vaddr, unsigned int nr_pages, -- cgit v1.2.3 From 62db0fafa8fc0f6c9f901e7eefdfc6bbd9731ec9 Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Fri, 13 May 2022 14:19:37 -0700 Subject: xen: sync xs_wire.h header with upstream xen Sync the xs_wire.h header file in Linux with the one in Xen. Signed-off-by: Stefano Stabellini Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20220513211938.719341-1-sstabellini@kernel.org Signed-off-by: Juergen Gross --- include/xen/interface/io/xs_wire.h | 37 +++++++++++++++++++++++++++++++++---- 1 file changed, 33 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h index d40a44f09b16..b62365478ac0 100644 --- a/include/xen/interface/io/xs_wire.h +++ b/include/xen/interface/io/xs_wire.h @@ -10,7 +10,8 @@ enum xsd_sockmsg_type { - XS_DEBUG, + XS_CONTROL, +#define XS_DEBUG XS_CONTROL XS_DIRECTORY, XS_READ, XS_GET_PERMS, @@ -30,8 +31,13 @@ enum xsd_sockmsg_type XS_IS_DOMAIN_INTRODUCED, XS_RESUME, XS_SET_TARGET, - XS_RESTRICT, - XS_RESET_WATCHES, + /* XS_RESTRICT has been removed */ + XS_RESET_WATCHES = XS_SET_TARGET + 2, + XS_DIRECTORY_PART, + + XS_TYPE_COUNT, /* Number of valid types. */ + + XS_INVALID = 0xffff /* Guaranteed to remain an invalid type */ }; #define XS_WRITE_NONE "NONE" @@ -59,7 +65,8 @@ static struct xsd_errors xsd_errors[] __attribute__((unused)) = { XSD_ERROR(EROFS), XSD_ERROR(EBUSY), XSD_ERROR(EAGAIN), - XSD_ERROR(EISCONN) + XSD_ERROR(EISCONN), + XSD_ERROR(E2BIG) }; struct xsd_sockmsg @@ -87,9 +94,31 @@ struct xenstore_domain_interface { char rsp[XENSTORE_RING_SIZE]; /* Replies and async watch events. */ XENSTORE_RING_IDX req_cons, req_prod; XENSTORE_RING_IDX rsp_cons, rsp_prod; + uint32_t server_features; /* Bitmap of features supported by the server */ + uint32_t connection; + uint32_t error; }; /* Violating this is very bad. See docs/misc/xenstore.txt. */ #define XENSTORE_PAYLOAD_MAX 4096 +/* Violating these just gets you an error back */ +#define XENSTORE_ABS_PATH_MAX 3072 +#define XENSTORE_REL_PATH_MAX 2048 + +/* The ability to reconnect a ring */ +#define XENSTORE_SERVER_FEATURE_RECONNECTION 1 +/* The presence of the "error" field in the ring page */ +#define XENSTORE_SERVER_FEATURE_ERROR 2 + +/* Valid values for the connection field */ +#define XENSTORE_CONNECTED 0 /* the steady-state */ +#define XENSTORE_RECONNECT 1 /* guest has initiated a reconnect */ + +/* Valid values for the error field */ +#define XENSTORE_ERROR_NONE 0 /* No error */ +#define XENSTORE_ERROR_COMM 1 /* Communication problem */ +#define XENSTORE_ERROR_RINGIDX 2 /* Invalid ring index */ +#define XENSTORE_ERROR_PROTO 3 /* Protocol violation (payload too long) */ + #endif /* _XS_WIRE_H */ -- cgit v1.2.3 From 81557a71564a8c44ee5b9262d08438b0170a25f3 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Tue, 17 May 2022 10:39:56 +0200 Subject: dt-bindings: pinctrl: Add MediaTek MT6795 pinctrl bindings Add devicetree and pinfunc bindings for MediaTek Helio X10 MT6795. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20220517083957.11816-2-angelogioacchino.delregno@collabora.com Signed-off-by: Linus Walleij --- include/dt-bindings/pinctrl/mt6795-pinfunc.h | 908 +++++++++++++++++++++++++++ 1 file changed, 908 insertions(+) create mode 100644 include/dt-bindings/pinctrl/mt6795-pinfunc.h (limited to 'include') diff --git a/include/dt-bindings/pinctrl/mt6795-pinfunc.h b/include/dt-bindings/pinctrl/mt6795-pinfunc.h new file mode 100644 index 000000000000..bd1c5a9fad06 --- /dev/null +++ b/include/dt-bindings/pinctrl/mt6795-pinfunc.h @@ -0,0 +1,908 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2022 Collabora Ltd. + * Author: AngeloGioacchino Del Regno + */ + +#ifndef __DTS_MT8173_PINFUNC_H +#define __DTS_MT8173_PINFUNC_H + +#include + +#define PINMUX_GPIO0__FUNC_GPIO0 (MTK_PIN_NO(0) | 0) +#define PINMUX_GPIO0__FUNC_IRDA_PDN (MTK_PIN_NO(0) | 1) +#define PINMUX_GPIO0__FUNC_I2S1_WS (MTK_PIN_NO(0) | 2) +#define PINMUX_GPIO0__FUNC_TDD_TMS (MTK_PIN_NO(0) | 4) +#define PINMUX_GPIO0__FUNC_UTXD0 (MTK_PIN_NO(0) | 5) + +#define PINMUX_GPIO1__FUNC_GPIO1 (MTK_PIN_NO(1) | 0) +#define PINMUX_GPIO1__FUNC_IRDA_RXD (MTK_PIN_NO(1) | 1) +#define PINMUX_GPIO1__FUNC_I2S1_BCK (MTK_PIN_NO(1) | 2) +#define PINMUX_GPIO1__FUNC_SDA4 (MTK_PIN_NO(1) | 3) +#define PINMUX_GPIO1__FUNC_TDD_TCK (MTK_PIN_NO(1) | 4) +#define PINMUX_GPIO1__FUNC_URXD0 (MTK_PIN_NO(1) | 5) + +#define PINMUX_GPIO2__FUNC_GPIO2 (MTK_PIN_NO(2) | 0) +#define PINMUX_GPIO2__FUNC_IRDA_TXD (MTK_PIN_NO(2) | 1) +#define PINMUX_GPIO2__FUNC_I2S1_MCK (MTK_PIN_NO(2) | 2) +#define PINMUX_GPIO2__FUNC_SCL4 (MTK_PIN_NO(2) | 3) +#define PINMUX_GPIO2__FUNC_TDD_TDI (MTK_PIN_NO(2) | 4) +#define PINMUX_GPIO2__FUNC_UTXD3 (MTK_PIN_NO(2) | 5) + +#define PINMUX_GPIO3__FUNC_GPIO3 (MTK_PIN_NO(3) | 0) +#define PINMUX_GPIO3__FUNC_DSI1_TE (MTK_PIN_NO(3) | 1) +#define PINMUX_GPIO3__FUNC_I2S1_DO_1 (MTK_PIN_NO(3) | 2) +#define PINMUX_GPIO3__FUNC_SDA3 (MTK_PIN_NO(3) | 3) +#define PINMUX_GPIO3__FUNC_TDD_TDO (MTK_PIN_NO(3) | 4) +#define PINMUX_GPIO3__FUNC_URXD3 (MTK_PIN_NO(3) | 5) + +#define PINMUX_GPIO4__FUNC_GPIO4 (MTK_PIN_NO(4) | 0) +#define PINMUX_GPIO4__FUNC_DISP_PWM1 (MTK_PIN_NO(4) | 1) +#define PINMUX_GPIO4__FUNC_I2S1_DO_2 (MTK_PIN_NO(4) | 2) +#define PINMUX_GPIO4__FUNC_SCL3 (MTK_PIN_NO(4) | 3) +#define PINMUX_GPIO4__FUNC_TDD_TRSTN (MTK_PIN_NO(4) | 4) + +#define PINMUX_GPIO5__FUNC_GPIO5 (MTK_PIN_NO(5) | 0) +#define PINMUX_GPIO5__FUNC_PCM1_CLK (MTK_PIN_NO(5) | 1) +#define PINMUX_GPIO5__FUNC_I2S2_WS (MTK_PIN_NO(5) | 2) +#define PINMUX_GPIO5__FUNC_SPI_CK_3 (MTK_PIN_NO(5) | 3) +#define PINMUX_GPIO5__FUNC_LTE_MD32_JTAG_TMS (MTK_PIN_NO(5) | 4) +#define PINMUX_GPIO5__FUNC_AP_MD32_JTAG_TMS (MTK_PIN_NO(5) | 5) + +#define PINMUX_GPIO6__FUNC_GPIO6 (MTK_PIN_NO(6) | 0) +#define PINMUX_GPIO6__FUNC_PCM1_SYNC (MTK_PIN_NO(6) | 1) +#define PINMUX_GPIO6__FUNC_I2S2_BCK (MTK_PIN_NO(6) | 2) +#define PINMUX_GPIO6__FUNC_SPI_MI_3 (MTK_PIN_NO(6) | 3) +#define PINMUX_GPIO6__FUNC_LTE_MD32_JTAG_TCK (MTK_PIN_NO(6) | 4) +#define PINMUX_GPIO6__FUNC_AP_MD32_JTAG_TCK (MTK_PIN_NO(6) | 5) + +#define PINMUX_GPIO7__FUNC_GPIO7 (MTK_PIN_NO(7) | 0) +#define PINMUX_GPIO7__FUNC_PCM1_DI (MTK_PIN_NO(7) | 1) +#define PINMUX_GPIO7__FUNC_I2S2_DI_1 (MTK_PIN_NO(7) | 2) +#define PINMUX_GPIO7__FUNC_SPI_MO_3 (MTK_PIN_NO(7) | 3) +#define PINMUX_GPIO7__FUNC_LTE_MD32_JTAG_TDI (MTK_PIN_NO(7) | 4) +#define PINMUX_GPIO7__FUNC_AP_MD32_JTAG_TDI (MTK_PIN_NO(7) | 5) + +#define PINMUX_GPIO8__FUNC_GPIO8 (MTK_PIN_NO(8) | 0) +#define PINMUX_GPIO8__FUNC_PCM1_DO (MTK_PIN_NO(8) | 1) +#define PINMUX_GPIO8__FUNC_I2S2_DI_2 (MTK_PIN_NO(8) | 2) +#define PINMUX_GPIO8__FUNC_SPI_CS_3 (MTK_PIN_NO(8) | 3) +#define PINMUX_GPIO8__FUNC_LTE_MD32_JTAG_TDO (MTK_PIN_NO(8) | 4) +#define PINMUX_GPIO8__FUNC_AP_MD32_JTAG_TDO (MTK_PIN_NO(8) | 5) + +#define PINMUX_GPIO9__FUNC_GPIO9 (MTK_PIN_NO(9) | 0) +#define PINMUX_GPIO9__FUNC_USB_DRVVBUS (MTK_PIN_NO(9) | 1) +#define PINMUX_GPIO9__FUNC_I2S2_MCK (MTK_PIN_NO(9) | 2) +#define PINMUX_GPIO9__FUNC_LTE_MD32_JTAG_TRST (MTK_PIN_NO(9) | 4) +#define PINMUX_GPIO9__FUNC_AP_MD32_JTAG_TRST (MTK_PIN_NO(9) | 5) + +#define PINMUX_GPIO10__FUNC_GPIO10 (MTK_PIN_NO(10) | 0) +#define PINMUX_GPIO10__FUNC_I2S0_WS (MTK_PIN_NO(10) | 2) + +#define PINMUX_GPIO11__FUNC_GPIO11 (MTK_PIN_NO(11) | 0) +#define PINMUX_GPIO11__FUNC_I2S0_BCK (MTK_PIN_NO(11) | 2) + +#define PINMUX_GPIO12__FUNC_GPIO12 (MTK_PIN_NO(12) | 0) +#define PINMUX_GPIO12__FUNC_I2S0_MCK (MTK_PIN_NO(12) | 2) + +#define PINMUX_GPIO13__FUNC_GPIO13 (MTK_PIN_NO(13) | 0) +#define PINMUX_GPIO13__FUNC_I2S0_DO (MTK_PIN_NO(13) | 2) + +#define PINMUX_GPIO14__FUNC_GPIO14 (MTK_PIN_NO(14) | 0) +#define PINMUX_GPIO14__FUNC_I2S0_DI (MTK_PIN_NO(14) | 2) +#define PINMUX_GPIO14__FUNC_DISP_PWM1 (MTK_PIN_NO(14) | 3) +#define PINMUX_GPIO14__FUNC_PWM4 (MTK_PIN_NO(14) | 4) +#define PINMUX_GPIO14__FUNC_IRDA_RXD (MTK_PIN_NO(14) | 5) +#define PINMUX_GPIO14__FUNC_I2S1_BCK (MTK_PIN_NO(14) | 6) + +#define PINMUX_GPIO15__FUNC_GPIO15 (MTK_PIN_NO(15) | 0) +#define PINMUX_GPIO15__FUNC_DSI1_TE (MTK_PIN_NO(15) | 2) +#define PINMUX_GPIO15__FUNC_USB_DRVVBUS (MTK_PIN_NO(15) | 3) +#define PINMUX_GPIO15__FUNC_PWM5 (MTK_PIN_NO(15) | 4) +#define PINMUX_GPIO15__FUNC_IRDA_TXD (MTK_PIN_NO(15) | 5) +#define PINMUX_GPIO15__FUNC_I2S1_MCK (MTK_PIN_NO(15) | 6) + +#define PINMUX_GPIO16__FUNC_GPIO16 (MTK_PIN_NO(16) | 0) +#define PINMUX_GPIO16__FUNC_IDDIG (MTK_PIN_NO(16) | 1) +#define PINMUX_GPIO16__FUNC_FLASH (MTK_PIN_NO(16) | 2) +#define PINMUX_GPIO16__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(16) | 3) +#define PINMUX_GPIO16__FUNC_PWM5 (MTK_PIN_NO(16) | 4) + +#define PINMUX_GPIO17__FUNC_GPIO17 (MTK_PIN_NO(17) | 0) +#define PINMUX_GPIO17__FUNC_SIM1_SCLK (MTK_PIN_NO(17) | 1) +#define PINMUX_GPIO17__FUNC_SIM2_SCLK (MTK_PIN_NO(17) | 2) + +#define PINMUX_GPIO18__FUNC_GPIO18 (MTK_PIN_NO(18) | 0) +#define PINMUX_GPIO18__FUNC_SIM1_SRST (MTK_PIN_NO(18) | 1) +#define PINMUX_GPIO18__FUNC_SIM2_SRST (MTK_PIN_NO(18) | 2) + +#define PINMUX_GPIO19__FUNC_GPIO19 (MTK_PIN_NO(19) | 0) +#define PINMUX_GPIO19__FUNC_SIM1_SDAT (MTK_PIN_NO(19) | 1) +#define PINMUX_GPIO19__FUNC_SIM2_SDAT (MTK_PIN_NO(19) | 2) + +#define PINMUX_GPIO20__FUNC_GPIO20 (MTK_PIN_NO(20) | 0) +#define PINMUX_GPIO20__FUNC_SIM2_SCLK (MTK_PIN_NO(20) | 1) +#define PINMUX_GPIO20__FUNC_SIM1_SCLK (MTK_PIN_NO(20) | 2) + +#define PINMUX_GPIO21__FUNC_GPIO21 (MTK_PIN_NO(21) | 0) +#define PINMUX_GPIO21__FUNC_SIM2_SRST (MTK_PIN_NO(21) | 1) +#define PINMUX_GPIO21__FUNC_SIM1_SRST (MTK_PIN_NO(21) | 2) + +#define PINMUX_GPIO22__FUNC_GPIO22 (MTK_PIN_NO(22) | 0) +#define PINMUX_GPIO22__FUNC_SIM2_SDAT (MTK_PIN_NO(22) | 1) +#define PINMUX_GPIO22__FUNC_SIM1_SDAT (MTK_PIN_NO(22) | 2) + +#define PINMUX_GPIO23__FUNC_GPIO23 (MTK_PIN_NO(23) | 0) +#define PINMUX_GPIO23__FUNC_MSDC3_DAT0 (MTK_PIN_NO(23) | 1) + +#define PINMUX_GPIO24__FUNC_GPIO24 (MTK_PIN_NO(24) | 0) +#define PINMUX_GPIO24__FUNC_MSDC3_DAT1 (MTK_PIN_NO(24) | 1) + +#define PINMUX_GPIO25__FUNC_GPIO25 (MTK_PIN_NO(25) | 0) +#define PINMUX_GPIO25__FUNC_MSDC3_DAT2 (MTK_PIN_NO(25) | 1) + +#define PINMUX_GPIO26__FUNC_GPIO26 (MTK_PIN_NO(26) | 0) +#define PINMUX_GPIO26__FUNC_MSDC3_DAT3 (MTK_PIN_NO(26) | 1) + +#define PINMUX_GPIO27__FUNC_GPIO27 (MTK_PIN_NO(27) | 0) +#define PINMUX_GPIO27__FUNC_MSDC3_CLK (MTK_PIN_NO(27) | 1) + +#define PINMUX_GPIO28__FUNC_GPIO28 (MTK_PIN_NO(28) | 0) +#define PINMUX_GPIO28__FUNC_MSDC3_CMD (MTK_PIN_NO(28) | 1) + +#define PINMUX_GPIO29__FUNC_GPIO29 (MTK_PIN_NO(29) | 0) +#define PINMUX_GPIO29__FUNC_PTA_RXD (MTK_PIN_NO(29) | 1) +#define PINMUX_GPIO29__FUNC_UCTS2 (MTK_PIN_NO(29) | 2) + +#define PINMUX_GPIO30__FUNC_GPIO30 (MTK_PIN_NO(30) | 0) +#define PINMUX_GPIO30__FUNC_PTA_TXD (MTK_PIN_NO(30) | 1) +#define PINMUX_GPIO30__FUNC_URTS2 (MTK_PIN_NO(30) | 2) + +#define PINMUX_GPIO31__FUNC_GPIO31 (MTK_PIN_NO(31) | 0) +#define PINMUX_GPIO31__FUNC_URXD2 (MTK_PIN_NO(31) | 1) +#define PINMUX_GPIO31__FUNC_UTXD2 (MTK_PIN_NO(31) | 2) + +#define PINMUX_GPIO32__FUNC_GPIO32 (MTK_PIN_NO(32) | 0) +#define PINMUX_GPIO32__FUNC_UTXD2 (MTK_PIN_NO(32) | 1) +#define PINMUX_GPIO32__FUNC_URXD2 (MTK_PIN_NO(32) | 2) + +#define PINMUX_GPIO33__FUNC_GPIO33 (MTK_PIN_NO(33) | 0) +#define PINMUX_GPIO33__FUNC_MRG_CLK (MTK_PIN_NO(33) | 1) +#define PINMUX_GPIO33__FUNC_PCM0_CLK (MTK_PIN_NO(33) | 2) + +#define PINMUX_GPIO34__FUNC_GPIO34 (MTK_PIN_NO(34) | 0) +#define PINMUX_GPIO34__FUNC_MRG_DI (MTK_PIN_NO(34) | 1) +#define PINMUX_GPIO34__FUNC_PCM0_DI (MTK_PIN_NO(34) | 2) + +#define PINMUX_GPIO35__FUNC_GPIO35 (MTK_PIN_NO(35) | 0) +#define PINMUX_GPIO35__FUNC_MRG_DO (MTK_PIN_NO(35) | 1) +#define PINMUX_GPIO35__FUNC_PCM0_DO (MTK_PIN_NO(35) | 2) + +#define PINMUX_GPIO36__FUNC_GPIO36 (MTK_PIN_NO(36) | 0) +#define PINMUX_GPIO36__FUNC_MRG_SYNC (MTK_PIN_NO(36) | 1) +#define PINMUX_GPIO36__FUNC_PCM0_SYNC (MTK_PIN_NO(36) | 2) + +#define PINMUX_GPIO37__FUNC_GPIO37 (MTK_PIN_NO(37) | 0) +#define PINMUX_GPIO37__FUNC_GPS_SYNC (MTK_PIN_NO(37) | 1) + +#define PINMUX_GPIO38__FUNC_GPIO38 (MTK_PIN_NO(38) | 0) +#define PINMUX_GPIO38__FUNC_DAIRSTB (MTK_PIN_NO(38) | 1) + +#define PINMUX_GPIO39__FUNC_GPIO39 (MTK_PIN_NO(39) | 0) +#define PINMUX_GPIO39__FUNC_CM2MCLK (MTK_PIN_NO(39) | 1) + +#define PINMUX_GPIO40__FUNC_GPIO40 (MTK_PIN_NO(40) | 0) +#define PINMUX_GPIO40__FUNC_CM3MCLK (MTK_PIN_NO(40) | 1) +#define PINMUX_GPIO40__FUNC_IRDA_PDN (MTK_PIN_NO(40) | 2) +#define PINMUX_GPIO40__FUNC_PWM6 (MTK_PIN_NO(40) | 3) +#define PINMUX_GPIO40__FUNC_I2S1_WS (MTK_PIN_NO(40) | 4) + +#define PINMUX_GPIO41__FUNC_GPIO41 (MTK_PIN_NO(41) | 0) +#define PINMUX_GPIO41__FUNC_CMPCLK (MTK_PIN_NO(41) | 1) +#define PINMUX_GPIO41__FUNC_CMCSK (MTK_PIN_NO(41) | 2) +#define PINMUX_GPIO41__FUNC_FLASH (MTK_PIN_NO(41) | 3) + +#define PINMUX_GPIO42__FUNC_GPIO42 (MTK_PIN_NO(42) | 0) +#define PINMUX_GPIO42__FUNC_CMMCLK (MTK_PIN_NO(42) | 1) + +#define PINMUX_GPIO43__FUNC_GPIO43 (MTK_PIN_NO(43) | 0) +#define PINMUX_GPIO43__FUNC_SDA2 (MTK_PIN_NO(43) | 1) + +#define PINMUX_GPIO44__FUNC_GPIO44 (MTK_PIN_NO(44) | 0) +#define PINMUX_GPIO44__FUNC_SCL2 (MTK_PIN_NO(44) | 1) + +#define PINMUX_GPIO45__FUNC_GPIO45 (MTK_PIN_NO(45) | 0) +#define PINMUX_GPIO45__FUNC_SDA0 (MTK_PIN_NO(45) | 1) + +#define PINMUX_GPIO46__FUNC_GPIO46 (MTK_PIN_NO(46) | 0) +#define PINMUX_GPIO46__FUNC_SCL0 (MTK_PIN_NO(46) | 1) + +#define PINMUX_GPIO47__FUNC_GPIO47 (MTK_PIN_NO(47) | 0) +#define PINMUX_GPIO47__FUNC_BPI_BUS0 (MTK_PIN_NO(47) | 1) + +#define PINMUX_GPIO48__FUNC_GPIO48 (MTK_PIN_NO(48) | 0) +#define PINMUX_GPIO48__FUNC_BPI_BUS1 (MTK_PIN_NO(48) | 1) + +#define PINMUX_GPIO49__FUNC_GPIO49 (MTK_PIN_NO(49) | 0) +#define PINMUX_GPIO49__FUNC_BPI_BUS2 (MTK_PIN_NO(49) | 1) + +#define PINMUX_GPIO50__FUNC_GPIO50 (MTK_PIN_NO(50) | 0) +#define PINMUX_GPIO50__FUNC_BPI_BUS3 (MTK_PIN_NO(50) | 1) + +#define PINMUX_GPIO51__FUNC_GPIO51 (MTK_PIN_NO(51) | 0) +#define PINMUX_GPIO51__FUNC_BPI_BUS4 (MTK_PIN_NO(51) | 1) + +#define PINMUX_GPIO52__FUNC_GPIO52 (MTK_PIN_NO(52) | 0) +#define PINMUX_GPIO52__FUNC_BPI_BUS5 (MTK_PIN_NO(52) | 1) + +#define PINMUX_GPIO53__FUNC_GPIO53 (MTK_PIN_NO(53) | 0) +#define PINMUX_GPIO53__FUNC_BPI_BUS6 (MTK_PIN_NO(53) | 1) + +#define PINMUX_GPIO54__FUNC_GPIO54 (MTK_PIN_NO(54) | 0) +#define PINMUX_GPIO54__FUNC_BPI_BUS7 (MTK_PIN_NO(54) | 1) + +#define PINMUX_GPIO55__FUNC_GPIO55 (MTK_PIN_NO(55) | 0) +#define PINMUX_GPIO55__FUNC_BPI_BUS8 (MTK_PIN_NO(55) | 1) + +#define PINMUX_GPIO56__FUNC_GPIO56 (MTK_PIN_NO(56) | 0) +#define PINMUX_GPIO56__FUNC_BPI_BUS9 (MTK_PIN_NO(56) | 1) + +#define PINMUX_GPIO57__FUNC_GPIO57 (MTK_PIN_NO(57) | 0) +#define PINMUX_GPIO57__FUNC_BPI_BUS10 (MTK_PIN_NO(57) | 1) + +#define PINMUX_GPIO58__FUNC_GPIO58 (MTK_PIN_NO(58) | 0) +#define PINMUX_GPIO58__FUNC_BPI_BUS11 (MTK_PIN_NO(58) | 1) + +#define PINMUX_GPIO59__FUNC_GPIO59 (MTK_PIN_NO(59) | 0) +#define PINMUX_GPIO59__FUNC_BPI_BUS12 (MTK_PIN_NO(59) | 1) + +#define PINMUX_GPIO60__FUNC_GPIO60 (MTK_PIN_NO(60) | 0) +#define PINMUX_GPIO60__FUNC_BPI_BUS13 (MTK_PIN_NO(60) | 1) + +#define PINMUX_GPIO61__FUNC_GPIO61 (MTK_PIN_NO(61) | 0) +#define PINMUX_GPIO61__FUNC_BPI_BUS14 (MTK_PIN_NO(61) | 1) + +#define PINMUX_GPIO62__FUNC_GPIO62 (MTK_PIN_NO(62) | 0) +#define PINMUX_GPIO62__FUNC_RFIC1_BSI_CK (MTK_PIN_NO(62) | 1) + +#define PINMUX_GPIO63__FUNC_GPIO63 (MTK_PIN_NO(63) | 0) +#define PINMUX_GPIO63__FUNC_RFIC1_BSI_D0 (MTK_PIN_NO(63) | 1) + +#define PINMUX_GPIO64__FUNC_GPIO64 (MTK_PIN_NO(64) | 0) +#define PINMUX_GPIO64__FUNC_RFIC1_BSI_D1 (MTK_PIN_NO(64) | 1) + +#define PINMUX_GPIO65__FUNC_GPIO65 (MTK_PIN_NO(65) | 0) +#define PINMUX_GPIO65__FUNC_RFIC1_BSI_D2 (MTK_PIN_NO(65) | 1) + +#define PINMUX_GPIO66__FUNC_GPIO66 (MTK_PIN_NO(66) | 0) +#define PINMUX_GPIO66__FUNC_RFIC1_BSI_CS (MTK_PIN_NO(66) | 1) + +#define PINMUX_GPIO67__FUNC_GPIO67 (MTK_PIN_NO(67) | 0) +#define PINMUX_GPIO67__FUNC_TD_TXBPI (MTK_PIN_NO(67) | 1) + +#define PINMUX_GPIO68__FUNC_GPIO68 (MTK_PIN_NO(68) | 0) +#define PINMUX_GPIO68__FUNC_RFIC0_BSI_CK (MTK_PIN_NO(68) | 1) + +#define PINMUX_GPIO69__FUNC_GPIO69 (MTK_PIN_NO(69) | 0) +#define PINMUX_GPIO69__FUNC_RFIC0_BSI_D0 (MTK_PIN_NO(69) | 1) + +#define PINMUX_GPIO70__FUNC_GPIO70 (MTK_PIN_NO(70) | 0) +#define PINMUX_GPIO70__FUNC_RFIC0_BSI_D1 (MTK_PIN_NO(70) | 1) + +#define PINMUX_GPIO71__FUNC_GPIO71 (MTK_PIN_NO(71) | 0) +#define PINMUX_GPIO71__FUNC_RFIC0_BSI_D2 (MTK_PIN_NO(71) | 1) + +#define PINMUX_GPIO72__FUNC_GPIO72 (MTK_PIN_NO(72) | 0) +#define PINMUX_GPIO72__FUNC_RFIC0_BSI_CS (MTK_PIN_NO(72) | 1) + +#define PINMUX_GPIO73__FUNC_GPIO73 (MTK_PIN_NO(73) | 0) +#define PINMUX_GPIO73__FUNC_MISC_BSI_DO (MTK_PIN_NO(73) | 1) + +#define PINMUX_GPIO74__FUNC_GPIO74 (MTK_PIN_NO(74) | 0) +#define PINMUX_GPIO74__FUNC_MISC_BSI_CK (MTK_PIN_NO(74) | 1) + +#define PINMUX_GPIO75__FUNC_GPIO75 (MTK_PIN_NO(75) | 0) +#define PINMUX_GPIO75__FUNC_MISC_BSI_CS0B (MTK_PIN_NO(75) | 1) +#define PINMUX_GPIO75__FUNC_MIPI1_SCLK (MTK_PIN_NO(75) | 2) + +#define PINMUX_GPIO76__FUNC_GPIO76 (MTK_PIN_NO(76) | 0) +#define PINMUX_GPIO76__FUNC_MISC_BSI_CS1B (MTK_PIN_NO(76) | 1) + +#define PINMUX_GPIO77__FUNC_GPIO77 (MTK_PIN_NO(77) | 0) +#define PINMUX_GPIO77__FUNC_MISC_BSI_DI (MTK_PIN_NO(77) | 1) +#define PINMUX_GPIO77__FUNC_MIPI1_SDATA (MTK_PIN_NO(77) | 2) + +#define PINMUX_GPIO78__FUNC_GPIO78 (MTK_PIN_NO(78) | 0) +#define PINMUX_GPIO78__FUNC_LTE_TXBPI (MTK_PIN_NO(78) | 1) + +#define PINMUX_GPIO79__FUNC_GPIO79 (MTK_PIN_NO(79) | 0) +#define PINMUX_GPIO79__FUNC_BPI_BUS15 (MTK_PIN_NO(79) | 1) + +#define PINMUX_GPIO80__FUNC_GPIO80 (MTK_PIN_NO(80) | 0) +#define PINMUX_GPIO80__FUNC_BPI_BUS16 (MTK_PIN_NO(80) | 1) + +#define PINMUX_GPIO81__FUNC_GPIO81 (MTK_PIN_NO(81) | 0) +#define PINMUX_GPIO81__FUNC_BPI_BUS17 (MTK_PIN_NO(81) | 1) + +#define PINMUX_GPIO82__FUNC_GPIO82 (MTK_PIN_NO(82) | 0) +#define PINMUX_GPIO82__FUNC_BPI_BUS18 (MTK_PIN_NO(82) | 1) + +#define PINMUX_GPIO83__FUNC_GPIO83 (MTK_PIN_NO(83) | 0) +#define PINMUX_GPIO83__FUNC_BPI_BUS19 (MTK_PIN_NO(83) | 1) + +#define PINMUX_GPIO84__FUNC_GPIO84 (MTK_PIN_NO(84) | 0) +#define PINMUX_GPIO84__FUNC_BPI_BUS20 (MTK_PIN_NO(84) | 1) + +#define PINMUX_GPIO85__FUNC_GPIO85 (MTK_PIN_NO(85) | 0) +#define PINMUX_GPIO85__FUNC_BPI_BUS21 (MTK_PIN_NO(85) | 1) + +#define PINMUX_GPIO86__FUNC_GPIO86 (MTK_PIN_NO(86) | 0) +#define PINMUX_GPIO86__FUNC_BPI_BUS22 (MTK_PIN_NO(86) | 1) + +#define PINMUX_GPIO87__FUNC_GPIO87 (MTK_PIN_NO(87) | 0) +#define PINMUX_GPIO87__FUNC_BPI_BUS23 (MTK_PIN_NO(87) | 1) + +#define PINMUX_GPIO88__FUNC_GPIO88 (MTK_PIN_NO(88) | 0) +#define PINMUX_GPIO88__FUNC_BPI_BUS24 (MTK_PIN_NO(88) | 1) + +#define PINMUX_GPIO89__FUNC_GPIO89 (MTK_PIN_NO(89) | 0) +#define PINMUX_GPIO89__FUNC_BPI_BUS25 (MTK_PIN_NO(89) | 1) + +#define PINMUX_GPIO90__FUNC_GPIO90 (MTK_PIN_NO(90) | 0) +#define PINMUX_GPIO90__FUNC_BPI_BUS26 (MTK_PIN_NO(90) | 1) + +#define PINMUX_GPIO91__FUNC_GPIO91 (MTK_PIN_NO(91) | 0) +#define PINMUX_GPIO91__FUNC_BPI_BUS27 (MTK_PIN_NO(91) | 1) + +#define PINMUX_GPIO92__FUNC_GPIO92 (MTK_PIN_NO(92) | 0) +#define PINMUX_GPIO92__FUNC_PCM1_CLK (MTK_PIN_NO(92) | 1) +#define PINMUX_GPIO92__FUNC_I2S0_BCK (MTK_PIN_NO(92) | 2) +#define PINMUX_GPIO92__FUNC_NLD6 (MTK_PIN_NO(92) | 3) + +#define PINMUX_GPIO93__FUNC_GPIO93 (MTK_PIN_NO(93) | 0) +#define PINMUX_GPIO93__FUNC_PCM1_SYNC (MTK_PIN_NO(93) | 1) +#define PINMUX_GPIO93__FUNC_I2S0_WS (MTK_PIN_NO(93) | 2) +#define PINMUX_GPIO93__FUNC_NLD7 (MTK_PIN_NO(93) | 3) + +#define PINMUX_GPIO94__FUNC_GPIO94 (MTK_PIN_NO(94) | 0) +#define PINMUX_GPIO94__FUNC_PCM1_DI (MTK_PIN_NO(94) | 1) +#define PINMUX_GPIO94__FUNC_I2S0_DI (MTK_PIN_NO(94) | 2) +#define PINMUX_GPIO94__FUNC_NREB (MTK_PIN_NO(94) | 3) + +#define PINMUX_GPIO95__FUNC_GPIO95 (MTK_PIN_NO(95) | 0) +#define PINMUX_GPIO95__FUNC_PCM1_DO (MTK_PIN_NO(95) | 1) +#define PINMUX_GPIO95__FUNC_I2S0_DO (MTK_PIN_NO(95) | 2) +#define PINMUX_GPIO95__FUNC_NRNB0 (MTK_PIN_NO(95) | 3) + +#define PINMUX_GPIO96__FUNC_GPIO96 (MTK_PIN_NO(96) | 0) +#define PINMUX_GPIO96__FUNC_URXD1 (MTK_PIN_NO(96) | 1) +#define PINMUX_GPIO96__FUNC_UTXD1 (MTK_PIN_NO(96) | 2) +#define PINMUX_GPIO96__FUNC_NWEB (MTK_PIN_NO(96) | 3) + +#define PINMUX_GPIO97__FUNC_GPIO97 (MTK_PIN_NO(97) | 0) +#define PINMUX_GPIO97__FUNC_UTXD1 (MTK_PIN_NO(97) | 1) +#define PINMUX_GPIO97__FUNC_URXD1 (MTK_PIN_NO(97) | 2) +#define PINMUX_GPIO97__FUNC_NCEB0 (MTK_PIN_NO(97) | 3) + +#define PINMUX_GPIO98__FUNC_GPIO98 (MTK_PIN_NO(98) | 0) +#define PINMUX_GPIO98__FUNC_URTS1 (MTK_PIN_NO(98) | 1) +#define PINMUX_GPIO98__FUNC_UCTS1 (MTK_PIN_NO(98) | 2) +#define PINMUX_GPIO98__FUNC_NALE (MTK_PIN_NO(98) | 3) + +#define PINMUX_GPIO99__FUNC_GPIO99 (MTK_PIN_NO(99) | 0) +#define PINMUX_GPIO99__FUNC_UCTS1 (MTK_PIN_NO(99) | 1) +#define PINMUX_GPIO99__FUNC_URTS1 (MTK_PIN_NO(99) | 2) +#define PINMUX_GPIO99__FUNC_NCLE (MTK_PIN_NO(99) | 3) + +#define PINMUX_GPIO100__FUNC_GPIO100 (MTK_PIN_NO(100) | 0) +#define PINMUX_GPIO100__FUNC_MSDC2_DAT0 (MTK_PIN_NO(100) | 1) +#define PINMUX_GPIO100__FUNC_URXD1 (MTK_PIN_NO(100) | 2) +#define PINMUX_GPIO100__FUNC_USB_DRVVBUS (MTK_PIN_NO(100) | 3) +#define PINMUX_GPIO100__FUNC_SDA4 (MTK_PIN_NO(100) | 4) + +#define PINMUX_GPIO101__FUNC_GPIO101 (MTK_PIN_NO(101) | 0) +#define PINMUX_GPIO101__FUNC_MSDC2_DAT1 (MTK_PIN_NO(101) | 1) +#define PINMUX_GPIO101__FUNC_UTXD1 (MTK_PIN_NO(101) | 2) +#define PINMUX_GPIO101__FUNC_SCL4 (MTK_PIN_NO(101) | 4) + +#define PINMUX_GPIO102__FUNC_GPIO102 (MTK_PIN_NO(102) | 0) +#define PINMUX_GPIO102__FUNC_MSDC2_DAT2 (MTK_PIN_NO(102) | 1) +#define PINMUX_GPIO102__FUNC_URTS1 (MTK_PIN_NO(102) | 2) +#define PINMUX_GPIO102__FUNC_UTXD0 (MTK_PIN_NO(102) | 3) +#define PINMUX_GPIO102__FUNC_PWM0 (MTK_PIN_NO(102) | 5) +#define PINMUX_GPIO102__FUNC_SPI_CK_1 (MTK_PIN_NO(102) | 6) + +#define PINMUX_GPIO103__FUNC_GPIO103 (MTK_PIN_NO(103) | 0) +#define PINMUX_GPIO103__FUNC_MSDC2_DAT3 (MTK_PIN_NO(103) | 1) +#define PINMUX_GPIO103__FUNC_UCTS1 (MTK_PIN_NO(103) | 2) +#define PINMUX_GPIO103__FUNC_URXD0 (MTK_PIN_NO(103) | 3) +#define PINMUX_GPIO103__FUNC_PWM1 (MTK_PIN_NO(103) | 5) +#define PINMUX_GPIO103__FUNC_SPI_MI_1 (MTK_PIN_NO(103) | 6) + +#define PINMUX_GPIO104__FUNC_GPIO104 (MTK_PIN_NO(104) | 0) +#define PINMUX_GPIO104__FUNC_MSDC2_CLK (MTK_PIN_NO(104) | 1) +#define PINMUX_GPIO104__FUNC_NLD4 (MTK_PIN_NO(104) | 2) +#define PINMUX_GPIO104__FUNC_UTXD3 (MTK_PIN_NO(104) | 3) +#define PINMUX_GPIO104__FUNC_SDA3 (MTK_PIN_NO(104) | 4) +#define PINMUX_GPIO104__FUNC_PWM2 (MTK_PIN_NO(104) | 5) +#define PINMUX_GPIO104__FUNC_SPI_MO_1 (MTK_PIN_NO(104) | 6) + +#define PINMUX_GPIO105__FUNC_GPIO105 (MTK_PIN_NO(105) | 0) +#define PINMUX_GPIO105__FUNC_MSDC2_CMD (MTK_PIN_NO(105) | 1) +#define PINMUX_GPIO105__FUNC_NLD5 (MTK_PIN_NO(105) | 2) +#define PINMUX_GPIO105__FUNC_URXD3 (MTK_PIN_NO(105) | 3) +#define PINMUX_GPIO105__FUNC_SCL3 (MTK_PIN_NO(105) | 4) +#define PINMUX_GPIO105__FUNC_PWM3 (MTK_PIN_NO(105) | 5) +#define PINMUX_GPIO105__FUNC_SPI_CS_1 (MTK_PIN_NO(105) | 6) + +#define PINMUX_GPIO106__FUNC_GPIO106 (MTK_PIN_NO(106) | 0) +#define PINMUX_GPIO106__FUNC_LCM_RST (MTK_PIN_NO(106) | 1) + +#define PINMUX_GPIO107__FUNC_GPIO107 (MTK_PIN_NO(107) | 0) +#define PINMUX_GPIO107__FUNC_DSI_TE (MTK_PIN_NO(107) | 1) + +#define PINMUX_GPIO108__FUNC_GPIO108 (MTK_PIN_NO(108) | 0) +#define PINMUX_GPIO108__FUNC_JTMS (MTK_PIN_NO(108) | 1) +#define PINMUX_GPIO108__FUNC_MFG_JTAG_TMS (MTK_PIN_NO(108) | 2) +#define PINMUX_GPIO108__FUNC_TDD_TMS (MTK_PIN_NO(108) | 3) +#define PINMUX_GPIO108__FUNC_LTE_MD32_JTAG_TMS (MTK_PIN_NO(108) | 4) +#define PINMUX_GPIO108__FUNC_AP_MD32_JTAG_TMS (MTK_PIN_NO(108) | 5) +#define PINMUX_GPIO108__FUNC_DFD_TMS (MTK_PIN_NO(108) | 6) + +#define PINMUX_GPIO109__FUNC_GPIO109 (MTK_PIN_NO(109) | 0) +#define PINMUX_GPIO109__FUNC_JTCK (MTK_PIN_NO(109) | 1) +#define PINMUX_GPIO109__FUNC_MFG_JTAG_TCK (MTK_PIN_NO(109) | 2) +#define PINMUX_GPIO109__FUNC_TDD_TCK (MTK_PIN_NO(109) | 3) +#define PINMUX_GPIO109__FUNC_LTE_MD32_JTAG_TCK (MTK_PIN_NO(109) | 4) +#define PINMUX_GPIO109__FUNC_AP_MD32_JTAG_TCK (MTK_PIN_NO(109) | 5) +#define PINMUX_GPIO109__FUNC_DFD_TCK (MTK_PIN_NO(109) | 6) + +#define PINMUX_GPIO110__FUNC_GPIO110 (MTK_PIN_NO(110) | 0) +#define PINMUX_GPIO110__FUNC_JTDI (MTK_PIN_NO(110) | 1) +#define PINMUX_GPIO110__FUNC_MFG_JTAG_TDI (MTK_PIN_NO(110) | 2) +#define PINMUX_GPIO110__FUNC_TDD_TDI (MTK_PIN_NO(110) | 3) +#define PINMUX_GPIO110__FUNC_LTE_MD32_JTAG_TDI (MTK_PIN_NO(110) | 4) +#define PINMUX_GPIO110__FUNC_AP_MD32_JTAG_TDI (MTK_PIN_NO(110) | 5) +#define PINMUX_GPIO110__FUNC_DFD_TDI (MTK_PIN_NO(110) | 6) + +#define PINMUX_GPIO111__FUNC_GPIO111 (MTK_PIN_NO(111) | 0) +#define PINMUX_GPIO111__FUNC_JTDO (MTK_PIN_NO(111) | 1) +#define PINMUX_GPIO111__FUNC_MFG_JTAG_TDO (MTK_PIN_NO(111) | 2) +#define PINMUX_GPIO111__FUNC_TDD_TDO (MTK_PIN_NO(111) | 3) +#define PINMUX_GPIO111__FUNC_LTE_MD32_JTAG_TDO (MTK_PIN_NO(111) | 4) +#define PINMUX_GPIO111__FUNC_AP_MD32_JTAG_TDO (MTK_PIN_NO(111) | 5) +#define PINMUX_GPIO111__FUNC_DFD_TDO (MTK_PIN_NO(111) | 6) + +#define PINMUX_GPIO112__FUNC_GPIO112 (MTK_PIN_NO(112) | 0) +#define PINMUX_GPIO112__FUNC_JTRST_B (MTK_PIN_NO(112) | 1) +#define PINMUX_GPIO112__FUNC_MFG_JTAG_TRSTN (MTK_PIN_NO(112) | 2) +#define PINMUX_GPIO112__FUNC_TDD_TRSTN (MTK_PIN_NO(112) | 3) +#define PINMUX_GPIO112__FUNC_LTE_MD32_JTAG_TRST (MTK_PIN_NO(112) | 4) +#define PINMUX_GPIO112__FUNC_AP_MD32_JTAG_TRST (MTK_PIN_NO(112) | 5) +#define PINMUX_GPIO112__FUNC_DFD_NTRST (MTK_PIN_NO(112) | 6) + +#define PINMUX_GPIO113__FUNC_GPIO113 (MTK_PIN_NO(113) | 0) +#define PINMUX_GPIO113__FUNC_URXD0 (MTK_PIN_NO(113) | 1) +#define PINMUX_GPIO113__FUNC_UTXD0 (MTK_PIN_NO(113) | 2) +#define PINMUX_GPIO113__FUNC_MD_URXD (MTK_PIN_NO(113) | 3) +#define PINMUX_GPIO113__FUNC_LTE_URXD (MTK_PIN_NO(113) | 4) +#define PINMUX_GPIO113__FUNC_TDD_TXD (MTK_PIN_NO(113) | 5) +#define PINMUX_GPIO113__FUNC_I2S2_WS (MTK_PIN_NO(113) | 6) + +#define PINMUX_GPIO114__FUNC_GPIO114 (MTK_PIN_NO(114) | 0) +#define PINMUX_GPIO114__FUNC_UTXD0 (MTK_PIN_NO(114) | 1) +#define PINMUX_GPIO114__FUNC_URXD0 (MTK_PIN_NO(114) | 2) +#define PINMUX_GPIO114__FUNC_MD_UTXD (MTK_PIN_NO(114) | 3) +#define PINMUX_GPIO114__FUNC_LTE_UTXD (MTK_PIN_NO(114) | 4) +#define PINMUX_GPIO114__FUNC_TDD_TXD (MTK_PIN_NO(114) | 5) +#define PINMUX_GPIO114__FUNC_I2S2_BCK (MTK_PIN_NO(114) | 6) + +#define PINMUX_GPIO115__FUNC_GPIO115 (MTK_PIN_NO(115) | 0) +#define PINMUX_GPIO115__FUNC_URTS0 (MTK_PIN_NO(115) | 1) +#define PINMUX_GPIO115__FUNC_UCTS0 (MTK_PIN_NO(115) | 2) +#define PINMUX_GPIO115__FUNC_MD_URXD (MTK_PIN_NO(115) | 3) +#define PINMUX_GPIO115__FUNC_LTE_URXD (MTK_PIN_NO(115) | 4) +#define PINMUX_GPIO115__FUNC_TDD_TXD (MTK_PIN_NO(115) | 5) +#define PINMUX_GPIO115__FUNC_I2S2_MCK (MTK_PIN_NO(115) | 6) + +#define PINMUX_GPIO116__FUNC_GPIO116 (MTK_PIN_NO(116) | 0) +#define PINMUX_GPIO116__FUNC_UCTS0 (MTK_PIN_NO(116) | 1) +#define PINMUX_GPIO116__FUNC_URTS0 (MTK_PIN_NO(116) | 2) +#define PINMUX_GPIO116__FUNC_MD_UTXD (MTK_PIN_NO(116) | 3) +#define PINMUX_GPIO116__FUNC_LTE_UTXD (MTK_PIN_NO(116) | 4) +#define PINMUX_GPIO116__FUNC_TDD_TXD (MTK_PIN_NO(116) | 5) +#define PINMUX_GPIO116__FUNC_I2S2_DI_1 (MTK_PIN_NO(116) | 6) + +#define PINMUX_GPIO117__FUNC_GPIO117 (MTK_PIN_NO(117) | 0) +#define PINMUX_GPIO117__FUNC_URXD3 (MTK_PIN_NO(117) | 1) +#define PINMUX_GPIO117__FUNC_UTXD3 (MTK_PIN_NO(117) | 2) +#define PINMUX_GPIO117__FUNC_MD_URXD (MTK_PIN_NO(117) | 3) +#define PINMUX_GPIO117__FUNC_LTE_URXD (MTK_PIN_NO(117) | 4) +#define PINMUX_GPIO117__FUNC_TDD_TXD (MTK_PIN_NO(117) | 5) + +#define PINMUX_GPIO118__FUNC_GPIO118 (MTK_PIN_NO(118) | 0) +#define PINMUX_GPIO118__FUNC_UTXD3 (MTK_PIN_NO(118) | 1) +#define PINMUX_GPIO118__FUNC_URXD3 (MTK_PIN_NO(118) | 2) +#define PINMUX_GPIO118__FUNC_MD_UTXD (MTK_PIN_NO(118) | 3) +#define PINMUX_GPIO118__FUNC_LTE_UTXD (MTK_PIN_NO(118) | 4) +#define PINMUX_GPIO118__FUNC_TDD_TXD (MTK_PIN_NO(118) | 5) + +#define PINMUX_GPIO119__FUNC_GPIO119 (MTK_PIN_NO(119) | 0) +#define PINMUX_GPIO119__FUNC_KROW0 (MTK_PIN_NO(119) | 1) + +#define PINMUX_GPIO120__FUNC_GPIO120 (MTK_PIN_NO(120) | 0) +#define PINMUX_GPIO120__FUNC_KROW1 (MTK_PIN_NO(120) | 1) +#define PINMUX_GPIO120__FUNC_PWM6 (MTK_PIN_NO(120) | 3) + +#define PINMUX_GPIO121__FUNC_GPIO121 (MTK_PIN_NO(121) | 0) +#define PINMUX_GPIO121__FUNC_KROW2 (MTK_PIN_NO(121) | 1) +#define PINMUX_GPIO121__FUNC_IRDA_PDN (MTK_PIN_NO(121) | 2) +#define PINMUX_GPIO121__FUNC_I2S1_DO_1 (MTK_PIN_NO(121) | 3) +#define PINMUX_GPIO121__FUNC_USB_DRVVBUS (MTK_PIN_NO(121) | 4) +#define PINMUX_GPIO121__FUNC_SPI_CK_2 (MTK_PIN_NO(121) | 5) +#define PINMUX_GPIO121__FUNC_PWM4 (MTK_PIN_NO(121) | 6) + +#define PINMUX_GPIO122__FUNC_GPIO122 (MTK_PIN_NO(122) | 0) +#define PINMUX_GPIO122__FUNC_KCOL0 (MTK_PIN_NO(122) | 1) + +#define PINMUX_GPIO123__FUNC_GPIO123 (MTK_PIN_NO(123) | 0) +#define PINMUX_GPIO123__FUNC_KCOL1 (MTK_PIN_NO(123) | 1) +#define PINMUX_GPIO123__FUNC_IRDA_RXD (MTK_PIN_NO(123) | 2) +#define PINMUX_GPIO123__FUNC_I2S2_DI_2 (MTK_PIN_NO(123) | 3) +#define PINMUX_GPIO123__FUNC_PWM5 (MTK_PIN_NO(123) | 4) + +#define PINMUX_GPIO124__FUNC_GPIO124 (MTK_PIN_NO(124) | 0) +#define PINMUX_GPIO124__FUNC_KCOL2 (MTK_PIN_NO(124) | 1) +#define PINMUX_GPIO124__FUNC_IRDA_TXD (MTK_PIN_NO(124) | 2) +#define PINMUX_GPIO124__FUNC_I2S1_DO_2 (MTK_PIN_NO(124) | 3) +#define PINMUX_GPIO124__FUNC_USB_DRVVBUS (MTK_PIN_NO(124) | 4) +#define PINMUX_GPIO124__FUNC_SPI_MI_2 (MTK_PIN_NO(124) | 5) +#define PINMUX_GPIO124__FUNC_PWM3 (MTK_PIN_NO(124) | 6) + +#define PINMUX_GPIO125__FUNC_GPIO125 (MTK_PIN_NO(125) | 0) +#define PINMUX_GPIO125__FUNC_SDA1 (MTK_PIN_NO(125) | 1) + +#define PINMUX_GPIO126__FUNC_GPIO126 (MTK_PIN_NO(126) | 0) +#define PINMUX_GPIO126__FUNC_SCL1 (MTK_PIN_NO(126) | 1) + +#define PINMUX_GPIO127__FUNC_GPIO127 (MTK_PIN_NO(127) | 0) +#define PINMUX_GPIO127__FUNC_MD_EINT1 (MTK_PIN_NO(127) | 1) +#define PINMUX_GPIO127__FUNC_DISP_PWM1 (MTK_PIN_NO(127) | 2) +#define PINMUX_GPIO127__FUNC_SPI_MO_2 (MTK_PIN_NO(127) | 3) + +#define PINMUX_GPIO128__FUNC_GPIO128 (MTK_PIN_NO(128) | 0) +#define PINMUX_GPIO128__FUNC_MD_EINT2 (MTK_PIN_NO(128) | 1) +#define PINMUX_GPIO128__FUNC_DSI1_TE (MTK_PIN_NO(128) | 2) +#define PINMUX_GPIO128__FUNC_SPI_CS_2 (MTK_PIN_NO(128) | 3) + +#define PINMUX_GPIO129__FUNC_GPIO129 (MTK_PIN_NO(129) | 0) +#define PINMUX_GPIO129__FUNC_I2S3_WS (MTK_PIN_NO(129) | 1) +#define PINMUX_GPIO129__FUNC_I2S2_WS (MTK_PIN_NO(129) | 2) +#define PINMUX_GPIO129__FUNC_PWM0 (MTK_PIN_NO(129) | 3) + +#define PINMUX_GPIO130__FUNC_GPIO130 (MTK_PIN_NO(130) | 0) +#define PINMUX_GPIO130__FUNC_I2S3_BCK (MTK_PIN_NO(130) | 1) +#define PINMUX_GPIO130__FUNC_I2S2_BCK (MTK_PIN_NO(130) | 2) +#define PINMUX_GPIO130__FUNC_PWM1 (MTK_PIN_NO(130) | 3) + +#define PINMUX_GPIO131__FUNC_GPIO131 (MTK_PIN_NO(131) | 0) +#define PINMUX_GPIO131__FUNC_I2S3_MCK (MTK_PIN_NO(131) | 1) +#define PINMUX_GPIO131__FUNC_I2S2_MCK (MTK_PIN_NO(131) | 2) +#define PINMUX_GPIO131__FUNC_PWM2 (MTK_PIN_NO(131) | 3) + +#define PINMUX_GPIO132__FUNC_GPIO132 (MTK_PIN_NO(132) | 0) +#define PINMUX_GPIO132__FUNC_I2S3_DO_1 (MTK_PIN_NO(132) | 1) +#define PINMUX_GPIO132__FUNC_I2S2_DI_1 (MTK_PIN_NO(132) | 2) +#define PINMUX_GPIO132__FUNC_PWM3 (MTK_PIN_NO(132) | 3) + +#define PINMUX_GPIO133__FUNC_GPIO133 (MTK_PIN_NO(133) | 0) +#define PINMUX_GPIO133__FUNC_I2S3_DO_2 (MTK_PIN_NO(133) | 1) +#define PINMUX_GPIO133__FUNC_I2S2_DI_2 (MTK_PIN_NO(133) | 2) +#define PINMUX_GPIO133__FUNC_PWM4 (MTK_PIN_NO(133) | 3) + +#define PINMUX_GPIO134__FUNC_GPIO134 (MTK_PIN_NO(134) | 0) +#define PINMUX_GPIO134__FUNC_I2S3_DO_3 (MTK_PIN_NO(134) | 1) +#define PINMUX_GPIO134__FUNC_DISP_PWM1 (MTK_PIN_NO(134) | 2) +#define PINMUX_GPIO134__FUNC_I2S1_DO_1 (MTK_PIN_NO(134) | 3) +#define PINMUX_GPIO134__FUNC_PWM5 (MTK_PIN_NO(134) | 4) + +#define PINMUX_GPIO135__FUNC_GPIO135 (MTK_PIN_NO(135) | 0) +#define PINMUX_GPIO135__FUNC_I2S3_DO_4 (MTK_PIN_NO(135) | 1) +#define PINMUX_GPIO135__FUNC_DSI1_TE (MTK_PIN_NO(135) | 2) +#define PINMUX_GPIO135__FUNC_I2S1_DO_2 (MTK_PIN_NO(135) | 3) +#define PINMUX_GPIO135__FUNC_PWM6 (MTK_PIN_NO(135) | 4) + +#define PINMUX_GPIO136__FUNC_GPIO136 (MTK_PIN_NO(136) | 0) +#define PINMUX_GPIO136__FUNC_SDA3 (MTK_PIN_NO(136) | 1) + +#define PINMUX_GPIO137__FUNC_GPIO137 (MTK_PIN_NO(137) | 0) +#define PINMUX_GPIO137__FUNC_SCL3 (MTK_PIN_NO(137) | 1) + +#define PINMUX_GPIO138__FUNC_GPIO138 (MTK_PIN_NO(138) | 0) +#define PINMUX_GPIO138__FUNC_DPI_CK (MTK_PIN_NO(138) | 1) +#define PINMUX_GPIO138__FUNC_NLD6 (MTK_PIN_NO(138) | 2) +#define PINMUX_GPIO138__FUNC_UTXD0 (MTK_PIN_NO(138) | 3) +#define PINMUX_GPIO138__FUNC_USB_DRVVBUS (MTK_PIN_NO(138) | 4) +#define PINMUX_GPIO138__FUNC_IRDA_PDN (MTK_PIN_NO(138) | 5) + +#define PINMUX_GPIO139__FUNC_GPIO139 (MTK_PIN_NO(139) | 0) +#define PINMUX_GPIO139__FUNC_DPI_DE (MTK_PIN_NO(139) | 1) +#define PINMUX_GPIO139__FUNC_NLD7 (MTK_PIN_NO(139) | 2) +#define PINMUX_GPIO139__FUNC_URXD0 (MTK_PIN_NO(139) | 3) +#define PINMUX_GPIO139__FUNC_MD_UTXD (MTK_PIN_NO(139) | 4) +#define PINMUX_GPIO139__FUNC_IRDA_RXD (MTK_PIN_NO(139) | 5) + +#define PINMUX_GPIO140__FUNC_GPIO140 (MTK_PIN_NO(140) | 0) +#define PINMUX_GPIO140__FUNC_DPI_D0 (MTK_PIN_NO(140) | 1) +#define PINMUX_GPIO140__FUNC_NREB (MTK_PIN_NO(140) | 2) +#define PINMUX_GPIO140__FUNC_UCTS0 (MTK_PIN_NO(140) | 3) +#define PINMUX_GPIO140__FUNC_MD_URXD (MTK_PIN_NO(140) | 4) +#define PINMUX_GPIO140__FUNC_IRDA_TXD (MTK_PIN_NO(140) | 5) + +#define PINMUX_GPIO141__FUNC_GPIO141 (MTK_PIN_NO(141) | 0) +#define PINMUX_GPIO141__FUNC_DPI_D1 (MTK_PIN_NO(141) | 1) +#define PINMUX_GPIO141__FUNC_NRNB0 (MTK_PIN_NO(141) | 2) +#define PINMUX_GPIO141__FUNC_URTS0 (MTK_PIN_NO(141) | 3) +#define PINMUX_GPIO141__FUNC_LTE_UTXD (MTK_PIN_NO(141) | 4) +#define PINMUX_GPIO141__FUNC_I2S2_WS (MTK_PIN_NO(141) | 5) + +#define PINMUX_GPIO142__FUNC_GPIO142 (MTK_PIN_NO(142) | 0) +#define PINMUX_GPIO142__FUNC_DPI_D2 (MTK_PIN_NO(142) | 1) +#define PINMUX_GPIO142__FUNC_NWEB (MTK_PIN_NO(142) | 2) +#define PINMUX_GPIO142__FUNC_UTXD1 (MTK_PIN_NO(142) | 3) +#define PINMUX_GPIO142__FUNC_LTE_URXD (MTK_PIN_NO(142) | 4) +#define PINMUX_GPIO142__FUNC_I2S2_BCK (MTK_PIN_NO(142) | 5) + +#define PINMUX_GPIO143__FUNC_GPIO143 (MTK_PIN_NO(143) | 0) +#define PINMUX_GPIO143__FUNC_DPI_D3 (MTK_PIN_NO(143) | 1) +#define PINMUX_GPIO143__FUNC_NCEB0 (MTK_PIN_NO(143) | 2) +#define PINMUX_GPIO143__FUNC_URXD1 (MTK_PIN_NO(143) | 3) +#define PINMUX_GPIO143__FUNC_TDD_TXD (MTK_PIN_NO(143) | 4) +#define PINMUX_GPIO143__FUNC_I2S2_MCK (MTK_PIN_NO(143) | 5) + +#define PINMUX_GPIO144__FUNC_GPIO144 (MTK_PIN_NO(144) | 0) +#define PINMUX_GPIO144__FUNC_DPI_D4 (MTK_PIN_NO(144) | 1) +#define PINMUX_GPIO144__FUNC_NALE (MTK_PIN_NO(144) | 2) +#define PINMUX_GPIO144__FUNC_UCTS1 (MTK_PIN_NO(144) | 3) +#define PINMUX_GPIO144__FUNC_TDD_TMS (MTK_PIN_NO(144) | 4) +#define PINMUX_GPIO144__FUNC_I2S2_DI_1 (MTK_PIN_NO(144) | 5) + +#define PINMUX_GPIO145__FUNC_GPIO145 (MTK_PIN_NO(145) | 0) +#define PINMUX_GPIO145__FUNC_DPI_D5 (MTK_PIN_NO(145) | 1) +#define PINMUX_GPIO145__FUNC_NCLE (MTK_PIN_NO(145) | 2) +#define PINMUX_GPIO145__FUNC_URTS1 (MTK_PIN_NO(145) | 3) +#define PINMUX_GPIO145__FUNC_TDD_TCK (MTK_PIN_NO(145) | 4) +#define PINMUX_GPIO145__FUNC_I2S2_DI_2 (MTK_PIN_NO(145) | 5) + +#define PINMUX_GPIO146__FUNC_GPIO146 (MTK_PIN_NO(146) | 0) +#define PINMUX_GPIO146__FUNC_DPI_D6 (MTK_PIN_NO(146) | 1) +#define PINMUX_GPIO146__FUNC_NLD8 (MTK_PIN_NO(146) | 2) +#define PINMUX_GPIO146__FUNC_UTXD2 (MTK_PIN_NO(146) | 3) +#define PINMUX_GPIO146__FUNC_TDD_TDI (MTK_PIN_NO(146) | 4) + +#define PINMUX_GPIO147__FUNC_GPIO147 (MTK_PIN_NO(147) | 0) +#define PINMUX_GPIO147__FUNC_DPI_D7 (MTK_PIN_NO(147) | 1) +#define PINMUX_GPIO147__FUNC_NLD9 (MTK_PIN_NO(147) | 2) +#define PINMUX_GPIO147__FUNC_URXD2 (MTK_PIN_NO(147) | 3) +#define PINMUX_GPIO147__FUNC_TDD_TDO (MTK_PIN_NO(147) | 4) +#define PINMUX_GPIO147__FUNC_I2S1_WS (MTK_PIN_NO(147) | 5) + +#define PINMUX_GPIO148__FUNC_GPIO148 (MTK_PIN_NO(148) | 0) +#define PINMUX_GPIO148__FUNC_DPI_D8 (MTK_PIN_NO(148) | 1) +#define PINMUX_GPIO148__FUNC_NLD10 (MTK_PIN_NO(148) | 2) +#define PINMUX_GPIO148__FUNC_UCTS2 (MTK_PIN_NO(148) | 3) +#define PINMUX_GPIO148__FUNC_TDD_TRSTN (MTK_PIN_NO(148) | 4) +#define PINMUX_GPIO148__FUNC_I2S1_BCK (MTK_PIN_NO(148) | 5) + +#define PINMUX_GPIO149__FUNC_GPIO149 (MTK_PIN_NO(149) | 0) +#define PINMUX_GPIO149__FUNC_DPI_D9 (MTK_PIN_NO(149) | 1) +#define PINMUX_GPIO149__FUNC_NLD11 (MTK_PIN_NO(149) | 2) +#define PINMUX_GPIO149__FUNC_URTS2 (MTK_PIN_NO(149) | 3) +#define PINMUX_GPIO149__FUNC_LTE_MD32_JTAG_TMS (MTK_PIN_NO(149) | 4) +#define PINMUX_GPIO149__FUNC_I2S1_MCK (MTK_PIN_NO(149) | 5) + +#define PINMUX_GPIO150__FUNC_GPIO150 (MTK_PIN_NO(150) | 0) +#define PINMUX_GPIO150__FUNC_DPI_D10 (MTK_PIN_NO(150) | 1) +#define PINMUX_GPIO150__FUNC_NLD12 (MTK_PIN_NO(150) | 2) +#define PINMUX_GPIO150__FUNC_UTXD3 (MTK_PIN_NO(150) | 3) +#define PINMUX_GPIO150__FUNC_LTE_MD32_JTAG_TCK (MTK_PIN_NO(150) | 4) +#define PINMUX_GPIO150__FUNC_I2S1_DO_1 (MTK_PIN_NO(150) | 5) + +#define PINMUX_GPIO151__FUNC_GPIO151 (MTK_PIN_NO(151) | 0) +#define PINMUX_GPIO151__FUNC_DPI_D11 (MTK_PIN_NO(151) | 1) +#define PINMUX_GPIO151__FUNC_NLD13 (MTK_PIN_NO(151) | 2) +#define PINMUX_GPIO151__FUNC_URXD3 (MTK_PIN_NO(151) | 3) +#define PINMUX_GPIO151__FUNC_LTE_MD32_JTAG_TDI (MTK_PIN_NO(151) | 4) +#define PINMUX_GPIO151__FUNC_I2S1_DO_2 (MTK_PIN_NO(151) | 5) + +#define PINMUX_GPIO152__FUNC_GPIO152 (MTK_PIN_NO(152) | 0) +#define PINMUX_GPIO152__FUNC_DPI_HSYNC (MTK_PIN_NO(152) | 1) +#define PINMUX_GPIO152__FUNC_NLD14 (MTK_PIN_NO(152) | 2) +#define PINMUX_GPIO152__FUNC_UCTS3 (MTK_PIN_NO(152) | 3) +#define PINMUX_GPIO152__FUNC_LTE_MD32_JTAG_TDO (MTK_PIN_NO(152) | 4) +#define PINMUX_GPIO152__FUNC_DSI1_TE (MTK_PIN_NO(152) | 5) + +#define PINMUX_GPIO153__FUNC_GPIO153 (MTK_PIN_NO(153) | 0) +#define PINMUX_GPIO153__FUNC_DPI_VSYNC (MTK_PIN_NO(153) | 1) +#define PINMUX_GPIO153__FUNC_NLD15 (MTK_PIN_NO(153) | 2) +#define PINMUX_GPIO153__FUNC_URTS3 (MTK_PIN_NO(153) | 3) +#define PINMUX_GPIO153__FUNC_LTE_MD32_JTAG_TRST (MTK_PIN_NO(153) | 4) +#define PINMUX_GPIO153__FUNC_DISP_PWM1 (MTK_PIN_NO(153) | 5) + +#define PINMUX_GPIO154__FUNC_GPIO154 (MTK_PIN_NO(154) | 0) +#define PINMUX_GPIO154__FUNC_MSDC0_DAT0 (MTK_PIN_NO(154) | 1) +#define PINMUX_GPIO154__FUNC_NLD8 (MTK_PIN_NO(154) | 2) + +#define PINMUX_GPIO155__FUNC_GPIO155 (MTK_PIN_NO(155) | 0) +#define PINMUX_GPIO155__FUNC_MSDC0_DAT1 (MTK_PIN_NO(155) | 1) +#define PINMUX_GPIO155__FUNC_NLD9 (MTK_PIN_NO(155) | 2) + +#define PINMUX_GPIO156__FUNC_GPIO156 (MTK_PIN_NO(156) | 0) +#define PINMUX_GPIO156__FUNC_MSDC0_DAT2 (MTK_PIN_NO(156) | 1) +#define PINMUX_GPIO156__FUNC_NLD10 (MTK_PIN_NO(156) | 2) + +#define PINMUX_GPIO157__FUNC_GPIO157 (MTK_PIN_NO(157) | 0) +#define PINMUX_GPIO157__FUNC_MSDC0_DAT3 (MTK_PIN_NO(157) | 1) +#define PINMUX_GPIO157__FUNC_NLD11 (MTK_PIN_NO(157) | 2) + +#define PINMUX_GPIO158__FUNC_GPIO158 (MTK_PIN_NO(158) | 0) +#define PINMUX_GPIO158__FUNC_MSDC0_DAT4 (MTK_PIN_NO(158) | 1) +#define PINMUX_GPIO158__FUNC_NLD12 (MTK_PIN_NO(158) | 2) + +#define PINMUX_GPIO159__FUNC_GPIO159 (MTK_PIN_NO(159) | 0) +#define PINMUX_GPIO159__FUNC_MSDC0_DAT5 (MTK_PIN_NO(159) | 1) +#define PINMUX_GPIO159__FUNC_NLD13 (MTK_PIN_NO(159) | 2) + +#define PINMUX_GPIO160__FUNC_GPIO160 (MTK_PIN_NO(160) | 0) +#define PINMUX_GPIO160__FUNC_MSDC0_DAT6 (MTK_PIN_NO(160) | 1) +#define PINMUX_GPIO160__FUNC_NLD14 (MTK_PIN_NO(160) | 2) + +#define PINMUX_GPIO161__FUNC_GPIO161 (MTK_PIN_NO(161) | 0) +#define PINMUX_GPIO161__FUNC_MSDC0_DAT7 (MTK_PIN_NO(161) | 1) +#define PINMUX_GPIO161__FUNC_NLD15 (MTK_PIN_NO(161) | 2) + +#define PINMUX_GPIO162__FUNC_GPIO162 (MTK_PIN_NO(162) | 0) +#define PINMUX_GPIO162__FUNC_MSDC0_CMD (MTK_PIN_NO(162) | 1) + +#define PINMUX_GPIO163__FUNC_GPIO163 (MTK_PIN_NO(163) | 0) +#define PINMUX_GPIO163__FUNC_MSDC0_CLK (MTK_PIN_NO(163) | 1) + +#define PINMUX_GPIO164__FUNC_GPIO164 (MTK_PIN_NO(164) | 0) +#define PINMUX_GPIO164__FUNC_MSDC0_DSL (MTK_PIN_NO(164) | 1) + +#define PINMUX_GPIO165__FUNC_GPIO165 (MTK_PIN_NO(165) | 0) +#define PINMUX_GPIO165__FUNC_MSDC0_RSTB (MTK_PIN_NO(165) | 1) + +#define PINMUX_GPIO166__FUNC_GPIO166 (MTK_PIN_NO(166) | 0) +#define PINMUX_GPIO166__FUNC_SPI_CK_0 (MTK_PIN_NO(166) | 1) +#define PINMUX_GPIO166__FUNC_PWM0 (MTK_PIN_NO(166) | 3) + +#define PINMUX_GPIO167__FUNC_GPIO167 (MTK_PIN_NO(167) | 0) +#define PINMUX_GPIO167__FUNC_SPI_MI_0 (MTK_PIN_NO(167) | 1) +#define PINMUX_GPIO167__FUNC_PWM1 (MTK_PIN_NO(167) | 3) +#define PINMUX_GPIO167__FUNC_SPI_MO_0 (MTK_PIN_NO(167) | 4) + +#define PINMUX_GPIO168__FUNC_GPIO168 (MTK_PIN_NO(168) | 0) +#define PINMUX_GPIO168__FUNC_SPI_MO_0 (MTK_PIN_NO(168) | 1) +#define PINMUX_GPIO168__FUNC_MD_EINT3 (MTK_PIN_NO(168) | 2) +#define PINMUX_GPIO168__FUNC_PWM2 (MTK_PIN_NO(168) | 3) +#define PINMUX_GPIO168__FUNC_SPI_MI_0 (MTK_PIN_NO(168) | 4) + +#define PINMUX_GPIO169__FUNC_GPIO169 (MTK_PIN_NO(169) | 0) +#define PINMUX_GPIO169__FUNC_SPI_CS_0 (MTK_PIN_NO(169) | 1) +#define PINMUX_GPIO169__FUNC_MD_EINT4 (MTK_PIN_NO(169) | 2) +#define PINMUX_GPIO169__FUNC_PWM3 (MTK_PIN_NO(169) | 3) + +#define PINMUX_GPIO170__FUNC_GPIO170 (MTK_PIN_NO(170) | 0) +#define PINMUX_GPIO170__FUNC_MSDC1_CMD (MTK_PIN_NO(170) | 1) + +#define PINMUX_GPIO171__FUNC_GPIO171 (MTK_PIN_NO(171) | 0) +#define PINMUX_GPIO171__FUNC_MSDC1_DAT0 (MTK_PIN_NO(171) | 1) + +#define PINMUX_GPIO172__FUNC_GPIO172 (MTK_PIN_NO(172) | 0) +#define PINMUX_GPIO172__FUNC_MSDC1_DAT1 (MTK_PIN_NO(172) | 1) + +#define PINMUX_GPIO173__FUNC_GPIO173 (MTK_PIN_NO(173) | 0) +#define PINMUX_GPIO173__FUNC_MSDC1_DAT2 (MTK_PIN_NO(173) | 1) + +#define PINMUX_GPIO174__FUNC_GPIO174 (MTK_PIN_NO(174) | 0) +#define PINMUX_GPIO174__FUNC_MSDC1_DAT3 (MTK_PIN_NO(174) | 1) + +#define PINMUX_GPIO175__FUNC_GPIO175 (MTK_PIN_NO(175) | 0) +#define PINMUX_GPIO175__FUNC_MSDC1_CLK (MTK_PIN_NO(175) | 1) + +#define PINMUX_GPIO176__FUNC_GPIO176 (MTK_PIN_NO(176) | 0) +#define PINMUX_GPIO176__FUNC_PWRAP_SPIMI (MTK_PIN_NO(176) | 1) +#define PINMUX_GPIO176__FUNC_PWRAP_SPIMO (MTK_PIN_NO(176) | 2) + +#define PINMUX_GPIO177__FUNC_GPIO177 (MTK_PIN_NO(177) | 0) +#define PINMUX_GPIO177__FUNC_PWRAP_SPIMO (MTK_PIN_NO(177) | 1) +#define PINMUX_GPIO177__FUNC_PWRAP_SPIMI (MTK_PIN_NO(177) | 2) + +#define PINMUX_GPIO178__FUNC_GPIO178 (MTK_PIN_NO(178) | 0) +#define PINMUX_GPIO178__FUNC_PWRAP_SPICK (MTK_PIN_NO(178) | 1) + +#define PINMUX_GPIO179__FUNC_GPIO179 (MTK_PIN_NO(179) | 0) +#define PINMUX_GPIO179__FUNC_PWRAP_SPICS (MTK_PIN_NO(179) | 1) + +#define PINMUX_GPIO180__FUNC_GPIO180 (MTK_PIN_NO(180) | 0) +#define PINMUX_GPIO180__FUNC_AUD_CLK_MOSI (MTK_PIN_NO(180) | 1) +#define PINMUX_GPIO180__FUNC_I2S1_WS (MTK_PIN_NO(180) | 2) +#define PINMUX_GPIO180__FUNC_I2S2_WS (MTK_PIN_NO(180) | 3) +#define PINMUX_GPIO180__FUNC_I2S0_WS (MTK_PIN_NO(180) | 4) + +#define PINMUX_GPIO181__FUNC_GPIO181 (MTK_PIN_NO(181) | 0) +#define PINMUX_GPIO181__FUNC_AUD_DAT_MISO_1 (MTK_PIN_NO(181) | 1) +#define PINMUX_GPIO181__FUNC_I2S1_BCK (MTK_PIN_NO(181) | 2) +#define PINMUX_GPIO181__FUNC_I2S2_BCK (MTK_PIN_NO(181) | 3) +#define PINMUX_GPIO181__FUNC_I2S0_BCK (MTK_PIN_NO(181) | 4) + +#define PINMUX_GPIO182__FUNC_GPIO182 (MTK_PIN_NO(182) | 0) +#define PINMUX_GPIO182__FUNC_AUD_DAT_MOSI_1 (MTK_PIN_NO(182) | 1) +#define PINMUX_GPIO182__FUNC_I2S1_MCK (MTK_PIN_NO(182) | 2) +#define PINMUX_GPIO182__FUNC_I2S2_MCK (MTK_PIN_NO(182) | 3) +#define PINMUX_GPIO182__FUNC_I2S0_MCK (MTK_PIN_NO(182) | 4) + +#define PINMUX_GPIO183__FUNC_GPIO183 (MTK_PIN_NO(183) | 0) +#define PINMUX_GPIO183__FUNC_AUD_DAT_MISO_2 (MTK_PIN_NO(183) | 1) +#define PINMUX_GPIO183__FUNC_I2S1_DO_1 (MTK_PIN_NO(183) | 2) +#define PINMUX_GPIO183__FUNC_I2S2_DI_1 (MTK_PIN_NO(183) | 3) +#define PINMUX_GPIO183__FUNC_I2S0_DO (MTK_PIN_NO(183) | 4) + +#define PINMUX_GPIO184__FUNC_GPIO184 (MTK_PIN_NO(184) | 0) +#define PINMUX_GPIO184__FUNC_AUD_DAT_MOSI_2 (MTK_PIN_NO(184) | 1) +#define PINMUX_GPIO184__FUNC_I2S1_DO_2 (MTK_PIN_NO(184) | 2) +#define PINMUX_GPIO184__FUNC_I2S2_DI_2 (MTK_PIN_NO(184) | 3) +#define PINMUX_GPIO184__FUNC_I2S0_DI (MTK_PIN_NO(184) | 4) + +#define PINMUX_GPIO185__FUNC_GPIO185 (MTK_PIN_NO(185) | 0) +#define PINMUX_GPIO185__FUNC_RTC32K_CK (MTK_PIN_NO(185) | 1) + +#define PINMUX_GPIO186__FUNC_GPIO186 (MTK_PIN_NO(186) | 0) +#define PINMUX_GPIO186__FUNC_DISP_PWM0 (MTK_PIN_NO(186) | 1) +#define PINMUX_GPIO186__FUNC_DISP_PWM1 (MTK_PIN_NO(186) | 2) + +#define PINMUX_GPIO187__FUNC_GPIO187 (MTK_PIN_NO(187) | 0) +#define PINMUX_GPIO187__FUNC_SRCLKENAI (MTK_PIN_NO(187) | 1) + +#define PINMUX_GPIO188__FUNC_GPIO188 (MTK_PIN_NO(188) | 0) +#define PINMUX_GPIO188__FUNC_SRCLKENAI2 (MTK_PIN_NO(188) | 1) + +#define PINMUX_GPIO189__FUNC_GPIO189 (MTK_PIN_NO(189) | 0) +#define PINMUX_GPIO189__FUNC_SRCLKENA0 (MTK_PIN_NO(189) | 1) + +#define PINMUX_GPIO190__FUNC_GPIO190 (MTK_PIN_NO(190) | 0) +#define PINMUX_GPIO190__FUNC_SRCLKENA1 (MTK_PIN_NO(190) | 1) + +#define PINMUX_GPIO191__FUNC_GPIO191 (MTK_PIN_NO(191) | 0) +#define PINMUX_GPIO191__FUNC_WATCHDOG_AO (MTK_PIN_NO(191) | 1) + +#define PINMUX_GPIO192__FUNC_GPIO192 (MTK_PIN_NO(192) | 0) +#define PINMUX_GPIO192__FUNC_I2S0_WS (MTK_PIN_NO(192) | 1) +#define PINMUX_GPIO192__FUNC_I2S1_WS (MTK_PIN_NO(192) | 2) +#define PINMUX_GPIO192__FUNC_I2S2_WS (MTK_PIN_NO(192) | 3) +#define PINMUX_GPIO192__FUNC_NCEB1 (MTK_PIN_NO(192) | 4) + +#define PINMUX_GPIO193__FUNC_GPIO193 (MTK_PIN_NO(193) | 0) +#define PINMUX_GPIO193__FUNC_I2S0_BCK (MTK_PIN_NO(193) | 1) +#define PINMUX_GPIO193__FUNC_I2S1_BCK (MTK_PIN_NO(193) | 2) +#define PINMUX_GPIO193__FUNC_I2S2_BCK (MTK_PIN_NO(193) | 3) +#define PINMUX_GPIO193__FUNC_NRNB1 (MTK_PIN_NO(193) | 4) + +#define PINMUX_GPIO194__FUNC_GPIO194 (MTK_PIN_NO(194) | 0) +#define PINMUX_GPIO194__FUNC_I2S0_MCK (MTK_PIN_NO(194) | 1) +#define PINMUX_GPIO194__FUNC_I2S1_MCK (MTK_PIN_NO(194) | 2) +#define PINMUX_GPIO194__FUNC_I2S2_MCK (MTK_PIN_NO(194) | 3) + +#define PINMUX_GPIO195__FUNC_GPIO195 (MTK_PIN_NO(195) | 0) +#define PINMUX_GPIO195__FUNC_I2S0_DO (MTK_PIN_NO(195) | 1) +#define PINMUX_GPIO195__FUNC_I2S1_DO_1 (MTK_PIN_NO(195) | 2) +#define PINMUX_GPIO195__FUNC_I2S2_DI_1 (MTK_PIN_NO(195) | 3) + +#define PINMUX_GPIO196__FUNC_GPIO196 (MTK_PIN_NO(196) | 0) +#define PINMUX_GPIO196__FUNC_I2S0_DI (MTK_PIN_NO(196) | 1) +#define PINMUX_GPIO196__FUNC_I2S1_DO_2 (MTK_PIN_NO(196) | 2) +#define PINMUX_GPIO196__FUNC_I2S2_DI_2 (MTK_PIN_NO(196) | 3) + + +#endif -- cgit v1.2.3 From 7782cfeca7d420e8bb707613d4cfb0f7ff29bb3a Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 13 May 2022 12:29:38 +0200 Subject: random: remove extern from functions in header Accoriding to the kernel style guide, having `extern` on functions in headers is old school and deprecated, and doesn't add anything. So remove them from random.h, and tidy up the file a little bit too. Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 77 ++++++++++++++++++++------------------------------ 1 file changed, 31 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index b52963955a99..97f879ea78a5 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -12,13 +12,12 @@ struct notifier_block; -extern void add_device_randomness(const void *, size_t); -extern void add_bootloader_randomness(const void *, size_t); -extern void add_input_randomness(unsigned int type, unsigned int code, - unsigned int value) __latent_entropy; -extern void add_interrupt_randomness(int irq) __latent_entropy; -extern void add_hwgenerator_randomness(const void *buffer, size_t count, - size_t entropy); +void add_device_randomness(const void *, size_t); +void add_bootloader_randomness(const void *, size_t); +void add_input_randomness(unsigned int type, unsigned int code, + unsigned int value) __latent_entropy; +void add_interrupt_randomness(int irq) __latent_entropy; +void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy); #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) @@ -26,30 +25,20 @@ static inline void add_latent_entropy(void) add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); } #else -static inline void add_latent_entropy(void) {} +static inline void add_latent_entropy(void) { } #endif #if IS_ENABLED(CONFIG_VMGENID) -extern void add_vmfork_randomness(const void *unique_vm_id, size_t size); -extern int register_random_vmfork_notifier(struct notifier_block *nb); -extern int unregister_random_vmfork_notifier(struct notifier_block *nb); +void add_vmfork_randomness(const void *unique_vm_id, size_t size); +int register_random_vmfork_notifier(struct notifier_block *nb); +int unregister_random_vmfork_notifier(struct notifier_block *nb); #else static inline int register_random_vmfork_notifier(struct notifier_block *nb) { return 0; } static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; } #endif -extern void get_random_bytes(void *buf, size_t nbytes); -extern int wait_for_random_bytes(void); -extern int __init random_init(const char *command_line); -extern bool rng_is_initialized(void); -extern int register_random_ready_notifier(struct notifier_block *nb); -extern int unregister_random_ready_notifier(struct notifier_block *nb); -extern size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); - -#ifndef MODULE -extern const struct file_operations random_fops, urandom_fops; -#endif - +void get_random_bytes(void *buf, size_t nbytes); +size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); u32 get_random_u32(void); u64 get_random_u64(void); static inline unsigned int get_random_int(void) @@ -81,11 +70,17 @@ static inline unsigned long get_random_long(void) static inline unsigned long get_random_canary(void) { - unsigned long val = get_random_long(); - - return val & CANARY_MASK; + return get_random_long() & CANARY_MASK; } +unsigned long randomize_page(unsigned long start, unsigned long range); + +int __init random_init(const char *command_line); +bool rng_is_initialized(void); +int wait_for_random_bytes(void); +int register_random_ready_notifier(struct notifier_block *nb); +int unregister_random_ready_notifier(struct notifier_block *nb); + /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). * Returns the result of the call to wait_for_random_bytes. */ static inline int get_random_bytes_wait(void *buf, size_t nbytes) @@ -109,8 +104,6 @@ declare_get_random_var_wait(int) declare_get_random_var_wait(long) #undef declare_get_random_var -unsigned long randomize_page(unsigned long start, unsigned long range); - /* * This is designed to be standalone for just prandom * users, but for now we include it from @@ -121,22 +114,10 @@ unsigned long randomize_page(unsigned long start, unsigned long range); #ifdef CONFIG_ARCH_RANDOM # include #else -static inline bool __must_check arch_get_random_long(unsigned long *v) -{ - return false; -} -static inline bool __must_check arch_get_random_int(unsigned int *v) -{ - return false; -} -static inline bool __must_check arch_get_random_seed_long(unsigned long *v) -{ - return false; -} -static inline bool __must_check arch_get_random_seed_int(unsigned int *v) -{ - return false; -} +static inline bool __must_check arch_get_random_long(unsigned long *v) { return false; } +static inline bool __must_check arch_get_random_int(unsigned int *v) { return false; } +static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { return false; } +static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { return false; } #endif /* @@ -160,8 +141,12 @@ static inline bool __init arch_get_random_long_early(unsigned long *v) #endif #ifdef CONFIG_SMP -extern int random_prepare_cpu(unsigned int cpu); -extern int random_online_cpu(unsigned int cpu); +int random_prepare_cpu(unsigned int cpu); +int random_online_cpu(unsigned int cpu); +#endif + +#ifndef MODULE +extern const struct file_operations random_fops, urandom_fops; #endif #endif /* _LINUX_RANDOM_H */ -- cgit v1.2.3 From 7c3a8a1db5e03d02cc0abb3357a84b8b326dfac3 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 13 May 2022 12:32:23 +0200 Subject: random: use proper return types on get_random_{int,long}_wait() Before these were returning signed values, but the API is intended to be used with unsigned values. Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 97f879ea78a5..883bf9a23d84 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -90,18 +90,18 @@ static inline int get_random_bytes_wait(void *buf, size_t nbytes) return ret; } -#define declare_get_random_var_wait(var) \ - static inline int get_random_ ## var ## _wait(var *out) { \ +#define declare_get_random_var_wait(name, ret_type) \ + static inline int get_random_ ## name ## _wait(ret_type *out) { \ int ret = wait_for_random_bytes(); \ if (unlikely(ret)) \ return ret; \ - *out = get_random_ ## var(); \ + *out = get_random_ ## name(); \ return 0; \ } -declare_get_random_var_wait(u32) -declare_get_random_var_wait(u64) -declare_get_random_var_wait(int) -declare_get_random_var_wait(long) +declare_get_random_var_wait(u32, u32) +declare_get_random_var_wait(u64, u32) +declare_get_random_var_wait(int, unsigned int) +declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var /* -- cgit v1.2.3 From a19402634c435a4eae226df53c141cdbb9922e7b Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 13 May 2022 13:18:46 +0200 Subject: random: make consistent use of buf and len The current code was a mix of "nbytes", "count", "size", "buffer", "in", and so forth. Instead, let's clean this up by naming input parameters "buf" (or "ubuf") and "len", so that you always understand that you're reading this variety of function argument. Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 883bf9a23d84..fc82f1dc36f1 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -12,12 +12,12 @@ struct notifier_block; -void add_device_randomness(const void *, size_t); -void add_bootloader_randomness(const void *, size_t); +void add_device_randomness(const void *buf, size_t len); +void add_bootloader_randomness(const void *buf, size_t len); void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; void add_interrupt_randomness(int irq) __latent_entropy; -void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy); +void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy); #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) @@ -29,7 +29,7 @@ static inline void add_latent_entropy(void) { } #endif #if IS_ENABLED(CONFIG_VMGENID) -void add_vmfork_randomness(const void *unique_vm_id, size_t size); +void add_vmfork_randomness(const void *unique_vm_id, size_t len); int register_random_vmfork_notifier(struct notifier_block *nb); int unregister_random_vmfork_notifier(struct notifier_block *nb); #else @@ -37,8 +37,8 @@ static inline int register_random_vmfork_notifier(struct notifier_block *nb) { r static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; } #endif -void get_random_bytes(void *buf, size_t nbytes); -size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); +void get_random_bytes(void *buf, size_t len); +size_t __must_check get_random_bytes_arch(void *buf, size_t len); u32 get_random_u32(void); u64 get_random_u64(void); static inline unsigned int get_random_int(void) -- cgit v1.2.3 From 248561ad25a8ba4ecbc7df42f9a5a82fd5fbb4f6 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sat, 14 May 2022 13:09:17 +0200 Subject: random: remove get_random_bytes_arch() and add rng_has_arch_random() The RNG incorporates RDRAND into its state at boot and every time it reseeds, so there's no reason for callers to use it directly. The hashing that the RNG does on it is preferable to using the bytes raw. The only current use case of get_random_bytes_arch() is vsprintf's siphash key for pointer hashing, which uses it to initialize the pointer secret earlier than usual if RDRAND is available. In order to replace this narrow use case, just expose whether RDRAND is mixed into the RNG, with a new function called rng_has_arch_random(). With that taken care of, there are no users of get_random_bytes_arch() left, so it can be removed. Later, if trust_cpu gets turned on by default (as most distros are doing), this one use of rng_has_arch_random() can probably go away as well. Cc: Steven Rostedt Cc: Sergey Senozhatsky Acked-by: Petr Mladek # for vsprintf.c Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index fc82f1dc36f1..6af130c6edb9 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -38,7 +38,6 @@ static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { #endif void get_random_bytes(void *buf, size_t len); -size_t __must_check get_random_bytes_arch(void *buf, size_t len); u32 get_random_u32(void); u64 get_random_u64(void); static inline unsigned int get_random_int(void) @@ -77,6 +76,7 @@ unsigned long randomize_page(unsigned long start, unsigned long range); int __init random_init(const char *command_line); bool rng_is_initialized(void); +bool rng_has_arch_random(void); int wait_for_random_bytes(void); int register_random_ready_notifier(struct notifier_block *nb); int unregister_random_ready_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 6701de6c51c172b5de5633374479503c81fefc0b Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sun, 15 May 2022 15:06:18 +0200 Subject: random: remove mostly unused async readiness notifier The register_random_ready_notifier() notifier is somewhat complicated, and was already recently rewritten to use notifier blocks. It is only used now by one consumer in the kernel, vsprintf.c, for which the async mechanism is really overly complex for what it actually needs. This commit removes register_random_ready_notifier() and unregister_random_ ready_notifier(), because it just adds complication with little utility, and changes vsprintf.c to just check on `!rng_is_initialized() && !rng_has_arch_random()`, which will eventually be true. Performance- wise, that code was already using a static branch, so there's basically no overhead at all to this change. Cc: Steven Rostedt Cc: Sergey Senozhatsky Acked-by: Petr Mladek # for vsprintf.c Reviewed-by: Petr Mladek Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 6af130c6edb9..d2360b2825b6 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -78,8 +78,6 @@ int __init random_init(const char *command_line); bool rng_is_initialized(void); bool rng_has_arch_random(void); int wait_for_random_bytes(void); -int register_random_ready_notifier(struct notifier_block *nb); -int unregister_random_ready_notifier(struct notifier_block *nb); /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). * Returns the result of the call to wait_for_random_bytes. */ -- cgit v1.2.3 From 5ad7dd882e45d7fe432c32e896e2aaa0b21746ea Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sat, 14 May 2022 13:59:30 +0200 Subject: random: move randomize_page() into mm where it belongs randomize_page is an mm function. It is documented like one. It contains the history of one. It has the naming convention of one. It looks just like another very similar function in mm, randomize_stack_top(). And it has always been maintained and updated by mm people. There is no need for it to be in random.c. In the "which shape does not look like the other ones" test, pointing to randomize_page() is correct. So move randomize_page() into mm/util.c, right next to the similar randomize_stack_top() function. This commit contains no actual code changes. Cc: Andrew Morton Signed-off-by: Jason A. Donenfeld --- include/linux/mm.h | 1 + include/linux/random.h | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9f44254af8ce..b0183450e484 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2677,6 +2677,7 @@ extern int install_special_mapping(struct mm_struct *mm, unsigned long flags, struct page **pages); unsigned long randomize_stack_top(unsigned long stack_top); +unsigned long randomize_page(unsigned long start, unsigned long range); extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/include/linux/random.h b/include/linux/random.h index d2360b2825b6..fae0c84027fd 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -72,8 +72,6 @@ static inline unsigned long get_random_canary(void) return get_random_long() & CANARY_MASK; } -unsigned long randomize_page(unsigned long start, unsigned long range); - int __init random_init(const char *command_line); bool rng_is_initialized(void); bool rng_has_arch_random(void); -- cgit v1.2.3 From 135c579d77d066aece83609329150b87fe81e454 Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Mon, 2 May 2022 18:25:05 +0900 Subject: tty: serial: samsung_tty: Fix suspend/resume on S5L We were restoring the IRQ masks then clearing them again, because ucon_mask wasn't set properly. Adding that makes suspend/resume work as intended. Signed-off-by: Hector Martin Link: https://lore.kernel.org/r/20220502092505.30934-1-marcan@marcan.st Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_s3c.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h index f6c3323fc4c5..dec15f5b3dec 100644 --- a/include/linux/serial_s3c.h +++ b/include/linux/serial_s3c.h @@ -256,6 +256,9 @@ #define APPLE_S5L_UCON_DEFAULT (S3C2410_UCON_TXIRQMODE | \ S3C2410_UCON_RXIRQMODE | \ S3C2410_UCON_RXFIFO_TOI) +#define APPLE_S5L_UCON_MASK (APPLE_S5L_UCON_RXTO_ENA_MSK | \ + APPLE_S5L_UCON_RXTHRESH_ENA_MSK | \ + APPLE_S5L_UCON_TXTHRESH_ENA_MSK) #define APPLE_S5L_UTRSTAT_RXTHRESH (1<<4) #define APPLE_S5L_UTRSTAT_TXTHRESH (1<<5) -- cgit v1.2.3 From 0b46ac44f2673be2ee51bb52149cab3546ff1696 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 9 May 2022 12:34:44 +0300 Subject: termbits.h: create termbits-common.h for identical bits MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some defines are the same across all archs. Move the most obvious intersection to termbits-common.h. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220509093446.6677-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/asm-generic/termbits-common.h | 65 ++++++++++++++++++++++++++++++ include/uapi/asm-generic/termbits.h | 53 +----------------------- 2 files changed, 67 insertions(+), 51 deletions(-) create mode 100644 include/uapi/asm-generic/termbits-common.h (limited to 'include') diff --git a/include/uapi/asm-generic/termbits-common.h b/include/uapi/asm-generic/termbits-common.h new file mode 100644 index 000000000000..4d084fe8def5 --- /dev/null +++ b/include/uapi/asm-generic/termbits-common.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_TERMBITS_COMMON_H +#define __ASM_GENERIC_TERMBITS_COMMON_H + +typedef unsigned char cc_t; +typedef unsigned int speed_t; + +/* c_iflag bits */ +#define IGNBRK 0x001 /* Ignore break condition */ +#define BRKINT 0x002 /* Signal interrupt on break */ +#define IGNPAR 0x004 /* Ignore characters with parity errors */ +#define PARMRK 0x008 /* Mark parity and framing errors */ +#define INPCK 0x010 /* Enable input parity check */ +#define ISTRIP 0x020 /* Strip 8th bit off characters */ +#define INLCR 0x040 /* Map NL to CR on input */ +#define IGNCR 0x080 /* Ignore CR */ +#define ICRNL 0x100 /* Map CR to NL on input */ +#define IXANY 0x800 /* Any character will restart after stop */ + +/* c_oflag bits */ +#define OPOST 0x01 /* Perform output processing */ +#define OCRNL 0x08 +#define ONOCR 0x10 +#define ONLRET 0x20 +#define OFILL 0x40 +#define OFDEL 0x80 + +/* c_cflag bit meaning */ +/* Common CBAUD rates */ +#define B0 0x00000000 /* hang up */ +#define B50 0x00000001 +#define B75 0x00000002 +#define B110 0x00000003 +#define B134 0x00000004 +#define B150 0x00000005 +#define B200 0x00000006 +#define B300 0x00000007 +#define B600 0x00000008 +#define B1200 0x00000009 +#define B1800 0x0000000a +#define B2400 0x0000000b +#define B4800 0x0000000c +#define B9600 0x0000000d +#define B19200 0x0000000e +#define B38400 0x0000000f +#define EXTA B19200 +#define EXTB B38400 + +#define CMSPAR 0x40000000 /* mark or space (stick) parity */ +#define CRTSCTS 0x80000000 /* flow control */ + +#define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */ + +/* tcflow() ACTION argument and TCXONC use these */ +#define TCOOFF 0 /* Suspend output */ +#define TCOON 1 /* Restart suspended output */ +#define TCIOFF 2 /* Send a STOP character */ +#define TCION 3 /* Send a START character */ + +/* tcflush() QUEUE_SELECTOR argument and TCFLSH use these */ +#define TCIFLUSH 0 /* Discard data received but not yet read */ +#define TCOFLUSH 1 /* Discard data written but not yet sent */ +#define TCIOFLUSH 2 /* Discard all pending data */ + +#endif /* __ASM_GENERIC_TERMBITS_COMMON_H */ diff --git a/include/uapi/asm-generic/termbits.h b/include/uapi/asm-generic/termbits.h index 470fd673ff84..78a85c326eef 100644 --- a/include/uapi/asm-generic/termbits.h +++ b/include/uapi/asm-generic/termbits.h @@ -4,8 +4,8 @@ #include -typedef unsigned char cc_t; -typedef unsigned int speed_t; +#include + typedef unsigned int tcflag_t; #define NCCS 19 @@ -60,31 +60,15 @@ struct ktermios { #define VEOL2 16 /* c_iflag bits */ -#define IGNBRK 0x00001 -#define BRKINT 0x00002 -#define IGNPAR 0x00004 -#define PARMRK 0x00008 -#define INPCK 0x00010 -#define ISTRIP 0x00020 -#define INLCR 0x00040 -#define IGNCR 0x00080 -#define ICRNL 0x00100 #define IUCLC 0x00200 #define IXON 0x00400 -#define IXANY 0x00800 #define IXOFF 0x01000 #define IMAXBEL 0x02000 #define IUTF8 0x04000 /* c_oflag bits */ -#define OPOST 0x00001 #define OLCUC 0x00002 #define ONLCR 0x00004 -#define OCRNL 0x00008 -#define ONOCR 0x00010 -#define ONLRET 0x00020 -#define OFILL 0x00040 -#define OFDEL 0x00080 #define NLDLY 0x00100 #define NL0 0x00000 #define NL1 0x00100 @@ -111,24 +95,6 @@ struct ktermios { /* c_cflag bit meaning */ #define CBAUD 0x0000100f -#define B0 0x00000000 /* hang up */ -#define B50 0x00000001 -#define B75 0x00000002 -#define B110 0x00000003 -#define B134 0x00000004 -#define B150 0x00000005 -#define B200 0x00000006 -#define B300 0x00000007 -#define B600 0x00000008 -#define B1200 0x00000009 -#define B1800 0x0000000a -#define B2400 0x0000000b -#define B4800 0x0000000c -#define B9600 0x0000000d -#define B19200 0x0000000e -#define B38400 0x0000000f -#define EXTA B19200 -#define EXTB B38400 #define CSIZE 0x00000030 #define CS5 0x00000000 #define CS6 0x00000010 @@ -158,10 +124,6 @@ struct ktermios { #define B3500000 0x0000100e #define B4000000 0x0000100f #define CIBAUD 0x100f0000 /* input baud rate */ -#define CMSPAR 0x40000000 /* mark or space (stick) parity */ -#define CRTSCTS 0x80000000 /* flow control */ - -#define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */ /* c_lflag bits */ #define ISIG 0x00001 @@ -181,17 +143,6 @@ struct ktermios { #define IEXTEN 0x08000 #define EXTPROC 0x10000 -/* tcflow() and TCXONC use these */ -#define TCOOFF 0 -#define TCOON 1 -#define TCIOFF 2 -#define TCION 3 - -/* tcflush() and TCFLSH use these */ -#define TCIFLUSH 0 -#define TCOFLUSH 1 -#define TCIOFLUSH 2 - /* tcsetattr uses these */ #define TCSANOW 0 #define TCSADRAIN 1 -- cgit v1.2.3 From c9b34088e80efe30459517fa3834cf78532c9a02 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 9 May 2022 12:34:45 +0300 Subject: termbits.h: Align lines & format MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Align c_cc defines. - Remove extra newlines. - Realign & adjust number of leading zeros. - Reorder c_cflag defines to ascending order - Make comment ending shorted (=remove period and one extra space from the comments in mips). Co-developed-by: Arnd Bergmann Signed-off-by: Arnd Bergmann Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220509093446.6677-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/asm-generic/termbits.h | 76 ++++++++++++++++++------------------- 1 file changed, 38 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/termbits.h b/include/uapi/asm-generic/termbits.h index 78a85c326eef..c92179563289 100644 --- a/include/uapi/asm-generic/termbits.h +++ b/include/uapi/asm-generic/termbits.h @@ -41,30 +41,30 @@ struct ktermios { }; /* c_cc characters */ -#define VINTR 0 -#define VQUIT 1 -#define VERASE 2 -#define VKILL 3 -#define VEOF 4 -#define VTIME 5 -#define VMIN 6 -#define VSWTC 7 -#define VSTART 8 -#define VSTOP 9 -#define VSUSP 10 -#define VEOL 11 -#define VREPRINT 12 -#define VDISCARD 13 -#define VWERASE 14 -#define VLNEXT 15 -#define VEOL2 16 +#define VINTR 0 +#define VQUIT 1 +#define VERASE 2 +#define VKILL 3 +#define VEOF 4 +#define VTIME 5 +#define VMIN 6 +#define VSWTC 7 +#define VSTART 8 +#define VSTOP 9 +#define VSUSP 10 +#define VEOL 11 +#define VREPRINT 12 +#define VDISCARD 13 +#define VWERASE 14 +#define VLNEXT 15 +#define VEOL2 16 /* c_iflag bits */ -#define IUCLC 0x00200 -#define IXON 0x00400 -#define IXOFF 0x01000 -#define IMAXBEL 0x02000 -#define IUTF8 0x04000 +#define IUCLC 0x0200 +#define IXON 0x0400 +#define IXOFF 0x1000 +#define IMAXBEL 0x2000 +#define IUTF8 0x4000 /* c_oflag bits */ #define OLCUC 0x00002 @@ -107,22 +107,22 @@ struct ktermios { #define HUPCL 0x00000400 #define CLOCAL 0x00000800 #define CBAUDEX 0x00001000 -#define BOTHER 0x00001000 -#define B57600 0x00001001 -#define B115200 0x00001002 -#define B230400 0x00001003 -#define B460800 0x00001004 -#define B500000 0x00001005 -#define B576000 0x00001006 -#define B921600 0x00001007 -#define B1000000 0x00001008 -#define B1152000 0x00001009 -#define B1500000 0x0000100a -#define B2000000 0x0000100b -#define B2500000 0x0000100c -#define B3000000 0x0000100d -#define B3500000 0x0000100e -#define B4000000 0x0000100f +#define BOTHER 0x00001000 +#define B57600 0x00001001 +#define B115200 0x00001002 +#define B230400 0x00001003 +#define B460800 0x00001004 +#define B500000 0x00001005 +#define B576000 0x00001006 +#define B921600 0x00001007 +#define B1000000 0x00001008 +#define B1152000 0x00001009 +#define B1500000 0x0000100a +#define B2000000 0x0000100b +#define B2500000 0x0000100c +#define B3000000 0x0000100d +#define B3500000 0x0000100e +#define B4000000 0x0000100f #define CIBAUD 0x100f0000 /* input baud rate */ /* c_lflag bits */ -- cgit v1.2.3 From 44e0b165b6c078b84767da4ba06ffa27af562c96 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 9 May 2022 12:34:46 +0300 Subject: termbits.h: Remove posix_types.h include MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Nothing in termbits seems to require anything from linux/posix_types.h. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220509093446.6677-4-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/asm-generic/termbits.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/termbits.h b/include/uapi/asm-generic/termbits.h index c92179563289..890ef29053e2 100644 --- a/include/uapi/asm-generic/termbits.h +++ b/include/uapi/asm-generic/termbits.h @@ -2,8 +2,6 @@ #ifndef __ASM_GENERIC_TERMBITS_H #define __ASM_GENERIC_TERMBITS_H -#include - #include typedef unsigned int tcflag_t; -- cgit v1.2.3 From 45cb7955c180a2a34d291e68938250c4f9bd294f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 14 Apr 2022 15:50:12 -0400 Subject: SUNRPC: Clean up svc_deferred_class trace events Replace the temporary fix from commit 4d5004451ab2 ("SUNRPC: Fix the svc_deferred_event trace class") with the use of __sockaddr and friends, which is the preferred solution (but only available in 5.18 and newer). Signed-off-by: Chuck Lever --- include/trace/events/sunrpc.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 3995c58a1c51..ee84e9289707 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -2015,19 +2015,18 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_STRUCT__entry( __field(const void *, dr) __field(u32, xid) - __array(__u8, addr, INET6_ADDRSTRLEN + 10) + __sockaddr(addr, dr->addrlen) ), TP_fast_assign( __entry->dr = dr; __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + (dr->xprt_hlen>>2))); - snprintf(__entry->addr, sizeof(__entry->addr) - 1, - "%pISpc", (struct sockaddr *)&dr->addr); + __assign_sockaddr(addr, &dr->addr, dr->addrlen); ), - TP_printk("addr=%s dr=%p xid=0x%08x", __entry->addr, __entry->dr, - __entry->xid) + TP_printk("addr=%pISpc dr=%p xid=0x%08x", __get_sockaddr(addr), + __entry->dr, __entry->xid) ); #define DEFINE_SVC_DEFERRED_EVENT(name) \ -- cgit v1.2.3 From 0b6c14bdd908879078ec85d65cfb78472a97e4e7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 1 Apr 2022 13:10:31 -0400 Subject: SUNRPC: Make cache_req::thread_wait an unsigned long The second parameter of wait_for_completion_interruptible_timeout() is a jiffies value whose type is "unsigned long". Avoid an unnecessary and potentially fraught implicit type conversion at the wait_for_completion_interruptible_timeout() call site in cache_wait_req(). Signed-off-by: Chuck Lever --- include/linux/sunrpc/cache.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index b134b2b3371c..ec5a555df96f 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -121,17 +121,17 @@ struct cache_detail { struct net *net; }; - /* this must be embedded in any request structure that * identifies an object that will want a callback on * a cache fill */ struct cache_req { struct cache_deferred_req *(*defer)(struct cache_req *req); - int thread_wait; /* How long (jiffies) we can block the - * current thread to wait for updates. - */ + unsigned long thread_wait; /* How long (jiffies) we can block the + * current thread to wait for updates. + */ }; + /* this must be embedded in a deferred_request that is being * delayed awaiting cache-fill */ -- cgit v1.2.3 From 983084b2672c593959e3148d6a17c8b920797dde Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 6 Apr 2022 14:38:59 -0400 Subject: SUNRPC: Remove svc_rqst::rq_xprt_hlen Clean up: This field is now always set to zero. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 2 -- include/trace/events/sunrpc.h | 3 +-- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 217711fc9cac..b73704fbd09b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -257,7 +257,6 @@ struct svc_rqst { void * rq_xprt_ctxt; /* transport specific context ptr */ struct svc_deferred_req*rq_deferred; /* deferred request we are replaying */ - size_t rq_xprt_hlen; /* xprt header len */ struct xdr_buf rq_arg; struct xdr_stream rq_arg_stream; struct xdr_stream rq_res_stream; @@ -397,7 +396,6 @@ struct svc_deferred_req { size_t daddrlen; void *xprt_ctxt; struct cache_deferred_req handle; - size_t xprt_hlen; int argslen; __be32 args[]; }; diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ee84e9289707..b61d9c90fa26 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -2020,8 +2020,7 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_fast_assign( __entry->dr = dr; - __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + - (dr->xprt_hlen>>2))); + __entry->xid = be32_to_cpu(*(__be32 *)dr->args); __assign_sockaddr(addr, &dr->addr, dr->addrlen); ), -- cgit v1.2.3 From 591502c5cb325b1c6ec59ab161927d606b918aa0 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Mon, 2 May 2022 14:19:24 -0700 Subject: fs/lock: add helper locks_owner_has_blockers to check for blockers Add helper locks_owner_has_blockers to check if there is any blockers for a given lockowner. Reviewed-by: J. Bruce Fields Signed-off-by: Dai Ngo Signed-off-by: Chuck Lever Reviewed-by: Jeff Layton --- include/linux/fs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..b8ed7f974fb4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1174,6 +1174,8 @@ extern void lease_unregister_notifier(struct notifier_block *); struct files_struct; extern void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); +extern bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) @@ -1309,6 +1311,11 @@ static inline int lease_modify(struct file_lock *fl, int arg, struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} +static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner) +{ + return false; +} #endif /* !CONFIG_FILE_LOCKING */ static inline struct inode *file_inode(const struct file *f) -- cgit v1.2.3 From 2443da2259e97688f93d64d17ab69b15f466078a Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Mon, 2 May 2022 14:19:25 -0700 Subject: fs/lock: add 2 callbacks to lock_manager_operations to resolve conflict Add 2 new callbacks, lm_lock_expirable and lm_expire_lock, to lock_manager_operations to allow the lock manager to take appropriate action to resolve the lock conflict if possible. A new field, lm_mod_owner, is also added to lock_manager_operations. The lm_mod_owner is used by the fs/lock code to make sure the lock manager module such as nfsd, is not freed while lock conflict is being resolved. lm_lock_expirable checks and returns true to indicate that the lock conflict can be resolved else return false. This callback must be called with the flc_lock held so it can not block. lm_expire_lock is called to resolve the lock conflict if the returned value from lm_lock_expirable is true. This callback is called without the flc_lock held since it's allowed to block. Upon returning from this callback, the lock conflict should be resolved and the caller is expected to restart the conflict check from the beginnning of the list. Lock manager, such as NFSv4 courteous server, uses this callback to resolve conflict by destroying lock owner, or the NFSv4 courtesy client (client that has expired but allowed to maintains its states) that owns the lock. Reviewed-by: J. Bruce Fields Signed-off-by: Dai Ngo Signed-off-by: Chuck Lever Reviewed-by: Jeff Layton --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index b8ed7f974fb4..aa6c1bbdb8c4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1029,6 +1029,7 @@ struct file_lock_operations { }; struct lock_manager_operations { + void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ @@ -1037,6 +1038,8 @@ struct lock_manager_operations { int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); bool (*lm_breaker_owns_lease)(struct file_lock *); + bool (*lm_lock_expirable)(struct file_lock *cfl); + void (*lm_expire_lock)(void); }; struct lock_manager { -- cgit v1.2.3 From 2059b698a2efcce3c67b0e61eab7d7680bbe10bd Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 10 May 2022 11:45:53 -0400 Subject: SUNRPC: Simplify synopsis of svc_pool_for_cpu() Clean up: There is one caller. The @cpu argument can be made implicit now that a get_cpu/put_cpu pair is no longer needed. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index b73704fbd09b..daecb009c05b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -504,7 +504,7 @@ int svc_register(const struct svc_serv *, struct net *, const int, void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); -struct svc_pool * svc_pool_for_cpu(struct svc_serv *serv, int cpu); +struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv); char * svc_print_addr(struct svc_rqst *, char *, size_t); const char * svc_proc_name(const struct svc_rqst *rqstp); int svc_encode_result_payload(struct svc_rqst *rqstp, -- cgit v1.2.3 From 53c83d6d8e399fad3d3d25df0ea0d54eb0f94f88 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 18 May 2022 15:23:45 +0200 Subject: siphash: add SPDX tags as sole licensing authority The text "dual BSD/GPLv2 license" is somewhat ambiguous, and moving this over to SPDX is overdue. This commit adds SPDX tags to the relevant files and clarifies that it's GPLv2 only and 3-clause BSD. It also removes the old text, so that the SPDX tags are the only source of the information. Suggested-by: Thomas Gleixner Signed-off-by: Jason A. Donenfeld Signed-off-by: Greg Kroah-Hartman --- include/linux/siphash.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/siphash.h b/include/linux/siphash.h index cce8a9acc76c..9e822311b29e 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -1,6 +1,5 @@ -/* Copyright (C) 2016 Jason A. Donenfeld . All Rights Reserved. - * - * This file is provided under a dual BSD/GPLv2 license. +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright (C) 2016-2022 Jason A. Donenfeld . All Rights Reserved. * * SipHash: a fast short-input PRF * https://131002.net/siphash/ -- cgit v1.2.3 From e6d3c99adf54fc1dcd07729990dc32acd3be874b Mon Sep 17 00:00:00 2001 From: Abhyuday Godhasara Date: Wed, 27 Apr 2022 00:48:03 -0700 Subject: driver: soc: xilinx: Update function prototype for xlnx_unregister_event As per the current implementation only single callback data gets saved per event, driver is throwing an error if try to register multiple callback for same event. So at time of unregistration of any event required things are event details and callback handler as parameter of xlnx_unregister_event(). As part of adding support of multiple callbacks for same event also require change in prototype of xlnx_unregister_event(). During unregistration of any events, now required things are event details, callback handler and agent's private data as parameter of xlnx_unregister_event(). Also modify the usage of xlnx_unregister_event() in xilinx/zynqmp_power.c driver as per new implementation. Signed-off-by: Abhyuday Godhasara Link: https://lore.kernel.org/r/20220427074803.19009-3-abhyuday.godhasara@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-event-manager.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/firmware/xlnx-event-manager.h b/include/linux/firmware/xlnx-event-manager.h index 3f87c4929d21..82e8254b0f80 100644 --- a/include/linux/firmware/xlnx-event-manager.h +++ b/include/linux/firmware/xlnx-event-manager.h @@ -17,7 +17,7 @@ int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, event_cb_func_t cb_fun, void *data); int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, - const u32 event, event_cb_func_t cb_fun); + const u32 event, event_cb_func_t cb_fun, void *data); #else static inline int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, const u32 event, const bool wake, @@ -27,7 +27,7 @@ static inline int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 } static inline int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, - const u32 event, event_cb_func_t cb_fun) + const u32 event, event_cb_func_t cb_fun, void *data) { return -ENODEV; } -- cgit v1.2.3 From 885525c1e7e27ea6207d648a8db20dfbbd9e4238 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 27 Apr 2022 11:56:48 +0200 Subject: clk: renesas: r9a06g032: Export function to set dmamux The dmamux register is located within the system controller. Without syscon, we need an extra helper in order to give write access to this register to a dmamux driver. Signed-off-by: Miquel Raynal Acked-by: Stephen Boyd Reviewed-by: Geert Uytterhoeven Acked-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20220427095653.91804-5-miquel.raynal@bootlin.com Signed-off-by: Vinod Koul --- include/linux/soc/renesas/r9a06g032-sysctrl.h | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 include/linux/soc/renesas/r9a06g032-sysctrl.h (limited to 'include') diff --git a/include/linux/soc/renesas/r9a06g032-sysctrl.h b/include/linux/soc/renesas/r9a06g032-sysctrl.h new file mode 100644 index 000000000000..066dfb15cbdd --- /dev/null +++ b/include/linux/soc/renesas/r9a06g032-sysctrl.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__ +#define __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__ + +#ifdef CONFIG_CLK_R9A06G032 +int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val); +#else +static inline int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val) { return -ENODEV; } +#endif + +#endif /* __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__ */ -- cgit v1.2.3 From 13dfd97a341a5cf9d15f415dd469f45e971ef12a Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 19 May 2022 14:02:32 +0300 Subject: notifier: Add atomic_notifier_call_chain_is_empty() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add atomic_notifier_call_chain_is_empty() that returns true if given atomic call chain is empty. The first user of this new notifier API function will be the kernel power-off core code that will support power-off call chains. The core code will need to check whether there is a power-off handler registered at all in order to decide whether to halt machine or power it off. Reviewed-by: Michał Mirosław Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/notifier.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 87069b8459af..95e2440037de 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -173,6 +173,8 @@ extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); +extern bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh); + #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ #define NOTIFY_STOP_MASK 0x8000 /* Don't call further */ -- cgit v1.2.3 From c82f898d873ce10d88f8d60b38c8dd19f1ed7c66 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:10 +0300 Subject: notifier: Add blocking/atomic_notifier_chain_register_unique_prio() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add variant of blocking/atomic_notifier_chain_register() functions that allow registration of a notifier only if it has unique priority, otherwise -EBUSY error code is returned by the new functions. Reviewed-by: Michał Mirosław Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/notifier.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 95e2440037de..aef88c2d1173 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -150,6 +150,11 @@ extern int raw_notifier_chain_register(struct raw_notifier_head *nh, extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); +extern int atomic_notifier_chain_register_unique_prio( + struct atomic_notifier_head *nh, struct notifier_block *nb); +extern int blocking_notifier_chain_register_unique_prio( + struct blocking_notifier_head *nh, struct notifier_block *nb); + extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, -- cgit v1.2.3 From 232edc2f72f5beda3586360de6254d443820050a Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:11 +0300 Subject: kernel/reboot: Introduce sys-off handler API In order to support power-off chaining we need to get rid of the global pm_* variables, replacing them with the new kernel API functions that support chaining. Introduce new generic sys-off handler API that brings the following features: 1. Power-off and restart handlers are registered using same API function that supports chaining, hence all power-off and restart modes will support chaining using this unified function. 2. Prevents notifier priority collisions by disallowing registration of multiple handlers at the non-default priority level. 3. Supports passing opaque user argument to callback, which allows us to remove global variables from drivers. This patch adds support of the following sys-off modes: - SYS_OFF_MODE_POWER_OFF_PREPARE that replaces global pm_power_off_prepare variable and provides chaining support for power-off-prepare handlers. - SYS_OFF_MODE_POWER_OFF that replaces global pm_power_off variable and provides chaining support for power-off handlers. - SYS_OFF_MODE_RESTART that provides a better restart API, removing a need from drivers to have a global scratch variable by utilizing the opaque callback argument. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 77 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index af907a3d68d1..b79f8942ea5f 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -7,6 +7,7 @@ #include struct device; +struct sys_off_handler; #define SYS_DOWN 0x0001 /* Notify of system down */ #define SYS_RESTART SYS_DOWN @@ -62,6 +63,82 @@ extern void machine_shutdown(void); struct pt_regs; extern void machine_crash_shutdown(struct pt_regs *); +/* + * sys-off handler API. + */ + +/* + * Standard sys-off priority levels. Users are expected to set priorities + * relative to the standard levels. + * + * SYS_OFF_PRIO_PLATFORM: Use this for platform-level handlers. + * + * SYS_OFF_PRIO_LOW: Use this for handler of last resort. + * + * SYS_OFF_PRIO_DEFAULT: Use this for normal handlers. + * + * SYS_OFF_PRIO_HIGH: Use this for higher priority handlers. + * + * SYS_OFF_PRIO_FIRMWARE: Use this if handler uses firmware call. + */ +#define SYS_OFF_PRIO_PLATFORM -256 +#define SYS_OFF_PRIO_LOW -128 +#define SYS_OFF_PRIO_DEFAULT 0 +#define SYS_OFF_PRIO_HIGH 192 +#define SYS_OFF_PRIO_FIRMWARE 224 + +enum sys_off_mode { + /** + * @SYS_OFF_MODE_POWER_OFF_PREPARE: + * + * Handlers prepare system to be powered off. Handlers are + * allowed to sleep. + */ + SYS_OFF_MODE_POWER_OFF_PREPARE, + + /** + * @SYS_OFF_MODE_POWER_OFF: + * + * Handlers power-off system. Handlers are disallowed to sleep. + */ + SYS_OFF_MODE_POWER_OFF, + + /** + * @SYS_OFF_MODE_RESTART: + * + * Handlers restart system. Handlers are disallowed to sleep. + */ + SYS_OFF_MODE_RESTART, +}; + +/** + * struct sys_off_data - sys-off callback argument + * + * @mode: Mode ID. Currently used only by the sys-off restart mode, + * see enum reboot_mode for the available modes. + * @cb_data: User's callback data. + * @cmd: Command string. Currently used only by the sys-off restart mode, + * NULL otherwise. + */ +struct sys_off_data { + int mode; + void *cb_data; + const char *cmd; +}; + +struct sys_off_handler * +register_sys_off_handler(enum sys_off_mode mode, + int priority, + int (*callback)(struct sys_off_data *data), + void *cb_data); +void unregister_sys_off_handler(struct sys_off_handler *handler); + +int devm_register_sys_off_handler(struct device *dev, + enum sys_off_mode mode, + int priority, + int (*callback)(struct sys_off_data *data), + void *cb_data); + /* * Architecture independent implemenations of sys_reboot commands. */ -- cgit v1.2.3 From 2b6aa7332f8020dfdaffe340ff038aac4df35238 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:13 +0300 Subject: kernel/reboot: Add do_kernel_power_off() Add do_kernel_power_off() helper that will remove open-coded pm_power_off invocations from the architecture code. This is the first step on the way to remove the global pm_power_off variable, which will allow us to implement consistent power-off chaining support. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index b79f8942ea5f..99a9753e77bc 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -63,6 +63,8 @@ extern void machine_shutdown(void); struct pt_regs; extern void machine_crash_shutdown(struct pt_regs *); +void do_kernel_power_off(void); + /* * sys-off handler API. */ -- cgit v1.2.3 From 0e2110d2e910e44cc7cf23fce14613e232602602 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:15 +0300 Subject: kernel/reboot: Add kernel_can_power_off() Add kernel_can_power_off() helper that replaces open-coded checks of the global pm_power_off variable. This is a necessary step towards supporting chained power-off handlers. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 99a9753e77bc..5837c6c2fb40 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -149,6 +149,7 @@ extern void kernel_restart_prepare(char *cmd); extern void kernel_restart(char *cmd); extern void kernel_halt(void); extern void kernel_power_off(void); +extern bool kernel_can_power_off(void); extern int C_A_D; /* for sysctl */ void ctrl_alt_del(void); -- cgit v1.2.3 From fb61375ecfba49e153af561402f49f6fe3bebd39 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:16 +0300 Subject: kernel/reboot: Add register_platform_power_off() Add platform-level registration helpers that will ease transition of the arch/platform power-off callbacks to the new sys-off based API, allowing us to remove the global pm_power_off variable in the future. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 5837c6c2fb40..a8fee1d09c65 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -141,6 +141,9 @@ int devm_register_sys_off_handler(struct device *dev, int (*callback)(struct sys_off_data *data), void *cb_data); +int register_platform_power_off(void (*power_off)(void)); +void unregister_platform_power_off(void (*power_off)(void)); + /* * Architecture independent implemenations of sys_reboot commands. */ -- cgit v1.2.3 From 5b71808eb7c97815fc3b9c386ca0ef6daf2dc053 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:32 +0300 Subject: reboot: Remove pm_power_off_prepare() All pm_power_off_prepare() users were converted to sys-off handler API. Remove the obsolete global callback variable. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index e65b3ab28377..3786d306dad2 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -21,7 +21,6 @@ * Callbacks for platform drivers to implement. */ extern void (*pm_power_off)(void); -extern void (*pm_power_off_prepare)(void); struct device; /* we have a circular dep with device.h */ #ifdef CONFIG_VT_CONSOLE_SLEEP -- cgit v1.2.3 From d2c5415327171e6c1bca2dc4d8a77f450ecf7150 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:34 +0300 Subject: kernel/reboot: Add devm_register_power_off_handler() Add devm_register_power_off_handler() helper that registers sys-off handler using power-off mode and with a default priority. Most drivers will want to register power-off handler with a default priority, so this helper will reduce the boilerplate code and make code easier to read and follow. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index a8fee1d09c65..3b063c5b6118 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -141,6 +141,10 @@ int devm_register_sys_off_handler(struct device *dev, int (*callback)(struct sys_off_data *data), void *cb_data); +int devm_register_power_off_handler(struct device *dev, + int (*callback)(struct sys_off_data *data), + void *cb_data); + int register_platform_power_off(void (*power_off)(void)); void unregister_platform_power_off(void (*power_off)(void)); -- cgit v1.2.3 From 6779db970bd287bb35b28bd5dc256fd7aef19d1c Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:35 +0300 Subject: kernel/reboot: Add devm_register_restart_handler() Add devm_register_restart_handler() helper that registers sys-off handler using restart mode and with a default priority. Most drivers will want to register restart handler with a default priority, so this helper will reduce the boilerplate code and make code easier to read and follow. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 3b063c5b6118..d29d37a2abb6 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -145,6 +145,10 @@ int devm_register_power_off_handler(struct device *dev, int (*callback)(struct sys_off_data *data), void *cb_data); +int devm_register_restart_handler(struct device *dev, + int (*callback)(struct sys_off_data *data), + void *cb_data); + int register_platform_power_off(void (*power_off)(void)); void unregister_platform_power_off(void (*power_off)(void)); -- cgit v1.2.3 From 15f214f9bdb7c1f560b4bf863c5a72ff53b442a4 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Fri, 13 May 2022 11:34:33 +0200 Subject: topology: Remove unused cpu_cluster_mask() default_topology[] uses cpu_clustergroup_mask() for the CLS level (guarded by CONFIG_SCHED_CLUSTER) which is currently provided by x86 (arch/x86/kernel/smpboot.c) and arm64 (drivers/base/arch_topology.c). Fixes: 778c558f49a2 ("sched: Add cluster scheduler level in core and related Kconfig for ARM64") Acked-by: Barry Song Signed-off-by: Dietmar Eggemann Link: https://lore.kernel.org/r/20220513093433.425163-1-dietmar.eggemann@arm.com Signed-off-by: Greg Kroah-Hartman --- include/linux/topology.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/topology.h b/include/linux/topology.h index f19bc3626297..4564faafd0e1 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -240,13 +240,6 @@ static inline const struct cpumask *cpu_smt_mask(int cpu) } #endif -#if defined(CONFIG_SCHED_CLUSTER) && !defined(cpu_cluster_mask) -static inline const struct cpumask *cpu_cluster_mask(int cpu) -{ - return topology_cluster_cpumask(cpu); -} -#endif - static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); -- cgit v1.2.3 From 0651ab90e4ade17f1d4f4367b70f6120480410f3 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Wed, 18 May 2022 11:08:57 +0200 Subject: ACPI: CPPC: Check _OSC for flexible address space MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ACPI 6.2 Section 6.2.11.2 'Platform-Wide OSPM Capabilities': Starting with ACPI Specification 6.2, all _CPC registers can be in PCC, System Memory, System IO, or Functional Fixed Hardware address spaces. OSPM support for this more flexible register space scheme is indicated by the “Flexible Address Space for CPPC Registers” _OSC bit Otherwise (cf ACPI 6.1, s8.4.7.1.1.X), _CPC registers must be in: - PCC or Functional Fixed Hardware address space if defined - SystemMemory address space (NULL register) if not defined Add the corresponding _OSC bit and check it when parsing _CPC objects. Signed-off-by: Pierre Gondois Reviewed-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d7136d13aa44..03465db16b68 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -574,6 +574,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 +#define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 #define OSC_SB_PRM_SUPPORT 0x00200000 @@ -581,6 +582,7 @@ extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; extern bool osc_sb_cppc_not_supported; +extern bool osc_cpc_flexible_adr_space_confirmed; /* USB4 Capabilities */ #define OSC_USB_USB3_TUNNELING 0x00000001 -- cgit v1.2.3 From 3cc30dd00a580ca0c9c0b01639841cfd72d10129 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Wed, 18 May 2022 11:09:00 +0200 Subject: cpufreq: CPPC: Enable fast_switch The communication mean of the _CPC desired performance can be PCC, System Memory, System IO, or Functional Fixed Hardware. commit b7898fda5bc7 ("cpufreq: Support for fast frequency switching") fast_switching is 'for switching CPU frequencies from interrupt context'. Writes to SystemMemory and SystemIo are fast and suitable this. This is not the case for PCC and might not be the case for FFH. Enable fast_switching for the cppc_cpufreq driver in above cases. Add cppc_allow_fast_switch() to check the desired performance register address space and set fast_switching accordingly. Signed-off-by: Pierre Gondois Reviewed-by: Sudeep Holla Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/acpi/cppc_acpi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index 92b7ea8d8f5e..c6108581d97d 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -141,6 +141,7 @@ extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls); extern int cppc_set_enable(int cpu, bool enable); extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps); extern bool acpi_cpc_valid(void); +extern bool cppc_allow_fast_switch(void); extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data); extern unsigned int cppc_get_transition_latency(int cpu); extern bool cpc_ffh_supported(void); @@ -175,6 +176,10 @@ static inline bool acpi_cpc_valid(void) { return false; } +static inline bool cppc_allow_fast_switch(void) +{ + return false; +} static inline unsigned int cppc_get_transition_latency(int cpu) { return CPUFREQ_ETERNAL; -- cgit v1.2.3 From 8f9ae5b3ae80f168a6224529e3787f4fb27f299a Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Wed, 4 May 2022 17:06:28 -0700 Subject: Bluetooth: eir: Add helpers for managing service data This adds helpers for accessing and appending service data (0x16) ad type. Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 62a9bb022aed..fe7935be7dc4 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -625,6 +625,7 @@ enum { #define EIR_SSP_RAND_R192 0x0F /* Simple Pairing Randomizer R-192 */ #define EIR_DEVICE_ID 0x10 /* device ID */ #define EIR_APPEARANCE 0x19 /* Device appearance */ +#define EIR_SERVICE_DATA 0x16 /* Service Data */ #define EIR_LE_BDADDR 0x1B /* LE Bluetooth device address */ #define EIR_LE_ROLE 0x1C /* LE role */ #define EIR_SSP_HASH_C256 0x1D /* Simple Pairing Hash C-256 */ -- cgit v1.2.3 From 66d29d802ef3bf55a49b07568b0048823d4a72a6 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 11 May 2022 16:56:56 +0200 Subject: PM: domains: Allocate gpd_timing_data dynamically based on governor If a genpd doesn't have an associated governor assigned, there's really no point to allocate the per device gpd_timing_data, as the data isn't being used by a governor anyway. To avoid wasting memory, let's therefore convert the corresponding td variable in the struct generic_pm_domain_data into a pointer and manage the allocation of its data dynamically. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 043d48e4420a..126a4b9ab215 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -193,7 +193,7 @@ struct pm_domain_data { struct generic_pm_domain_data { struct pm_domain_data base; - struct gpd_timing_data td; + struct gpd_timing_data *td; struct notifier_block nb; struct notifier_block *power_nb; int cpu; -- cgit v1.2.3 From 9c74f2ac4801473d03b0e29fab74eb94a9944521 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 11 May 2022 16:56:57 +0200 Subject: PM: domains: Move the next_wakeup variable into the struct gpd_timing_data If the corresponding genpd for the device doesn't use a governor, the variable next_wakeup within the struct generic_pm_domain_data becomes superfluous. To avoid wasting memory, let's move it into the struct gpd_timing_data, which is already being allocated based upon if there is governor assigned. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 126a4b9ab215..1f370f074f30 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -182,6 +182,7 @@ struct gpd_timing_data { s64 suspend_latency_ns; s64 resume_latency_ns; s64 effective_constraint_ns; + ktime_t next_wakeup; bool constraint_changed; bool cached_suspend_ok; }; @@ -200,7 +201,6 @@ struct generic_pm_domain_data { unsigned int performance_state; unsigned int default_pstate; unsigned int rpm_pstate; - ktime_t next_wakeup; void *data; }; -- cgit v1.2.3 From f38d1a6d002526a4e8840e9bb19733e9d4ce1a67 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 11 May 2022 16:57:02 +0200 Subject: PM: domains: Allocate governor data dynamically based on a genpd governor If a genpd doesn't have an associated governor assigned, several variables in the struct generic_pm_domain becomes superfluous. Rather than wasting memory in allocated genpds, let's move the variables from the struct generic_pm_domain into a new separate struct. In this way, we can instead dynamically decide when we need to allocate the corresponding data for it. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 1f370f074f30..ebc351698090 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -91,6 +91,14 @@ struct gpd_dev_ops { int (*stop)(struct device *dev); }; +struct genpd_governor_data { + s64 max_off_time_ns; + bool max_off_time_changed; + ktime_t next_wakeup; + bool cached_power_down_ok; + bool cached_power_down_state_idx; +}; + struct genpd_power_state { s64 power_off_latency_ns; s64 power_on_latency_ns; @@ -114,6 +122,7 @@ struct generic_pm_domain { struct list_head child_links; /* Links with PM domain as a child */ struct list_head dev_list; /* List of devices */ struct dev_power_governor *gov; + struct genpd_governor_data *gd; /* Data used by a genpd governor. */ struct work_struct power_off_work; struct fwnode_handle *provider; /* Identity of the domain provider */ bool has_provider; @@ -134,11 +143,6 @@ struct generic_pm_domain { int (*set_performance_state)(struct generic_pm_domain *genpd, unsigned int state); struct gpd_dev_ops dev_ops; - s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ - ktime_t next_wakeup; /* Maintained by the domain governor */ - bool max_off_time_changed; - bool cached_power_down_ok; - bool cached_power_down_state_idx; int (*attach_dev)(struct generic_pm_domain *domain, struct device *dev); void (*detach_dev)(struct generic_pm_domain *domain, -- cgit v1.2.3 From 0e7579ca732a39cc377e17509dda9bfc4f6ba78e Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 19 May 2022 17:30:49 +0300 Subject: io_uring: fix incorrect __kernel_rwf_t cast Currently 'make C=1 fs/io_uring.o' generates sparse warning: CHECK fs/io_uring.c fs/io_uring.c: note: in included file (through include/trace/trace_events.h, include/trace/define_trace.h, i nclude/trace/events/io_uring.h): ./include/trace/events/io_uring.h:488:1: warning: incorrect type in assignment (different base types) expected unsigned int [usertype] op_flags got restricted __kernel_rwf_t const [usertype] rw_flags This happen on cast of sqe->rw_flags which is defined as __kernel_rwf_t, this type is bitwise and requires __force attribute for any casts. However rw_flags is a member of the union, and its access can be safely replaced by using of its neighbours, so let's use poll32_events to fix the sparse warning. Signed-off-by: Vasily Averin Link: https://lore.kernel.org/r/6f009241-a63f-ae43-a04b-62841aaef293@openvz.org Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 42534ec2ab9d..7cfd9c5cff37 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -520,7 +520,7 @@ TRACE_EVENT(io_uring_req_failed, __entry->off = sqe->off; __entry->addr = sqe->addr; __entry->len = sqe->len; - __entry->op_flags = sqe->rw_flags; + __entry->op_flags = sqe->poll32_events; __entry->buf_index = sqe->buf_index; __entry->personality = sqe->personality; __entry->file_index = sqe->file_index; -- cgit v1.2.3 From 4853f68d158ac59b05985a6af5b7da7ccdbc14c8 Mon Sep 17 00:00:00 2001 From: Liao Chang Date: Fri, 8 Apr 2022 18:09:09 +0800 Subject: kexec_file: Fix kexec_file.c build error for riscv platform When CONFIG_KEXEC_FILE is set for riscv platform, the compilation of kernel/kexec_file.c generate build error: kernel/kexec_file.c: In function 'crash_prepare_elf64_headers': ./arch/riscv/include/asm/page.h:110:71: error: request for member 'virt_addr' in something not a structure or union 110 | ((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < kernel_map.virt_addr)) | ^ ./arch/riscv/include/asm/page.h:131:2: note: in expansion of macro 'is_linear_mapping' 131 | is_linear_mapping(_x) ? \ | ^~~~~~~~~~~~~~~~~ ./arch/riscv/include/asm/page.h:140:31: note: in expansion of macro '__va_to_pa_nodebug' 140 | #define __phys_addr_symbol(x) __va_to_pa_nodebug(x) | ^~~~~~~~~~~~~~~~~~ ./arch/riscv/include/asm/page.h:143:24: note: in expansion of macro '__phys_addr_symbol' 143 | #define __pa_symbol(x) __phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0)) | ^~~~~~~~~~~~~~~~~~ kernel/kexec_file.c:1327:36: note: in expansion of macro '__pa_symbol' 1327 | phdr->p_offset = phdr->p_paddr = __pa_symbol(_text); This occurs is because the "kernel_map" referenced in macro is_linear_mapping() is suppose to be the one of struct kernel_mapping defined in arch/riscv/mm/init.c, but the 2nd argument of crash_prepare_elf64_header() has same symbol name, in expansion of macro is_linear_mapping in function crash_prepare_elf64_header(), "kernel_map" actually is the local variable. Signed-off-by: Liao Chang Link: https://lore.kernel.org/r/20220408100914.150110-2-lizhengyu3@huawei.com Signed-off-by: Palmer Dabbelt --- include/linux/kexec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 58d1b58a971e..ebb1bffbf068 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -227,7 +227,7 @@ struct crash_mem { extern int crash_exclude_mem_range(struct crash_mem *mem, unsigned long long mstart, unsigned long long mend); -extern int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map, +extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, void **addr, unsigned long *sz); #endif /* CONFIG_KEXEC_FILE */ -- cgit v1.2.3 From 6c1e423a3c84953edcf91ff03ab97829b287184a Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 18 May 2022 17:45:27 +0200 Subject: can: can-dev: remove obsolete CAN LED support Since commit 30f3b42147ba6f ("can: mark led trigger as broken") the CAN specific LED support was disabled and marked as BROKEN. As the common LED support with CONFIG_LEDS_TRIGGER_NETDEV should do this work now the code can be removed as preparation for a CAN netdevice Kconfig rework. Link: https://lore.kernel.org/all/20220518154527.29046-1-socketcan@hartkopp.net Suggested-by: Vincent Mailhol Signed-off-by: Oliver Hartkopp [mkl: remove led.h from MAINTAINERS] Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 10 ---------- include/linux/can/led.h | 51 ------------------------------------------------- 2 files changed, 61 deletions(-) delete mode 100644 include/linux/can/led.h (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index c2ea47f30046..e22dc03c850e 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -85,15 +84,6 @@ struct can_priv { int (*do_get_berr_counter)(const struct net_device *dev, struct can_berr_counter *bec); int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv); - -#ifdef CONFIG_CAN_LEDS - struct led_trigger *tx_led_trig; - char tx_led_trig_name[CAN_LED_NAME_SZ]; - struct led_trigger *rx_led_trig; - char rx_led_trig_name[CAN_LED_NAME_SZ]; - struct led_trigger *rxtx_led_trig; - char rxtx_led_trig_name[CAN_LED_NAME_SZ]; -#endif }; static inline bool can_tdc_is_enabled(const struct can_priv *priv) diff --git a/include/linux/can/led.h b/include/linux/can/led.h deleted file mode 100644 index 7c3cfd798c56..000000000000 --- a/include/linux/can/led.h +++ /dev/null @@ -1,51 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2012, Fabio Baltieri - */ - -#ifndef _CAN_LED_H -#define _CAN_LED_H - -#include -#include -#include - -enum can_led_event { - CAN_LED_EVENT_OPEN, - CAN_LED_EVENT_STOP, - CAN_LED_EVENT_TX, - CAN_LED_EVENT_RX, -}; - -#ifdef CONFIG_CAN_LEDS - -/* keep space for interface name + "-tx"/"-rx"/"-rxtx" - * suffix and null terminator - */ -#define CAN_LED_NAME_SZ (IFNAMSIZ + 6) - -void can_led_event(struct net_device *netdev, enum can_led_event event); -void devm_can_led_init(struct net_device *netdev); -int __init can_led_notifier_init(void); -void __exit can_led_notifier_exit(void); - -#else - -static inline void can_led_event(struct net_device *netdev, - enum can_led_event event) -{ -} -static inline void devm_can_led_init(struct net_device *netdev) -{ -} -static inline int can_led_notifier_init(void) -{ - return 0; -} -static inline void can_led_notifier_exit(void) -{ -} - -#endif - -#endif /* !_CAN_LED_H */ -- cgit v1.2.3 From 2c8a81dc0cc533c666c64f4139a608b0ae55d96f Mon Sep 17 00:00:00 2001 From: Tong Tiangen Date: Tue, 17 May 2022 07:45:47 +0000 Subject: riscv/mm: fix two page table check related issues Two page table check related issues have been fixed here. 1. Open CONFIG_PAGE_TABLE_CHECK in riscv32, we got a compile error[1]: error: implicit declaration of function 'pud_leaf' Add pud_leaf() definition to incluce/asm-generic/pgtable-nopmd.h to fix this issue. 2. Keep consistent with other pud_xxx() helpers, move pud_user() to pgtable-64.h and add pud_user() to pgtable-nopmd.h. [1]https://lore.kernel.org/linux-mm/202205161811.2nLxmN2O-lkp@intel.com/T/ Link: https://lkml.kernel.org/r/20220517074548.2227779-2-tongtiangen@huawei.com Fixes: 856eed79f8d3 ("riscv/mm: enable ARCH_SUPPORTS_PAGE_TABLE_CHECK") Signed-off-by: Tong Tiangen Reported-by: kernel test robot Cc: Anshuman Khandual Cc: Pasha Tatashin Cc: Anshuman Khandual Cc: Albert Ou Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Guohanjun Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Will Deacon Cc: Xie XiuQi Signed-off-by: Andrew Morton --- include/asm-generic/pgtable-nopmd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h index 10789cf51d16..8ffd64e7a24c 100644 --- a/include/asm-generic/pgtable-nopmd.h +++ b/include/asm-generic/pgtable-nopmd.h @@ -30,6 +30,8 @@ typedef struct { pud_t pud; } pmd_t; static inline int pud_none(pud_t pud) { return 0; } static inline int pud_bad(pud_t pud) { return 0; } static inline int pud_present(pud_t pud) { return 1; } +static inline int pud_user(pud_t pud) { return 0; } +static inline int pud_leaf(pud_t pud) { return 0; } static inline void pud_clear(pud_t *pud) { } #define pmd_ERROR(pmd) (pud_ERROR((pmd).pud)) -- cgit v1.2.3 From b265cdebdfefbee4ef1ae2972af36f7a7cac5148 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 19 May 2022 14:08:48 -0700 Subject: sched: coredump.h: clarify the use of MMF_VM_HUGEPAGE Patch series "Make khugepaged collapse readonly FS THP more consistent", v4. The readonly FS THP relies on khugepaged to collapse THP for suitable vmas. But the behavior is inconsistent for "always" mode (https://lore.kernel.org/linux-mm/00f195d4-d039-3cf2-d3a1-a2c88de397a0@suse.cz/). The "always" mode means THP allocation should be tried all the time and khugepaged should try to collapse THP all the time. Of course the allocation and collapse may fail due to other factors and conditions. Currently file THP may not be collapsed by khugepaged even though all the conditions are met. That does break the semantics of "always" mode. So make sure readonly FS vmas are registered to khugepaged to fix the break. Register suitable vmas in common mmap path, that could cover both readonly FS vmas and shmem vmas, so remove the khugepaged calls in shmem.c. The patch 1-7 are minor bug fixes, clean up and preparation patches. Patch 8 is the real meat. Tested with khugepaged test in selftests and the testcase provided by Vlastimil Babka in https://lore.kernel.org/lkml/df3b5d1c-a36b-2c73-3e27-99e74983de3a@suse.cz/ by commenting out MADV_HUGEPAGE call. This patch (of 8): MMF_VM_HUGEPAGE is set as long as the mm is available for khugepaged by khugepaged_enter(), not only when VM_HUGEPAGE is set on vma. Correct the comment to avoid confusion. Link: https://lkml.kernel.org/r/20220510203222.24246-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20220510203222.24246-2-shy828301@gmail.com Signed-off-by: Yang Shi Reviewed-by: Miaohe Lin Acked-by: Song Liu Acked-by: Vlastmil Babka Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Rik van Riel Cc: Song Liu Cc: Theodore Ts'o Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/sched/coredump.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 4d9e3a656875..4d0a5be28b70 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -57,7 +57,8 @@ static inline int get_dumpable(struct mm_struct *mm) #endif /* leave room for more dump flags */ #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ -#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ +#define MMF_VM_HUGEPAGE 17 /* set when mm is available for + khugepaged */ /* * This one-shot flag is dropped due to necessity of changing exe once again * on NFS restore -- cgit v1.2.3 From 78d12c19e02d8151b1c82228ae6bb10f174a68e2 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 19 May 2022 14:08:49 -0700 Subject: mm: thp: only regular file could be THP eligible Since commit a4aeaa06d45e ("mm: khugepaged: skip huge page collapse for special files"), khugepaged just collapses THP for regular file which is the intended usecase for readonly fs THP. Only show regular file as THP eligible accordingly. And make file_thp_enabled() available for khugepaged too in order to remove duplicate code. Link: https://lkml.kernel.org/r/20220510203222.24246-5-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Song Liu Acked-by: Vlastmil Babka Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Rik van Riel Cc: Song Liu Cc: Theodore Ts'o Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index fbf36bb1be22..de29821231c9 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -173,6 +173,20 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } +static inline bool file_thp_enabled(struct vm_area_struct *vma) +{ + struct inode *inode; + + if (!vma->vm_file) + return false; + + inode = vma->vm_file->f_inode; + + return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) && + (vma->vm_flags & VM_EXEC) && + !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); +} + bool transparent_hugepage_active(struct vm_area_struct *vma); #define transparent_hugepage_use_zero_page() \ -- cgit v1.2.3 From d2081b2bf8195b8239c67fdd61518e077da7cbec Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 19 May 2022 14:08:49 -0700 Subject: mm: khugepaged: make khugepaged_enter() void function The most callers of khugepaged_enter() don't care about the return value. Only dup_mmap(), anonymous THP page fault and MADV_HUGEPAGE handle the error by returning -ENOMEM. Actually it is not harmful for them to ignore the error case either. It also sounds overkilling to fail fork() and page fault early due to khugepaged_enter() error, and MADV_HUGEPAGE does set VM_HUGEPAGE flag regardless of the error. Link: https://lkml.kernel.org/r/20220510203222.24246-6-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Song Liu Acked-by: Vlastmil Babka Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Rik van Riel Cc: Song Liu Cc: Theodore Ts'o Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/khugepaged.h | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 2fcc01891b47..0423d3619f26 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -12,10 +12,10 @@ extern struct attribute_group khugepaged_attr_group; extern int khugepaged_init(void); extern void khugepaged_destroy(void); extern int start_stop_khugepaged(void); -extern int __khugepaged_enter(struct mm_struct *mm); +extern void __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); -extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags); +extern void khugepaged_enter_vma_merge(struct vm_area_struct *vma, + unsigned long vm_flags); extern void khugepaged_min_free_kbytes_update(void); #ifdef CONFIG_SHMEM extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr); @@ -40,11 +40,10 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm, (transparent_hugepage_flags & \ (1<flags)) - return __khugepaged_enter(mm); - return 0; + __khugepaged_enter(mm); } static inline void khugepaged_exit(struct mm_struct *mm) @@ -53,7 +52,7 @@ static inline void khugepaged_exit(struct mm_struct *mm) __khugepaged_exit(mm); } -static inline int khugepaged_enter(struct vm_area_struct *vma, +static inline void khugepaged_enter(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) @@ -62,27 +61,22 @@ static inline int khugepaged_enter(struct vm_area_struct *vma, (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && !(vm_flags & VM_NOHUGEPAGE) && !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - if (__khugepaged_enter(vma->vm_mm)) - return -ENOMEM; - return 0; + __khugepaged_enter(vma->vm_mm); } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - return 0; } static inline void khugepaged_exit(struct mm_struct *mm) { } -static inline int khugepaged_enter(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline void khugepaged_enter(struct vm_area_struct *vma, + unsigned long vm_flags) { - return 0; } -static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline void khugepaged_enter_vma_merge(struct vm_area_struct *vma, + unsigned long vm_flags) { - return 0; } static inline void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) -- cgit v1.2.3 From 2647d11b9e71d495b2d4985ebaf7a734373a4b80 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 19 May 2022 14:08:49 -0700 Subject: mm: khugepaged: make hugepage_vma_check() non-static The hugepage_vma_check() could be reused by khugepaged_enter() and khugepaged_enter_vma_merge(), but it is static in khugepaged.c. Make it non-static and declare it in khugepaged.h. Link: https://lkml.kernel.org/r/20220510203222.24246-7-shy828301@gmail.com Signed-off-by: Yang Shi Suggested-by: Vlastimil Babka Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Rik van Riel Cc: Song Liu Cc: Song Liu Cc: Theodore Ts'o Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/khugepaged.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 0423d3619f26..c340f6bb39d6 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -3,8 +3,6 @@ #define _LINUX_KHUGEPAGED_H #include /* MMF_VM_HUGEPAGE */ -#include - #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern struct attribute_group khugepaged_attr_group; @@ -12,6 +10,8 @@ extern struct attribute_group khugepaged_attr_group; extern int khugepaged_init(void); extern void khugepaged_destroy(void); extern int start_stop_khugepaged(void); +extern bool hugepage_vma_check(struct vm_area_struct *vma, + unsigned long vm_flags); extern void __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); extern void khugepaged_enter_vma_merge(struct vm_area_struct *vma, @@ -55,13 +55,11 @@ static inline void khugepaged_exit(struct mm_struct *mm) static inline void khugepaged_enter(struct vm_area_struct *vma, unsigned long vm_flags) { - if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) - if ((khugepaged_always() || - (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) || - (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && - !(vm_flags & VM_NOHUGEPAGE) && - !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && + khugepaged_enabled()) { + if (hugepage_vma_check(vma, vm_flags)) __khugepaged_enter(vma->vm_mm); + } } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) -- cgit v1.2.3 From c791576c60288c89b351ea2d2098f6a872d78fa7 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 19 May 2022 14:08:50 -0700 Subject: mm: khugepaged: introduce khugepaged_enter_vma() helper The khugepaged_enter_vma_merge() actually does as the same thing as the khugepaged_enter() section called by shmem_mmap(), so consolidate them into one helper and rename it to khugepaged_enter_vma(). Link: https://lkml.kernel.org/r/20220510203222.24246-8-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Vlastmil Babka Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Rik van Riel Cc: Song Liu Cc: Song Liu Cc: Theodore Ts'o Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/khugepaged.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index c340f6bb39d6..392d34c3c59a 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -14,8 +14,8 @@ extern bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags); extern void __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); -extern void khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags); +extern void khugepaged_enter_vma(struct vm_area_struct *vma, + unsigned long vm_flags); extern void khugepaged_min_free_kbytes_update(void); #ifdef CONFIG_SHMEM extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr); @@ -72,8 +72,8 @@ static inline void khugepaged_enter(struct vm_area_struct *vma, unsigned long vm_flags) { } -static inline void khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline void khugepaged_enter_vma(struct vm_area_struct *vma, + unsigned long vm_flags) { } static inline void collapse_pte_mapped_thp(struct mm_struct *mm, -- cgit v1.2.3 From bc4a68adb151f08b50822158c7767f5726346370 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 19 May 2022 14:08:50 -0700 Subject: mm/swap: remove unneeded return value of free_swap_slot The return value of free_swap_slot is always 0 and also ignored now. Remove it to clean up the code. Link: https://lkml.kernel.org/r/20220509131416.17553-5-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alistair Popple Cc: David Howells Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: NeilBrown Cc: Peter Xu Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/swap_slots.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h index 347f1a304190..15adfb8c813a 100644 --- a/include/linux/swap_slots.h +++ b/include/linux/swap_slots.h @@ -24,7 +24,7 @@ struct swap_slots_cache { void disable_swap_slots_cache_lock(void); void reenable_swap_slots_cache_unlock(void); void enable_swap_slots_cache(void); -int free_swap_slot(swp_entry_t entry); +void free_swap_slot(swp_entry_t entry); extern bool swap_slot_cache_enabled; -- cgit v1.2.3 From 3db3264d8a5f4816c022eb9052694ce51e657bfc Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 19 May 2022 14:08:51 -0700 Subject: mm/swap: make page_swapcount and __lru_add_drain_all static Make page_swapcount and __lru_add_drain_all static. They are only used within the file now. Link: https://lkml.kernel.org/r/20220509131416.17553-9-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alistair Popple Cc: David Howells Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: NeilBrown Cc: Peter Xu Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Oscar Salvador Signed-off-by: Andrew Morton --- include/linux/swap.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6bf1506e5080..0ff887cad383 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -485,7 +485,6 @@ int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); -extern int page_swapcount(struct page *); extern int __swap_count(swp_entry_t entry); extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); @@ -557,12 +556,6 @@ static inline void put_swap_page(struct page *page, swp_entry_t swp) { } - -static inline int page_swapcount(struct page *page) -{ - return 0; -} - static inline int __swap_count(swp_entry_t entry) { return 0; -- cgit v1.2.3 From a930c210c42dec32b031ad7645bd6904701b5297 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 19 May 2022 14:08:52 -0700 Subject: mm/swap: fix the obsolete comment for SWP_TYPE_SHIFT Since commit 3159f943aafd ("xarray: Replace exceptional entries"), there is only one bit of 'type' can be shifted up. Update the corresponding comment. Link: https://lkml.kernel.org/r/20220509131416.17553-13-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Cc: Alistair Popple Cc: David Howells Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: NeilBrown Cc: Peter Xu Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Oscar Salvador Signed-off-by: Andrew Morton --- include/linux/swapops.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 09945342bf76..fe220df499f1 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -13,10 +13,10 @@ * get good packing density in that tree, so the index should be dense in * the low-order bits. * - * We arrange the `type' and `offset' fields so that `type' is at the seven + * We arrange the `type' and `offset' fields so that `type' is at the six * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for - * shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry(). + * shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ -- cgit v1.2.3 From ff351f4bb9606a6c9a1f3fcdd918635b51514779 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 19 May 2022 14:08:52 -0700 Subject: mm/swap: fix comment about swap extent Since commit 4efaceb1c5f8 ("mm, swap: use rbtree for swap_extent"), rbtree is used for swap extent. Also curr_swap_extent is removed at that time. Update the corresponding comment. Link: https://lkml.kernel.org/r/20220509131416.17553-16-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Cc: Alistair Popple Cc: David Hildenbrand Cc: David Howells Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: NeilBrown Cc: Peter Xu Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Oscar Salvador Signed-off-by: Andrew Morton --- include/linux/swap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 0ff887cad383..04c0713c1d6e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -168,8 +168,8 @@ struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of - * disk blocks. A list of swap extents maps the entire swapfile. (Where the - * term `swapfile' refers to either a blockdevice or an IS_REG file. Apart + * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the + * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. -- cgit v1.2.3 From f6498b776d280b30a4614d8261840961e993c2c8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 19 May 2022 14:08:53 -0700 Subject: mm: zswap: add basic meminfo and vmstat coverage Currently it requires poking at debugfs to figure out the size and population of the zswap cache on a host. There are no counters for reads and writes against the cache. As a result, it's difficult to understand zswap behavior on production systems. Print zswap memory consumption and how many pages are zswapped out in /proc/meminfo. Count zswapouts and zswapins in /proc/vmstat. Link: https://lkml.kernel.org/r/20220510152847.230957-6-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: David Hildenbrand Cc: Dan Streetman Cc: Michal Hocko Cc: Minchan Kim Cc: Roman Gushchin Cc: Seth Jennings Cc: Shakeel Butt Signed-off-by: Andrew Morton --- include/linux/swap.h | 5 +++++ include/linux/vm_event_item.h | 4 ++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 04c0713c1d6e..f3ae17b43f20 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -620,6 +620,11 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) } #endif +#ifdef CONFIG_ZSWAP +extern u64 zswap_pool_total_size; +extern atomic_t zswap_stored_pages; +#endif + #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index e83967e4c20e..404024486fa5 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -136,6 +136,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_KSM COW_KSM, #endif +#ifdef CONFIG_ZSWAP + ZSWPIN, + ZSWPOUT, +#endif #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, DIRECT_MAP_LEVEL3_SPLIT, -- cgit v1.2.3 From f4840ccfca25db225b3371a8f7b5770febee87c5 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 19 May 2022 14:08:53 -0700 Subject: zswap: memcg accounting Applications can currently escape their cgroup memory containment when zswap is enabled. This patch adds per-cgroup tracking and limiting of zswap backend memory to rectify this. The existing cgroup2 memory.stat file is extended to show zswap statistics analogous to what's in meminfo and vmstat. Furthermore, two new control files, memory.zswap.current and memory.zswap.max, are added to allow tuning zswap usage on a per-workload basis. This is important since not all workloads benefit from zswap equally; some even suffer compared to disk swap when memory contents don't compress well. The optimal size of the zswap pool, and the threshold for writeback, also depends on the size of the workload's warm set. The implementation doesn't use a traditional page_counter transaction. zswap is unconventional as a memory consumer in that we only know the amount of memory to charge once expensive compression has occurred. If zwap is disabled or the limit is already exceeded we obviously don't want to compress page upon page only to reject them all. Instead, the limit is checked against current usage, then we compress and charge. This allows some limit overrun, but not enough to matter in practice. [hannes@cmpxchg.org: fix for CONFIG_SLOB builds] Link: https://lkml.kernel.org/r/YnwD14zxYjUJPc2w@cmpxchg.org [hannes@cmpxchg.org: opt out of cgroups v1] Link: https://lkml.kernel.org/r/Yn6it9mBYFA+/lTb@cmpxchg.org Link: https://lkml.kernel.org/r/20220510152847.230957-7-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Seth Jennings Cc: Dan Streetman Cc: Minchan Kim Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 54 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8ea4b541c31e..9ecead1042b9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -35,6 +35,8 @@ enum memcg_stat_item { MEMCG_PERCPU_B, MEMCG_VMALLOC, MEMCG_KMEM, + MEMCG_ZSWAP_B, + MEMCG_ZSWAPPED, MEMCG_NR_STAT, }; @@ -252,6 +254,10 @@ struct mem_cgroup { /* Range enforcement for interrupt charges */ struct work_struct high_work; +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) + unsigned long zswap_max; +#endif + unsigned long soft_limit; /* vmpressure notifications */ @@ -1273,6 +1279,10 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) return NULL; } +static inline void obj_cgroup_put(struct obj_cgroup *objcg) +{ +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } @@ -1694,6 +1704,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); struct obj_cgroup *get_obj_cgroup_from_current(void); +struct obj_cgroup *get_obj_cgroup_from_page(struct page *page); int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); @@ -1730,6 +1741,20 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) struct mem_cgroup *mem_cgroup_from_obj(void *p); +static inline void count_objcg_event(struct obj_cgroup *objcg, + enum vm_event_item idx) +{ + struct mem_cgroup *memcg; + + if (mem_cgroup_kmem_disabled()) + return; + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + count_memcg_events(memcg, idx, 1); + rcu_read_unlock(); +} + #else static inline bool mem_cgroup_kmem_disabled(void) { @@ -1756,6 +1781,11 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } +static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page) +{ + return NULL; +} + static inline bool memcg_kmem_enabled(void) { return false; @@ -1771,6 +1801,30 @@ static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) return NULL; } +static inline void count_objcg_event(struct obj_cgroup *objcg, + enum vm_event_item idx) +{ +} + #endif /* CONFIG_MEMCG_KMEM */ +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); +void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); +void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); +#else +static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) +{ + return true; +} +static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, + size_t size) +{ +} +static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, + size_t size) +{ +} +#endif + #endif /* _LINUX_MEMCONTROL_H */ -- cgit v1.2.3 From 6d4675e601357834dadd2ba1d803f6484596015c Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 19 May 2022 14:08:54 -0700 Subject: mm: don't be stuck to rmap lock on reclaim path The rmap locks(i_mmap_rwsem and anon_vma->root->rwsem) could be contended under memory pressure if processes keep working on their vmas(e.g., fork, mmap, munmap). It makes reclaim path stuck. In our real workload traces, we see kswapd is waiting the lock for 300ms+(worst case, a sec) and it makes other processes entering direct reclaim, which were also stuck on the lock. This patch makes lru aging path try_lock mode like shink_page_list so the reclaim context will keep working with next lru pages without being stuck. if it found the rmap lock contended, it rotates the page back to head of lru in both active/inactive lrus to make them consistent behavior, which is basic starting point rather than adding more heristic. Since this patch introduces a new "contended" field as out-param along with try_lock in-param in rmap_walk_control, it's not immutable any longer if the try_lock is set so remove const keywords on rmap related functions. Since rmap walking is already expensive operation, I doubt the const would help sizable benefit( And we didn't have it until 5.17). In a heavy app workload in Android, trace shows following statistics. It almost removes rmap lock contention from reclaim path. Martin Liu reported: Before: max_dur(ms) min_dur(ms) max-min(dur)ms avg_dur(ms) sum_dur(ms) count blocked_function 1632 0 1631 151.542173 31672 209 page_lock_anon_vma_read 601 0 601 145.544681 28817 198 rmap_walk_file After: max_dur(ms) min_dur(ms) max-min(dur)ms avg_dur(ms) sum_dur(ms) count blocked_function NaN NaN NaN NaN NaN 0.0 NaN 0 0 0 0.127645 1 12 rmap_walk_file [minchan@kernel.org: add comment, per Matthew] Link: https://lkml.kernel.org/r/YnNqeB5tUf6LZ57b@google.com Link: https://lkml.kernel.org/r/20220510215423.164547-1-minchan@kernel.org Signed-off-by: Minchan Kim Acked-by: Johannes Weiner Cc: Suren Baghdasaryan Cc: Michal Hocko Cc: John Dias Cc: Tim Murray Cc: Matthew Wilcox Cc: Vladimir Davydov Cc: Martin Liu Cc: Minchan Kim Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/fs.h | 5 +++++ include/linux/ksm.h | 4 ++-- include/linux/rmap.h | 28 ++++++++++++++++++++-------- 3 files changed, 27 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index b81cacc51d2f..044b67f8d861 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -477,6 +477,11 @@ static inline void i_mmap_unlock_write(struct address_space *mapping) up_write(&mapping->i_mmap_rwsem); } +static inline int i_mmap_trylock_read(struct address_space *mapping) +{ + return down_read_trylock(&mapping->i_mmap_rwsem); +} + static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 0630e545f4cb..0b4f17418f64 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -51,7 +51,7 @@ static inline void ksm_exit(struct mm_struct *mm) struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc); +void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -79,7 +79,7 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, } static inline void rmap_walk_ksm(struct folio *folio, - const struct rmap_walk_control *rwc) + struct rmap_walk_control *rwc) { } diff --git a/include/linux/rmap.h b/include/linux/rmap.h index cbe279a6f0de..9ec23138e410 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -128,6 +128,11 @@ static inline void anon_vma_lock_read(struct anon_vma *anon_vma) down_read(&anon_vma->root->rwsem); } +static inline int anon_vma_trylock_read(struct anon_vma *anon_vma) +{ + return down_read_trylock(&anon_vma->root->rwsem); +} + static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) { up_read(&anon_vma->root->rwsem); @@ -366,17 +371,14 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); -/* - * Called by memory-failure.c to kill processes. - */ -struct anon_vma *folio_lock_anon_vma_read(struct folio *folio); -void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); /* * rmap_walk_control: To control rmap traversing for specific needs * * arg: passed to rmap_one() and invalid_vma() + * try_lock: bail out if the rmap lock is contended + * contended: indicate the rmap traversal bailed out due to lock contention * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition * anon_lock: for getting anon_lock by optimized way rather than default @@ -384,6 +386,8 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); */ struct rmap_walk_control { void *arg; + bool try_lock; + bool contended; /* * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. @@ -391,12 +395,20 @@ struct rmap_walk_control { bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct folio *folio); - struct anon_vma *(*anon_lock)(struct folio *folio); + struct anon_vma *(*anon_lock)(struct folio *folio, + struct rmap_walk_control *rwc); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc); -void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc); +void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); +void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); + +/* + * Called by memory-failure.c to kill processes. + */ +struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, + struct rmap_walk_control *rwc); +void page_unlock_anon_vma_read(struct anon_vma *anon_vma); #else /* !CONFIG_MMU */ -- cgit v1.2.3 From 10e0f7530205799e7e971aba699a7cb3a47456de Mon Sep 17 00:00:00 2001 From: Wonhyuk Yang Date: Thu, 19 May 2022 14:08:54 -0700 Subject: mm/page_alloc: fix tracepoint mm_page_alloc_zone_locked() Currently, trace point mm_page_alloc_zone_locked() doesn't show correct information. First, when alloc_flag has ALLOC_HARDER/ALLOC_CMA, page can be allocated from MIGRATE_HIGHATOMIC/MIGRATE_CMA. Nevertheless, tracepoint use requested migration type not MIGRATE_HIGHATOMIC and MIGRATE_CMA. Second, after commit 44042b4498728 ("mm/page_alloc: allow high-order pages to be stored on the per-cpu lists") percpu-list can store high order pages. But trace point determine whether it is a refiil of percpu-list by comparing requested order and 0. To handle these problems, make mm_page_alloc_zone_locked() only be called by __rmqueue_smallest with correct migration type. With a new argument called percpu_refill, it can show roughly whether it is a refill of percpu-list. Link: https://lkml.kernel.org/r/20220512025307.57924-1-vvghjk1234@gmail.com Signed-off-by: Wonhyuk Yang Acked-by: Mel Gorman Cc: Baik Song An Cc: Hong Yeon Kim Cc: Taeung Song Cc: Cc: Steven Rostedt Cc: Ingo Molnar Signed-off-by: Andrew Morton --- include/trace/events/kmem.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 71c141804222..f76668305ac5 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -229,20 +229,23 @@ TRACE_EVENT(mm_page_alloc, DECLARE_EVENT_CLASS(mm_page, - TP_PROTO(struct page *page, unsigned int order, int migratetype), + TP_PROTO(struct page *page, unsigned int order, int migratetype, + int percpu_refill), - TP_ARGS(page, order, migratetype), + TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) + __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; + __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", @@ -250,14 +253,15 @@ DECLARE_EVENT_CLASS(mm_page, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, - __entry->order == 0) + __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, - TP_PROTO(struct page *page, unsigned int order, int migratetype), + TP_PROTO(struct page *page, unsigned int order, int migratetype, + int percpu_refill), - TP_ARGS(page, order, migratetype) + TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, -- cgit v1.2.3 From 3f913fc5f9745613088d3c569778c9813ab9c129 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Thu, 19 May 2022 14:08:55 -0700 Subject: mm: fix missing handler for __GFP_NOWARN We expect no warnings to be issued when we specify __GFP_NOWARN, but currently in paths like alloc_pages() and kmalloc(), there are still some warnings printed, fix it. But for some warnings that report usage problems, we don't deal with them. If such warnings are printed, then we should fix the usage problems. Such as the following case: WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); [zhengqi.arch@bytedance.com: v2] Link: https://lkml.kernel.org/r/20220511061951.1114-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20220510113809.80626-1-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Cc: Akinobu Mita Cc: Vlastimil Babka Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- include/linux/fault-inject.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 2d04f6448cde..9f6e25467844 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -20,6 +20,7 @@ struct fault_attr { atomic_t space; unsigned long verbose; bool task_filter; + bool no_warn; unsigned long stacktrace_depth; unsigned long require_start; unsigned long require_end; @@ -39,6 +40,7 @@ struct fault_attr { .ratelimit_state = RATELIMIT_STATE_INIT_DISABLED, \ .verbose = 2, \ .dname = NULL, \ + .no_warn = false, \ } #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER -- cgit v1.2.3 From 37462a920392cb86541650a6f4121155f11f1199 Mon Sep 17 00:00:00 2001 From: Christophe de Dinechin Date: Thu, 14 Apr 2022 17:08:54 +0200 Subject: nodemask.h: fix compilation error with GCC12 With gcc version 12.0.1 20220401 (Red Hat 12.0.1-0), building with defconfig results in the following compilation error: | CC mm/swapfile.o | mm/swapfile.c: In function `setup_swap_info': | mm/swapfile.c:2291:47: error: array subscript -1 is below array bounds | of `struct plist_node[]' [-Werror=array-bounds] | 2291 | p->avail_lists[i].prio = 1; | | ~~~~~~~~~~~~~~^~~ | In file included from mm/swapfile.c:16: | ./include/linux/swap.h:292:27: note: while referencing `avail_lists' | 292 | struct plist_node avail_lists[]; /* | | ^~~~~~~~~~~ This is due to the compiler detecting that the mask in node_states[__state] could theoretically be zero, which would lead to first_node() returning -1 through find_first_bit. I believe that the warning/error is legitimate. I first tried adding a test to check that the node mask is not emtpy, since a similar test exists in the case where MAX_NUMNODES == 1. However, adding the if statement causes other warnings to appear in for_each_cpu_node_but, because it introduces a dangling else ambiguity. And unfortunately, GCC is not smart enough to detect that the added test makes the case where (node) == -1 impossible, so it still complains with the same message. This is why I settled on replacing that with a harmless, but relatively useless (node) >= 0 test. Based on the warning for the dangling else, I also decided to fix the case where MAX_NUMNODES == 1 by moving the condition inside the for loop. It will still only be tested once. This ensures that the meaning of an else following for_each_node_mask or derivatives would not silently have a different meaning depending on the configuration. Link: https://lkml.kernel.org/r/20220414150855.2407137-3-dinechin@redhat.com Signed-off-by: Christophe de Dinechin Signed-off-by: Christophe de Dinechin Reviewed-by: Andrew Morton Cc: Ben Segall Cc: "Michael S. Tsirkin" Cc: Steven Rostedt Cc: Ingo Molnar Cc: Mel Gorman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Paolo Bonzini Cc: Daniel Bristot de Oliveira Cc: Jason Wang Cc: Zhen Lei Cc: Juri Lelli Cc: Peter Zijlstra Cc: Signed-off-by: Andrew Morton --- include/linux/nodemask.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 567c3ddba2c4..c6199dbe2591 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -375,14 +375,13 @@ static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, } #if MAX_NUMNODES > 1 -#define for_each_node_mask(node, mask) \ - for ((node) = first_node(mask); \ - (node) < MAX_NUMNODES; \ - (node) = next_node((node), (mask))) +#define for_each_node_mask(node, mask) \ + for ((node) = first_node(mask); \ + (node >= 0) && (node) < MAX_NUMNODES; \ + (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ -#define for_each_node_mask(node, mask) \ - if (!nodes_empty(mask)) \ - for ((node) = 0; (node) < 1; (node)++) +#define for_each_node_mask(node, mask) \ + for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++) #endif /* MAX_NUMNODES */ /* -- cgit v1.2.3 From 2b132903de7124dd9a758be0c27562e91a510848 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 11 May 2022 12:46:53 +0300 Subject: tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate Fixes following sparse warnings: CHECK mm/vmscan.c mm/vmscan.c: note: in included file (through include/trace/trace_events.h, include/trace/define_trace.h, include/trace/events/vmscan.h): ./include/trace/events/vmscan.h:281:1: sparse: warning: cast to restricted isolate_mode_t ./include/trace/events/vmscan.h:281:1: sparse: warning: restricted isolate_mode_t degrades to integer Link: https://lkml.kernel.org/r/e85d7ff2-fd10-53f8-c24e-ba0458439c1b@openvz.org Signed-off-by: Vasily Averin Acked-by: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- include/trace/events/vmscan.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 408c86244d64..d2123dd960d5 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -297,7 +297,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __field(unsigned long, nr_scanned) __field(unsigned long, nr_skipped) __field(unsigned long, nr_taken) - __field(isolate_mode_t, isolate_mode) + __field(unsigned int, isolate_mode) __field(int, lru) ), @@ -308,7 +308,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __entry->nr_scanned = nr_scanned; __entry->nr_skipped = nr_skipped; __entry->nr_taken = nr_taken; - __entry->isolate_mode = isolate_mode; + __entry->isolate_mode = (__force unsigned int)isolate_mode; __entry->lru = lru; ), -- cgit v1.2.3 From a66a82f2a55ef1f47daeb45e0b4074d88ce5ca99 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 4 May 2022 19:54:56 -0700 Subject: dt-bindings: clock: Add Qualcomm SC8280XP GCC bindings Add binding for the Qualcomm SC8280XP Global Clock controller. The clock-names property is purposefully omitted, to clearly communicate to the writer (and reader) of the DeviceTree source based on this binding that the order of "clocks" is significant, in contrast to previous GCC bindings. Signed-off-by: Bjorn Andersson Reviewed-by: Stephen Boyd Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220505025457.1693716-2-bjorn.andersson@linaro.org --- include/dt-bindings/clock/qcom,gcc-sc8280xp.h | 496 ++++++++++++++++++++++++++ 1 file changed, 496 insertions(+) create mode 100644 include/dt-bindings/clock/qcom,gcc-sc8280xp.h (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-sc8280xp.h b/include/dt-bindings/clock/qcom,gcc-sc8280xp.h new file mode 100644 index 000000000000..cb2fb638825c --- /dev/null +++ b/include/dt-bindings/clock/qcom,gcc-sc8280xp.h @@ -0,0 +1,496 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2022, Linaro Ltd. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GCC_DIREWOLF_H +#define _DT_BINDINGS_CLK_QCOM_GCC_DIREWOLF_H + +/* GCC clocks */ +#define GCC_GPLL0 0 +#define GCC_GPLL0_OUT_EVEN 1 +#define GCC_GPLL2 2 +#define GCC_GPLL4 3 +#define GCC_GPLL7 4 +#define GCC_GPLL8 5 +#define GCC_GPLL9 6 +#define GCC_AGGRE_NOC_PCIE0_TUNNEL_AXI_CLK 7 +#define GCC_AGGRE_NOC_PCIE1_TUNNEL_AXI_CLK 8 +#define GCC_AGGRE_NOC_PCIE_4_AXI_CLK 9 +#define GCC_AGGRE_NOC_PCIE_SOUTH_SF_AXI_CLK 10 +#define GCC_AGGRE_UFS_CARD_AXI_CLK 11 +#define GCC_AGGRE_UFS_PHY_AXI_CLK 12 +#define GCC_AGGRE_USB3_MP_AXI_CLK 13 +#define GCC_AGGRE_USB3_PRIM_AXI_CLK 14 +#define GCC_AGGRE_USB3_SEC_AXI_CLK 15 +#define GCC_AGGRE_USB4_1_AXI_CLK 16 +#define GCC_AGGRE_USB4_AXI_CLK 17 +#define GCC_AGGRE_USB_NOC_AXI_CLK 18 +#define GCC_AGGRE_USB_NOC_NORTH_AXI_CLK 19 +#define GCC_AGGRE_USB_NOC_SOUTH_AXI_CLK 20 +#define GCC_AHB2PHY0_CLK 21 +#define GCC_AHB2PHY2_CLK 22 +#define GCC_BOOT_ROM_AHB_CLK 23 +#define GCC_CAMERA_AHB_CLK 24 +#define GCC_CAMERA_HF_AXI_CLK 25 +#define GCC_CAMERA_SF_AXI_CLK 26 +#define GCC_CAMERA_THROTTLE_NRT_AXI_CLK 27 +#define GCC_CAMERA_THROTTLE_RT_AXI_CLK 28 +#define GCC_CAMERA_THROTTLE_XO_CLK 29 +#define GCC_CAMERA_XO_CLK 30 +#define GCC_CFG_NOC_USB3_MP_AXI_CLK 31 +#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK 32 +#define GCC_CFG_NOC_USB3_SEC_AXI_CLK 33 +#define GCC_CNOC_PCIE0_TUNNEL_CLK 34 +#define GCC_CNOC_PCIE1_TUNNEL_CLK 35 +#define GCC_CNOC_PCIE4_QX_CLK 36 +#define GCC_DDRSS_GPU_AXI_CLK 37 +#define GCC_DDRSS_PCIE_SF_TBU_CLK 38 +#define GCC_DISP1_AHB_CLK 39 +#define GCC_DISP1_HF_AXI_CLK 40 +#define GCC_DISP1_SF_AXI_CLK 41 +#define GCC_DISP1_THROTTLE_NRT_AXI_CLK 42 +#define GCC_DISP1_THROTTLE_RT_AXI_CLK 43 +#define GCC_DISP1_XO_CLK 44 +#define GCC_DISP_AHB_CLK 45 +#define GCC_DISP_HF_AXI_CLK 46 +#define GCC_DISP_SF_AXI_CLK 47 +#define GCC_DISP_THROTTLE_NRT_AXI_CLK 48 +#define GCC_DISP_THROTTLE_RT_AXI_CLK 49 +#define GCC_DISP_XO_CLK 50 +#define GCC_EMAC0_AXI_CLK 51 +#define GCC_EMAC0_PTP_CLK 52 +#define GCC_EMAC0_PTP_CLK_SRC 53 +#define GCC_EMAC0_RGMII_CLK 54 +#define GCC_EMAC0_RGMII_CLK_SRC 55 +#define GCC_EMAC0_SLV_AHB_CLK 56 +#define GCC_EMAC1_AXI_CLK 57 +#define GCC_EMAC1_PTP_CLK 58 +#define GCC_EMAC1_PTP_CLK_SRC 59 +#define GCC_EMAC1_RGMII_CLK 60 +#define GCC_EMAC1_RGMII_CLK_SRC 61 +#define GCC_EMAC1_SLV_AHB_CLK 62 +#define GCC_GP1_CLK 63 +#define GCC_GP1_CLK_SRC 64 +#define GCC_GP2_CLK 65 +#define GCC_GP2_CLK_SRC 66 +#define GCC_GP3_CLK 67 +#define GCC_GP3_CLK_SRC 68 +#define GCC_GP4_CLK 69 +#define GCC_GP4_CLK_SRC 70 +#define GCC_GP5_CLK 71 +#define GCC_GP5_CLK_SRC 72 +#define GCC_GPU_CFG_AHB_CLK 73 +#define GCC_GPU_GPLL0_CLK_SRC 74 +#define GCC_GPU_GPLL0_DIV_CLK_SRC 75 +#define GCC_GPU_IREF_EN 76 +#define GCC_GPU_MEMNOC_GFX_CLK 77 +#define GCC_GPU_SNOC_DVM_GFX_CLK 78 +#define GCC_GPU_TCU_THROTTLE_AHB_CLK 79 +#define GCC_GPU_TCU_THROTTLE_CLK 80 +#define GCC_PCIE0_PHY_RCHNG_CLK 81 +#define GCC_PCIE1_PHY_RCHNG_CLK 82 +#define GCC_PCIE2A_PHY_RCHNG_CLK 83 +#define GCC_PCIE2B_PHY_RCHNG_CLK 84 +#define GCC_PCIE3A_PHY_RCHNG_CLK 85 +#define GCC_PCIE3B_PHY_RCHNG_CLK 86 +#define GCC_PCIE4_PHY_RCHNG_CLK 87 +#define GCC_PCIE_0_AUX_CLK 88 +#define GCC_PCIE_0_AUX_CLK_SRC 89 +#define GCC_PCIE_0_CFG_AHB_CLK 90 +#define GCC_PCIE_0_MSTR_AXI_CLK 91 +#define GCC_PCIE_0_PHY_RCHNG_CLK_SRC 92 +#define GCC_PCIE_0_PIPE_CLK 93 +#define GCC_PCIE_0_SLV_AXI_CLK 94 +#define GCC_PCIE_0_SLV_Q2A_AXI_CLK 95 +#define GCC_PCIE_1_AUX_CLK 96 +#define GCC_PCIE_1_AUX_CLK_SRC 97 +#define GCC_PCIE_1_CFG_AHB_CLK 98 +#define GCC_PCIE_1_MSTR_AXI_CLK 99 +#define GCC_PCIE_1_PHY_RCHNG_CLK_SRC 100 +#define GCC_PCIE_1_PIPE_CLK 101 +#define GCC_PCIE_1_SLV_AXI_CLK 102 +#define GCC_PCIE_1_SLV_Q2A_AXI_CLK 103 +#define GCC_PCIE_2A2B_CLKREF_CLK 104 +#define GCC_PCIE_2A_AUX_CLK 105 +#define GCC_PCIE_2A_AUX_CLK_SRC 106 +#define GCC_PCIE_2A_CFG_AHB_CLK 107 +#define GCC_PCIE_2A_MSTR_AXI_CLK 108 +#define GCC_PCIE_2A_PHY_RCHNG_CLK_SRC 109 +#define GCC_PCIE_2A_PIPE_CLK 110 +#define GCC_PCIE_2A_PIPE_CLK_SRC 111 +#define GCC_PCIE_2A_PIPE_DIV_CLK_SRC 112 +#define GCC_PCIE_2A_PIPEDIV2_CLK 113 +#define GCC_PCIE_2A_SLV_AXI_CLK 114 +#define GCC_PCIE_2A_SLV_Q2A_AXI_CLK 115 +#define GCC_PCIE_2B_AUX_CLK 116 +#define GCC_PCIE_2B_AUX_CLK_SRC 117 +#define GCC_PCIE_2B_CFG_AHB_CLK 118 +#define GCC_PCIE_2B_MSTR_AXI_CLK 119 +#define GCC_PCIE_2B_PHY_RCHNG_CLK_SRC 120 +#define GCC_PCIE_2B_PIPE_CLK 121 +#define GCC_PCIE_2B_PIPE_CLK_SRC 122 +#define GCC_PCIE_2B_PIPE_DIV_CLK_SRC 123 +#define GCC_PCIE_2B_PIPEDIV2_CLK 124 +#define GCC_PCIE_2B_SLV_AXI_CLK 125 +#define GCC_PCIE_2B_SLV_Q2A_AXI_CLK 126 +#define GCC_PCIE_3A3B_CLKREF_CLK 127 +#define GCC_PCIE_3A_AUX_CLK 128 +#define GCC_PCIE_3A_AUX_CLK_SRC 129 +#define GCC_PCIE_3A_CFG_AHB_CLK 130 +#define GCC_PCIE_3A_MSTR_AXI_CLK 131 +#define GCC_PCIE_3A_PHY_RCHNG_CLK_SRC 132 +#define GCC_PCIE_3A_PIPE_CLK 133 +#define GCC_PCIE_3A_PIPE_CLK_SRC 134 +#define GCC_PCIE_3A_PIPE_DIV_CLK_SRC 135 +#define GCC_PCIE_3A_PIPEDIV2_CLK 136 +#define GCC_PCIE_3A_SLV_AXI_CLK 137 +#define GCC_PCIE_3A_SLV_Q2A_AXI_CLK 138 +#define GCC_PCIE_3B_AUX_CLK 139 +#define GCC_PCIE_3B_AUX_CLK_SRC 140 +#define GCC_PCIE_3B_CFG_AHB_CLK 141 +#define GCC_PCIE_3B_MSTR_AXI_CLK 142 +#define GCC_PCIE_3B_PHY_RCHNG_CLK_SRC 143 +#define GCC_PCIE_3B_PIPE_CLK 144 +#define GCC_PCIE_3B_PIPE_CLK_SRC 145 +#define GCC_PCIE_3B_PIPE_DIV_CLK_SRC 146 +#define GCC_PCIE_3B_PIPEDIV2_CLK 147 +#define GCC_PCIE_3B_SLV_AXI_CLK 148 +#define GCC_PCIE_3B_SLV_Q2A_AXI_CLK 149 +#define GCC_PCIE_4_AUX_CLK 150 +#define GCC_PCIE_4_AUX_CLK_SRC 151 +#define GCC_PCIE_4_CFG_AHB_CLK 152 +#define GCC_PCIE_4_CLKREF_CLK 153 +#define GCC_PCIE_4_MSTR_AXI_CLK 154 +#define GCC_PCIE_4_PHY_RCHNG_CLK_SRC 155 +#define GCC_PCIE_4_PIPE_CLK 156 +#define GCC_PCIE_4_PIPE_CLK_SRC 157 +#define GCC_PCIE_4_PIPE_DIV_CLK_SRC 158 +#define GCC_PCIE_4_PIPEDIV2_CLK 159 +#define GCC_PCIE_4_SLV_AXI_CLK 160 +#define GCC_PCIE_4_SLV_Q2A_AXI_CLK 161 +#define GCC_PCIE_RSCC_AHB_CLK 162 +#define GCC_PCIE_RSCC_XO_CLK 163 +#define GCC_PCIE_RSCC_XO_CLK_SRC 164 +#define GCC_PCIE_THROTTLE_CFG_CLK 165 +#define GCC_PDM2_CLK 166 +#define GCC_PDM2_CLK_SRC 167 +#define GCC_PDM_AHB_CLK 168 +#define GCC_PDM_XO4_CLK 169 +#define GCC_QMIP_CAMERA_NRT_AHB_CLK 170 +#define GCC_QMIP_CAMERA_RT_AHB_CLK 171 +#define GCC_QMIP_DISP1_AHB_CLK 172 +#define GCC_QMIP_DISP1_ROT_AHB_CLK 173 +#define GCC_QMIP_DISP_AHB_CLK 174 +#define GCC_QMIP_DISP_ROT_AHB_CLK 175 +#define GCC_QMIP_VIDEO_CVP_AHB_CLK 176 +#define GCC_QMIP_VIDEO_VCODEC_AHB_CLK 177 +#define GCC_QUPV3_WRAP0_CORE_2X_CLK 178 +#define GCC_QUPV3_WRAP0_CORE_CLK 179 +#define GCC_QUPV3_WRAP0_QSPI0_CLK 180 +#define GCC_QUPV3_WRAP0_S0_CLK 181 +#define GCC_QUPV3_WRAP0_S0_CLK_SRC 182 +#define GCC_QUPV3_WRAP0_S1_CLK 183 +#define GCC_QUPV3_WRAP0_S1_CLK_SRC 184 +#define GCC_QUPV3_WRAP0_S2_CLK 185 +#define GCC_QUPV3_WRAP0_S2_CLK_SRC 186 +#define GCC_QUPV3_WRAP0_S3_CLK 187 +#define GCC_QUPV3_WRAP0_S3_CLK_SRC 188 +#define GCC_QUPV3_WRAP0_S4_CLK 189 +#define GCC_QUPV3_WRAP0_S4_CLK_SRC 190 +#define GCC_QUPV3_WRAP0_S4_DIV_CLK_SRC 191 +#define GCC_QUPV3_WRAP0_S5_CLK 192 +#define GCC_QUPV3_WRAP0_S5_CLK_SRC 193 +#define GCC_QUPV3_WRAP0_S6_CLK 194 +#define GCC_QUPV3_WRAP0_S6_CLK_SRC 195 +#define GCC_QUPV3_WRAP0_S7_CLK 196 +#define GCC_QUPV3_WRAP0_S7_CLK_SRC 197 +#define GCC_QUPV3_WRAP1_CORE_2X_CLK 198 +#define GCC_QUPV3_WRAP1_CORE_CLK 199 +#define GCC_QUPV3_WRAP1_QSPI0_CLK 200 +#define GCC_QUPV3_WRAP1_S0_CLK 201 +#define GCC_QUPV3_WRAP1_S0_CLK_SRC 202 +#define GCC_QUPV3_WRAP1_S1_CLK 203 +#define GCC_QUPV3_WRAP1_S1_CLK_SRC 204 +#define GCC_QUPV3_WRAP1_S2_CLK 205 +#define GCC_QUPV3_WRAP1_S2_CLK_SRC 206 +#define GCC_QUPV3_WRAP1_S3_CLK 207 +#define GCC_QUPV3_WRAP1_S3_CLK_SRC 208 +#define GCC_QUPV3_WRAP1_S4_CLK 209 +#define GCC_QUPV3_WRAP1_S4_CLK_SRC 210 +#define GCC_QUPV3_WRAP1_S4_DIV_CLK_SRC 211 +#define GCC_QUPV3_WRAP1_S5_CLK 212 +#define GCC_QUPV3_WRAP1_S5_CLK_SRC 213 +#define GCC_QUPV3_WRAP1_S6_CLK 214 +#define GCC_QUPV3_WRAP1_S6_CLK_SRC 215 +#define GCC_QUPV3_WRAP1_S7_CLK 216 +#define GCC_QUPV3_WRAP1_S7_CLK_SRC 217 +#define GCC_QUPV3_WRAP2_CORE_2X_CLK 218 +#define GCC_QUPV3_WRAP2_CORE_CLK 219 +#define GCC_QUPV3_WRAP2_QSPI0_CLK 220 +#define GCC_QUPV3_WRAP2_S0_CLK 221 +#define GCC_QUPV3_WRAP2_S0_CLK_SRC 222 +#define GCC_QUPV3_WRAP2_S1_CLK 223 +#define GCC_QUPV3_WRAP2_S1_CLK_SRC 224 +#define GCC_QUPV3_WRAP2_S2_CLK 225 +#define GCC_QUPV3_WRAP2_S2_CLK_SRC 226 +#define GCC_QUPV3_WRAP2_S3_CLK 227 +#define GCC_QUPV3_WRAP2_S3_CLK_SRC 228 +#define GCC_QUPV3_WRAP2_S4_CLK 229 +#define GCC_QUPV3_WRAP2_S4_CLK_SRC 230 +#define GCC_QUPV3_WRAP2_S4_DIV_CLK_SRC 231 +#define GCC_QUPV3_WRAP2_S5_CLK 232 +#define GCC_QUPV3_WRAP2_S5_CLK_SRC 233 +#define GCC_QUPV3_WRAP2_S6_CLK 234 +#define GCC_QUPV3_WRAP2_S6_CLK_SRC 235 +#define GCC_QUPV3_WRAP2_S7_CLK 236 +#define GCC_QUPV3_WRAP2_S7_CLK_SRC 237 +#define GCC_QUPV3_WRAP_0_M_AHB_CLK 238 +#define GCC_QUPV3_WRAP_0_S_AHB_CLK 239 +#define GCC_QUPV3_WRAP_1_M_AHB_CLK 240 +#define GCC_QUPV3_WRAP_1_S_AHB_CLK 241 +#define GCC_QUPV3_WRAP_2_M_AHB_CLK 242 +#define GCC_QUPV3_WRAP_2_S_AHB_CLK 243 +#define GCC_SDCC2_AHB_CLK 244 +#define GCC_SDCC2_APPS_CLK 245 +#define GCC_SDCC2_APPS_CLK_SRC 246 +#define GCC_SDCC4_AHB_CLK 247 +#define GCC_SDCC4_APPS_CLK 248 +#define GCC_SDCC4_APPS_CLK_SRC 249 +#define GCC_SYS_NOC_USB_AXI_CLK 250 +#define GCC_UFS_1_CARD_CLKREF_CLK 251 +#define GCC_UFS_CARD_AHB_CLK 252 +#define GCC_UFS_CARD_AXI_CLK 253 +#define GCC_UFS_CARD_AXI_CLK_SRC 254 +#define GCC_UFS_CARD_CLKREF_CLK 255 +#define GCC_UFS_CARD_ICE_CORE_CLK 256 +#define GCC_UFS_CARD_ICE_CORE_CLK_SRC 257 +#define GCC_UFS_CARD_PHY_AUX_CLK 258 +#define GCC_UFS_CARD_PHY_AUX_CLK_SRC 259 +#define GCC_UFS_CARD_RX_SYMBOL_0_CLK 260 +#define GCC_UFS_CARD_RX_SYMBOL_0_CLK_SRC 261 +#define GCC_UFS_CARD_RX_SYMBOL_1_CLK 262 +#define GCC_UFS_CARD_RX_SYMBOL_1_CLK_SRC 263 +#define GCC_UFS_CARD_TX_SYMBOL_0_CLK 264 +#define GCC_UFS_CARD_TX_SYMBOL_0_CLK_SRC 265 +#define GCC_UFS_CARD_UNIPRO_CORE_CLK 266 +#define GCC_UFS_CARD_UNIPRO_CORE_CLK_SRC 267 +#define GCC_UFS_PHY_AHB_CLK 268 +#define GCC_UFS_PHY_AXI_CLK 269 +#define GCC_UFS_PHY_AXI_CLK_SRC 270 +#define GCC_UFS_PHY_ICE_CORE_CLK 271 +#define GCC_UFS_PHY_ICE_CORE_CLK_SRC 272 +#define GCC_UFS_PHY_PHY_AUX_CLK 273 +#define GCC_UFS_PHY_PHY_AUX_CLK_SRC 274 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK 275 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK_SRC 276 +#define GCC_UFS_PHY_RX_SYMBOL_1_CLK 277 +#define GCC_UFS_PHY_RX_SYMBOL_1_CLK_SRC 278 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK 279 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK_SRC 280 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK 281 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC 282 +#define GCC_UFS_REF_CLKREF_CLK 283 +#define GCC_USB2_HS0_CLKREF_CLK 284 +#define GCC_USB2_HS1_CLKREF_CLK 285 +#define GCC_USB2_HS2_CLKREF_CLK 286 +#define GCC_USB2_HS3_CLKREF_CLK 287 +#define GCC_USB30_MP_MASTER_CLK 288 +#define GCC_USB30_MP_MASTER_CLK_SRC 289 +#define GCC_USB30_MP_MOCK_UTMI_CLK 290 +#define GCC_USB30_MP_MOCK_UTMI_CLK_SRC 291 +#define GCC_USB30_MP_MOCK_UTMI_POSTDIV_CLK_SRC 292 +#define GCC_USB30_MP_SLEEP_CLK 293 +#define GCC_USB30_PRIM_MASTER_CLK 294 +#define GCC_USB30_PRIM_MASTER_CLK_SRC 295 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK 296 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC 297 +#define GCC_USB30_PRIM_MOCK_UTMI_POSTDIV_CLK_SRC 298 +#define GCC_USB30_PRIM_SLEEP_CLK 299 +#define GCC_USB30_SEC_MASTER_CLK 300 +#define GCC_USB30_SEC_MASTER_CLK_SRC 301 +#define GCC_USB30_SEC_MOCK_UTMI_CLK 302 +#define GCC_USB30_SEC_MOCK_UTMI_CLK_SRC 303 +#define GCC_USB30_SEC_MOCK_UTMI_POSTDIV_CLK_SRC 304 +#define GCC_USB30_SEC_SLEEP_CLK 305 +#define GCC_USB34_PRIM_PHY_PIPE_CLK_SRC 306 +#define GCC_USB34_SEC_PHY_PIPE_CLK_SRC 307 +#define GCC_USB3_MP0_CLKREF_CLK 308 +#define GCC_USB3_MP1_CLKREF_CLK 309 +#define GCC_USB3_MP_PHY_AUX_CLK 310 +#define GCC_USB3_MP_PHY_AUX_CLK_SRC 311 +#define GCC_USB3_MP_PHY_COM_AUX_CLK 312 +#define GCC_USB3_MP_PHY_PIPE_0_CLK 313 +#define GCC_USB3_MP_PHY_PIPE_0_CLK_SRC 314 +#define GCC_USB3_MP_PHY_PIPE_1_CLK 315 +#define GCC_USB3_MP_PHY_PIPE_1_CLK_SRC 316 +#define GCC_USB3_PRIM_PHY_AUX_CLK 317 +#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC 318 +#define GCC_USB3_PRIM_PHY_COM_AUX_CLK 319 +#define GCC_USB3_PRIM_PHY_PIPE_CLK 320 +#define GCC_USB3_PRIM_PHY_PIPE_CLK_SRC 321 +#define GCC_USB3_SEC_PHY_AUX_CLK 322 +#define GCC_USB3_SEC_PHY_AUX_CLK_SRC 323 +#define GCC_USB3_SEC_PHY_COM_AUX_CLK 324 +#define GCC_USB3_SEC_PHY_PIPE_CLK 325 +#define GCC_USB3_SEC_PHY_PIPE_CLK_SRC 326 +#define GCC_USB4_1_CFG_AHB_CLK 327 +#define GCC_USB4_1_DP_CLK 328 +#define GCC_USB4_1_MASTER_CLK 329 +#define GCC_USB4_1_MASTER_CLK_SRC 330 +#define GCC_USB4_1_PHY_DP_CLK_SRC 331 +#define GCC_USB4_1_PHY_P2RR2P_PIPE_CLK 332 +#define GCC_USB4_1_PHY_P2RR2P_PIPE_CLK_SRC 333 +#define GCC_USB4_1_PHY_PCIE_PIPE_CLK 334 +#define GCC_USB4_1_PHY_PCIE_PIPE_CLK_SRC 335 +#define GCC_USB4_1_PHY_PCIE_PIPE_MUX_CLK_SRC 336 +#define GCC_USB4_1_PHY_PCIE_PIPEGMUX_CLK_SRC 337 +#define GCC_USB4_1_PHY_RX0_CLK 338 +#define GCC_USB4_1_PHY_RX0_CLK_SRC 339 +#define GCC_USB4_1_PHY_RX1_CLK 340 +#define GCC_USB4_1_PHY_RX1_CLK_SRC 341 +#define GCC_USB4_1_PHY_SYS_CLK_SRC 342 +#define GCC_USB4_1_PHY_USB_PIPE_CLK 343 +#define GCC_USB4_1_SB_IF_CLK 344 +#define GCC_USB4_1_SB_IF_CLK_SRC 345 +#define GCC_USB4_1_SYS_CLK 346 +#define GCC_USB4_1_TMU_CLK 347 +#define GCC_USB4_1_TMU_CLK_SRC 348 +#define GCC_USB4_CFG_AHB_CLK 349 +#define GCC_USB4_CLKREF_CLK 350 +#define GCC_USB4_DP_CLK 351 +#define GCC_USB4_EUD_CLKREF_CLK 352 +#define GCC_USB4_MASTER_CLK 353 +#define GCC_USB4_MASTER_CLK_SRC 354 +#define GCC_USB4_PHY_DP_CLK_SRC 355 +#define GCC_USB4_PHY_P2RR2P_PIPE_CLK 356 +#define GCC_USB4_PHY_P2RR2P_PIPE_CLK_SRC 357 +#define GCC_USB4_PHY_PCIE_PIPE_CLK 358 +#define GCC_USB4_PHY_PCIE_PIPE_CLK_SRC 359 +#define GCC_USB4_PHY_PCIE_PIPE_MUX_CLK_SRC 360 +#define GCC_USB4_PHY_PCIE_PIPEGMUX_CLK_SRC 361 +#define GCC_USB4_PHY_RX0_CLK 362 +#define GCC_USB4_PHY_RX0_CLK_SRC 363 +#define GCC_USB4_PHY_RX1_CLK 364 +#define GCC_USB4_PHY_RX1_CLK_SRC 365 +#define GCC_USB4_PHY_SYS_CLK_SRC 366 +#define GCC_USB4_PHY_USB_PIPE_CLK 367 +#define GCC_USB4_SB_IF_CLK 368 +#define GCC_USB4_SB_IF_CLK_SRC 369 +#define GCC_USB4_SYS_CLK 370 +#define GCC_USB4_TMU_CLK 371 +#define GCC_USB4_TMU_CLK_SRC 372 +#define GCC_VIDEO_AHB_CLK 373 +#define GCC_VIDEO_AXI0_CLK 374 +#define GCC_VIDEO_AXI1_CLK 375 +#define GCC_VIDEO_CVP_THROTTLE_CLK 376 +#define GCC_VIDEO_VCODEC_THROTTLE_CLK 377 +#define GCC_VIDEO_XO_CLK 378 +#define GCC_AGGRE_UFS_CARD_AXI_HW_CTL_CLK 379 +#define GCC_AGGRE_UFS_PHY_AXI_HW_CTL_CLK 380 +#define GCC_UFS_CARD_AXI_HW_CTL_CLK 381 +#define GCC_UFS_CARD_ICE_CORE_HW_CTL_CLK 382 +#define GCC_UFS_CARD_PHY_AUX_HW_CTL_CLK 383 +#define GCC_UFS_CARD_UNIPRO_CORE_HW_CTL_CLK 384 +#define GCC_UFS_PHY_AXI_HW_CTL_CLK 385 +#define GCC_UFS_PHY_ICE_CORE_HW_CTL_CLK 386 +#define GCC_UFS_PHY_PHY_AUX_HW_CTL_CLK 387 +#define GCC_UFS_PHY_UNIPRO_CORE_HW_CTL_CLK 388 + +/* GCC resets */ +#define GCC_EMAC0_BCR 0 +#define GCC_EMAC1_BCR 1 +#define GCC_PCIE_0_LINK_DOWN_BCR 2 +#define GCC_PCIE_0_NOCSR_COM_PHY_BCR 3 +#define GCC_PCIE_0_PHY_BCR 4 +#define GCC_PCIE_0_PHY_NOCSR_COM_PHY_BCR 5 +#define GCC_PCIE_0_TUNNEL_BCR 6 +#define GCC_PCIE_1_LINK_DOWN_BCR 7 +#define GCC_PCIE_1_NOCSR_COM_PHY_BCR 8 +#define GCC_PCIE_1_PHY_BCR 9 +#define GCC_PCIE_1_PHY_NOCSR_COM_PHY_BCR 10 +#define GCC_PCIE_1_TUNNEL_BCR 11 +#define GCC_PCIE_2A_BCR 12 +#define GCC_PCIE_2A_LINK_DOWN_BCR 13 +#define GCC_PCIE_2A_NOCSR_COM_PHY_BCR 14 +#define GCC_PCIE_2A_PHY_BCR 15 +#define GCC_PCIE_2A_PHY_NOCSR_COM_PHY_BCR 16 +#define GCC_PCIE_2B_BCR 17 +#define GCC_PCIE_2B_LINK_DOWN_BCR 18 +#define GCC_PCIE_2B_NOCSR_COM_PHY_BCR 19 +#define GCC_PCIE_2B_PHY_BCR 20 +#define GCC_PCIE_2B_PHY_NOCSR_COM_PHY_BCR 21 +#define GCC_PCIE_3A_BCR 22 +#define GCC_PCIE_3A_LINK_DOWN_BCR 23 +#define GCC_PCIE_3A_NOCSR_COM_PHY_BCR 24 +#define GCC_PCIE_3A_PHY_BCR 25 +#define GCC_PCIE_3A_PHY_NOCSR_COM_PHY_BCR 26 +#define GCC_PCIE_3B_BCR 27 +#define GCC_PCIE_3B_LINK_DOWN_BCR 28 +#define GCC_PCIE_3B_NOCSR_COM_PHY_BCR 29 +#define GCC_PCIE_3B_PHY_BCR 30 +#define GCC_PCIE_3B_PHY_NOCSR_COM_PHY_BCR 31 +#define GCC_PCIE_4_BCR 32 +#define GCC_PCIE_4_LINK_DOWN_BCR 33 +#define GCC_PCIE_4_NOCSR_COM_PHY_BCR 34 +#define GCC_PCIE_4_PHY_BCR 35 +#define GCC_PCIE_4_PHY_NOCSR_COM_PHY_BCR 36 +#define GCC_PCIE_PHY_CFG_AHB_BCR 37 +#define GCC_PCIE_PHY_COM_BCR 38 +#define GCC_PCIE_RSCC_BCR 39 +#define GCC_QUSB2PHY_HS0_MP_BCR 40 +#define GCC_QUSB2PHY_HS1_MP_BCR 41 +#define GCC_QUSB2PHY_HS2_MP_BCR 42 +#define GCC_QUSB2PHY_HS3_MP_BCR 43 +#define GCC_QUSB2PHY_PRIM_BCR 44 +#define GCC_QUSB2PHY_SEC_BCR 45 +#define GCC_SDCC2_BCR 46 +#define GCC_SDCC4_BCR 47 +#define GCC_UFS_CARD_BCR 48 +#define GCC_UFS_PHY_BCR 49 +#define GCC_USB2_PHY_PRIM_BCR 50 +#define GCC_USB2_PHY_SEC_BCR 51 +#define GCC_USB30_MP_BCR 52 +#define GCC_USB30_PRIM_BCR 53 +#define GCC_USB30_SEC_BCR 54 +#define GCC_USB3_DP_PHY_PRIM_BCR 55 +#define GCC_USB3_DP_PHY_SEC_BCR 56 +#define GCC_USB3_PHY_PRIM_BCR 57 +#define GCC_USB3_PHY_SEC_BCR 58 +#define GCC_USB3_UNIPHY_MP0_BCR 59 +#define GCC_USB3_UNIPHY_MP1_BCR 60 +#define GCC_USB3PHY_PHY_PRIM_BCR 61 +#define GCC_USB3PHY_PHY_SEC_BCR 62 +#define GCC_USB3UNIPHY_PHY_MP0_BCR 63 +#define GCC_USB3UNIPHY_PHY_MP1_BCR 64 +#define GCC_USB4_1_BCR 65 +#define GCC_USB4_1_DP_PHY_PRIM_BCR 66 +#define GCC_USB4_1_DPPHY_AUX_BCR 67 +#define GCC_USB4_1_PHY_PRIM_BCR 68 +#define GCC_USB4_BCR 69 +#define GCC_USB4_DP_PHY_PRIM_BCR 70 +#define GCC_USB4_DPPHY_AUX_BCR 71 +#define GCC_USB4_PHY_PRIM_BCR 72 +#define GCC_USB4PHY_1_PHY_PRIM_BCR 73 +#define GCC_USB4PHY_PHY_PRIM_BCR 74 +#define GCC_USB_PHY_CFG_AHB2PHY_BCR 75 +#define GCC_VIDEO_BCR 76 +#define GCC_VIDEO_AXI0_CLK_ARES 77 +#define GCC_VIDEO_AXI1_CLK_ARES 78 + +/* GCC GDSCs */ +#define PCIE_0_TUNNEL_GDSC 0 +#define PCIE_1_TUNNEL_GDSC 1 +#define PCIE_2A_GDSC 2 +#define PCIE_2B_GDSC 3 +#define PCIE_3A_GDSC 4 +#define PCIE_3B_GDSC 5 +#define PCIE_4_GDSC 6 +#define UFS_CARD_GDSC 7 +#define UFS_PHY_GDSC 8 +#define USB30_MP_GDSC 9 +#define USB30_PRIM_GDSC 10 +#define USB30_SEC_GDSC 11 + +#endif -- cgit v1.2.3 From 546a3fee174969ff323d70ff27b1ef181f0d7ceb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 17 May 2022 13:46:54 +0200 Subject: sched: Reverse sched_class layout Because GCC-12 is fully stupid about array bounds and it's just really hard to get a solid array definition from a linker script, flip the array order to avoid needing negative offsets :-/ This makes the whole relational pointer magic a little less obvious, but alas. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/YoOLLmLG7HRTXeEm@hirez.programming.kicks-ass.net --- include/asm-generic/vmlinux.lds.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 69138e9db787..7515a465ec03 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -126,13 +126,13 @@ */ #define SCHED_DATA \ STRUCT_ALIGN(); \ - __begin_sched_classes = .; \ - *(__idle_sched_class) \ - *(__fair_sched_class) \ - *(__rt_sched_class) \ - *(__dl_sched_class) \ + __sched_class_highest = .; \ *(__stop_sched_class) \ - __end_sched_classes = .; + *(__dl_sched_class) \ + *(__rt_sched_class) \ + *(__fair_sched_class) \ + *(__idle_sched_class) \ + __sched_class_lowest = .; /* The actual configuration determine if the init/exit sections * are handled as text/data or they can be discarded (which -- cgit v1.2.3 From 991d8d8142cad94f9c5c05db25e67fa83d6f772a Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Fri, 13 May 2022 11:34:33 +0200 Subject: topology: Remove unused cpu_cluster_mask() default_topology[] uses cpu_clustergroup_mask() for the CLS level (guarded by CONFIG_SCHED_CLUSTER) which is currently provided by x86 (arch/x86/kernel/smpboot.c) and arm64 (drivers/base/arch_topology.c). Fixes: 778c558f49a2c ("sched: Add cluster scheduler level in core and related Kconfig for ARM64") Signed-off-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra (Intel) Acked-by: Barry Song Link: https://lore.kernel.org/r/20220513093433.425163-1-dietmar.eggemann@arm.com --- include/linux/topology.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/topology.h b/include/linux/topology.h index f19bc3626297..4564faafd0e1 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -240,13 +240,6 @@ static inline const struct cpumask *cpu_smt_mask(int cpu) } #endif -#if defined(CONFIG_SCHED_CLUSTER) && !defined(cpu_cluster_mask) -static inline const struct cpumask *cpu_cluster_mask(int cpu) -{ - return topology_cluster_cpumask(cpu); -} -#endif - static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); -- cgit v1.2.3 From 5cebb40bc9554aafcc492431181f43c6231b0459 Mon Sep 17 00:00:00 2001 From: Harini Katakam Date: Wed, 18 May 2022 22:37:56 +0530 Subject: net: macb: Fix PTP one step sync support PTP one step sync packets cannot have CSUM padding and insertion in SW since time stamp is inserted on the fly by HW. In addition, ptp4l version 3.0 and above report an error when skb timestamps are reported for packets that not processed for TX TS after transmission. Add a helper to identify PTP one step sync and fix the above two errors. Add a common mask for PTP header flag field "twoStepflag". Also reset ptp OSS bit when one step is not selected. Fixes: ab91f0a9b5f4 ("net: macb: Add hardware PTP support") Fixes: 653e92a9175e ("net: macb: add support for padding and fcs computation") Signed-off-by: Harini Katakam Reviewed-by: Radhey Shyam Pandey Reviewed-by: Claudiu Beznea Link: https://lore.kernel.org/r/20220518170756.7752-1-harini.katakam@xilinx.com Signed-off-by: Jakub Kicinski --- include/linux/ptp_classify.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index fefa7790dc46..2b6ea36ad162 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -43,6 +43,9 @@ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ #define OFF_PTP_SEQUENCE_ID 30 +/* PTP header flag fields */ +#define PTP_FLAG_TWOSTEP BIT(1) + /* Below defines should actually be removed at some point in time. */ #define IP6_HLEN 40 #define UDP_HLEN 8 -- cgit v1.2.3 From 057e5fc03369f8f2ed9b2ca884754b1d80b83620 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 12 May 2022 19:15:32 +0800 Subject: scsi: libsas: Refactor sas_ata_hard_reset() Create function sas_ata_wait_after_reset() from sas_ata_hard_reset() as some LLDDs may want to check for a remote ATA phy is up after reset. Link: https://lore.kernel.org/r/1652354134-171343-2-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Reviewed-by: Xiang Chen Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/sas_ata.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/scsi/sas_ata.h b/include/scsi/sas_ata.h index d47dea70855d..a1df4f9d57a3 100644 --- a/include/scsi/sas_ata.h +++ b/include/scsi/sas_ata.h @@ -34,6 +34,7 @@ void sas_resume_sata(struct asd_sas_port *port); void sas_ata_end_eh(struct ata_port *ap); int sas_execute_ata_cmd(struct domain_device *device, u8 *fis, int force_phy_id); +int sas_ata_wait_after_reset(struct domain_device *dev, unsigned long deadline); #else @@ -91,6 +92,12 @@ static inline int sas_execute_ata_cmd(struct domain_device *device, u8 *fis, { return 0; } + +static inline int sas_ata_wait_after_reset(struct domain_device *dev, + unsigned long deadline) +{ + return -ETIMEDOUT; +} #endif #endif /* _SAS_ATA_H_ */ -- cgit v1.2.3 From 827fc630e4c8087df5a8e8ee013b686bd6f13736 Mon Sep 17 00:00:00 2001 From: Muneendra Kumar Date: Thu, 19 May 2022 05:31:07 -0700 Subject: scsi: nvme-fc: Add new routine nvme_fc_io_getuuid() Add nvme_fc_io_getuuid() to the nvme-fc transport. The routine is invoked by the FC LLDD on a per-I/O request basis. The routine translates from the FC-specific request structure to the bio and the cgroup structure in order to obtain the FC appid stored in the cgroup structure. If a value is not set or a bio is not found, a NULL appid (aka uuid) will be returned to the LLDD. Link: https://lore.kernel.org/r/20220519123110.17361-2-jsmart2021@gmail.com Reviewed-by: Hannes Reinecke Reviewed-by: Himanshu Madhani Acked-by: Christoph Hellwig Signed-off-by: Muneendra Kumar Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- include/linux/nvme-fc-driver.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 5358a5facdee..fa092b9be2fd 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -564,6 +564,15 @@ int nvme_fc_rcv_ls_req(struct nvme_fc_remote_port *remoteport, void *lsreqbuf, u32 lsreqbuf_len); +/* + * Routine called to get the appid field associated with request by the lldd + * + * If the return value is NULL : the user/libvirt has not set the appid to VM + * If the return value is non-zero: Returns the appid associated with VM + * + * @req: IO request from nvme fc to driver + */ +char *nvme_fc_io_getuuid(struct nvmefc_fcp_req *req); /* * *************** LLDD FC-NVME Target/Subsystem API *************** @@ -1048,5 +1057,10 @@ int nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *tgtport, void nvmet_fc_rcv_fcp_abort(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq); +/* + * add a define, visible to the compiler, that indicates support + * for feature. Allows for conditional compilation in LLDDs. + */ +#define NVME_FC_FEAT_UUID 0x0001 #endif /* _NVME_FC_DRIVER_H */ -- cgit v1.2.3 From dd11376b9f1b73aca3f8c6eb541486bbb6996f05 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 11 May 2022 14:25:52 -0700 Subject: scsi: ufs: Split the drivers/scsi/ufs directory Split the drivers/scsi/ufs directory into 'core' and 'host' directories under the drivers/ufs/ directory. Move shared header files into the include/ufs/ directory. This separation makes it clear which header files UFS drivers are allowed to include (include/ufs/*.h) and which header files UFS drivers are not allowed to include (drivers/ufs/core/*.h). Update the MAINTAINERS file. Add myself as a UFS reviewer. Link: https://lore.kernel.org/r/20220511212552.655341-1-bvanassche@acm.org Cc: Adrian Hunter Cc: Avri Altman Cc: Bean Huo Cc: Bjorn Andersson Cc: Keoseong Park Tested-by: Bean Huo Tested-by: Adrian Hunter Reviewed-by: Bean Huo Acked-by: Avri Altman Acked-by: Adrian Hunter Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/ufs/ufs.h | 623 +++++++++++++++++++++++ include/ufs/ufs_quirks.h | 116 +++++ include/ufs/ufshcd.h | 1230 ++++++++++++++++++++++++++++++++++++++++++++++ include/ufs/ufshci.h | 510 +++++++++++++++++++ include/ufs/unipro.h | 316 ++++++++++++ 5 files changed, 2795 insertions(+) create mode 100644 include/ufs/ufs.h create mode 100644 include/ufs/ufs_quirks.h create mode 100644 include/ufs/ufshcd.h create mode 100644 include/ufs/ufshci.h create mode 100644 include/ufs/unipro.h (limited to 'include') diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h new file mode 100644 index 000000000000..1bba3fead2ce --- /dev/null +++ b/include/ufs/ufs.h @@ -0,0 +1,623 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Universal Flash Storage Host controller driver + * Copyright (C) 2011-2013 Samsung India Software Operations + * + * Authors: + * Santosh Yaraganavi + * Vinayak Holikatti + */ + +#ifndef _UFS_H +#define _UFS_H + +#include +#include +#include + +#define GENERAL_UPIU_REQUEST_SIZE (sizeof(struct utp_upiu_req)) +#define QUERY_DESC_MAX_SIZE 255 +#define QUERY_DESC_MIN_SIZE 2 +#define QUERY_DESC_HDR_SIZE 2 +#define QUERY_OSF_SIZE (GENERAL_UPIU_REQUEST_SIZE - \ + (sizeof(struct utp_upiu_header))) +#define UFS_SENSE_SIZE 18 + +#define UPIU_HEADER_DWORD(byte3, byte2, byte1, byte0)\ + cpu_to_be32((byte3 << 24) | (byte2 << 16) |\ + (byte1 << 8) | (byte0)) +/* + * UFS device may have standard LUs and LUN id could be from 0x00 to + * 0x7F. Standard LUs use "Peripheral Device Addressing Format". + * UFS device may also have the Well Known LUs (also referred as W-LU) + * which again could be from 0x00 to 0x7F. For W-LUs, device only use + * the "Extended Addressing Format" which means the W-LUNs would be + * from 0xc100 (SCSI_W_LUN_BASE) onwards. + * This means max. LUN number reported from UFS device could be 0xC17F. + */ +#define UFS_UPIU_MAX_UNIT_NUM_ID 0x7F +#define UFS_MAX_LUNS (SCSI_W_LUN_BASE + UFS_UPIU_MAX_UNIT_NUM_ID) +#define UFS_UPIU_WLUN_ID (1 << 7) +#define UFS_RPMB_UNIT 0xC4 + +/* WriteBooster buffer is available only for the logical unit from 0 to 7 */ +#define UFS_UPIU_MAX_WB_LUN_ID 8 + +/* + * WriteBooster buffer lifetime has a limit setted by vendor. + * If it is over the limit, WriteBooster feature will be disabled. + */ +#define UFS_WB_EXCEED_LIFETIME 0x0B + +/* Well known logical unit id in LUN field of UPIU */ +enum { + UFS_UPIU_REPORT_LUNS_WLUN = 0x81, + UFS_UPIU_UFS_DEVICE_WLUN = 0xD0, + UFS_UPIU_BOOT_WLUN = 0xB0, + UFS_UPIU_RPMB_WLUN = 0xC4, +}; + +/* + * UFS Protocol Information Unit related definitions + */ + +/* Task management functions */ +enum { + UFS_ABORT_TASK = 0x01, + UFS_ABORT_TASK_SET = 0x02, + UFS_CLEAR_TASK_SET = 0x04, + UFS_LOGICAL_RESET = 0x08, + UFS_QUERY_TASK = 0x80, + UFS_QUERY_TASK_SET = 0x81, +}; + +/* UTP UPIU Transaction Codes Initiator to Target */ +enum { + UPIU_TRANSACTION_NOP_OUT = 0x00, + UPIU_TRANSACTION_COMMAND = 0x01, + UPIU_TRANSACTION_DATA_OUT = 0x02, + UPIU_TRANSACTION_TASK_REQ = 0x04, + UPIU_TRANSACTION_QUERY_REQ = 0x16, +}; + +/* UTP UPIU Transaction Codes Target to Initiator */ +enum { + UPIU_TRANSACTION_NOP_IN = 0x20, + UPIU_TRANSACTION_RESPONSE = 0x21, + UPIU_TRANSACTION_DATA_IN = 0x22, + UPIU_TRANSACTION_TASK_RSP = 0x24, + UPIU_TRANSACTION_READY_XFER = 0x31, + UPIU_TRANSACTION_QUERY_RSP = 0x36, + UPIU_TRANSACTION_REJECT_UPIU = 0x3F, +}; + +/* UPIU Read/Write flags */ +enum { + UPIU_CMD_FLAGS_NONE = 0x00, + UPIU_CMD_FLAGS_WRITE = 0x20, + UPIU_CMD_FLAGS_READ = 0x40, +}; + +/* UPIU Task Attributes */ +enum { + UPIU_TASK_ATTR_SIMPLE = 0x00, + UPIU_TASK_ATTR_ORDERED = 0x01, + UPIU_TASK_ATTR_HEADQ = 0x02, + UPIU_TASK_ATTR_ACA = 0x03, +}; + +/* UPIU Query request function */ +enum { + UPIU_QUERY_FUNC_STANDARD_READ_REQUEST = 0x01, + UPIU_QUERY_FUNC_STANDARD_WRITE_REQUEST = 0x81, +}; + +/* Flag idn for Query Requests*/ +enum flag_idn { + QUERY_FLAG_IDN_FDEVICEINIT = 0x01, + QUERY_FLAG_IDN_PERMANENT_WPE = 0x02, + QUERY_FLAG_IDN_PWR_ON_WPE = 0x03, + QUERY_FLAG_IDN_BKOPS_EN = 0x04, + QUERY_FLAG_IDN_LIFE_SPAN_MODE_ENABLE = 0x05, + QUERY_FLAG_IDN_PURGE_ENABLE = 0x06, + QUERY_FLAG_IDN_RESERVED2 = 0x07, + QUERY_FLAG_IDN_FPHYRESOURCEREMOVAL = 0x08, + QUERY_FLAG_IDN_BUSY_RTC = 0x09, + QUERY_FLAG_IDN_RESERVED3 = 0x0A, + QUERY_FLAG_IDN_PERMANENTLY_DISABLE_FW_UPDATE = 0x0B, + QUERY_FLAG_IDN_WB_EN = 0x0E, + QUERY_FLAG_IDN_WB_BUFF_FLUSH_EN = 0x0F, + QUERY_FLAG_IDN_WB_BUFF_FLUSH_DURING_HIBERN8 = 0x10, + QUERY_FLAG_IDN_HPB_RESET = 0x11, + QUERY_FLAG_IDN_HPB_EN = 0x12, +}; + +/* Attribute idn for Query requests */ +enum attr_idn { + QUERY_ATTR_IDN_BOOT_LU_EN = 0x00, + QUERY_ATTR_IDN_MAX_HPB_SINGLE_CMD = 0x01, + QUERY_ATTR_IDN_POWER_MODE = 0x02, + QUERY_ATTR_IDN_ACTIVE_ICC_LVL = 0x03, + QUERY_ATTR_IDN_OOO_DATA_EN = 0x04, + QUERY_ATTR_IDN_BKOPS_STATUS = 0x05, + QUERY_ATTR_IDN_PURGE_STATUS = 0x06, + QUERY_ATTR_IDN_MAX_DATA_IN = 0x07, + QUERY_ATTR_IDN_MAX_DATA_OUT = 0x08, + QUERY_ATTR_IDN_DYN_CAP_NEEDED = 0x09, + QUERY_ATTR_IDN_REF_CLK_FREQ = 0x0A, + QUERY_ATTR_IDN_CONF_DESC_LOCK = 0x0B, + QUERY_ATTR_IDN_MAX_NUM_OF_RTT = 0x0C, + QUERY_ATTR_IDN_EE_CONTROL = 0x0D, + QUERY_ATTR_IDN_EE_STATUS = 0x0E, + QUERY_ATTR_IDN_SECONDS_PASSED = 0x0F, + QUERY_ATTR_IDN_CNTX_CONF = 0x10, + QUERY_ATTR_IDN_CORR_PRG_BLK_NUM = 0x11, + QUERY_ATTR_IDN_RESERVED2 = 0x12, + QUERY_ATTR_IDN_RESERVED3 = 0x13, + QUERY_ATTR_IDN_FFU_STATUS = 0x14, + QUERY_ATTR_IDN_PSA_STATE = 0x15, + QUERY_ATTR_IDN_PSA_DATA_SIZE = 0x16, + QUERY_ATTR_IDN_REF_CLK_GATING_WAIT_TIME = 0x17, + QUERY_ATTR_IDN_CASE_ROUGH_TEMP = 0x18, + QUERY_ATTR_IDN_HIGH_TEMP_BOUND = 0x19, + QUERY_ATTR_IDN_LOW_TEMP_BOUND = 0x1A, + QUERY_ATTR_IDN_WB_FLUSH_STATUS = 0x1C, + QUERY_ATTR_IDN_AVAIL_WB_BUFF_SIZE = 0x1D, + QUERY_ATTR_IDN_WB_BUFF_LIFE_TIME_EST = 0x1E, + QUERY_ATTR_IDN_CURR_WB_BUFF_SIZE = 0x1F, +}; + +/* Descriptor idn for Query requests */ +enum desc_idn { + QUERY_DESC_IDN_DEVICE = 0x0, + QUERY_DESC_IDN_CONFIGURATION = 0x1, + QUERY_DESC_IDN_UNIT = 0x2, + QUERY_DESC_IDN_RFU_0 = 0x3, + QUERY_DESC_IDN_INTERCONNECT = 0x4, + QUERY_DESC_IDN_STRING = 0x5, + QUERY_DESC_IDN_RFU_1 = 0x6, + QUERY_DESC_IDN_GEOMETRY = 0x7, + QUERY_DESC_IDN_POWER = 0x8, + QUERY_DESC_IDN_HEALTH = 0x9, + QUERY_DESC_IDN_MAX, +}; + +enum desc_header_offset { + QUERY_DESC_LENGTH_OFFSET = 0x00, + QUERY_DESC_DESC_TYPE_OFFSET = 0x01, +}; + +/* Unit descriptor parameters offsets in bytes*/ +enum unit_desc_param { + UNIT_DESC_PARAM_LEN = 0x0, + UNIT_DESC_PARAM_TYPE = 0x1, + UNIT_DESC_PARAM_UNIT_INDEX = 0x2, + UNIT_DESC_PARAM_LU_ENABLE = 0x3, + UNIT_DESC_PARAM_BOOT_LUN_ID = 0x4, + UNIT_DESC_PARAM_LU_WR_PROTECT = 0x5, + UNIT_DESC_PARAM_LU_Q_DEPTH = 0x6, + UNIT_DESC_PARAM_PSA_SENSITIVE = 0x7, + UNIT_DESC_PARAM_MEM_TYPE = 0x8, + UNIT_DESC_PARAM_DATA_RELIABILITY = 0x9, + UNIT_DESC_PARAM_LOGICAL_BLK_SIZE = 0xA, + UNIT_DESC_PARAM_LOGICAL_BLK_COUNT = 0xB, + UNIT_DESC_PARAM_ERASE_BLK_SIZE = 0x13, + UNIT_DESC_PARAM_PROVISIONING_TYPE = 0x17, + UNIT_DESC_PARAM_PHY_MEM_RSRC_CNT = 0x18, + UNIT_DESC_PARAM_CTX_CAPABILITIES = 0x20, + UNIT_DESC_PARAM_LARGE_UNIT_SIZE_M1 = 0x22, + UNIT_DESC_PARAM_HPB_LU_MAX_ACTIVE_RGNS = 0x23, + UNIT_DESC_PARAM_HPB_PIN_RGN_START_OFF = 0x25, + UNIT_DESC_PARAM_HPB_NUM_PIN_RGNS = 0x27, + UNIT_DESC_PARAM_WB_BUF_ALLOC_UNITS = 0x29, +}; + +/* Device descriptor parameters offsets in bytes*/ +enum device_desc_param { + DEVICE_DESC_PARAM_LEN = 0x0, + DEVICE_DESC_PARAM_TYPE = 0x1, + DEVICE_DESC_PARAM_DEVICE_TYPE = 0x2, + DEVICE_DESC_PARAM_DEVICE_CLASS = 0x3, + DEVICE_DESC_PARAM_DEVICE_SUB_CLASS = 0x4, + DEVICE_DESC_PARAM_PRTCL = 0x5, + DEVICE_DESC_PARAM_NUM_LU = 0x6, + DEVICE_DESC_PARAM_NUM_WLU = 0x7, + DEVICE_DESC_PARAM_BOOT_ENBL = 0x8, + DEVICE_DESC_PARAM_DESC_ACCSS_ENBL = 0x9, + DEVICE_DESC_PARAM_INIT_PWR_MODE = 0xA, + DEVICE_DESC_PARAM_HIGH_PR_LUN = 0xB, + DEVICE_DESC_PARAM_SEC_RMV_TYPE = 0xC, + DEVICE_DESC_PARAM_SEC_LU = 0xD, + DEVICE_DESC_PARAM_BKOP_TERM_LT = 0xE, + DEVICE_DESC_PARAM_ACTVE_ICC_LVL = 0xF, + DEVICE_DESC_PARAM_SPEC_VER = 0x10, + DEVICE_DESC_PARAM_MANF_DATE = 0x12, + DEVICE_DESC_PARAM_MANF_NAME = 0x14, + DEVICE_DESC_PARAM_PRDCT_NAME = 0x15, + DEVICE_DESC_PARAM_SN = 0x16, + DEVICE_DESC_PARAM_OEM_ID = 0x17, + DEVICE_DESC_PARAM_MANF_ID = 0x18, + DEVICE_DESC_PARAM_UD_OFFSET = 0x1A, + DEVICE_DESC_PARAM_UD_LEN = 0x1B, + DEVICE_DESC_PARAM_RTT_CAP = 0x1C, + DEVICE_DESC_PARAM_FRQ_RTC = 0x1D, + DEVICE_DESC_PARAM_UFS_FEAT = 0x1F, + DEVICE_DESC_PARAM_FFU_TMT = 0x20, + DEVICE_DESC_PARAM_Q_DPTH = 0x21, + DEVICE_DESC_PARAM_DEV_VER = 0x22, + DEVICE_DESC_PARAM_NUM_SEC_WPA = 0x24, + DEVICE_DESC_PARAM_PSA_MAX_DATA = 0x25, + DEVICE_DESC_PARAM_PSA_TMT = 0x29, + DEVICE_DESC_PARAM_PRDCT_REV = 0x2A, + DEVICE_DESC_PARAM_HPB_VER = 0x40, + DEVICE_DESC_PARAM_HPB_CONTROL = 0x42, + DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP = 0x4F, + DEVICE_DESC_PARAM_WB_PRESRV_USRSPC_EN = 0x53, + DEVICE_DESC_PARAM_WB_TYPE = 0x54, + DEVICE_DESC_PARAM_WB_SHARED_ALLOC_UNITS = 0x55, +}; + +/* Interconnect descriptor parameters offsets in bytes*/ +enum interconnect_desc_param { + INTERCONNECT_DESC_PARAM_LEN = 0x0, + INTERCONNECT_DESC_PARAM_TYPE = 0x1, + INTERCONNECT_DESC_PARAM_UNIPRO_VER = 0x2, + INTERCONNECT_DESC_PARAM_MPHY_VER = 0x4, +}; + +/* Geometry descriptor parameters offsets in bytes*/ +enum geometry_desc_param { + GEOMETRY_DESC_PARAM_LEN = 0x0, + GEOMETRY_DESC_PARAM_TYPE = 0x1, + GEOMETRY_DESC_PARAM_DEV_CAP = 0x4, + GEOMETRY_DESC_PARAM_MAX_NUM_LUN = 0xC, + GEOMETRY_DESC_PARAM_SEG_SIZE = 0xD, + GEOMETRY_DESC_PARAM_ALLOC_UNIT_SIZE = 0x11, + GEOMETRY_DESC_PARAM_MIN_BLK_SIZE = 0x12, + GEOMETRY_DESC_PARAM_OPT_RD_BLK_SIZE = 0x13, + GEOMETRY_DESC_PARAM_OPT_WR_BLK_SIZE = 0x14, + GEOMETRY_DESC_PARAM_MAX_IN_BUF_SIZE = 0x15, + GEOMETRY_DESC_PARAM_MAX_OUT_BUF_SIZE = 0x16, + GEOMETRY_DESC_PARAM_RPMB_RW_SIZE = 0x17, + GEOMETRY_DESC_PARAM_DYN_CAP_RSRC_PLC = 0x18, + GEOMETRY_DESC_PARAM_DATA_ORDER = 0x19, + GEOMETRY_DESC_PARAM_MAX_NUM_CTX = 0x1A, + GEOMETRY_DESC_PARAM_TAG_UNIT_SIZE = 0x1B, + GEOMETRY_DESC_PARAM_TAG_RSRC_SIZE = 0x1C, + GEOMETRY_DESC_PARAM_SEC_RM_TYPES = 0x1D, + GEOMETRY_DESC_PARAM_MEM_TYPES = 0x1E, + GEOMETRY_DESC_PARAM_SCM_MAX_NUM_UNITS = 0x20, + GEOMETRY_DESC_PARAM_SCM_CAP_ADJ_FCTR = 0x24, + GEOMETRY_DESC_PARAM_NPM_MAX_NUM_UNITS = 0x26, + GEOMETRY_DESC_PARAM_NPM_CAP_ADJ_FCTR = 0x2A, + GEOMETRY_DESC_PARAM_ENM1_MAX_NUM_UNITS = 0x2C, + GEOMETRY_DESC_PARAM_ENM1_CAP_ADJ_FCTR = 0x30, + GEOMETRY_DESC_PARAM_ENM2_MAX_NUM_UNITS = 0x32, + GEOMETRY_DESC_PARAM_ENM2_CAP_ADJ_FCTR = 0x36, + GEOMETRY_DESC_PARAM_ENM3_MAX_NUM_UNITS = 0x38, + GEOMETRY_DESC_PARAM_ENM3_CAP_ADJ_FCTR = 0x3C, + GEOMETRY_DESC_PARAM_ENM4_MAX_NUM_UNITS = 0x3E, + GEOMETRY_DESC_PARAM_ENM4_CAP_ADJ_FCTR = 0x42, + GEOMETRY_DESC_PARAM_OPT_LOG_BLK_SIZE = 0x44, + GEOMETRY_DESC_PARAM_HPB_REGION_SIZE = 0x48, + GEOMETRY_DESC_PARAM_HPB_NUMBER_LU = 0x49, + GEOMETRY_DESC_PARAM_HPB_SUBREGION_SIZE = 0x4A, + GEOMETRY_DESC_PARAM_HPB_MAX_ACTIVE_REGS = 0x4B, + GEOMETRY_DESC_PARAM_WB_MAX_ALLOC_UNITS = 0x4F, + GEOMETRY_DESC_PARAM_WB_MAX_WB_LUNS = 0x53, + GEOMETRY_DESC_PARAM_WB_BUFF_CAP_ADJ = 0x54, + GEOMETRY_DESC_PARAM_WB_SUP_RED_TYPE = 0x55, + GEOMETRY_DESC_PARAM_WB_SUP_WB_TYPE = 0x56, +}; + +/* Health descriptor parameters offsets in bytes*/ +enum health_desc_param { + HEALTH_DESC_PARAM_LEN = 0x0, + HEALTH_DESC_PARAM_TYPE = 0x1, + HEALTH_DESC_PARAM_EOL_INFO = 0x2, + HEALTH_DESC_PARAM_LIFE_TIME_EST_A = 0x3, + HEALTH_DESC_PARAM_LIFE_TIME_EST_B = 0x4, +}; + +/* WriteBooster buffer mode */ +enum { + WB_BUF_MODE_LU_DEDICATED = 0x0, + WB_BUF_MODE_SHARED = 0x1, +}; + +/* + * Logical Unit Write Protect + * 00h: LU not write protected + * 01h: LU write protected when fPowerOnWPEn =1 + * 02h: LU permanently write protected when fPermanentWPEn =1 + */ +enum ufs_lu_wp_type { + UFS_LU_NO_WP = 0x00, + UFS_LU_POWER_ON_WP = 0x01, + UFS_LU_PERM_WP = 0x02, +}; + +/* bActiveICCLevel parameter current units */ +enum { + UFSHCD_NANO_AMP = 0, + UFSHCD_MICRO_AMP = 1, + UFSHCD_MILI_AMP = 2, + UFSHCD_AMP = 3, +}; + +/* Possible values for dExtendedUFSFeaturesSupport */ +enum { + UFS_DEV_LOW_TEMP_NOTIF = BIT(4), + UFS_DEV_HIGH_TEMP_NOTIF = BIT(5), + UFS_DEV_EXT_TEMP_NOTIF = BIT(6), + UFS_DEV_HPB_SUPPORT = BIT(7), + UFS_DEV_WRITE_BOOSTER_SUP = BIT(8), +}; +#define UFS_DEV_HPB_SUPPORT_VERSION 0x310 + +#define POWER_DESC_MAX_ACTV_ICC_LVLS 16 + +/* Attribute bActiveICCLevel parameter bit masks definitions */ +#define ATTR_ICC_LVL_UNIT_OFFSET 14 +#define ATTR_ICC_LVL_UNIT_MASK (0x3 << ATTR_ICC_LVL_UNIT_OFFSET) +#define ATTR_ICC_LVL_VALUE_MASK 0x3FF + +/* Power descriptor parameters offsets in bytes */ +enum power_desc_param_offset { + PWR_DESC_LEN = 0x0, + PWR_DESC_TYPE = 0x1, + PWR_DESC_ACTIVE_LVLS_VCC_0 = 0x2, + PWR_DESC_ACTIVE_LVLS_VCCQ_0 = 0x22, + PWR_DESC_ACTIVE_LVLS_VCCQ2_0 = 0x42, +}; + +/* Exception event mask values */ +enum { + MASK_EE_STATUS = 0xFFFF, + MASK_EE_DYNCAP_EVENT = BIT(0), + MASK_EE_SYSPOOL_EVENT = BIT(1), + MASK_EE_URGENT_BKOPS = BIT(2), + MASK_EE_TOO_HIGH_TEMP = BIT(3), + MASK_EE_TOO_LOW_TEMP = BIT(4), + MASK_EE_WRITEBOOSTER_EVENT = BIT(5), + MASK_EE_PERFORMANCE_THROTTLING = BIT(6), +}; +#define MASK_EE_URGENT_TEMP (MASK_EE_TOO_HIGH_TEMP | MASK_EE_TOO_LOW_TEMP) + +/* Background operation status */ +enum bkops_status { + BKOPS_STATUS_NO_OP = 0x0, + BKOPS_STATUS_NON_CRITICAL = 0x1, + BKOPS_STATUS_PERF_IMPACT = 0x2, + BKOPS_STATUS_CRITICAL = 0x3, + BKOPS_STATUS_MAX = BKOPS_STATUS_CRITICAL, +}; + +/* UTP QUERY Transaction Specific Fields OpCode */ +enum query_opcode { + UPIU_QUERY_OPCODE_NOP = 0x0, + UPIU_QUERY_OPCODE_READ_DESC = 0x1, + UPIU_QUERY_OPCODE_WRITE_DESC = 0x2, + UPIU_QUERY_OPCODE_READ_ATTR = 0x3, + UPIU_QUERY_OPCODE_WRITE_ATTR = 0x4, + UPIU_QUERY_OPCODE_READ_FLAG = 0x5, + UPIU_QUERY_OPCODE_SET_FLAG = 0x6, + UPIU_QUERY_OPCODE_CLEAR_FLAG = 0x7, + UPIU_QUERY_OPCODE_TOGGLE_FLAG = 0x8, +}; + +/* bRefClkFreq attribute values */ +enum ufs_ref_clk_freq { + REF_CLK_FREQ_19_2_MHZ = 0, + REF_CLK_FREQ_26_MHZ = 1, + REF_CLK_FREQ_38_4_MHZ = 2, + REF_CLK_FREQ_52_MHZ = 3, + REF_CLK_FREQ_INVAL = -1, +}; + +/* Query response result code */ +enum { + QUERY_RESULT_SUCCESS = 0x00, + QUERY_RESULT_NOT_READABLE = 0xF6, + QUERY_RESULT_NOT_WRITEABLE = 0xF7, + QUERY_RESULT_ALREADY_WRITTEN = 0xF8, + QUERY_RESULT_INVALID_LENGTH = 0xF9, + QUERY_RESULT_INVALID_VALUE = 0xFA, + QUERY_RESULT_INVALID_SELECTOR = 0xFB, + QUERY_RESULT_INVALID_INDEX = 0xFC, + QUERY_RESULT_INVALID_IDN = 0xFD, + QUERY_RESULT_INVALID_OPCODE = 0xFE, + QUERY_RESULT_GENERAL_FAILURE = 0xFF, +}; + +/* UTP Transfer Request Command Type (CT) */ +enum { + UPIU_COMMAND_SET_TYPE_SCSI = 0x0, + UPIU_COMMAND_SET_TYPE_UFS = 0x1, + UPIU_COMMAND_SET_TYPE_QUERY = 0x2, +}; + +/* UTP Transfer Request Command Offset */ +#define UPIU_COMMAND_TYPE_OFFSET 28 + +/* Offset of the response code in the UPIU header */ +#define UPIU_RSP_CODE_OFFSET 8 + +enum { + MASK_SCSI_STATUS = 0xFF, + MASK_TASK_RESPONSE = 0xFF00, + MASK_RSP_UPIU_RESULT = 0xFFFF, + MASK_QUERY_DATA_SEG_LEN = 0xFFFF, + MASK_RSP_UPIU_DATA_SEG_LEN = 0xFFFF, + MASK_RSP_EXCEPTION_EVENT = 0x10000, + MASK_TM_SERVICE_RESP = 0xFF, + MASK_TM_FUNC = 0xFF, +}; + +/* Task management service response */ +enum { + UPIU_TASK_MANAGEMENT_FUNC_COMPL = 0x00, + UPIU_TASK_MANAGEMENT_FUNC_NOT_SUPPORTED = 0x04, + UPIU_TASK_MANAGEMENT_FUNC_SUCCEEDED = 0x08, + UPIU_TASK_MANAGEMENT_FUNC_FAILED = 0x05, + UPIU_INCORRECT_LOGICAL_UNIT_NO = 0x09, +}; + +/* UFS device power modes */ +enum ufs_dev_pwr_mode { + UFS_ACTIVE_PWR_MODE = 1, + UFS_SLEEP_PWR_MODE = 2, + UFS_POWERDOWN_PWR_MODE = 3, + UFS_DEEPSLEEP_PWR_MODE = 4, +}; + +#define UFS_WB_BUF_REMAIN_PERCENT(val) ((val) / 10) + +/** + * struct utp_cmd_rsp - Response UPIU structure + * @residual_transfer_count: Residual transfer count DW-3 + * @reserved: Reserved double words DW-4 to DW-7 + * @sense_data_len: Sense data length DW-8 U16 + * @sense_data: Sense data field DW-8 to DW-12 + */ +struct utp_cmd_rsp { + __be32 residual_transfer_count; + __be32 reserved[4]; + __be16 sense_data_len; + u8 sense_data[UFS_SENSE_SIZE]; +}; + +struct ufshpb_active_field { + __be16 active_rgn; + __be16 active_srgn; +}; +#define HPB_ACT_FIELD_SIZE 4 + +/** + * struct utp_hpb_rsp - Response UPIU structure + * @residual_transfer_count: Residual transfer count DW-3 + * @reserved1: Reserved double words DW-4 to DW-7 + * @sense_data_len: Sense data length DW-8 U16 + * @desc_type: Descriptor type of sense data + * @additional_len: Additional length of sense data + * @hpb_op: HPB operation type + * @lun: LUN of response UPIU + * @active_rgn_cnt: Active region count + * @inactive_rgn_cnt: Inactive region count + * @hpb_active_field: Recommended to read HPB region and subregion + * @hpb_inactive_field: To be inactivated HPB region and subregion + */ +struct utp_hpb_rsp { + __be32 residual_transfer_count; + __be32 reserved1[4]; + __be16 sense_data_len; + u8 desc_type; + u8 additional_len; + u8 hpb_op; + u8 lun; + u8 active_rgn_cnt; + u8 inactive_rgn_cnt; + struct ufshpb_active_field hpb_active_field[2]; + __be16 hpb_inactive_field[2]; +}; +#define UTP_HPB_RSP_SIZE 40 + +/** + * struct utp_upiu_rsp - general upiu response structure + * @header: UPIU header structure DW-0 to DW-2 + * @sr: fields structure for scsi command DW-3 to DW-12 + * @qr: fields structure for query request DW-3 to DW-7 + */ +struct utp_upiu_rsp { + struct utp_upiu_header header; + union { + struct utp_cmd_rsp sr; + struct utp_hpb_rsp hr; + struct utp_upiu_query qr; + }; +}; + +/** + * struct ufs_query_req - parameters for building a query request + * @query_func: UPIU header query function + * @upiu_req: the query request data + */ +struct ufs_query_req { + u8 query_func; + struct utp_upiu_query upiu_req; +}; + +/** + * struct ufs_query_resp - UPIU QUERY + * @response: device response code + * @upiu_res: query response data + */ +struct ufs_query_res { + u8 response; + struct utp_upiu_query upiu_res; +}; + +/* + * VCCQ & VCCQ2 current requirement when UFS device is in sleep state + * and link is in Hibern8 state. + */ +#define UFS_VREG_LPM_LOAD_UA 1000 /* uA */ + +struct ufs_vreg { + struct regulator *reg; + const char *name; + bool always_on; + bool enabled; + int max_uA; +}; + +struct ufs_vreg_info { + struct ufs_vreg *vcc; + struct ufs_vreg *vccq; + struct ufs_vreg *vccq2; + struct ufs_vreg *vdd_hba; +}; + +struct ufs_dev_info { + bool f_power_on_wp_en; + /* Keeps information if any of the LU is power on write protected */ + bool is_lu_power_on_wp; + /* Maximum number of general LU supported by the UFS device */ + u8 max_lu_supported; + u16 wmanufacturerid; + /*UFS device Product Name */ + u8 *model; + u16 wspecversion; + u32 clk_gating_wait_us; + + /* UFS HPB related flag */ + bool hpb_enabled; + + /* UFS WB related flags */ + bool wb_enabled; + bool wb_buf_flush_enabled; + u8 wb_dedicated_lu; + u8 wb_buffer_type; + + bool b_rpm_dev_flush_capable; + u8 b_presrv_uspc_en; +}; + +/* + * This enum is used in string mapping in include/trace/events/ufs.h. + */ +enum ufs_trace_str_t { + UFS_CMD_SEND, UFS_CMD_COMP, UFS_DEV_COMP, + UFS_QUERY_SEND, UFS_QUERY_COMP, UFS_QUERY_ERR, + UFS_TM_SEND, UFS_TM_COMP, UFS_TM_ERR +}; + +/* + * Transaction Specific Fields (TSF) type in the UPIU package, this enum is + * used in include/trace/events/ufs.h for UFS command trace. + */ +enum ufs_trace_tsf_t { + UFS_TSF_CDB, UFS_TSF_OSF, UFS_TSF_TM_INPUT, UFS_TSF_TM_OUTPUT +}; + +#endif /* End of Header */ diff --git a/include/ufs/ufs_quirks.h b/include/ufs/ufs_quirks.h new file mode 100644 index 000000000000..bcb4f004bed5 --- /dev/null +++ b/include/ufs/ufs_quirks.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2014-2016, The Linux Foundation. All rights reserved. + */ + +#ifndef _UFS_QUIRKS_H_ +#define _UFS_QUIRKS_H_ + +/* return true if s1 is a prefix of s2 */ +#define STR_PRFX_EQUAL(s1, s2) !strncmp(s1, s2, strlen(s1)) + +#define UFS_ANY_VENDOR 0xFFFF +#define UFS_ANY_MODEL "ANY_MODEL" + +#define UFS_VENDOR_MICRON 0x12C +#define UFS_VENDOR_SAMSUNG 0x1CE +#define UFS_VENDOR_SKHYNIX 0x1AD +#define UFS_VENDOR_TOSHIBA 0x198 +#define UFS_VENDOR_WDC 0x145 + +/** + * ufs_dev_quirk - ufs device quirk info + * @card: ufs card details + * @quirk: device quirk + */ +struct ufs_dev_quirk { + u16 wmanufacturerid; + const u8 *model; + unsigned int quirk; +}; + +/* + * Some vendor's UFS device sends back to back NACs for the DL data frames + * causing the host controller to raise the DFES error status. Sometimes + * such UFS devices send back to back NAC without waiting for new + * retransmitted DL frame from the host and in such cases it might be possible + * the Host UniPro goes into bad state without raising the DFES error + * interrupt. If this happens then all the pending commands would timeout + * only after respective SW command (which is generally too large). + * + * We can workaround such device behaviour like this: + * - As soon as SW sees the DL NAC error, it should schedule the error handler + * - Error handler would sleep for 50ms to see if there are any fatal errors + * raised by UFS controller. + * - If there are fatal errors then SW does normal error recovery. + * - If there are no fatal errors then SW sends the NOP command to device + * to check if link is alive. + * - If NOP command times out, SW does normal error recovery + * - If NOP command succeed, skip the error handling. + * + * If DL NAC error is seen multiple times with some vendor's UFS devices then + * enable this quirk to initiate quick error recovery and also silence related + * error logs to reduce spamming of kernel logs. + */ +#define UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS (1 << 2) + +/* + * Few Toshiba UFS device models advertise RX_MIN_ACTIVATETIME_CAPABILITY as + * 600us which may not be enough for reliable hibern8 exit hardware sequence + * from UFS device. + * To workaround this issue, host should set its PA_TACTIVATE time to 1ms even + * if device advertises RX_MIN_ACTIVATETIME_CAPABILITY less than 1ms. + */ +#define UFS_DEVICE_QUIRK_PA_TACTIVATE (1 << 4) + +/* + * It seems some UFS devices may keep drawing more than sleep current + * (atleast for 500us) from UFS rails (especially from VCCQ rail). + * To avoid this situation, add 2ms delay before putting these UFS + * rails in LPM mode. + */ +#define UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM (1 << 6) + +/* + * Some UFS devices require host PA_TACTIVATE to be lower than device + * PA_TACTIVATE, enabling this quirk ensure this. + */ +#define UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE (1 << 7) + +/* + * The max. value PA_SaveConfigTime is 250 (10us) but this is not enough for + * some vendors. + * Gear switch from PWM to HS may fail even with this max. PA_SaveConfigTime. + * Gear switch can be issued by host controller as an error recovery and any + * software delay will not help on this case so we need to increase + * PA_SaveConfigTime to >32us as per vendor recommendation. + */ +#define UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME (1 << 8) + +/* + * Some UFS devices require VS_DebugSaveConfigTime is 0x10, + * enabling this quirk ensure this. + */ +#define UFS_DEVICE_QUIRK_HOST_VS_DEBUGSAVECONFIGTIME (1 << 9) + +/* + * Some pre-3.1 UFS devices can support extended features by upgrading + * the firmware. Enable this quirk to make UFS core driver probe and enable + * supported features on such devices. + */ +#define UFS_DEVICE_QUIRK_SUPPORT_EXTENDED_FEATURES (1 << 10) + +/* + * Some UFS devices require delay after VCC power rail is turned-off. + * Enable this quirk to introduce 5ms delays after VCC power-off during + * suspend flow. + */ +#define UFS_DEVICE_QUIRK_DELAY_AFTER_LPM (1 << 11) + +/* + * Some UFS devices require L2P entry should be swapped before being sent to the + * UFS device for HPB READ command. + */ +#define UFS_DEVICE_QUIRK_SWAP_L2P_ENTRY_FOR_HPB_READ (1 << 12) + +#endif /* UFS_QUIRKS_H_ */ diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h new file mode 100644 index 000000000000..a92271421718 --- /dev/null +++ b/include/ufs/ufshcd.h @@ -0,0 +1,1230 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Universal Flash Storage Host controller driver + * Copyright (C) 2011-2013 Samsung India Software Operations + * Copyright (c) 2013-2016, The Linux Foundation. All rights reserved. + * + * Authors: + * Santosh Yaraganavi + * Vinayak Holikatti + */ + +#ifndef _UFSHCD_H +#define _UFSHCD_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define UFSHCD "ufshcd" + +struct ufs_hba; + +enum dev_cmd_type { + DEV_CMD_TYPE_NOP = 0x0, + DEV_CMD_TYPE_QUERY = 0x1, +}; + +enum ufs_event_type { + /* uic specific errors */ + UFS_EVT_PA_ERR = 0, + UFS_EVT_DL_ERR, + UFS_EVT_NL_ERR, + UFS_EVT_TL_ERR, + UFS_EVT_DME_ERR, + + /* fatal errors */ + UFS_EVT_AUTO_HIBERN8_ERR, + UFS_EVT_FATAL_ERR, + UFS_EVT_LINK_STARTUP_FAIL, + UFS_EVT_RESUME_ERR, + UFS_EVT_SUSPEND_ERR, + UFS_EVT_WL_SUSP_ERR, + UFS_EVT_WL_RES_ERR, + + /* abnormal events */ + UFS_EVT_DEV_RESET, + UFS_EVT_HOST_RESET, + UFS_EVT_ABORT, + + UFS_EVT_CNT, +}; + +/** + * struct uic_command - UIC command structure + * @command: UIC command + * @argument1: UIC command argument 1 + * @argument2: UIC command argument 2 + * @argument3: UIC command argument 3 + * @cmd_active: Indicate if UIC command is outstanding + * @done: UIC command completion + */ +struct uic_command { + u32 command; + u32 argument1; + u32 argument2; + u32 argument3; + int cmd_active; + struct completion done; +}; + +/* Used to differentiate the power management options */ +enum ufs_pm_op { + UFS_RUNTIME_PM, + UFS_SYSTEM_PM, + UFS_SHUTDOWN_PM, +}; + +/* Host <-> Device UniPro Link state */ +enum uic_link_state { + UIC_LINK_OFF_STATE = 0, /* Link powered down or disabled */ + UIC_LINK_ACTIVE_STATE = 1, /* Link is in Fast/Slow/Sleep state */ + UIC_LINK_HIBERN8_STATE = 2, /* Link is in Hibernate state */ + UIC_LINK_BROKEN_STATE = 3, /* Link is in broken state */ +}; + +#define ufshcd_is_link_off(hba) ((hba)->uic_link_state == UIC_LINK_OFF_STATE) +#define ufshcd_is_link_active(hba) ((hba)->uic_link_state == \ + UIC_LINK_ACTIVE_STATE) +#define ufshcd_is_link_hibern8(hba) ((hba)->uic_link_state == \ + UIC_LINK_HIBERN8_STATE) +#define ufshcd_is_link_broken(hba) ((hba)->uic_link_state == \ + UIC_LINK_BROKEN_STATE) +#define ufshcd_set_link_off(hba) ((hba)->uic_link_state = UIC_LINK_OFF_STATE) +#define ufshcd_set_link_active(hba) ((hba)->uic_link_state = \ + UIC_LINK_ACTIVE_STATE) +#define ufshcd_set_link_hibern8(hba) ((hba)->uic_link_state = \ + UIC_LINK_HIBERN8_STATE) +#define ufshcd_set_link_broken(hba) ((hba)->uic_link_state = \ + UIC_LINK_BROKEN_STATE) + +#define ufshcd_set_ufs_dev_active(h) \ + ((h)->curr_dev_pwr_mode = UFS_ACTIVE_PWR_MODE) +#define ufshcd_set_ufs_dev_sleep(h) \ + ((h)->curr_dev_pwr_mode = UFS_SLEEP_PWR_MODE) +#define ufshcd_set_ufs_dev_poweroff(h) \ + ((h)->curr_dev_pwr_mode = UFS_POWERDOWN_PWR_MODE) +#define ufshcd_set_ufs_dev_deepsleep(h) \ + ((h)->curr_dev_pwr_mode = UFS_DEEPSLEEP_PWR_MODE) +#define ufshcd_is_ufs_dev_active(h) \ + ((h)->curr_dev_pwr_mode == UFS_ACTIVE_PWR_MODE) +#define ufshcd_is_ufs_dev_sleep(h) \ + ((h)->curr_dev_pwr_mode == UFS_SLEEP_PWR_MODE) +#define ufshcd_is_ufs_dev_poweroff(h) \ + ((h)->curr_dev_pwr_mode == UFS_POWERDOWN_PWR_MODE) +#define ufshcd_is_ufs_dev_deepsleep(h) \ + ((h)->curr_dev_pwr_mode == UFS_DEEPSLEEP_PWR_MODE) + +/* + * UFS Power management levels. + * Each level is in increasing order of power savings, except DeepSleep + * which is lower than PowerDown with power on but not PowerDown with + * power off. + */ +enum ufs_pm_level { + UFS_PM_LVL_0, + UFS_PM_LVL_1, + UFS_PM_LVL_2, + UFS_PM_LVL_3, + UFS_PM_LVL_4, + UFS_PM_LVL_5, + UFS_PM_LVL_6, + UFS_PM_LVL_MAX +}; + +struct ufs_pm_lvl_states { + enum ufs_dev_pwr_mode dev_state; + enum uic_link_state link_state; +}; + +/** + * struct ufshcd_lrb - local reference block + * @utr_descriptor_ptr: UTRD address of the command + * @ucd_req_ptr: UCD address of the command + * @ucd_rsp_ptr: Response UPIU address for this command + * @ucd_prdt_ptr: PRDT address of the command + * @utrd_dma_addr: UTRD dma address for debug + * @ucd_prdt_dma_addr: PRDT dma address for debug + * @ucd_rsp_dma_addr: UPIU response dma address for debug + * @ucd_req_dma_addr: UPIU request dma address for debug + * @cmd: pointer to SCSI command + * @scsi_status: SCSI status of the command + * @command_type: SCSI, UFS, Query. + * @task_tag: Task tag of the command + * @lun: LUN of the command + * @intr_cmd: Interrupt command (doesn't participate in interrupt aggregation) + * @issue_time_stamp: time stamp for debug purposes + * @compl_time_stamp: time stamp for statistics + * @crypto_key_slot: the key slot to use for inline crypto (-1 if none) + * @data_unit_num: the data unit number for the first block for inline crypto + * @req_abort_skip: skip request abort task flag + */ +struct ufshcd_lrb { + struct utp_transfer_req_desc *utr_descriptor_ptr; + struct utp_upiu_req *ucd_req_ptr; + struct utp_upiu_rsp *ucd_rsp_ptr; + struct ufshcd_sg_entry *ucd_prdt_ptr; + + dma_addr_t utrd_dma_addr; + dma_addr_t ucd_req_dma_addr; + dma_addr_t ucd_rsp_dma_addr; + dma_addr_t ucd_prdt_dma_addr; + + struct scsi_cmnd *cmd; + int scsi_status; + + int command_type; + int task_tag; + u8 lun; /* UPIU LUN id field is only 8-bit wide */ + bool intr_cmd; + ktime_t issue_time_stamp; + ktime_t compl_time_stamp; +#ifdef CONFIG_SCSI_UFS_CRYPTO + int crypto_key_slot; + u64 data_unit_num; +#endif + + bool req_abort_skip; +}; + +/** + * struct ufs_query - holds relevant data structures for query request + * @request: request upiu and function + * @descriptor: buffer for sending/receiving descriptor + * @response: response upiu and response + */ +struct ufs_query { + struct ufs_query_req request; + u8 *descriptor; + struct ufs_query_res response; +}; + +/** + * struct ufs_dev_cmd - all assosiated fields with device management commands + * @type: device management command type - Query, NOP OUT + * @lock: lock to allow one command at a time + * @complete: internal commands completion + * @query: Device management query information + */ +struct ufs_dev_cmd { + enum dev_cmd_type type; + struct mutex lock; + struct completion *complete; + struct ufs_query query; +}; + +/** + * struct ufs_clk_info - UFS clock related info + * @list: list headed by hba->clk_list_head + * @clk: clock node + * @name: clock name + * @max_freq: maximum frequency supported by the clock + * @min_freq: min frequency that can be used for clock scaling + * @curr_freq: indicates the current frequency that it is set to + * @keep_link_active: indicates that the clk should not be disabled if + * link is active + * @enabled: variable to check against multiple enable/disable + */ +struct ufs_clk_info { + struct list_head list; + struct clk *clk; + const char *name; + u32 max_freq; + u32 min_freq; + u32 curr_freq; + bool keep_link_active; + bool enabled; +}; + +enum ufs_notify_change_status { + PRE_CHANGE, + POST_CHANGE, +}; + +struct ufs_pa_layer_attr { + u32 gear_rx; + u32 gear_tx; + u32 lane_rx; + u32 lane_tx; + u32 pwr_rx; + u32 pwr_tx; + u32 hs_rate; +}; + +struct ufs_pwr_mode_info { + bool is_valid; + struct ufs_pa_layer_attr info; +}; + +/** + * struct ufs_hba_variant_ops - variant specific callbacks + * @name: variant name + * @init: called when the driver is initialized + * @exit: called to cleanup everything done in init + * @get_ufs_hci_version: called to get UFS HCI version + * @clk_scale_notify: notifies that clks are scaled up/down + * @setup_clocks: called before touching any of the controller registers + * @hce_enable_notify: called before and after HCE enable bit is set to allow + * variant specific Uni-Pro initialization. + * @link_startup_notify: called before and after Link startup is carried out + * to allow variant specific Uni-Pro initialization. + * @pwr_change_notify: called before and after a power mode change + * is carried out to allow vendor spesific capabilities + * to be set. + * @setup_xfer_req: called before any transfer request is issued + * to set some things + * @setup_task_mgmt: called before any task management request is issued + * to set some things + * @hibern8_notify: called around hibern8 enter/exit + * @apply_dev_quirks: called to apply device specific quirks + * @fixup_dev_quirks: called to modify device specific quirks + * @suspend: called during host controller PM callback + * @resume: called during host controller PM callback + * @dbg_register_dump: used to dump controller debug information + * @phy_initialization: used to initialize phys + * @device_reset: called to issue a reset pulse on the UFS device + * @config_scaling_param: called to configure clock scaling parameters + * @program_key: program or evict an inline encryption key + * @event_notify: called to notify important events + */ +struct ufs_hba_variant_ops { + const char *name; + int (*init)(struct ufs_hba *); + void (*exit)(struct ufs_hba *); + u32 (*get_ufs_hci_version)(struct ufs_hba *); + int (*clk_scale_notify)(struct ufs_hba *, bool, + enum ufs_notify_change_status); + int (*setup_clocks)(struct ufs_hba *, bool, + enum ufs_notify_change_status); + int (*hce_enable_notify)(struct ufs_hba *, + enum ufs_notify_change_status); + int (*link_startup_notify)(struct ufs_hba *, + enum ufs_notify_change_status); + int (*pwr_change_notify)(struct ufs_hba *, + enum ufs_notify_change_status status, + struct ufs_pa_layer_attr *, + struct ufs_pa_layer_attr *); + void (*setup_xfer_req)(struct ufs_hba *hba, int tag, + bool is_scsi_cmd); + void (*setup_task_mgmt)(struct ufs_hba *, int, u8); + void (*hibern8_notify)(struct ufs_hba *, enum uic_cmd_dme, + enum ufs_notify_change_status); + int (*apply_dev_quirks)(struct ufs_hba *hba); + void (*fixup_dev_quirks)(struct ufs_hba *hba); + int (*suspend)(struct ufs_hba *, enum ufs_pm_op, + enum ufs_notify_change_status); + int (*resume)(struct ufs_hba *, enum ufs_pm_op); + void (*dbg_register_dump)(struct ufs_hba *hba); + int (*phy_initialization)(struct ufs_hba *); + int (*device_reset)(struct ufs_hba *hba); + void (*config_scaling_param)(struct ufs_hba *hba, + struct devfreq_dev_profile *profile, + struct devfreq_simple_ondemand_data *data); + int (*program_key)(struct ufs_hba *hba, + const union ufs_crypto_cfg_entry *cfg, int slot); + void (*event_notify)(struct ufs_hba *hba, + enum ufs_event_type evt, void *data); +}; + +/* clock gating state */ +enum clk_gating_state { + CLKS_OFF, + CLKS_ON, + REQ_CLKS_OFF, + REQ_CLKS_ON, +}; + +/** + * struct ufs_clk_gating - UFS clock gating related info + * @gate_work: worker to turn off clocks after some delay as specified in + * delay_ms + * @ungate_work: worker to turn on clocks that will be used in case of + * interrupt context + * @state: the current clocks state + * @delay_ms: gating delay in ms + * @is_suspended: clk gating is suspended when set to 1 which can be used + * during suspend/resume + * @delay_attr: sysfs attribute to control delay_attr + * @enable_attr: sysfs attribute to enable/disable clock gating + * @is_enabled: Indicates the current status of clock gating + * @is_initialized: Indicates whether clock gating is initialized or not + * @active_reqs: number of requests that are pending and should be waited for + * completion before gating clocks. + * @clk_gating_workq: workqueue for clock gating work. + */ +struct ufs_clk_gating { + struct delayed_work gate_work; + struct work_struct ungate_work; + enum clk_gating_state state; + unsigned long delay_ms; + bool is_suspended; + struct device_attribute delay_attr; + struct device_attribute enable_attr; + bool is_enabled; + bool is_initialized; + int active_reqs; + struct workqueue_struct *clk_gating_workq; +}; + +struct ufs_saved_pwr_info { + struct ufs_pa_layer_attr info; + bool is_valid; +}; + +/** + * struct ufs_clk_scaling - UFS clock scaling related data + * @active_reqs: number of requests that are pending. If this is zero when + * devfreq ->target() function is called then schedule "suspend_work" to + * suspend devfreq. + * @tot_busy_t: Total busy time in current polling window + * @window_start_t: Start time (in jiffies) of the current polling window + * @busy_start_t: Start time of current busy period + * @enable_attr: sysfs attribute to enable/disable clock scaling + * @saved_pwr_info: UFS power mode may also be changed during scaling and this + * one keeps track of previous power mode. + * @workq: workqueue to schedule devfreq suspend/resume work + * @suspend_work: worker to suspend devfreq + * @resume_work: worker to resume devfreq + * @min_gear: lowest HS gear to scale down to + * @is_enabled: tracks if scaling is currently enabled or not, controlled by + * clkscale_enable sysfs node + * @is_allowed: tracks if scaling is currently allowed or not, used to block + * clock scaling which is not invoked from devfreq governor + * @is_initialized: Indicates whether clock scaling is initialized or not + * @is_busy_started: tracks if busy period has started or not + * @is_suspended: tracks if devfreq is suspended or not + */ +struct ufs_clk_scaling { + int active_reqs; + unsigned long tot_busy_t; + ktime_t window_start_t; + ktime_t busy_start_t; + struct device_attribute enable_attr; + struct ufs_saved_pwr_info saved_pwr_info; + struct workqueue_struct *workq; + struct work_struct suspend_work; + struct work_struct resume_work; + u32 min_gear; + bool is_enabled; + bool is_allowed; + bool is_initialized; + bool is_busy_started; + bool is_suspended; +}; + +#define UFS_EVENT_HIST_LENGTH 8 +/** + * struct ufs_event_hist - keeps history of errors + * @pos: index to indicate cyclic buffer position + * @val: cyclic buffer for registers value + * @tstamp: cyclic buffer for time stamp + * @cnt: error counter + */ +struct ufs_event_hist { + int pos; + u32 val[UFS_EVENT_HIST_LENGTH]; + ktime_t tstamp[UFS_EVENT_HIST_LENGTH]; + unsigned long long cnt; +}; + +/** + * struct ufs_stats - keeps usage/err statistics + * @last_intr_status: record the last interrupt status. + * @last_intr_ts: record the last interrupt timestamp. + * @hibern8_exit_cnt: Counter to keep track of number of exits, + * reset this after link-startup. + * @last_hibern8_exit_tstamp: Set time after the hibern8 exit. + * Clear after the first successful command completion. + * @event: array with event history. + */ +struct ufs_stats { + u32 last_intr_status; + ktime_t last_intr_ts; + + u32 hibern8_exit_cnt; + ktime_t last_hibern8_exit_tstamp; + struct ufs_event_hist event[UFS_EVT_CNT]; +}; + +/** + * enum ufshcd_state - UFS host controller state + * @UFSHCD_STATE_RESET: Link is not operational. Postpone SCSI command + * processing. + * @UFSHCD_STATE_OPERATIONAL: The host controller is operational and can process + * SCSI commands. + * @UFSHCD_STATE_EH_SCHEDULED_NON_FATAL: The error handler has been scheduled. + * SCSI commands may be submitted to the controller. + * @UFSHCD_STATE_EH_SCHEDULED_FATAL: The error handler has been scheduled. Fail + * newly submitted SCSI commands with error code DID_BAD_TARGET. + * @UFSHCD_STATE_ERROR: An unrecoverable error occurred, e.g. link recovery + * failed. Fail all SCSI commands with error code DID_ERROR. + */ +enum ufshcd_state { + UFSHCD_STATE_RESET, + UFSHCD_STATE_OPERATIONAL, + UFSHCD_STATE_EH_SCHEDULED_NON_FATAL, + UFSHCD_STATE_EH_SCHEDULED_FATAL, + UFSHCD_STATE_ERROR, +}; + +enum ufshcd_quirks { + /* Interrupt aggregation support is broken */ + UFSHCD_QUIRK_BROKEN_INTR_AGGR = 1 << 0, + + /* + * delay before each dme command is required as the unipro + * layer has shown instabilities + */ + UFSHCD_QUIRK_DELAY_BEFORE_DME_CMDS = 1 << 1, + + /* + * If UFS host controller is having issue in processing LCC (Line + * Control Command) coming from device then enable this quirk. + * When this quirk is enabled, host controller driver should disable + * the LCC transmission on UFS device (by clearing TX_LCC_ENABLE + * attribute of device to 0). + */ + UFSHCD_QUIRK_BROKEN_LCC = 1 << 2, + + /* + * The attribute PA_RXHSUNTERMCAP specifies whether or not the + * inbound Link supports unterminated line in HS mode. Setting this + * attribute to 1 fixes moving to HS gear. + */ + UFSHCD_QUIRK_BROKEN_PA_RXHSUNTERMCAP = 1 << 3, + + /* + * This quirk needs to be enabled if the host controller only allows + * accessing the peer dme attributes in AUTO mode (FAST AUTO or + * SLOW AUTO). + */ + UFSHCD_QUIRK_DME_PEER_ACCESS_AUTO_MODE = 1 << 4, + + /* + * This quirk needs to be enabled if the host controller doesn't + * advertise the correct version in UFS_VER register. If this quirk + * is enabled, standard UFS host driver will call the vendor specific + * ops (get_ufs_hci_version) to get the correct version. + */ + UFSHCD_QUIRK_BROKEN_UFS_HCI_VERSION = 1 << 5, + + /* + * Clear handling for transfer/task request list is just opposite. + */ + UFSHCI_QUIRK_BROKEN_REQ_LIST_CLR = 1 << 6, + + /* + * This quirk needs to be enabled if host controller doesn't allow + * that the interrupt aggregation timer and counter are reset by s/w. + */ + UFSHCI_QUIRK_SKIP_RESET_INTR_AGGR = 1 << 7, + + /* + * This quirks needs to be enabled if host controller cannot be + * enabled via HCE register. + */ + UFSHCI_QUIRK_BROKEN_HCE = 1 << 8, + + /* + * This quirk needs to be enabled if the host controller regards + * resolution of the values of PRDTO and PRDTL in UTRD as byte. + */ + UFSHCD_QUIRK_PRDT_BYTE_GRAN = 1 << 9, + + /* + * This quirk needs to be enabled if the host controller reports + * OCS FATAL ERROR with device error through sense data + */ + UFSHCD_QUIRK_BROKEN_OCS_FATAL_ERROR = 1 << 10, + + /* + * This quirk needs to be enabled if the host controller has + * auto-hibernate capability but it doesn't work. + */ + UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8 = 1 << 11, + + /* + * This quirk needs to disable manual flush for write booster + */ + UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL = 1 << 12, + + /* + * This quirk needs to disable unipro timeout values + * before power mode change + */ + UFSHCD_QUIRK_SKIP_DEF_UNIPRO_TIMEOUT_SETTING = 1 << 13, + + /* + * This quirk allows only sg entries aligned with page size. + */ + UFSHCD_QUIRK_ALIGN_SG_WITH_PAGE_SIZE = 1 << 14, + + /* + * This quirk needs to be enabled if the host controller does not + * support UIC command + */ + UFSHCD_QUIRK_BROKEN_UIC_CMD = 1 << 15, + + /* + * This quirk needs to be enabled if the host controller cannot + * support physical host configuration. + */ + UFSHCD_QUIRK_SKIP_PH_CONFIGURATION = 1 << 16, +}; + +enum ufshcd_caps { + /* Allow dynamic clk gating */ + UFSHCD_CAP_CLK_GATING = 1 << 0, + + /* Allow hiberb8 with clk gating */ + UFSHCD_CAP_HIBERN8_WITH_CLK_GATING = 1 << 1, + + /* Allow dynamic clk scaling */ + UFSHCD_CAP_CLK_SCALING = 1 << 2, + + /* Allow auto bkops to enabled during runtime suspend */ + UFSHCD_CAP_AUTO_BKOPS_SUSPEND = 1 << 3, + + /* + * This capability allows host controller driver to use the UFS HCI's + * interrupt aggregation capability. + * CAUTION: Enabling this might reduce overall UFS throughput. + */ + UFSHCD_CAP_INTR_AGGR = 1 << 4, + + /* + * This capability allows the device auto-bkops to be always enabled + * except during suspend (both runtime and suspend). + * Enabling this capability means that device will always be allowed + * to do background operation when it's active but it might degrade + * the performance of ongoing read/write operations. + */ + UFSHCD_CAP_KEEP_AUTO_BKOPS_ENABLED_EXCEPT_SUSPEND = 1 << 5, + + /* + * This capability allows host controller driver to automatically + * enable runtime power management by itself instead of waiting + * for userspace to control the power management. + */ + UFSHCD_CAP_RPM_AUTOSUSPEND = 1 << 6, + + /* + * This capability allows the host controller driver to turn-on + * WriteBooster, if the underlying device supports it and is + * provisioned to be used. This would increase the write performance. + */ + UFSHCD_CAP_WB_EN = 1 << 7, + + /* + * This capability allows the host controller driver to use the + * inline crypto engine, if it is present + */ + UFSHCD_CAP_CRYPTO = 1 << 8, + + /* + * This capability allows the controller regulators to be put into + * lpm mode aggressively during clock gating. + * This would increase power savings. + */ + UFSHCD_CAP_AGGR_POWER_COLLAPSE = 1 << 9, + + /* + * This capability allows the host controller driver to use DeepSleep, + * if it is supported by the UFS device. The host controller driver must + * support device hardware reset via the hba->device_reset() callback, + * in order to exit DeepSleep state. + */ + UFSHCD_CAP_DEEPSLEEP = 1 << 10, + + /* + * This capability allows the host controller driver to use temperature + * notification if it is supported by the UFS device. + */ + UFSHCD_CAP_TEMP_NOTIF = 1 << 11, +}; + +struct ufs_hba_variant_params { + struct devfreq_dev_profile devfreq_profile; + struct devfreq_simple_ondemand_data ondemand_data; + u16 hba_enable_delay_us; + u32 wb_flush_threshold; +}; + +#ifdef CONFIG_SCSI_UFS_HPB +/** + * struct ufshpb_dev_info - UFSHPB device related info + * @num_lu: the number of user logical unit to check whether all lu finished + * initialization + * @rgn_size: device reported HPB region size + * @srgn_size: device reported HPB sub-region size + * @slave_conf_cnt: counter to check all lu finished initialization + * @hpb_disabled: flag to check if HPB is disabled + * @max_hpb_single_cmd: device reported bMAX_DATA_SIZE_FOR_SINGLE_CMD value + * @is_legacy: flag to check HPB 1.0 + * @control_mode: either host or device + */ +struct ufshpb_dev_info { + int num_lu; + int rgn_size; + int srgn_size; + atomic_t slave_conf_cnt; + bool hpb_disabled; + u8 max_hpb_single_cmd; + bool is_legacy; + u8 control_mode; +}; +#endif + +struct ufs_hba_monitor { + unsigned long chunk_size; + + unsigned long nr_sec_rw[2]; + ktime_t total_busy[2]; + + unsigned long nr_req[2]; + /* latencies*/ + ktime_t lat_sum[2]; + ktime_t lat_max[2]; + ktime_t lat_min[2]; + + u32 nr_queued[2]; + ktime_t busy_start_ts[2]; + + ktime_t enabled_ts; + bool enabled; +}; + +/** + * struct ufs_hba - per adapter private structure + * @mmio_base: UFSHCI base register address + * @ucdl_base_addr: UFS Command Descriptor base address + * @utrdl_base_addr: UTP Transfer Request Descriptor base address + * @utmrdl_base_addr: UTP Task Management Descriptor base address + * @ucdl_dma_addr: UFS Command Descriptor DMA address + * @utrdl_dma_addr: UTRDL DMA address + * @utmrdl_dma_addr: UTMRDL DMA address + * @host: Scsi_Host instance of the driver + * @dev: device handle + * @ufs_device_wlun: WLUN that controls the entire UFS device. + * @hwmon_device: device instance registered with the hwmon core. + * @curr_dev_pwr_mode: active UFS device power mode. + * @uic_link_state: active state of the link to the UFS device. + * @rpm_lvl: desired UFS power management level during runtime PM. + * @spm_lvl: desired UFS power management level during system PM. + * @pm_op_in_progress: whether or not a PM operation is in progress. + * @ahit: value of Auto-Hibernate Idle Timer register. + * @lrb: local reference block + * @outstanding_tasks: Bits representing outstanding task requests + * @outstanding_lock: Protects @outstanding_reqs. + * @outstanding_reqs: Bits representing outstanding transfer requests + * @capabilities: UFS Controller Capabilities + * @nutrs: Transfer Request Queue depth supported by controller + * @nutmrs: Task Management Queue depth supported by controller + * @reserved_slot: Used to submit device commands. Protected by @dev_cmd.lock. + * @ufs_version: UFS Version to which controller complies + * @vops: pointer to variant specific operations + * @vps: pointer to variant specific parameters + * @priv: pointer to variant specific private data + * @irq: Irq number of the controller + * @is_irq_enabled: whether or not the UFS controller interrupt is enabled. + * @dev_ref_clk_freq: reference clock frequency + * @quirks: bitmask with information about deviations from the UFSHCI standard. + * @dev_quirks: bitmask with information about deviations from the UFS standard. + * @tmf_tag_set: TMF tag set. + * @tmf_queue: Used to allocate TMF tags. + * @tmf_rqs: array with pointers to TMF requests while these are in progress. + * @active_uic_cmd: handle of active UIC command + * @uic_cmd_mutex: mutex for UIC command + * @uic_async_done: completion used during UIC processing + * @ufshcd_state: UFSHCD state + * @eh_flags: Error handling flags + * @intr_mask: Interrupt Mask Bits + * @ee_ctrl_mask: Exception event control mask + * @ee_drv_mask: Exception event mask for driver + * @ee_usr_mask: Exception event mask for user (set via debugfs) + * @ee_ctrl_mutex: Used to serialize exception event information. + * @is_powered: flag to check if HBA is powered + * @shutting_down: flag to check if shutdown has been invoked + * @host_sem: semaphore used to serialize concurrent contexts + * @eh_wq: Workqueue that eh_work works on + * @eh_work: Worker to handle UFS errors that require s/w attention + * @eeh_work: Worker to handle exception events + * @errors: HBA errors + * @uic_error: UFS interconnect layer error status + * @saved_err: sticky error mask + * @saved_uic_err: sticky UIC error mask + * @ufs_stats: various error counters + * @force_reset: flag to force eh_work perform a full reset + * @force_pmc: flag to force a power mode change + * @silence_err_logs: flag to silence error logs + * @dev_cmd: ufs device management command information + * @last_dme_cmd_tstamp: time stamp of the last completed DME command + * @nop_out_timeout: NOP OUT timeout value + * @dev_info: information about the UFS device + * @auto_bkops_enabled: to track whether bkops is enabled in device + * @vreg_info: UFS device voltage regulator information + * @clk_list_head: UFS host controller clocks list node head + * @req_abort_count: number of times ufshcd_abort() has been called + * @lanes_per_direction: number of lanes per data direction between the UFS + * controller and the UFS device. + * @pwr_info: holds current power mode + * @max_pwr_info: keeps the device max valid pwm + * @clk_gating: information related to clock gating + * @caps: bitmask with information about UFS controller capabilities + * @devfreq: frequency scaling information owned by the devfreq core + * @clk_scaling: frequency scaling information owned by the UFS driver + * @is_sys_suspended: whether or not the entire system has been suspended + * @urgent_bkops_lvl: keeps track of urgent bkops level for device + * @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for + * device is known or not. + * @clk_scaling_lock: used to serialize device commands and clock scaling + * @desc_size: descriptor sizes reported by device + * @scsi_block_reqs_cnt: reference counting for scsi block requests + * @bsg_dev: struct device associated with the BSG queue + * @bsg_queue: BSG queue associated with the UFS controller + * @rpm_dev_flush_recheck_work: used to suspend from RPM (runtime power + * management) after the UFS device has finished a WriteBooster buffer + * flush or auto BKOP. + * @ufshpb_dev: information related to HPB (Host Performance Booster). + * @monitor: statistics about UFS commands + * @crypto_capabilities: Content of crypto capabilities register (0x100) + * @crypto_cap_array: Array of crypto capabilities + * @crypto_cfg_register: Start of the crypto cfg array + * @crypto_profile: the crypto profile of this hba (if applicable) + * @debugfs_root: UFS controller debugfs root directory + * @debugfs_ee_work: used to restore ee_ctrl_mask after a delay + * @debugfs_ee_rate_limit_ms: user configurable delay after which to restore + * ee_ctrl_mask + * @luns_avail: number of regular and well known LUNs supported by the UFS + * device + * @complete_put: whether or not to call ufshcd_rpm_put() from inside + * ufshcd_resume_complete() + */ +struct ufs_hba { + void __iomem *mmio_base; + + /* Virtual memory reference */ + struct utp_transfer_cmd_desc *ucdl_base_addr; + struct utp_transfer_req_desc *utrdl_base_addr; + struct utp_task_req_desc *utmrdl_base_addr; + + /* DMA memory reference */ + dma_addr_t ucdl_dma_addr; + dma_addr_t utrdl_dma_addr; + dma_addr_t utmrdl_dma_addr; + + struct Scsi_Host *host; + struct device *dev; + struct scsi_device *ufs_device_wlun; + +#ifdef CONFIG_SCSI_UFS_HWMON + struct device *hwmon_device; +#endif + + enum ufs_dev_pwr_mode curr_dev_pwr_mode; + enum uic_link_state uic_link_state; + /* Desired UFS power management level during runtime PM */ + enum ufs_pm_level rpm_lvl; + /* Desired UFS power management level during system PM */ + enum ufs_pm_level spm_lvl; + int pm_op_in_progress; + + /* Auto-Hibernate Idle Timer register value */ + u32 ahit; + + struct ufshcd_lrb *lrb; + + unsigned long outstanding_tasks; + spinlock_t outstanding_lock; + unsigned long outstanding_reqs; + + u32 capabilities; + int nutrs; + int nutmrs; + u32 reserved_slot; + u32 ufs_version; + const struct ufs_hba_variant_ops *vops; + struct ufs_hba_variant_params *vps; + void *priv; + unsigned int irq; + bool is_irq_enabled; + enum ufs_ref_clk_freq dev_ref_clk_freq; + + unsigned int quirks; /* Deviations from standard UFSHCI spec. */ + + /* Device deviations from standard UFS device spec. */ + unsigned int dev_quirks; + + struct blk_mq_tag_set tmf_tag_set; + struct request_queue *tmf_queue; + struct request **tmf_rqs; + + struct uic_command *active_uic_cmd; + struct mutex uic_cmd_mutex; + struct completion *uic_async_done; + + enum ufshcd_state ufshcd_state; + u32 eh_flags; + u32 intr_mask; + u16 ee_ctrl_mask; + u16 ee_drv_mask; + u16 ee_usr_mask; + struct mutex ee_ctrl_mutex; + bool is_powered; + bool shutting_down; + struct semaphore host_sem; + + /* Work Queues */ + struct workqueue_struct *eh_wq; + struct work_struct eh_work; + struct work_struct eeh_work; + + /* HBA Errors */ + u32 errors; + u32 uic_error; + u32 saved_err; + u32 saved_uic_err; + struct ufs_stats ufs_stats; + bool force_reset; + bool force_pmc; + bool silence_err_logs; + + /* Device management request data */ + struct ufs_dev_cmd dev_cmd; + ktime_t last_dme_cmd_tstamp; + int nop_out_timeout; + + /* Keeps information of the UFS device connected to this host */ + struct ufs_dev_info dev_info; + bool auto_bkops_enabled; + struct ufs_vreg_info vreg_info; + struct list_head clk_list_head; + + /* Number of requests aborts */ + int req_abort_count; + + /* Number of lanes available (1 or 2) for Rx/Tx */ + u32 lanes_per_direction; + struct ufs_pa_layer_attr pwr_info; + struct ufs_pwr_mode_info max_pwr_info; + + struct ufs_clk_gating clk_gating; + /* Control to enable/disable host capabilities */ + u32 caps; + + struct devfreq *devfreq; + struct ufs_clk_scaling clk_scaling; + bool is_sys_suspended; + + enum bkops_status urgent_bkops_lvl; + bool is_urgent_bkops_lvl_checked; + + struct rw_semaphore clk_scaling_lock; + unsigned char desc_size[QUERY_DESC_IDN_MAX]; + atomic_t scsi_block_reqs_cnt; + + struct device bsg_dev; + struct request_queue *bsg_queue; + struct delayed_work rpm_dev_flush_recheck_work; + +#ifdef CONFIG_SCSI_UFS_HPB + struct ufshpb_dev_info ufshpb_dev; +#endif + + struct ufs_hba_monitor monitor; + +#ifdef CONFIG_SCSI_UFS_CRYPTO + union ufs_crypto_capabilities crypto_capabilities; + union ufs_crypto_cap_entry *crypto_cap_array; + u32 crypto_cfg_register; + struct blk_crypto_profile crypto_profile; +#endif +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs_root; + struct delayed_work debugfs_ee_work; + u32 debugfs_ee_rate_limit_ms; +#endif + u32 luns_avail; + bool complete_put; +}; + +/* Returns true if clocks can be gated. Otherwise false */ +static inline bool ufshcd_is_clkgating_allowed(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_CLK_GATING; +} +static inline bool ufshcd_can_hibern8_during_gating(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_HIBERN8_WITH_CLK_GATING; +} +static inline int ufshcd_is_clkscaling_supported(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_CLK_SCALING; +} +static inline bool ufshcd_can_autobkops_during_suspend(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_AUTO_BKOPS_SUSPEND; +} +static inline bool ufshcd_is_rpm_autosuspend_allowed(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_RPM_AUTOSUSPEND; +} + +static inline bool ufshcd_is_intr_aggr_allowed(struct ufs_hba *hba) +{ + return (hba->caps & UFSHCD_CAP_INTR_AGGR) && + !(hba->quirks & UFSHCD_QUIRK_BROKEN_INTR_AGGR); +} + +static inline bool ufshcd_can_aggressive_pc(struct ufs_hba *hba) +{ + return !!(ufshcd_is_link_hibern8(hba) && + (hba->caps & UFSHCD_CAP_AGGR_POWER_COLLAPSE)); +} + +static inline bool ufshcd_is_auto_hibern8_supported(struct ufs_hba *hba) +{ + return (hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT) && + !(hba->quirks & UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8); +} + +static inline bool ufshcd_is_auto_hibern8_enabled(struct ufs_hba *hba) +{ + return FIELD_GET(UFSHCI_AHIBERN8_TIMER_MASK, hba->ahit); +} + +static inline bool ufshcd_is_wb_allowed(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_WB_EN; +} + +#define ufshcd_writel(hba, val, reg) \ + writel((val), (hba)->mmio_base + (reg)) +#define ufshcd_readl(hba, reg) \ + readl((hba)->mmio_base + (reg)) + +/** + * ufshcd_rmwl - perform read/modify/write for a controller register + * @hba: per adapter instance + * @mask: mask to apply on read value + * @val: actual value to write + * @reg: register address + */ +static inline void ufshcd_rmwl(struct ufs_hba *hba, u32 mask, u32 val, u32 reg) +{ + u32 tmp; + + tmp = ufshcd_readl(hba, reg); + tmp &= ~mask; + tmp |= (val & mask); + ufshcd_writel(hba, tmp, reg); +} + +int ufshcd_alloc_host(struct device *, struct ufs_hba **); +void ufshcd_dealloc_host(struct ufs_hba *); +int ufshcd_hba_enable(struct ufs_hba *hba); +int ufshcd_init(struct ufs_hba *, void __iomem *, unsigned int); +int ufshcd_link_recovery(struct ufs_hba *hba); +int ufshcd_make_hba_operational(struct ufs_hba *hba); +void ufshcd_remove(struct ufs_hba *); +int ufshcd_uic_hibern8_enter(struct ufs_hba *hba); +int ufshcd_uic_hibern8_exit(struct ufs_hba *hba); +void ufshcd_delay_us(unsigned long us, unsigned long tolerance); +void ufshcd_parse_dev_ref_clk_freq(struct ufs_hba *hba, struct clk *refclk); +void ufshcd_update_evt_hist(struct ufs_hba *hba, u32 id, u32 val); +void ufshcd_hba_stop(struct ufs_hba *hba); +void ufshcd_schedule_eh_work(struct ufs_hba *hba); + +static inline void check_upiu_size(void) +{ + BUILD_BUG_ON(ALIGNED_UPIU_SIZE < + GENERAL_UPIU_REQUEST_SIZE + QUERY_DESC_MAX_SIZE); +} + +/** + * ufshcd_set_variant - set variant specific data to the hba + * @hba: per adapter instance + * @variant: pointer to variant specific data + */ +static inline void ufshcd_set_variant(struct ufs_hba *hba, void *variant) +{ + BUG_ON(!hba); + hba->priv = variant; +} + +/** + * ufshcd_get_variant - get variant specific data from the hba + * @hba: per adapter instance + */ +static inline void *ufshcd_get_variant(struct ufs_hba *hba) +{ + BUG_ON(!hba); + return hba->priv; +} + +#ifdef CONFIG_PM +extern int ufshcd_runtime_suspend(struct device *dev); +extern int ufshcd_runtime_resume(struct device *dev); +#endif +#ifdef CONFIG_PM_SLEEP +extern int ufshcd_system_suspend(struct device *dev); +extern int ufshcd_system_resume(struct device *dev); +#endif +extern int ufshcd_shutdown(struct ufs_hba *hba); +extern int ufshcd_dme_configure_adapt(struct ufs_hba *hba, + int agreed_gear, + int adapt_val); +extern int ufshcd_dme_set_attr(struct ufs_hba *hba, u32 attr_sel, + u8 attr_set, u32 mib_val, u8 peer); +extern int ufshcd_dme_get_attr(struct ufs_hba *hba, u32 attr_sel, + u32 *mib_val, u8 peer); +extern int ufshcd_config_pwr_mode(struct ufs_hba *hba, + struct ufs_pa_layer_attr *desired_pwr_mode); + +/* UIC command interfaces for DME primitives */ +#define DME_LOCAL 0 +#define DME_PEER 1 +#define ATTR_SET_NOR 0 /* NORMAL */ +#define ATTR_SET_ST 1 /* STATIC */ + +static inline int ufshcd_dme_set(struct ufs_hba *hba, u32 attr_sel, + u32 mib_val) +{ + return ufshcd_dme_set_attr(hba, attr_sel, ATTR_SET_NOR, + mib_val, DME_LOCAL); +} + +static inline int ufshcd_dme_st_set(struct ufs_hba *hba, u32 attr_sel, + u32 mib_val) +{ + return ufshcd_dme_set_attr(hba, attr_sel, ATTR_SET_ST, + mib_val, DME_LOCAL); +} + +static inline int ufshcd_dme_peer_set(struct ufs_hba *hba, u32 attr_sel, + u32 mib_val) +{ + return ufshcd_dme_set_attr(hba, attr_sel, ATTR_SET_NOR, + mib_val, DME_PEER); +} + +static inline int ufshcd_dme_peer_st_set(struct ufs_hba *hba, u32 attr_sel, + u32 mib_val) +{ + return ufshcd_dme_set_attr(hba, attr_sel, ATTR_SET_ST, + mib_val, DME_PEER); +} + +static inline int ufshcd_dme_get(struct ufs_hba *hba, + u32 attr_sel, u32 *mib_val) +{ + return ufshcd_dme_get_attr(hba, attr_sel, mib_val, DME_LOCAL); +} + +static inline int ufshcd_dme_peer_get(struct ufs_hba *hba, + u32 attr_sel, u32 *mib_val) +{ + return ufshcd_dme_get_attr(hba, attr_sel, mib_val, DME_PEER); +} + +static inline bool ufshcd_is_hs_mode(struct ufs_pa_layer_attr *pwr_info) +{ + return (pwr_info->pwr_rx == FAST_MODE || + pwr_info->pwr_rx == FASTAUTO_MODE) && + (pwr_info->pwr_tx == FAST_MODE || + pwr_info->pwr_tx == FASTAUTO_MODE); +} + +static inline int ufshcd_disable_host_tx_lcc(struct ufs_hba *hba) +{ + return ufshcd_dme_set(hba, UIC_ARG_MIB(PA_LOCAL_TX_LCC_ENABLE), 0); +} + +/* Expose Query-Request API */ +int ufshcd_query_descriptor_retry(struct ufs_hba *hba, + enum query_opcode opcode, + enum desc_idn idn, u8 index, + u8 selector, + u8 *desc_buf, int *buf_len); +int ufshcd_read_desc_param(struct ufs_hba *hba, + enum desc_idn desc_id, + int desc_index, + u8 param_offset, + u8 *param_read_buf, + u8 param_size); +int ufshcd_query_attr_retry(struct ufs_hba *hba, enum query_opcode opcode, + enum attr_idn idn, u8 index, u8 selector, + u32 *attr_val); +int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode, + enum attr_idn idn, u8 index, u8 selector, u32 *attr_val); +int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode, + enum flag_idn idn, u8 index, bool *flag_res); + +void ufshcd_auto_hibern8_enable(struct ufs_hba *hba); +void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit); +void ufshcd_fixup_dev_quirks(struct ufs_hba *hba, + const struct ufs_dev_quirk *fixups); +#define SD_ASCII_STD true +#define SD_RAW false +int ufshcd_read_string_desc(struct ufs_hba *hba, u8 desc_index, + u8 **buf, bool ascii); + +int ufshcd_hold(struct ufs_hba *hba, bool async); +void ufshcd_release(struct ufs_hba *hba); + +void ufshcd_clkgate_delay_set(struct device *dev, unsigned long value); + +void ufshcd_map_desc_id_to_length(struct ufs_hba *hba, enum desc_idn desc_id, + int *desc_length); + +u32 ufshcd_get_local_unipro_ver(struct ufs_hba *hba); + +int ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd); + +int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba, + struct utp_upiu_req *req_upiu, + struct utp_upiu_req *rsp_upiu, + int msgcode, + u8 *desc_buff, int *buff_len, + enum query_opcode desc_op); + +int ufshcd_wb_toggle(struct ufs_hba *hba, bool enable); +int ufshcd_suspend_prepare(struct device *dev); +int __ufshcd_suspend_prepare(struct device *dev, bool rpm_ok_for_spm); +void ufshcd_resume_complete(struct device *dev); + +/* Wrapper functions for safely calling variant operations */ +static inline int ufshcd_vops_init(struct ufs_hba *hba) +{ + if (hba->vops && hba->vops->init) + return hba->vops->init(hba); + + return 0; +} + +static inline int ufshcd_vops_phy_initialization(struct ufs_hba *hba) +{ + if (hba->vops && hba->vops->phy_initialization) + return hba->vops->phy_initialization(hba); + + return 0; +} + +extern struct ufs_pm_lvl_states ufs_pm_lvl_states[]; + +int ufshcd_dump_regs(struct ufs_hba *hba, size_t offset, size_t len, + const char *prefix); + +int __ufshcd_write_ee_control(struct ufs_hba *hba, u32 ee_ctrl_mask); +int ufshcd_write_ee_control(struct ufs_hba *hba); +int ufshcd_update_ee_control(struct ufs_hba *hba, u16 *mask, u16 *other_mask, + u16 set, u16 clr); + +#endif /* End of Header */ diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h new file mode 100644 index 000000000000..f81aa95ffbc4 --- /dev/null +++ b/include/ufs/ufshci.h @@ -0,0 +1,510 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Universal Flash Storage Host controller driver + * Copyright (C) 2011-2013 Samsung India Software Operations + * + * Authors: + * Santosh Yaraganavi + * Vinayak Holikatti + */ + +#ifndef _UFSHCI_H +#define _UFSHCI_H + +#include + +enum { + TASK_REQ_UPIU_SIZE_DWORDS = 8, + TASK_RSP_UPIU_SIZE_DWORDS = 8, + ALIGNED_UPIU_SIZE = 512, +}; + +/* UFSHCI Registers */ +enum { + REG_CONTROLLER_CAPABILITIES = 0x00, + REG_UFS_VERSION = 0x08, + REG_CONTROLLER_DEV_ID = 0x10, + REG_CONTROLLER_PROD_ID = 0x14, + REG_AUTO_HIBERNATE_IDLE_TIMER = 0x18, + REG_INTERRUPT_STATUS = 0x20, + REG_INTERRUPT_ENABLE = 0x24, + REG_CONTROLLER_STATUS = 0x30, + REG_CONTROLLER_ENABLE = 0x34, + REG_UIC_ERROR_CODE_PHY_ADAPTER_LAYER = 0x38, + REG_UIC_ERROR_CODE_DATA_LINK_LAYER = 0x3C, + REG_UIC_ERROR_CODE_NETWORK_LAYER = 0x40, + REG_UIC_ERROR_CODE_TRANSPORT_LAYER = 0x44, + REG_UIC_ERROR_CODE_DME = 0x48, + REG_UTP_TRANSFER_REQ_INT_AGG_CONTROL = 0x4C, + REG_UTP_TRANSFER_REQ_LIST_BASE_L = 0x50, + REG_UTP_TRANSFER_REQ_LIST_BASE_H = 0x54, + REG_UTP_TRANSFER_REQ_DOOR_BELL = 0x58, + REG_UTP_TRANSFER_REQ_LIST_CLEAR = 0x5C, + REG_UTP_TRANSFER_REQ_LIST_RUN_STOP = 0x60, + REG_UTP_TASK_REQ_LIST_BASE_L = 0x70, + REG_UTP_TASK_REQ_LIST_BASE_H = 0x74, + REG_UTP_TASK_REQ_DOOR_BELL = 0x78, + REG_UTP_TASK_REQ_LIST_CLEAR = 0x7C, + REG_UTP_TASK_REQ_LIST_RUN_STOP = 0x80, + REG_UIC_COMMAND = 0x90, + REG_UIC_COMMAND_ARG_1 = 0x94, + REG_UIC_COMMAND_ARG_2 = 0x98, + REG_UIC_COMMAND_ARG_3 = 0x9C, + + UFSHCI_REG_SPACE_SIZE = 0xA0, + + REG_UFS_CCAP = 0x100, + REG_UFS_CRYPTOCAP = 0x104, + + UFSHCI_CRYPTO_REG_SPACE_SIZE = 0x400, +}; + +/* Controller capability masks */ +enum { + MASK_TRANSFER_REQUESTS_SLOTS = 0x0000001F, + MASK_TASK_MANAGEMENT_REQUEST_SLOTS = 0x00070000, + MASK_AUTO_HIBERN8_SUPPORT = 0x00800000, + MASK_64_ADDRESSING_SUPPORT = 0x01000000, + MASK_OUT_OF_ORDER_DATA_DELIVERY_SUPPORT = 0x02000000, + MASK_UIC_DME_TEST_MODE_SUPPORT = 0x04000000, + MASK_CRYPTO_SUPPORT = 0x10000000, +}; + +#define UFS_MASK(mask, offset) ((mask) << (offset)) + +/* UFS Version 08h */ +#define MINOR_VERSION_NUM_MASK UFS_MASK(0xFFFF, 0) +#define MAJOR_VERSION_NUM_MASK UFS_MASK(0xFFFF, 16) + +/* + * Controller UFSHCI version + * - 2.x and newer use the following scheme: + * major << 8 + minor << 4 + * - 1.x has been converted to match this in + * ufshcd_get_ufs_version() + */ +static inline u32 ufshci_version(u32 major, u32 minor) +{ + return (major << 8) + (minor << 4); +} + +/* + * HCDDID - Host Controller Identification Descriptor + * - Device ID and Device Class 10h + */ +#define DEVICE_CLASS UFS_MASK(0xFFFF, 0) +#define DEVICE_ID UFS_MASK(0xFF, 24) + +/* + * HCPMID - Host Controller Identification Descriptor + * - Product/Manufacturer ID 14h + */ +#define MANUFACTURE_ID_MASK UFS_MASK(0xFFFF, 0) +#define PRODUCT_ID_MASK UFS_MASK(0xFFFF, 16) + +/* AHIT - Auto-Hibernate Idle Timer */ +#define UFSHCI_AHIBERN8_TIMER_MASK GENMASK(9, 0) +#define UFSHCI_AHIBERN8_SCALE_MASK GENMASK(12, 10) +#define UFSHCI_AHIBERN8_SCALE_FACTOR 10 +#define UFSHCI_AHIBERN8_MAX (1023 * 100000) + +/* + * IS - Interrupt Status - 20h + */ +#define UTP_TRANSFER_REQ_COMPL 0x1 +#define UIC_DME_END_PT_RESET 0x2 +#define UIC_ERROR 0x4 +#define UIC_TEST_MODE 0x8 +#define UIC_POWER_MODE 0x10 +#define UIC_HIBERNATE_EXIT 0x20 +#define UIC_HIBERNATE_ENTER 0x40 +#define UIC_LINK_LOST 0x80 +#define UIC_LINK_STARTUP 0x100 +#define UTP_TASK_REQ_COMPL 0x200 +#define UIC_COMMAND_COMPL 0x400 +#define DEVICE_FATAL_ERROR 0x800 +#define CONTROLLER_FATAL_ERROR 0x10000 +#define SYSTEM_BUS_FATAL_ERROR 0x20000 +#define CRYPTO_ENGINE_FATAL_ERROR 0x40000 + +#define UFSHCD_UIC_HIBERN8_MASK (UIC_HIBERNATE_ENTER |\ + UIC_HIBERNATE_EXIT) + +#define UFSHCD_UIC_PWR_MASK (UFSHCD_UIC_HIBERN8_MASK |\ + UIC_POWER_MODE) + +#define UFSHCD_UIC_MASK (UIC_COMMAND_COMPL | UFSHCD_UIC_PWR_MASK) + +#define UFSHCD_ERROR_MASK (UIC_ERROR |\ + DEVICE_FATAL_ERROR |\ + CONTROLLER_FATAL_ERROR |\ + SYSTEM_BUS_FATAL_ERROR |\ + CRYPTO_ENGINE_FATAL_ERROR) + +#define INT_FATAL_ERRORS (DEVICE_FATAL_ERROR |\ + CONTROLLER_FATAL_ERROR |\ + SYSTEM_BUS_FATAL_ERROR |\ + CRYPTO_ENGINE_FATAL_ERROR |\ + UIC_LINK_LOST) + +/* HCS - Host Controller Status 30h */ +#define DEVICE_PRESENT 0x1 +#define UTP_TRANSFER_REQ_LIST_READY 0x2 +#define UTP_TASK_REQ_LIST_READY 0x4 +#define UIC_COMMAND_READY 0x8 +#define HOST_ERROR_INDICATOR 0x10 +#define DEVICE_ERROR_INDICATOR 0x20 +#define UIC_POWER_MODE_CHANGE_REQ_STATUS_MASK UFS_MASK(0x7, 8) + +#define UFSHCD_STATUS_READY (UTP_TRANSFER_REQ_LIST_READY |\ + UTP_TASK_REQ_LIST_READY |\ + UIC_COMMAND_READY) + +enum { + PWR_OK = 0x0, + PWR_LOCAL = 0x01, + PWR_REMOTE = 0x02, + PWR_BUSY = 0x03, + PWR_ERROR_CAP = 0x04, + PWR_FATAL_ERROR = 0x05, +}; + +/* HCE - Host Controller Enable 34h */ +#define CONTROLLER_ENABLE 0x1 +#define CONTROLLER_DISABLE 0x0 +#define CRYPTO_GENERAL_ENABLE 0x2 + +/* UECPA - Host UIC Error Code PHY Adapter Layer 38h */ +#define UIC_PHY_ADAPTER_LAYER_ERROR 0x80000000 +#define UIC_PHY_ADAPTER_LAYER_ERROR_CODE_MASK 0x1F +#define UIC_PHY_ADAPTER_LAYER_LANE_ERR_MASK 0xF +#define UIC_PHY_ADAPTER_LAYER_GENERIC_ERROR 0x10 + +/* UECDL - Host UIC Error Code Data Link Layer 3Ch */ +#define UIC_DATA_LINK_LAYER_ERROR 0x80000000 +#define UIC_DATA_LINK_LAYER_ERROR_CODE_MASK 0xFFFF +#define UIC_DATA_LINK_LAYER_ERROR_TCX_REP_TIMER_EXP 0x2 +#define UIC_DATA_LINK_LAYER_ERROR_AFCX_REQ_TIMER_EXP 0x4 +#define UIC_DATA_LINK_LAYER_ERROR_FCX_PRO_TIMER_EXP 0x8 +#define UIC_DATA_LINK_LAYER_ERROR_RX_BUF_OF 0x20 +#define UIC_DATA_LINK_LAYER_ERROR_PA_INIT 0x2000 +#define UIC_DATA_LINK_LAYER_ERROR_NAC_RECEIVED 0x0001 +#define UIC_DATA_LINK_LAYER_ERROR_TCx_REPLAY_TIMEOUT 0x0002 + +/* UECN - Host UIC Error Code Network Layer 40h */ +#define UIC_NETWORK_LAYER_ERROR 0x80000000 +#define UIC_NETWORK_LAYER_ERROR_CODE_MASK 0x7 +#define UIC_NETWORK_UNSUPPORTED_HEADER_TYPE 0x1 +#define UIC_NETWORK_BAD_DEVICEID_ENC 0x2 +#define UIC_NETWORK_LHDR_TRAP_PACKET_DROPPING 0x4 + +/* UECT - Host UIC Error Code Transport Layer 44h */ +#define UIC_TRANSPORT_LAYER_ERROR 0x80000000 +#define UIC_TRANSPORT_LAYER_ERROR_CODE_MASK 0x7F +#define UIC_TRANSPORT_UNSUPPORTED_HEADER_TYPE 0x1 +#define UIC_TRANSPORT_UNKNOWN_CPORTID 0x2 +#define UIC_TRANSPORT_NO_CONNECTION_RX 0x4 +#define UIC_TRANSPORT_CONTROLLED_SEGMENT_DROPPING 0x8 +#define UIC_TRANSPORT_BAD_TC 0x10 +#define UIC_TRANSPORT_E2E_CREDIT_OVERFOW 0x20 +#define UIC_TRANSPORT_SAFETY_VALUE_DROPPING 0x40 + +/* UECDME - Host UIC Error Code DME 48h */ +#define UIC_DME_ERROR 0x80000000 +#define UIC_DME_ERROR_CODE_MASK 0x1 + +/* UTRIACR - Interrupt Aggregation control register - 0x4Ch */ +#define INT_AGGR_TIMEOUT_VAL_MASK 0xFF +#define INT_AGGR_COUNTER_THRESHOLD_MASK UFS_MASK(0x1F, 8) +#define INT_AGGR_COUNTER_AND_TIMER_RESET 0x10000 +#define INT_AGGR_STATUS_BIT 0x100000 +#define INT_AGGR_PARAM_WRITE 0x1000000 +#define INT_AGGR_ENABLE 0x80000000 + +/* UTRLRSR - UTP Transfer Request Run-Stop Register 60h */ +#define UTP_TRANSFER_REQ_LIST_RUN_STOP_BIT 0x1 + +/* UTMRLRSR - UTP Task Management Request Run-Stop Register 80h */ +#define UTP_TASK_REQ_LIST_RUN_STOP_BIT 0x1 + +/* UICCMD - UIC Command */ +#define COMMAND_OPCODE_MASK 0xFF +#define GEN_SELECTOR_INDEX_MASK 0xFFFF + +#define MIB_ATTRIBUTE_MASK UFS_MASK(0xFFFF, 16) +#define RESET_LEVEL 0xFF + +#define ATTR_SET_TYPE_MASK UFS_MASK(0xFF, 16) +#define CONFIG_RESULT_CODE_MASK 0xFF +#define GENERIC_ERROR_CODE_MASK 0xFF + +/* GenSelectorIndex calculation macros for M-PHY attributes */ +#define UIC_ARG_MPHY_TX_GEN_SEL_INDEX(lane) (lane) +#define UIC_ARG_MPHY_RX_GEN_SEL_INDEX(lane) (PA_MAXDATALANES + (lane)) + +#define UIC_ARG_MIB_SEL(attr, sel) ((((attr) & 0xFFFF) << 16) |\ + ((sel) & 0xFFFF)) +#define UIC_ARG_MIB(attr) UIC_ARG_MIB_SEL(attr, 0) +#define UIC_ARG_ATTR_TYPE(t) (((t) & 0xFF) << 16) +#define UIC_GET_ATTR_ID(v) (((v) >> 16) & 0xFFFF) + +/* Link Status*/ +enum link_status { + UFSHCD_LINK_IS_DOWN = 1, + UFSHCD_LINK_IS_UP = 2, +}; + +/* UIC Commands */ +enum uic_cmd_dme { + UIC_CMD_DME_GET = 0x01, + UIC_CMD_DME_SET = 0x02, + UIC_CMD_DME_PEER_GET = 0x03, + UIC_CMD_DME_PEER_SET = 0x04, + UIC_CMD_DME_POWERON = 0x10, + UIC_CMD_DME_POWEROFF = 0x11, + UIC_CMD_DME_ENABLE = 0x12, + UIC_CMD_DME_RESET = 0x14, + UIC_CMD_DME_END_PT_RST = 0x15, + UIC_CMD_DME_LINK_STARTUP = 0x16, + UIC_CMD_DME_HIBER_ENTER = 0x17, + UIC_CMD_DME_HIBER_EXIT = 0x18, + UIC_CMD_DME_TEST_MODE = 0x1A, +}; + +/* UIC Config result code / Generic error code */ +enum { + UIC_CMD_RESULT_SUCCESS = 0x00, + UIC_CMD_RESULT_INVALID_ATTR = 0x01, + UIC_CMD_RESULT_FAILURE = 0x01, + UIC_CMD_RESULT_INVALID_ATTR_VALUE = 0x02, + UIC_CMD_RESULT_READ_ONLY_ATTR = 0x03, + UIC_CMD_RESULT_WRITE_ONLY_ATTR = 0x04, + UIC_CMD_RESULT_BAD_INDEX = 0x05, + UIC_CMD_RESULT_LOCKED_ATTR = 0x06, + UIC_CMD_RESULT_BAD_TEST_FEATURE_INDEX = 0x07, + UIC_CMD_RESULT_PEER_COMM_FAILURE = 0x08, + UIC_CMD_RESULT_BUSY = 0x09, + UIC_CMD_RESULT_DME_FAILURE = 0x0A, +}; + +#define MASK_UIC_COMMAND_RESULT 0xFF + +#define INT_AGGR_COUNTER_THLD_VAL(c) (((c) & 0x1F) << 8) +#define INT_AGGR_TIMEOUT_VAL(t) (((t) & 0xFF) << 0) + +/* Interrupt disable masks */ +enum { + /* Interrupt disable mask for UFSHCI v1.0 */ + INTERRUPT_MASK_ALL_VER_10 = 0x30FFF, + INTERRUPT_MASK_RW_VER_10 = 0x30000, + + /* Interrupt disable mask for UFSHCI v1.1 */ + INTERRUPT_MASK_ALL_VER_11 = 0x31FFF, + + /* Interrupt disable mask for UFSHCI v2.1 */ + INTERRUPT_MASK_ALL_VER_21 = 0x71FFF, +}; + +/* CCAP - Crypto Capability 100h */ +union ufs_crypto_capabilities { + __le32 reg_val; + struct { + u8 num_crypto_cap; + u8 config_count; + u8 reserved; + u8 config_array_ptr; + }; +}; + +enum ufs_crypto_key_size { + UFS_CRYPTO_KEY_SIZE_INVALID = 0x0, + UFS_CRYPTO_KEY_SIZE_128 = 0x1, + UFS_CRYPTO_KEY_SIZE_192 = 0x2, + UFS_CRYPTO_KEY_SIZE_256 = 0x3, + UFS_CRYPTO_KEY_SIZE_512 = 0x4, +}; + +enum ufs_crypto_alg { + UFS_CRYPTO_ALG_AES_XTS = 0x0, + UFS_CRYPTO_ALG_BITLOCKER_AES_CBC = 0x1, + UFS_CRYPTO_ALG_AES_ECB = 0x2, + UFS_CRYPTO_ALG_ESSIV_AES_CBC = 0x3, +}; + +/* x-CRYPTOCAP - Crypto Capability X */ +union ufs_crypto_cap_entry { + __le32 reg_val; + struct { + u8 algorithm_id; + u8 sdus_mask; /* Supported data unit size mask */ + u8 key_size; + u8 reserved; + }; +}; + +#define UFS_CRYPTO_CONFIGURATION_ENABLE (1 << 7) +#define UFS_CRYPTO_KEY_MAX_SIZE 64 +/* x-CRYPTOCFG - Crypto Configuration X */ +union ufs_crypto_cfg_entry { + __le32 reg_val[32]; + struct { + u8 crypto_key[UFS_CRYPTO_KEY_MAX_SIZE]; + u8 data_unit_size; + u8 crypto_cap_idx; + u8 reserved_1; + u8 config_enable; + u8 reserved_multi_host; + u8 reserved_2; + u8 vsb[2]; + u8 reserved_3[56]; + }; +}; + +/* + * Request Descriptor Definitions + */ + +/* Transfer request command type */ +enum { + UTP_CMD_TYPE_SCSI = 0x0, + UTP_CMD_TYPE_UFS = 0x1, + UTP_CMD_TYPE_DEV_MANAGE = 0x2, +}; + +/* To accommodate UFS2.0 required Command type */ +enum { + UTP_CMD_TYPE_UFS_STORAGE = 0x1, +}; + +enum { + UTP_SCSI_COMMAND = 0x00000000, + UTP_NATIVE_UFS_COMMAND = 0x10000000, + UTP_DEVICE_MANAGEMENT_FUNCTION = 0x20000000, + UTP_REQ_DESC_INT_CMD = 0x01000000, + UTP_REQ_DESC_CRYPTO_ENABLE_CMD = 0x00800000, +}; + +/* UTP Transfer Request Data Direction (DD) */ +enum { + UTP_NO_DATA_TRANSFER = 0x00000000, + UTP_HOST_TO_DEVICE = 0x02000000, + UTP_DEVICE_TO_HOST = 0x04000000, +}; + +/* Overall command status values */ +enum utp_ocs { + OCS_SUCCESS = 0x0, + OCS_INVALID_CMD_TABLE_ATTR = 0x1, + OCS_INVALID_PRDT_ATTR = 0x2, + OCS_MISMATCH_DATA_BUF_SIZE = 0x3, + OCS_MISMATCH_RESP_UPIU_SIZE = 0x4, + OCS_PEER_COMM_FAILURE = 0x5, + OCS_ABORTED = 0x6, + OCS_FATAL_ERROR = 0x7, + OCS_DEVICE_FATAL_ERROR = 0x8, + OCS_INVALID_CRYPTO_CONFIG = 0x9, + OCS_GENERAL_CRYPTO_ERROR = 0xA, + OCS_INVALID_COMMAND_STATUS = 0x0F, +}; + +enum { + MASK_OCS = 0x0F, +}; + +/* The maximum length of the data byte count field in the PRDT is 256KB */ +#define PRDT_DATA_BYTE_COUNT_MAX (256 * 1024) +/* The granularity of the data byte count field in the PRDT is 32-bit */ +#define PRDT_DATA_BYTE_COUNT_PAD 4 + +/** + * struct ufshcd_sg_entry - UFSHCI PRD Entry + * @addr: Physical address; DW-0 and DW-1. + * @reserved: Reserved for future use DW-2 + * @size: size of physical segment DW-3 + */ +struct ufshcd_sg_entry { + __le64 addr; + __le32 reserved; + __le32 size; +}; + +/** + * struct utp_transfer_cmd_desc - UTP Command Descriptor (UCD) + * @command_upiu: Command UPIU Frame address + * @response_upiu: Response UPIU Frame address + * @prd_table: Physical Region Descriptor + */ +struct utp_transfer_cmd_desc { + u8 command_upiu[ALIGNED_UPIU_SIZE]; + u8 response_upiu[ALIGNED_UPIU_SIZE]; + struct ufshcd_sg_entry prd_table[SG_ALL]; +}; + +/** + * struct request_desc_header - Descriptor Header common to both UTRD and UTMRD + * @dword0: Descriptor Header DW0 + * @dword1: Descriptor Header DW1 + * @dword2: Descriptor Header DW2 + * @dword3: Descriptor Header DW3 + */ +struct request_desc_header { + __le32 dword_0; + __le32 dword_1; + __le32 dword_2; + __le32 dword_3; +}; + +/** + * struct utp_transfer_req_desc - UTP Transfer Request Descriptor (UTRD) + * @header: UTRD header DW-0 to DW-3 + * @command_desc_base_addr_lo: UCD base address low DW-4 + * @command_desc_base_addr_hi: UCD base address high DW-5 + * @response_upiu_length: response UPIU length DW-6 + * @response_upiu_offset: response UPIU offset DW-6 + * @prd_table_length: Physical region descriptor length DW-7 + * @prd_table_offset: Physical region descriptor offset DW-7 + */ +struct utp_transfer_req_desc { + + /* DW 0-3 */ + struct request_desc_header header; + + /* DW 4-5*/ + __le32 command_desc_base_addr_lo; + __le32 command_desc_base_addr_hi; + + /* DW 6 */ + __le16 response_upiu_length; + __le16 response_upiu_offset; + + /* DW 7 */ + __le16 prd_table_length; + __le16 prd_table_offset; +}; + +/* + * UTMRD structure. + */ +struct utp_task_req_desc { + /* DW 0-3 */ + struct request_desc_header header; + + /* DW 4-11 - Task request UPIU structure */ + struct { + struct utp_upiu_header req_header; + __be32 input_param1; + __be32 input_param2; + __be32 input_param3; + __be32 __reserved1[2]; + } upiu_req; + + /* DW 12-19 - Task Management Response UPIU structure */ + struct { + struct utp_upiu_header rsp_header; + __be32 output_param1; + __be32 output_param2; + __be32 __reserved2[3]; + } upiu_rsp; +}; + +#endif /* End of Header */ diff --git a/include/ufs/unipro.h b/include/ufs/unipro.h new file mode 100644 index 000000000000..0521f887e3ac --- /dev/null +++ b/include/ufs/unipro.h @@ -0,0 +1,316 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2013 Samsung Electronics Co., Ltd. + */ + +#ifndef _UNIPRO_H_ +#define _UNIPRO_H_ + +/* + * M-TX Configuration Attributes + */ +#define TX_HIBERN8TIME_CAPABILITY 0x000F +#define TX_MODE 0x0021 +#define TX_HSRATE_SERIES 0x0022 +#define TX_HSGEAR 0x0023 +#define TX_PWMGEAR 0x0024 +#define TX_AMPLITUDE 0x0025 +#define TX_HS_SLEWRATE 0x0026 +#define TX_SYNC_SOURCE 0x0027 +#define TX_HS_SYNC_LENGTH 0x0028 +#define TX_HS_PREPARE_LENGTH 0x0029 +#define TX_LS_PREPARE_LENGTH 0x002A +#define TX_HIBERN8_CONTROL 0x002B +#define TX_LCC_ENABLE 0x002C +#define TX_PWM_BURST_CLOSURE_EXTENSION 0x002D +#define TX_BYPASS_8B10B_ENABLE 0x002E +#define TX_DRIVER_POLARITY 0x002F +#define TX_HS_UNTERMINATED_LINE_DRIVE_ENABLE 0x0030 +#define TX_LS_TERMINATED_LINE_DRIVE_ENABLE 0x0031 +#define TX_LCC_SEQUENCER 0x0032 +#define TX_MIN_ACTIVATETIME 0x0033 +#define TX_PWM_G6_G7_SYNC_LENGTH 0x0034 +#define TX_REFCLKFREQ 0x00EB +#define TX_CFGCLKFREQVAL 0x00EC +#define CFGEXTRATTR 0x00F0 +#define DITHERCTRL2 0x00F1 + +/* + * M-RX Configuration Attributes + */ +#define RX_MODE 0x00A1 +#define RX_HSRATE_SERIES 0x00A2 +#define RX_HSGEAR 0x00A3 +#define RX_PWMGEAR 0x00A4 +#define RX_LS_TERMINATED_ENABLE 0x00A5 +#define RX_HS_UNTERMINATED_ENABLE 0x00A6 +#define RX_ENTER_HIBERN8 0x00A7 +#define RX_BYPASS_8B10B_ENABLE 0x00A8 +#define RX_TERMINATION_FORCE_ENABLE 0x00A9 +#define RX_MIN_ACTIVATETIME_CAPABILITY 0x008F +#define RX_HIBERN8TIME_CAPABILITY 0x0092 +#define RX_REFCLKFREQ 0x00EB +#define RX_CFGCLKFREQVAL 0x00EC +#define CFGWIDEINLN 0x00F0 +#define CFGRXCDR8 0x00BA +#define ENARXDIRECTCFG4 0x00F2 +#define CFGRXOVR8 0x00BD +#define RXDIRECTCTRL2 0x00C7 +#define ENARXDIRECTCFG3 0x00F3 +#define RXCALCTRL 0x00B4 +#define ENARXDIRECTCFG2 0x00F4 +#define CFGRXOVR4 0x00E9 +#define RXSQCTRL 0x00B5 +#define CFGRXOVR6 0x00BF +#define RX_HS_G1_SYNC_LENGTH_CAP 0x008B +#define RX_HS_G1_PREP_LENGTH_CAP 0x008C +#define RX_HS_G2_SYNC_LENGTH_CAP 0x0094 +#define RX_HS_G3_SYNC_LENGTH_CAP 0x0095 +#define RX_HS_G2_PREP_LENGTH_CAP 0x0096 +#define RX_HS_G3_PREP_LENGTH_CAP 0x0097 +#define RX_ADV_GRANULARITY_CAP 0x0098 +#define RX_MIN_ACTIVATETIME_CAP 0x008F +#define RX_HIBERN8TIME_CAP 0x0092 +#define RX_ADV_HIBERN8TIME_CAP 0x0099 +#define RX_ADV_MIN_ACTIVATETIME_CAP 0x009A + + +#define is_mphy_tx_attr(attr) (attr < RX_MODE) +#define RX_ADV_FINE_GRAN_STEP(x) ((((x) & 0x3) << 1) | 0x1) +#define SYNC_LEN_FINE(x) ((x) & 0x3F) +#define SYNC_LEN_COARSE(x) ((1 << 6) | ((x) & 0x3F)) +#define PREP_LEN(x) ((x) & 0xF) + +#define RX_MIN_ACTIVATETIME_UNIT_US 100 +#define HIBERN8TIME_UNIT_US 100 + +/* + * Common Block Attributes + */ +#define TX_GLOBALHIBERNATE UNIPRO_CB_OFFSET(0x002B) +#define REFCLKMODE UNIPRO_CB_OFFSET(0x00BF) +#define DIRECTCTRL19 UNIPRO_CB_OFFSET(0x00CD) +#define DIRECTCTRL10 UNIPRO_CB_OFFSET(0x00E6) +#define CDIRECTCTRL6 UNIPRO_CB_OFFSET(0x00EA) +#define RTOBSERVESELECT UNIPRO_CB_OFFSET(0x00F0) +#define CBDIVFACTOR UNIPRO_CB_OFFSET(0x00F1) +#define CBDCOCTRL5 UNIPRO_CB_OFFSET(0x00F3) +#define CBPRGPLL2 UNIPRO_CB_OFFSET(0x00F8) +#define CBPRGTUNING UNIPRO_CB_OFFSET(0x00FB) + +#define UNIPRO_CB_OFFSET(x) (0x8000 | x) + +/* + * PHY Adapter attributes + */ +#define PA_ACTIVETXDATALANES 0x1560 +#define PA_ACTIVERXDATALANES 0x1580 +#define PA_TXTRAILINGCLOCKS 0x1564 +#define PA_PHY_TYPE 0x1500 +#define PA_AVAILTXDATALANES 0x1520 +#define PA_AVAILRXDATALANES 0x1540 +#define PA_MINRXTRAILINGCLOCKS 0x1543 +#define PA_TXPWRSTATUS 0x1567 +#define PA_RXPWRSTATUS 0x1582 +#define PA_TXFORCECLOCK 0x1562 +#define PA_TXPWRMODE 0x1563 +#define PA_LEGACYDPHYESCDL 0x1570 +#define PA_MAXTXSPEEDFAST 0x1521 +#define PA_MAXTXSPEEDSLOW 0x1522 +#define PA_MAXRXSPEEDFAST 0x1541 +#define PA_MAXRXSPEEDSLOW 0x1542 +#define PA_TXLINKSTARTUPHS 0x1544 +#define PA_LOCAL_TX_LCC_ENABLE 0x155E +#define PA_TXSPEEDFAST 0x1565 +#define PA_TXSPEEDSLOW 0x1566 +#define PA_REMOTEVERINFO 0x15A0 +#define PA_TXGEAR 0x1568 +#define PA_TXTERMINATION 0x1569 +#define PA_HSSERIES 0x156A +#define PA_PWRMODE 0x1571 +#define PA_RXGEAR 0x1583 +#define PA_RXTERMINATION 0x1584 +#define PA_MAXRXPWMGEAR 0x1586 +#define PA_MAXRXHSGEAR 0x1587 +#define PA_RXHSUNTERMCAP 0x15A5 +#define PA_RXLSTERMCAP 0x15A6 +#define PA_GRANULARITY 0x15AA +#define PA_PACPREQTIMEOUT 0x1590 +#define PA_PACPREQEOBTIMEOUT 0x1591 +#define PA_HIBERN8TIME 0x15A7 +#define PA_LOCALVERINFO 0x15A9 +#define PA_GRANULARITY 0x15AA +#define PA_TACTIVATE 0x15A8 +#define PA_PACPFRAMECOUNT 0x15C0 +#define PA_PACPERRORCOUNT 0x15C1 +#define PA_PHYTESTCONTROL 0x15C2 +#define PA_PWRMODEUSERDATA0 0x15B0 +#define PA_PWRMODEUSERDATA1 0x15B1 +#define PA_PWRMODEUSERDATA2 0x15B2 +#define PA_PWRMODEUSERDATA3 0x15B3 +#define PA_PWRMODEUSERDATA4 0x15B4 +#define PA_PWRMODEUSERDATA5 0x15B5 +#define PA_PWRMODEUSERDATA6 0x15B6 +#define PA_PWRMODEUSERDATA7 0x15B7 +#define PA_PWRMODEUSERDATA8 0x15B8 +#define PA_PWRMODEUSERDATA9 0x15B9 +#define PA_PWRMODEUSERDATA10 0x15BA +#define PA_PWRMODEUSERDATA11 0x15BB +#define PA_CONNECTEDTXDATALANES 0x1561 +#define PA_CONNECTEDRXDATALANES 0x1581 +#define PA_LOGICALLANEMAP 0x15A1 +#define PA_SLEEPNOCONFIGTIME 0x15A2 +#define PA_STALLNOCONFIGTIME 0x15A3 +#define PA_SAVECONFIGTIME 0x15A4 +#define PA_TXHSADAPTTYPE 0x15D4 + +/* Adpat type for PA_TXHSADAPTTYPE attribute */ +#define PA_REFRESH_ADAPT 0x00 +#define PA_INITIAL_ADAPT 0x01 +#define PA_NO_ADAPT 0x03 + +#define PA_TACTIVATE_TIME_UNIT_US 10 +#define PA_HIBERN8_TIME_UNIT_US 100 + +/*Other attributes*/ +#define VS_MPHYCFGUPDT 0xD085 +#define VS_DEBUGOMC 0xD09E +#define VS_POWERSTATE 0xD083 + +#define PA_GRANULARITY_MIN_VAL 1 +#define PA_GRANULARITY_MAX_VAL 6 + +/* PHY Adapter Protocol Constants */ +#define PA_MAXDATALANES 4 + +#define DL_FC0ProtectionTimeOutVal_Default 8191 +#define DL_TC0ReplayTimeOutVal_Default 65535 +#define DL_AFC0ReqTimeOutVal_Default 32767 +#define DL_FC1ProtectionTimeOutVal_Default 8191 +#define DL_TC1ReplayTimeOutVal_Default 65535 +#define DL_AFC1ReqTimeOutVal_Default 32767 + +#define DME_LocalFC0ProtectionTimeOutVal 0xD041 +#define DME_LocalTC0ReplayTimeOutVal 0xD042 +#define DME_LocalAFC0ReqTimeOutVal 0xD043 + +/* PA power modes */ +enum { + FAST_MODE = 1, + SLOW_MODE = 2, + FASTAUTO_MODE = 4, + SLOWAUTO_MODE = 5, + UNCHANGED = 7, +}; + +#define PWRMODE_MASK 0xF +#define PWRMODE_RX_OFFSET 4 + +/* PA TX/RX Frequency Series */ +enum { + PA_HS_MODE_A = 1, + PA_HS_MODE_B = 2, +}; + +enum ufs_pwm_gear_tag { + UFS_PWM_DONT_CHANGE, /* Don't change Gear */ + UFS_PWM_G1, /* PWM Gear 1 (default for reset) */ + UFS_PWM_G2, /* PWM Gear 2 */ + UFS_PWM_G3, /* PWM Gear 3 */ + UFS_PWM_G4, /* PWM Gear 4 */ + UFS_PWM_G5, /* PWM Gear 5 */ + UFS_PWM_G6, /* PWM Gear 6 */ + UFS_PWM_G7, /* PWM Gear 7 */ +}; + +enum ufs_hs_gear_tag { + UFS_HS_DONT_CHANGE, /* Don't change Gear */ + UFS_HS_G1, /* HS Gear 1 (default for reset) */ + UFS_HS_G2, /* HS Gear 2 */ + UFS_HS_G3, /* HS Gear 3 */ + UFS_HS_G4, /* HS Gear 4 */ +}; + +enum ufs_unipro_ver { + UFS_UNIPRO_VER_RESERVED = 0, + UFS_UNIPRO_VER_1_40 = 1, /* UniPro version 1.40 */ + UFS_UNIPRO_VER_1_41 = 2, /* UniPro version 1.41 */ + UFS_UNIPRO_VER_1_6 = 3, /* UniPro version 1.6 */ + UFS_UNIPRO_VER_1_61 = 4, /* UniPro version 1.61 */ + UFS_UNIPRO_VER_1_8 = 5, /* UniPro version 1.8 */ + UFS_UNIPRO_VER_MAX = 6, /* UniPro unsupported version */ + /* UniPro version field mask in PA_LOCALVERINFO */ + UFS_UNIPRO_VER_MASK = 0xF, +}; + +/* + * Data Link Layer Attributes + */ +#define DL_TC0TXFCTHRESHOLD 0x2040 +#define DL_FC0PROTTIMEOUTVAL 0x2041 +#define DL_TC0REPLAYTIMEOUTVAL 0x2042 +#define DL_AFC0REQTIMEOUTVAL 0x2043 +#define DL_AFC0CREDITTHRESHOLD 0x2044 +#define DL_TC0OUTACKTHRESHOLD 0x2045 +#define DL_TC1TXFCTHRESHOLD 0x2060 +#define DL_FC1PROTTIMEOUTVAL 0x2061 +#define DL_TC1REPLAYTIMEOUTVAL 0x2062 +#define DL_AFC1REQTIMEOUTVAL 0x2063 +#define DL_AFC1CREDITTHRESHOLD 0x2064 +#define DL_TC1OUTACKTHRESHOLD 0x2065 +#define DL_TXPREEMPTIONCAP 0x2000 +#define DL_TC0TXMAXSDUSIZE 0x2001 +#define DL_TC0RXINITCREDITVAL 0x2002 +#define DL_TC0TXBUFFERSIZE 0x2005 +#define DL_PEERTC0PRESENT 0x2046 +#define DL_PEERTC0RXINITCREVAL 0x2047 +#define DL_TC1TXMAXSDUSIZE 0x2003 +#define DL_TC1RXINITCREDITVAL 0x2004 +#define DL_TC1TXBUFFERSIZE 0x2006 +#define DL_PEERTC1PRESENT 0x2066 +#define DL_PEERTC1RXINITCREVAL 0x2067 + +/* + * Network Layer Attributes + */ +#define N_DEVICEID 0x3000 +#define N_DEVICEID_VALID 0x3001 +#define N_TC0TXMAXSDUSIZE 0x3020 +#define N_TC1TXMAXSDUSIZE 0x3021 + +/* + * Transport Layer Attributes + */ +#define T_NUMCPORTS 0x4000 +#define T_NUMTESTFEATURES 0x4001 +#define T_CONNECTIONSTATE 0x4020 +#define T_PEERDEVICEID 0x4021 +#define T_PEERCPORTID 0x4022 +#define T_TRAFFICCLASS 0x4023 +#define T_PROTOCOLID 0x4024 +#define T_CPORTFLAGS 0x4025 +#define T_TXTOKENVALUE 0x4026 +#define T_RXTOKENVALUE 0x4027 +#define T_LOCALBUFFERSPACE 0x4028 +#define T_PEERBUFFERSPACE 0x4029 +#define T_CREDITSTOSEND 0x402A +#define T_CPORTMODE 0x402B +#define T_TC0TXMAXSDUSIZE 0x4060 +#define T_TC1TXMAXSDUSIZE 0x4061 + +/* CPort setting */ +#define E2EFC_ON (1 << 0) +#define E2EFC_OFF (0 << 0) +#define CSD_N_ON (0 << 1) +#define CSD_N_OFF (1 << 1) +#define CSV_N_ON (0 << 2) +#define CSV_N_OFF (1 << 2) +#define CPORT_DEF_FLAGS (CSV_N_OFF | CSD_N_OFF | E2EFC_OFF) + +/* CPort connection state */ +enum { + CPORT_IDLE = 0, + CPORT_CONNECTED, +}; + +#endif /* _UNIPRO_H_ */ -- cgit v1.2.3 From 59df85d5fbae17175c391d89ad03e9e7a01b7a55 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 1 Mar 2022 19:56:53 -0500 Subject: linux/mount.h: trim includes Signed-off-by: Al Viro --- include/linux/mount.h | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/mount.h b/include/linux/mount.h index 7f18a7555dff..b3b149dcbf96 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -11,17 +11,15 @@ #define _LINUX_MOUNT_H #include -#include -#include -#include -#include -#include +#include struct super_block; -struct vfsmount; struct dentry; -struct mnt_namespace; +struct user_namespace; +struct file_system_type; struct fs_context; +struct file; +struct path; #define MNT_NOSUID 0x01 #define MNT_NODEV 0x02 @@ -81,9 +79,6 @@ static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt) return smp_load_acquire(&mnt->mnt_userns); } -struct file; /* forward dec */ -struct path; - extern int mnt_want_write(struct vfsmount *mnt); extern int mnt_want_write_file(struct file *file); extern void mnt_drop_write(struct vfsmount *mnt); @@ -94,12 +89,10 @@ extern struct vfsmount *mnt_clone_internal(const struct path *path); extern bool __mnt_is_readonly(struct vfsmount *mnt); extern bool mnt_may_suid(struct vfsmount *mnt); -struct path; extern struct vfsmount *clone_private_mount(const struct path *path); extern int __mnt_want_write(struct vfsmount *); extern void __mnt_drop_write(struct vfsmount *); -struct file_system_type; extern struct vfsmount *fc_mount(struct fs_context *fc); extern struct vfsmount *vfs_create_mount(struct fs_context *fc); extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, -- cgit v1.2.3 From 70f8d9c5750bbb0ca4ef7e23d6abcb05e6061138 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 2 Mar 2022 17:49:09 -0500 Subject: move mount-related externs from fs.h to mount.h Signed-off-by: Al Viro --- include/linux/fs.h | 11 ----------- include/linux/mount.h | 12 ++++++++++++ 2 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..14df7c049b43 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2461,22 +2461,11 @@ struct super_block *sget(struct file_system_type *type, extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); -extern struct vfsmount *kern_mount(struct file_system_type *); -extern void kern_unmount(struct vfsmount *mnt); -extern int may_umount_tree(struct vfsmount *); -extern int may_umount(struct vfsmount *); -extern long do_mount(const char *, const char __user *, - const char *, unsigned long, void *); -extern struct vfsmount *collect_mounts(const struct path *); -extern void drop_collected_mounts(struct vfsmount *); -extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, - struct vfsmount *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); -extern bool our_mnt(struct vfsmount *mnt); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); diff --git a/include/linux/mount.h b/include/linux/mount.h index b3b149dcbf96..55a4abaf6715 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -108,6 +108,18 @@ extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(const char *name); extern bool path_is_mountpoint(const struct path *path); +extern bool our_mnt(struct vfsmount *mnt); + +extern struct vfsmount *kern_mount(struct file_system_type *); +extern void kern_unmount(struct vfsmount *mnt); +extern int may_umount_tree(struct vfsmount *); +extern int may_umount(struct vfsmount *); +extern long do_mount(const char *, const char __user *, + const char *, unsigned long, void *); +extern struct vfsmount *collect_mounts(const struct path *); +extern void drop_collected_mounts(struct vfsmount *); +extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, + struct vfsmount *); extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); #endif /* _LINUX_MOUNT_H */ -- cgit v1.2.3 From 58e5bdeb9c2b06895e723c0b1e670f54510ff782 Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Fri, 20 May 2022 14:36:30 +0530 Subject: nvme: enable uring-passthrough for admin commands Add two new opcodes that userspace can use for admin commands: NVME_URING_CMD_ADMIN : non-vectroed NVME_URING_CMD_ADMIN_VEC : vectored variant Wire up support when these are issued on controller node(/dev/nvmeX). Signed-off-by: Kanchan Joshi Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220520090630.70394-3-joshi.k@samsung.com Signed-off-by: Jens Axboe --- include/uapi/linux/nvme_ioctl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index 0b1876aa5a59..2f76cba67166 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -108,5 +108,7 @@ struct nvme_uring_cmd { /* io_uring async commands: */ #define NVME_URING_CMD_IO _IOWR('N', 0x80, struct nvme_uring_cmd) #define NVME_URING_CMD_IO_VEC _IOWR('N', 0x81, struct nvme_uring_cmd) +#define NVME_URING_CMD_ADMIN _IOWR('N', 0x82, struct nvme_uring_cmd) +#define NVME_URING_CMD_ADMIN_VEC _IOWR('N', 0x83, struct nvme_uring_cmd) #endif /* _UAPI_LINUX_NVME_IOCTL_H */ -- cgit v1.2.3 From 84d0940454a3bca6c7c59cf16b6de2f173e81a11 Mon Sep 17 00:00:00 2001 From: Fabio Baltieri Date: Thu, 28 Apr 2022 10:04:18 +0000 Subject: dt-bindings: Add mfd/cros_ec definitions Add a dt-bindings include file for cros_ec devicetree definition, define a pair of special purpose PWM channels in it. Signed-off-by: Fabio Baltieri Acked-by: Rob Herring Signed-off-by: Thierry Reding --- include/dt-bindings/mfd/cros_ec.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/dt-bindings/mfd/cros_ec.h (limited to 'include') diff --git a/include/dt-bindings/mfd/cros_ec.h b/include/dt-bindings/mfd/cros_ec.h new file mode 100644 index 000000000000..3b29cd049578 --- /dev/null +++ b/include/dt-bindings/mfd/cros_ec.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * DTS binding definitions used for the Chromium OS Embedded Controller. + * + * Copyright (c) 2022 The Chromium OS Authors. All rights reserved. + */ + +#ifndef _DT_BINDINGS_MFD_CROS_EC_H +#define _DT_BINDINGS_MFD_CROS_EC_H + +/* Typed channel for keyboard backlight. */ +#define CROS_EC_PWM_DT_KB_LIGHT 0 +/* Typed channel for display backlight. */ +#define CROS_EC_PWM_DT_DISPLAY_LIGHT 1 +/* Number of typed channels. */ +#define CROS_EC_PWM_DT_COUNT 2 + +#endif -- cgit v1.2.3 From 3bc253c2e652cf5f12cd8c00d80d8ec55d67d1a7 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 19 May 2022 16:30:10 -0700 Subject: bpf: Add bpf_skc_to_mptcp_sock_proto This patch implements a new struct bpf_func_proto, named bpf_skc_to_mptcp_sock_proto. Define a new bpf_id BTF_SOCK_TYPE_MPTCP, and a new helper bpf_skc_to_mptcp_sock(), which invokes another new helper bpf_mptcp_sock_from_subflow() in net/mptcp/bpf.c to get struct mptcp_sock from a given subflow socket. v2: Emit BTF type, add func_id checks in verifier.c and bpf_trace.c, remove build check for CONFIG_BPF_JIT v5: Drop EXPORT_SYMBOL (Martin) Co-developed-by: Nicolas Rybowski Co-developed-by: Matthieu Baerts Signed-off-by: Nicolas Rybowski Signed-off-by: Matthieu Baerts Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220519233016.105670-2-mathew.j.martineau@linux.intel.com --- include/linux/bpf.h | 1 + include/linux/btf_ids.h | 3 ++- include/net/mptcp.h | 6 ++++++ include/uapi/linux/bpf.h | 7 +++++++ 4 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c107392b0ba7..a3ef078401cf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2231,6 +2231,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index bc5d9cc34e4c..335a19092368 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -178,7 +178,8 @@ extern struct btf_id_set name; BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) \ - BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock) enum { #define BTF_SOCK_TYPE(name, str) name, diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 8b1afd6f5cc4..2ba09de955c7 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -284,4 +284,10 @@ static inline int mptcpv6_init(void) { return 0; } static inline void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { } #endif +#if defined(CONFIG_MPTCP) && defined(CONFIG_BPF_SYSCALL) +struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk); +#else +static inline struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk) { return NULL; } +#endif + #endif /* __NET_MPTCP_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0210f85131b3..56688bee20d9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5172,6 +5172,12 @@ union bpf_attr { * Return * Map value associated to *key* on *cpu*, or **NULL** if no entry * was found or *cpu* is invalid. + * + * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5370,6 +5376,7 @@ union bpf_attr { FN(ima_file_hash), \ FN(kptr_xchg), \ FN(map_lookup_percpu_elem), \ + FN(skc_to_mptcp_sock), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From b23316aabffa835ecc516cb81daeef5b9155e8a5 Mon Sep 17 00:00:00 2001 From: Yuntao Wang Date: Thu, 19 May 2022 23:06:10 +0800 Subject: selftests/bpf: Add missing trampoline program type to trampoline_count test Currently the trampoline_count test doesn't include any fmod_ret bpf programs, fix it to make the test cover all possible trampoline program types. Since fmod_ret bpf programs can't be attached to __set_task_comm function, as it's neither whitelisted for error injection nor a security hook, change it to bpf_modify_return_test. This patch also does some other cleanups such as removing duplicate code, dropping inconsistent comments, etc. Signed-off-by: Yuntao Wang Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20220519150610.601313-1-ytcoode@gmail.com --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a3ef078401cf..cc4d5e394031 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -724,7 +724,7 @@ struct btf_func_model { #define BPF_TRAMP_F_RET_FENTRY_RET BIT(4) /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 - * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 + * bytes on x86. */ #define BPF_MAX_TRAMP_LINKS 38 -- cgit v1.2.3 From d5a42de8bdbe25081f07b801d8b35f4d75a791f4 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Thu, 19 May 2022 17:18:33 -0700 Subject: net: Add a second bind table hashed by port and address We currently have one tcp bind table (bhash) which hashes by port number only. In the socket bind path, we check for bind conflicts by traversing the specified port's inet_bind2_bucket while holding the bucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, checking for a bind conflict is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch proposes adding a second bind table, bhash2, that hashes by port and ip address. Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the spinlock. Signed-off-by: Joanne Koong Reviewed-by: Eric Dumazet Acked-by: Kuniyuki Iwashima Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 3 ++ include/net/inet_hashtables.h | 68 +++++++++++++++++++++++++++++++++++++- include/net/sock.h | 14 ++++++++ 3 files changed, 84 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 85cd695e7fd1..077cd730ce2f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -25,6 +25,7 @@ #undef INET_CSK_CLEAR_TIMERS struct inet_bind_bucket; +struct inet_bind2_bucket; struct tcp_congestion_ops; /* @@ -57,6 +58,7 @@ struct inet_connection_sock_af_ops { * * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node + * @icsk_bind2_hash: Bind node in the bhash2 table * @icsk_timeout: Timeout * @icsk_retransmit_timer: Resend (no ack) * @icsk_rto: Retransmit timeout @@ -83,6 +85,7 @@ struct inet_connection_sock { struct inet_sock icsk_inet; struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; + struct inet_bind2_bucket *icsk_bind2_hash; unsigned long icsk_timeout; struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ebfa3df6f8dc..a0887b70967b 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -90,11 +90,32 @@ struct inet_bind_bucket { struct hlist_head owners; }; +struct inet_bind2_bucket { + possible_net_t ib_net; + int l3mdev; + unsigned short port; + union { +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr v6_rcv_saddr; +#endif + __be32 rcv_saddr; + }; + /* Node in the inet2_bind_hashbucket chain */ + struct hlist_node node; + /* List of sockets hashed to this bucket */ + struct hlist_head owners; +}; + static inline struct net *ib_net(struct inet_bind_bucket *ib) { return read_pnet(&ib->ib_net); } +static inline struct net *ib2_net(struct inet_bind2_bucket *ib) +{ + return read_pnet(&ib->ib_net); +} + #define inet_bind_bucket_for_each(tb, head) \ hlist_for_each_entry(tb, head, node) @@ -103,6 +124,15 @@ struct inet_bind_hashbucket { struct hlist_head chain; }; +/* This is synchronized using the inet_bind_hashbucket's spinlock. + * Instead of having separate spinlocks, the inet_bind2_hashbucket can share + * the inet_bind_hashbucket's given that in every case where the bhash2 table + * is useful, a lookup in the bhash table also occurs. + */ +struct inet_bind2_hashbucket { + struct hlist_head chain; +}; + /* Sockets can be hashed in established or listening table. * We must use different 'nulls' end-of-chain value for all hash buckets : * A socket might transition from ESTABLISH to LISTEN state without @@ -134,6 +164,12 @@ struct inet_hashinfo { */ struct kmem_cache *bind_bucket_cachep; struct inet_bind_hashbucket *bhash; + /* The 2nd binding table hashed by port and address. + * This is used primarily for expediting the resolution of bind + * conflicts. + */ + struct kmem_cache *bind2_bucket_cachep; + struct inet_bind2_hashbucket *bhash2; unsigned int bhash_size; /* The 2nd listener table hashed by local port and address */ @@ -193,6 +229,36 @@ inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb); +static inline bool check_bind_bucket_match(struct inet_bind_bucket *tb, + struct net *net, + const unsigned short port, + int l3mdev) +{ + return net_eq(ib_net(tb), net) && tb->port == port && + tb->l3mdev == l3mdev; +} + +struct inet_bind2_bucket * +inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net, + struct inet_bind2_hashbucket *head, + const unsigned short port, int l3mdev, + const struct sock *sk); + +void inet_bind2_bucket_destroy(struct kmem_cache *cachep, + struct inet_bind2_bucket *tb); + +struct inet_bind2_bucket * +inet_bind2_bucket_find(struct inet_hashinfo *hinfo, struct net *net, + const unsigned short port, int l3mdev, + struct sock *sk, + struct inet_bind2_hashbucket **head); + +bool check_bind2_bucket_match_nulladdr(struct inet_bind2_bucket *tb, + struct net *net, + const unsigned short port, + int l3mdev, + const struct sock *sk); + static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, const u32 bhash_size) { @@ -200,7 +266,7 @@ static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, } void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, - const unsigned short snum); + struct inet_bind2_bucket *tb2, const unsigned short snum); /* Caller must disable local BH processing. */ int __inet_inherit_port(const struct sock *sk, struct sock *child); diff --git a/include/net/sock.h b/include/net/sock.h index 72ca97ccb460..c585ef6565d9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -348,6 +348,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_bind2_node: bind node in the bhash2 table */ struct sock { /* @@ -537,6 +538,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct hlist_node sk_bind2_node; }; enum sk_pacing { @@ -817,6 +819,16 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_add_head(&sk->sk_bind_node, list); } +static inline void __sk_del_bind2_node(struct sock *sk) +{ + __hlist_del(&sk->sk_bind2_node); +} + +static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) +{ + hlist_add_head(&sk->sk_bind2_node, list); +} + #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ @@ -834,6 +846,8 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) +#define sk_for_each_bound_bhash2(__sk, list) \ + hlist_for_each_entry(__sk, list, sk_bind2_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset -- cgit v1.2.3 From 538101dd7ce360f29effeb45aecb1953bc0fd01b Mon Sep 17 00:00:00 2001 From: Chanho Park Date: Fri, 20 May 2022 12:06:25 +0900 Subject: dt-bindings: clock: exynosautov9: correct count of NR_CLK _NR_CLKS which can be used to register clocks via nr_clk_ids. The clock IDs are started from 1. So, _NR_CLKS should be defined to "the last clock id + 1" Fixes: 680e1c8370a2 ("dt-bindings: clock: add clock binding definitions for Exynos Auto v9") Signed-off-by: Chanho Park Link: https://lore.kernel.org/r/20220520030625.145324-1-chanho61.park@samsung.com Reviewed-by: Chanwoo Choi Reviewed-by: Krzysztof Kozlowski Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/samsung,exynosautov9.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/samsung,exynosautov9.h b/include/dt-bindings/clock/samsung,exynosautov9.h index 71ec0a955364..ea9f91b4eb1a 100644 --- a/include/dt-bindings/clock/samsung,exynosautov9.h +++ b/include/dt-bindings/clock/samsung,exynosautov9.h @@ -166,7 +166,7 @@ #define GOUT_CLKCMU_PERIC1_IP 248 #define GOUT_CLKCMU_PERIS_BUS 249 -#define TOP_NR_CLK 249 +#define TOP_NR_CLK 250 /* CMU_BUSMC */ #define CLK_MOUT_BUSMC_BUS_USER 1 @@ -174,7 +174,7 @@ #define CLK_GOUT_BUSMC_PDMA0_PCLK 3 #define CLK_GOUT_BUSMC_SPDMA_PCLK 4 -#define BUSMC_NR_CLK 4 +#define BUSMC_NR_CLK 5 /* CMU_CORE */ #define CLK_MOUT_CORE_BUS_USER 1 @@ -183,7 +183,7 @@ #define CLK_GOUT_CORE_CCI_PCLK 4 #define CLK_GOUT_CORE_CMU_CORE_PCLK 5 -#define CORE_NR_CLK 5 +#define CORE_NR_CLK 6 /* CMU_FSYS2 */ #define CLK_MOUT_FSYS2_BUS_USER 1 @@ -194,7 +194,7 @@ #define CLK_GOUT_FSYS2_UFS_EMBD1_ACLK 6 #define CLK_GOUT_FSYS2_UFS_EMBD1_UNIPRO 7 -#define FSYS2_NR_CLK 7 +#define FSYS2_NR_CLK 8 /* CMU_PERIC0 */ #define CLK_MOUT_PERIC0_BUS_USER 1 @@ -240,7 +240,7 @@ #define CLK_GOUT_PERIC0_PCLK_10 41 #define CLK_GOUT_PERIC0_PCLK_11 42 -#define PERIC0_NR_CLK 42 +#define PERIC0_NR_CLK 43 /* CMU_PERIC1 */ #define CLK_MOUT_PERIC1_BUS_USER 1 @@ -286,7 +286,7 @@ #define CLK_GOUT_PERIC1_PCLK_10 41 #define CLK_GOUT_PERIC1_PCLK_11 42 -#define PERIC1_NR_CLK 42 +#define PERIC1_NR_CLK 43 /* CMU_PERIS */ #define CLK_MOUT_PERIS_BUS_USER 1 @@ -294,6 +294,6 @@ #define CLK_GOUT_WDT_CLUSTER0 3 #define CLK_GOUT_WDT_CLUSTER1 4 -#define PERIS_NR_CLK 4 +#define PERIS_NR_CLK 5 #endif /* _DT_BINDINGS_CLOCK_EXYNOSAUTOV9_H */ -- cgit v1.2.3 From 722dc8a1d5c8691ab9923b723db4354537206f97 Mon Sep 17 00:00:00 2001 From: Gabriel Fernandez Date: Mon, 16 May 2022 09:05:47 +0200 Subject: dt-bindings: rcc: stm32: add new compatible for STM32MP13 SoC New compatible to manage clock and reset of STM32MP13 SoC. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Gabriel Fernandez Link: https://lore.kernel.org/r/20220516070600.7692-2-gabriel.fernandez@foss.st.com Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/stm32mp13-clks.h | 229 +++++++++++++++++++++++++++ include/dt-bindings/reset/stm32mp13-resets.h | 100 ++++++++++++ 2 files changed, 329 insertions(+) create mode 100644 include/dt-bindings/clock/stm32mp13-clks.h create mode 100644 include/dt-bindings/reset/stm32mp13-resets.h (limited to 'include') diff --git a/include/dt-bindings/clock/stm32mp13-clks.h b/include/dt-bindings/clock/stm32mp13-clks.h new file mode 100644 index 000000000000..02befd25edce --- /dev/null +++ b/include/dt-bindings/clock/stm32mp13-clks.h @@ -0,0 +1,229 @@ +/* SPDX-License-Identifier: GPL-2.0+ or BSD-3-Clause */ +/* + * Copyright (C) STMicroelectronics 2020 - All Rights Reserved + * Author: Gabriel Fernandez for STMicroelectronics. + */ + +#ifndef _DT_BINDINGS_STM32MP13_CLKS_H_ +#define _DT_BINDINGS_STM32MP13_CLKS_H_ + +/* OSCILLATOR clocks */ +#define CK_HSE 0 +#define CK_CSI 1 +#define CK_LSI 2 +#define CK_LSE 3 +#define CK_HSI 4 +#define CK_HSE_DIV2 5 + +/* PLL */ +#define PLL1 6 +#define PLL2 7 +#define PLL3 8 +#define PLL4 9 + +/* ODF */ +#define PLL1_P 10 +#define PLL1_Q 11 +#define PLL1_R 12 +#define PLL2_P 13 +#define PLL2_Q 14 +#define PLL2_R 15 +#define PLL3_P 16 +#define PLL3_Q 17 +#define PLL3_R 18 +#define PLL4_P 19 +#define PLL4_Q 20 +#define PLL4_R 21 + +#define PCLK1 22 +#define PCLK2 23 +#define PCLK3 24 +#define PCLK4 25 +#define PCLK5 26 +#define PCLK6 27 + +/* SYSTEM CLOCK */ +#define CK_PER 28 +#define CK_MPU 29 +#define CK_AXI 30 +#define CK_MLAHB 31 + +/* BASE TIMER */ +#define CK_TIMG1 32 +#define CK_TIMG2 33 +#define CK_TIMG3 34 + +/* AUX */ +#define RTC 35 + +/* TRACE & DEBUG clocks */ +#define CK_DBG 36 +#define CK_TRACE 37 + +/* MCO clocks */ +#define CK_MCO1 38 +#define CK_MCO2 39 + +/* IP clocks */ +#define SYSCFG 40 +#define VREF 41 +#define DTS 42 +#define PMBCTRL 43 +#define HDP 44 +#define IWDG2 45 +#define STGENRO 46 +#define USART1 47 +#define RTCAPB 48 +#define TZC 49 +#define TZPC 50 +#define IWDG1 51 +#define BSEC 52 +#define DMA1 53 +#define DMA2 54 +#define DMAMUX1 55 +#define DMAMUX2 56 +#define GPIOA 57 +#define GPIOB 58 +#define GPIOC 59 +#define GPIOD 60 +#define GPIOE 61 +#define GPIOF 62 +#define GPIOG 63 +#define GPIOH 64 +#define GPIOI 65 +#define CRYP1 66 +#define HASH1 67 +#define BKPSRAM 68 +#define MDMA 69 +#define CRC1 70 +#define USBH 71 +#define DMA3 72 +#define TSC 73 +#define PKA 74 +#define AXIMC 75 +#define MCE 76 +#define ETH1TX 77 +#define ETH2TX 78 +#define ETH1RX 79 +#define ETH2RX 80 +#define ETH1MAC 81 +#define ETH2MAC 82 +#define ETH1STP 83 +#define ETH2STP 84 + +/* IP clocks with parents */ +#define SDMMC1_K 85 +#define SDMMC2_K 86 +#define ADC1_K 87 +#define ADC2_K 88 +#define FMC_K 89 +#define QSPI_K 90 +#define RNG1_K 91 +#define USBPHY_K 92 +#define STGEN_K 93 +#define SPDIF_K 94 +#define SPI1_K 95 +#define SPI2_K 96 +#define SPI3_K 97 +#define SPI4_K 98 +#define SPI5_K 99 +#define I2C1_K 100 +#define I2C2_K 101 +#define I2C3_K 102 +#define I2C4_K 103 +#define I2C5_K 104 +#define TIM2_K 105 +#define TIM3_K 106 +#define TIM4_K 107 +#define TIM5_K 108 +#define TIM6_K 109 +#define TIM7_K 110 +#define TIM12_K 111 +#define TIM13_K 112 +#define TIM14_K 113 +#define TIM1_K 114 +#define TIM8_K 115 +#define TIM15_K 116 +#define TIM16_K 117 +#define TIM17_K 118 +#define LPTIM1_K 119 +#define LPTIM2_K 120 +#define LPTIM3_K 121 +#define LPTIM4_K 122 +#define LPTIM5_K 123 +#define USART1_K 124 +#define USART2_K 125 +#define USART3_K 126 +#define UART4_K 127 +#define UART5_K 128 +#define USART6_K 129 +#define UART7_K 130 +#define UART8_K 131 +#define DFSDM_K 132 +#define FDCAN_K 133 +#define SAI1_K 134 +#define SAI2_K 135 +#define ADFSDM_K 136 +#define USBO_K 137 +#define LTDC_PX 138 +#define ETH1CK_K 139 +#define ETH1PTP_K 140 +#define ETH2CK_K 141 +#define ETH2PTP_K 142 +#define DCMIPP_K 143 +#define SAES_K 144 +#define DTS_K 145 + +/* DDR */ +#define DDRC1 146 +#define DDRC1LP 147 +#define DDRC2 148 +#define DDRC2LP 149 +#define DDRPHYC 150 +#define DDRPHYCLP 151 +#define DDRCAPB 152 +#define DDRCAPBLP 153 +#define AXIDCG 154 +#define DDRPHYCAPB 155 +#define DDRPHYCAPBLP 156 +#define DDRPERFM 157 + +#define ADC1 158 +#define ADC2 159 +#define SAI1 160 +#define SAI2 161 + +#define STM32MP1_LAST_CLK 162 + +/* SCMI clock identifiers */ +#define CK_SCMI_HSE 0 +#define CK_SCMI_HSI 1 +#define CK_SCMI_CSI 2 +#define CK_SCMI_LSE 3 +#define CK_SCMI_LSI 4 +#define CK_SCMI_HSE_DIV2 5 +#define CK_SCMI_PLL2_Q 6 +#define CK_SCMI_PLL2_R 7 +#define CK_SCMI_PLL3_P 8 +#define CK_SCMI_PLL3_Q 9 +#define CK_SCMI_PLL3_R 10 +#define CK_SCMI_PLL4_P 11 +#define CK_SCMI_PLL4_Q 12 +#define CK_SCMI_PLL4_R 13 +#define CK_SCMI_MPU 14 +#define CK_SCMI_AXI 15 +#define CK_SCMI_MLAHB 16 +#define CK_SCMI_CKPER 17 +#define CK_SCMI_PCLK1 18 +#define CK_SCMI_PCLK2 19 +#define CK_SCMI_PCLK3 20 +#define CK_SCMI_PCLK4 21 +#define CK_SCMI_PCLK5 22 +#define CK_SCMI_PCLK6 23 +#define CK_SCMI_CKTIMG1 24 +#define CK_SCMI_CKTIMG2 25 +#define CK_SCMI_CKTIMG3 26 +#define CK_SCMI_RTC 27 +#define CK_SCMI_RTCAPB 28 + +#endif /* _DT_BINDINGS_STM32MP13_CLKS_H_ */ diff --git a/include/dt-bindings/reset/stm32mp13-resets.h b/include/dt-bindings/reset/stm32mp13-resets.h new file mode 100644 index 000000000000..934864e90da6 --- /dev/null +++ b/include/dt-bindings/reset/stm32mp13-resets.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */ +/* + * Copyright (C) STMicroelectronics 2018 - All Rights Reserved + * Author: Gabriel Fernandez for STMicroelectronics. + */ + +#ifndef _DT_BINDINGS_STM32MP13_RESET_H_ +#define _DT_BINDINGS_STM32MP13_RESET_H_ + +#define TIM2_R 13568 +#define TIM3_R 13569 +#define TIM4_R 13570 +#define TIM5_R 13571 +#define TIM6_R 13572 +#define TIM7_R 13573 +#define LPTIM1_R 13577 +#define SPI2_R 13579 +#define SPI3_R 13580 +#define USART3_R 13583 +#define UART4_R 13584 +#define UART5_R 13585 +#define UART7_R 13586 +#define UART8_R 13587 +#define I2C1_R 13589 +#define I2C2_R 13590 +#define SPDIF_R 13594 +#define TIM1_R 13632 +#define TIM8_R 13633 +#define SPI1_R 13640 +#define USART6_R 13645 +#define SAI1_R 13648 +#define SAI2_R 13649 +#define DFSDM_R 13652 +#define FDCAN_R 13656 +#define LPTIM2_R 13696 +#define LPTIM3_R 13697 +#define LPTIM4_R 13698 +#define LPTIM5_R 13699 +#define SYSCFG_R 13707 +#define VREF_R 13709 +#define DTS_R 13712 +#define PMBCTRL_R 13713 +#define LTDC_R 13760 +#define DCMIPP_R 13761 +#define DDRPERFM_R 13768 +#define USBPHY_R 13776 +#define STGEN_R 13844 +#define USART1_R 13888 +#define USART2_R 13889 +#define SPI4_R 13890 +#define SPI5_R 13891 +#define I2C3_R 13892 +#define I2C4_R 13893 +#define I2C5_R 13894 +#define TIM12_R 13895 +#define TIM13_R 13896 +#define TIM14_R 13897 +#define TIM15_R 13898 +#define TIM16_R 13899 +#define TIM17_R 13900 +#define DMA1_R 13952 +#define DMA2_R 13953 +#define DMAMUX1_R 13954 +#define DMA3_R 13955 +#define DMAMUX2_R 13956 +#define ADC1_R 13957 +#define ADC2_R 13958 +#define USBO_R 13960 +#define GPIOA_R 14080 +#define GPIOB_R 14081 +#define GPIOC_R 14082 +#define GPIOD_R 14083 +#define GPIOE_R 14084 +#define GPIOF_R 14085 +#define GPIOG_R 14086 +#define GPIOH_R 14087 +#define GPIOI_R 14088 +#define TSC_R 14095 +#define PKA_R 14146 +#define SAES_R 14147 +#define CRYP1_R 14148 +#define HASH1_R 14149 +#define RNG1_R 14150 +#define AXIMC_R 14160 +#define MDMA_R 14208 +#define MCE_R 14209 +#define ETH1MAC_R 14218 +#define FMC_R 14220 +#define QSPI_R 14222 +#define SDMMC1_R 14224 +#define SDMMC2_R 14225 +#define CRC1_R 14228 +#define USBH_R 14232 +#define ETH2MAC_R 14238 + +/* SCMI reset domain identifiers */ +#define RST_SCMI_LTDC 0 +#define RST_SCMI_MDMA 1 + +#endif /* _DT_BINDINGS_STM32MP13_RESET_H_ */ -- cgit v1.2.3 From 1b3418ac6451b771b677e049b8a48d96e258e922 Mon Sep 17 00:00:00 2001 From: Yongqiang Niu Date: Wed, 6 Apr 2022 17:12:13 +0800 Subject: dt-bindings: gce: add the GCE header file for MT8186 Add the GCE header file to define GCE subsys ids, hardware event ids and constants for MT8186. Signed-off-by: Yongqiang Niu Acked-by: Rob Herring Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Jassi Brar --- include/dt-bindings/gce/mt8186-gce.h | 421 +++++++++++++++++++++++++++++++++++ 1 file changed, 421 insertions(+) create mode 100644 include/dt-bindings/gce/mt8186-gce.h (limited to 'include') diff --git a/include/dt-bindings/gce/mt8186-gce.h b/include/dt-bindings/gce/mt8186-gce.h new file mode 100644 index 000000000000..f12e3cb586ce --- /dev/null +++ b/include/dt-bindings/gce/mt8186-gce.h @@ -0,0 +1,421 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (C) 2022 MediaTek Inc. + * Author: Yongqiang Niu + */ + +#ifndef _DT_BINDINGS_GCE_MT8186_H +#define _DT_BINDINGS_GCE_MT8186_H + +/* assign timeout 0 also means default */ +#define CMDQ_NO_TIMEOUT 0xffffffff +#define CMDQ_TIMEOUT_DEFAULT 1000 + +/* GCE thread priority */ +#define CMDQ_THR_PRIO_LOWEST 0 +#define CMDQ_THR_PRIO_1 1 +#define CMDQ_THR_PRIO_2 2 +#define CMDQ_THR_PRIO_3 3 +#define CMDQ_THR_PRIO_4 4 +#define CMDQ_THR_PRIO_5 5 +#define CMDQ_THR_PRIO_6 6 +#define CMDQ_THR_PRIO_HIGHEST 7 + +/* CPR count in 32bit register */ +#define GCE_CPR_COUNT 1312 + +/* GCE subsys table */ +#define SUBSYS_1300XXXX 0 +#define SUBSYS_1400XXXX 1 +#define SUBSYS_1401XXXX 2 +#define SUBSYS_1402XXXX 3 +#define SUBSYS_1502XXXX 4 +#define SUBSYS_1582XXXX 5 +#define SUBSYS_1B00XXXX 6 +#define SUBSYS_1C00XXXX 7 +#define SUBSYS_1C10XXXX 8 +#define SUBSYS_1000XXXX 9 +#define SUBSYS_1001XXXX 10 +#define SUBSYS_1020XXXX 11 +#define SUBSYS_1021XXXX 12 +#define SUBSYS_1022XXXX 13 +#define SUBSYS_1023XXXX 14 +#define SUBSYS_1060XXXX 15 +#define SUBSYS_1602XXXX 16 +#define SUBSYS_1608XXXX 17 +#define SUBSYS_1700XXXX 18 +#define SUBSYS_1701XXXX 19 +#define SUBSYS_1702XXXX 20 +#define SUBSYS_1703XXXX 21 +#define SUBSYS_1706XXXX 22 +#define SUBSYS_1A00XXXX 23 +#define SUBSYS_1A01XXXX 24 +#define SUBSYS_1A02XXXX 25 +#define SUBSYS_1A03XXXX 26 +#define SUBSYS_1A04XXXX 27 +#define SUBSYS_1A05XXXX 28 +#define SUBSYS_1A06XXXX 29 +#define SUBSYS_NO_SUPPORT 99 + +/* GCE General Purpose Register (GPR) support + * Leave note for scenario usage here + */ +/* GCE: write mask */ +#define GCE_GPR_R00 0x00 +#define GCE_GPR_R01 0x01 +/* MDP: P1: JPEG dest */ +#define GCE_GPR_R02 0x02 +#define GCE_GPR_R03 0x03 +/* MDP: PQ color */ +#define GCE_GPR_R04 0x04 +/* MDP: 2D sharpness */ +#define GCE_GPR_R05 0x05 +/* DISP: poll esd */ +#define GCE_GPR_R06 0x06 +#define GCE_GPR_R07 0x07 +/* MDP: P4: 2D sharpness dst */ +#define GCE_GPR_R08 0x08 +#define GCE_GPR_R09 0x09 +/* VCU: poll with timeout for GPR timer */ +#define GCE_GPR_R10 0x0A +#define GCE_GPR_R11 0x0B +/* CMDQ: debug */ +#define GCE_GPR_R12 0x0C +#define GCE_GPR_R13 0x0D +/* CMDQ: P7: debug */ +#define GCE_GPR_R14 0x0E +#define GCE_GPR_R15 0x0F + +/* GCE hardware events */ +/* VDEC */ +#define CMDQ_EVENT_LINE_COUNT_THRESHOLD_INTERRUPT 0 +#define CMDQ_EVENT_VDEC_INT 1 +#define CMDQ_EVENT_VDEC_PAUSE 2 +#define CMDQ_EVENT_VDEC_DEC_ERROR 3 +#define CMDQ_EVENT_MDEC_TIMEOUT 4 +#define CMDQ_EVENT_DRAM_ACCESS_DONE 5 +#define CMDQ_EVENT_INI_FETCH_RDY 6 +#define CMDQ_EVENT_PROCESS_FLAG 7 +#define CMDQ_EVENT_SEARCH_START_CODE_DONE 8 +#define CMDQ_EVENT_REF_REORDER_DONE 9 +#define CMDQ_EVENT_WP_TBLE_DONE 10 +#define CMDQ_EVENT_COUNT_SRAM_CLR_DONE 11 +#define CMDQ_EVENT_GCE_CNT_OP_THRESHOLD 15 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_0 16 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_1 17 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_2 18 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_3 19 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_4 20 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_5 21 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_6 22 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_7 23 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_8 24 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_9 25 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_10 26 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_11 27 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_12 28 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_13 29 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_14 30 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_15 31 +#define CMDQ_EVENT_WPE_GCE_FRAME_DONE 32 + +/* CAM */ +#define CMDQ_EVENT_ISP_FRAME_DONE_A 65 +#define CMDQ_EVENT_ISP_FRAME_DONE_B 66 +#define CMDQ_EVENT_CAMSV1_PASS1_DONE 70 +#define CMDQ_EVENT_CAMSV2_PASS1_DONE 71 +#define CMDQ_EVENT_CAMSV3_PASS1_DONE 72 +#define CMDQ_EVENT_MRAW_0_PASS1_DONE 73 +#define CMDQ_EVENT_SENINF_CAM0_FIFO_FULL 75 +#define CMDQ_EVENT_SENINF_CAM1_FIFO_FULL 76 +#define CMDQ_EVENT_SENINF_CAM2_FIFO_FULL 77 +#define CMDQ_EVENT_SENINF_CAM3_FIFO_FULL 78 +#define CMDQ_EVENT_SENINF_CAM4_FIFO_FULL 79 +#define CMDQ_EVENT_SENINF_CAM5_FIFO_FULL 80 +#define CMDQ_EVENT_SENINF_CAM6_FIFO_FULL 81 +#define CMDQ_EVENT_SENINF_CAM7_FIFO_FULL 82 +#define CMDQ_EVENT_SENINF_CAM8_FIFO_FULL 83 +#define CMDQ_EVENT_SENINF_CAM9_FIFO_FULL 84 +#define CMDQ_EVENT_SENINF_CAM10_FIFO_FULL 85 +#define CMDQ_EVENT_SENINF_CAM11_FIFO_FULL 86 +#define CMDQ_EVENT_SENINF_CAM12_FIFO_FULL 87 +#define CMDQ_EVENT_TG_OVRUN_A_INT 88 +#define CMDQ_EVENT_DMA_R1_ERROR_A_INT 89 +#define CMDQ_EVENT_TG_OVRUN_B_INT 90 +#define CMDQ_EVENT_DMA_R1_ERROR_B_INT 91 +#define CMDQ_EVENT_TG_OVRUN_M0_INT 94 +#define CMDQ_EVENT_R1_ERROR_M0_INT 95 +#define CMDQ_EVENT_TG_GRABERR_M0_INT 96 +#define CMDQ_EVENT_TG_GRABERR_A_INT 98 +#define CMDQ_EVENT_CQ_VR_SNAP_A_INT 99 +#define CMDQ_EVENT_TG_GRABERR_B_INT 100 +#define CMDQ_EVENT_CQ_VR_SNAP_B_INT 101 +/* VENC */ +#define CMDQ_EVENT_VENC_CMDQ_FRAME_DONE 129 +#define CMDQ_EVENT_VENC_CMDQ_PAUSE_DONE 130 +#define CMDQ_EVENT_JPGENC_CMDQ_DONE 131 +#define CMDQ_EVENT_VENC_CMDQ_MB_DONE 132 +#define CMDQ_EVENT_VENC_CMDQ_128BYTE_CNT_DONE 133 +#define CMDQ_EVENT_VENC_CMDQ_PPS_DONE 136 +#define CMDQ_EVENT_VENC_CMDQ_SPS_DONE 137 +#define CMDQ_EVENT_VENC_CMDQ_VPS_DONE 138 +/* IPE */ +#define CMDQ_EVENT_FDVT_DONE 161 +#define CMDQ_EVENT_FE_DONE 162 +#define CMDQ_EVENT_RSC_DONE 163 +#define CMDQ_EVENT_DVS_DONE_ASYNC_SHOT 164 +#define CMDQ_EVENT_DVP_DONE_ASYNC_SHOT 165 +/* IMG2 */ +#define CMDQ_EVENT_GCE_IMG2_EVENT0 193 +#define CMDQ_EVENT_GCE_IMG2_EVENT1 194 +#define CMDQ_EVENT_GCE_IMG2_EVENT2 195 +#define CMDQ_EVENT_GCE_IMG2_EVENT3 196 +#define CMDQ_EVENT_GCE_IMG2_EVENT4 197 +#define CMDQ_EVENT_GCE_IMG2_EVENT5 198 +#define CMDQ_EVENT_GCE_IMG2_EVENT6 199 +#define CMDQ_EVENT_GCE_IMG2_EVENT7 200 +#define CMDQ_EVENT_GCE_IMG2_EVENT8 201 +#define CMDQ_EVENT_GCE_IMG2_EVENT9 202 +#define CMDQ_EVENT_GCE_IMG2_EVENT10 203 +#define CMDQ_EVENT_GCE_IMG2_EVENT11 204 +#define CMDQ_EVENT_GCE_IMG2_EVENT12 205 +#define CMDQ_EVENT_GCE_IMG2_EVENT13 206 +#define CMDQ_EVENT_GCE_IMG2_EVENT14 207 +#define CMDQ_EVENT_GCE_IMG2_EVENT15 208 +#define CMDQ_EVENT_GCE_IMG2_EVENT16 209 +#define CMDQ_EVENT_GCE_IMG2_EVENT17 210 +#define CMDQ_EVENT_GCE_IMG2_EVENT18 211 +#define CMDQ_EVENT_GCE_IMG2_EVENT19 212 +#define CMDQ_EVENT_GCE_IMG2_EVENT20 213 +#define CMDQ_EVENT_GCE_IMG2_EVENT21 214 +#define CMDQ_EVENT_GCE_IMG2_EVENT22 215 +#define CMDQ_EVENT_GCE_IMG2_EVENT23 216 +/* IMG1 */ +#define CMDQ_EVENT_GCE_IMG1_EVENT0 225 +#define CMDQ_EVENT_GCE_IMG1_EVENT1 226 +#define CMDQ_EVENT_GCE_IMG1_EVENT2 227 +#define CMDQ_EVENT_GCE_IMG1_EVENT3 228 +#define CMDQ_EVENT_GCE_IMG1_EVENT4 229 +#define CMDQ_EVENT_GCE_IMG1_EVENT5 230 +#define CMDQ_EVENT_GCE_IMG1_EVENT6 231 +#define CMDQ_EVENT_GCE_IMG1_EVENT7 232 +#define CMDQ_EVENT_GCE_IMG1_EVENT8 233 +#define CMDQ_EVENT_GCE_IMG1_EVENT9 234 +#define CMDQ_EVENT_GCE_IMG1_EVENT10 235 +#define CMDQ_EVENT_GCE_IMG1_EVENT11 236 +#define CMDQ_EVENT_GCE_IMG1_EVENT12 237 +#define CMDQ_EVENT_GCE_IMG1_EVENT13 238 +#define CMDQ_EVENT_GCE_IMG1_EVENT14 239 +#define CMDQ_EVENT_GCE_IMG1_EVENT15 240 +#define CMDQ_EVENT_GCE_IMG1_EVENT16 241 +#define CMDQ_EVENT_GCE_IMG1_EVENT17 242 +#define CMDQ_EVENT_GCE_IMG1_EVENT18 243 +#define CMDQ_EVENT_GCE_IMG1_EVENT19 244 +#define CMDQ_EVENT_GCE_IMG1_EVENT20 245 +#define CMDQ_EVENT_GCE_IMG1_EVENT21 246 +#define CMDQ_EVENT_GCE_IMG1_EVENT22 247 +#define CMDQ_EVENT_GCE_IMG1_EVENT23 248 +/* MDP */ +#define CMDQ_EVENT_MDP_RDMA0_SOF 256 +#define CMDQ_EVENT_MDP_RDMA1_SOF 257 +#define CMDQ_EVENT_MDP_AAL0_SOF 258 +#define CMDQ_EVENT_MDP_AAL1_SOF 259 +#define CMDQ_EVENT_MDP_HDR0_SOF 260 +#define CMDQ_EVENT_MDP_RSZ0_SOF 261 +#define CMDQ_EVENT_MDP_RSZ1_SOF 262 +#define CMDQ_EVENT_MDP_WROT0_SOF 263 +#define CMDQ_EVENT_MDP_WROT1_SOF 264 +#define CMDQ_EVENT_MDP_TDSHP0_SOF 265 +#define CMDQ_EVENT_MDP_TDSHP1_SOF 266 +#define CMDQ_EVENT_IMG_DL_RELAY0_SOF 267 +#define CMDQ_EVENT_IMG_DL_RELAY1_SOF 268 +#define CMDQ_EVENT_MDP_COLOR0_SOF 269 +#define CMDQ_EVENT_MDP_WROT3_FRAME_DONE 288 +#define CMDQ_EVENT_MDP_WROT2_FRAME_DONE 289 +#define CMDQ_EVENT_MDP_WROT1_FRAME_DONE 290 +#define CMDQ_EVENT_MDP_WROT0_FRAME_DONE 291 +#define CMDQ_EVENT_MDP_TDSHP3_FRAME_DONE 292 +#define CMDQ_EVENT_MDP_TDSHP2_FRAME_DONE 293 +#define CMDQ_EVENT_MDP_TDSHP1_FRAME_DONE 294 +#define CMDQ_EVENT_MDP_TDSHP0_FRAME_DONE 295 +#define CMDQ_EVENT_MDP_RSZ3_FRAME_DONE 296 +#define CMDQ_EVENT_MDP_RSZ2_FRAME_DONE 297 +#define CMDQ_EVENT_MDP_RSZ1_FRAME_DONE 298 +#define CMDQ_EVENT_MDP_RSZ0_FRAME_DONE 299 +#define CMDQ_EVENT_MDP_RDMA3_FRAME_DONE 300 +#define CMDQ_EVENT_MDP_RDMA2_FRAME_DONE 301 +#define CMDQ_EVENT_MDP_RDMA1_FRAME_DONE 302 +#define CMDQ_EVENT_MDP_RDMA0_FRAME_DONE 303 +#define CMDQ_EVENT_MDP_HDR1_FRAME_DONE 304 +#define CMDQ_EVENT_MDP_HDR0_FRAME_DONE 305 +#define CMDQ_EVENT_MDP_COLOR0_FRAME_DONE 306 +#define CMDQ_EVENT_MDP_AAL3_FRAME_DONE 307 +#define CMDQ_EVENT_MDP_AAL2_FRAME_DONE 308 +#define CMDQ_EVENT_MDP_AAL1_FRAME_DONE 309 +#define CMDQ_EVENT_MDP_AAL0_FRAME_DONE 310 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_0 320 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_1 321 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_2 322 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_3 323 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_4 324 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_5 325 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_6 326 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_7 327 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_8 328 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_9 329 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_10 330 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_11 331 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_12 332 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_13 333 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_14 334 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_15 335 +#define CMDQ_EVENT_MDP_WROT3_SW_RST_DONE_ENG_EVENT 336 +#define CMDQ_EVENT_MDP_WROT2_SW_RST_DONE_ENG_EVENT 337 +#define CMDQ_EVENT_MDP_WROT1_SW_RST_DONE_ENG_EVENT 338 +#define CMDQ_EVENT_MDP_WROT0_SW_RST_DONE_ENG_EVENT 339 +#define CMDQ_EVENT_MDP_RDMA3_SW_RST_DONE_ENG_EVENT 340 +#define CMDQ_EVENT_MDP_RDMA2_SW_RST_DONE_ENG_EVENT 341 +#define CMDQ_EVENT_MDP_RDMA1_SW_RST_DONE_ENG_EVENT 342 +#define CMDQ_EVENT_MDP_RDMA0_SW_RST_DONE_ENG_EVENT 343 +/* DISP */ +#define CMDQ_EVENT_DISP_OVL0_SOF 384 +#define CMDQ_EVENT_DISP_OVL0_2L_SOF 385 +#define CMDQ_EVENT_DISP_RDMA0_SOF 386 +#define CMDQ_EVENT_DISP_RSZ0_SOF 387 +#define CMDQ_EVENT_DISP_COLOR0_SOF 388 +#define CMDQ_EVENT_DISP_CCORR0_SOF 389 +#define CMDQ_EVENT_DISP_CCORR1_SOF 390 +#define CMDQ_EVENT_DISP_AAL0_SOF 391 +#define CMDQ_EVENT_DISP_GAMMA0_SOF 392 +#define CMDQ_EVENT_DISP_POSTMASK0_SOF 393 +#define CMDQ_EVENT_DISP_DITHER0_SOF 394 +#define CMDQ_EVENT_DISP_CM0_SOF 395 +#define CMDQ_EVENT_DISP_SPR0_SOF 396 +#define CMDQ_EVENT_DISP_DSC_WRAP0_SOF 397 +#define CMDQ_EVENT_DSI0_SOF 398 +#define CMDQ_EVENT_DISP_WDMA0_SOF 399 +#define CMDQ_EVENT_DISP_PWM0_SOF 400 +#define CMDQ_EVENT_DSI0_FRAME_DONE 410 +#define CMDQ_EVENT_DISP_WDMA0_FRAME_DONE 411 +#define CMDQ_EVENT_DISP_SPR0_FRAME_DONE 412 +#define CMDQ_EVENT_DISP_RSZ0_FRAME_DONE 413 +#define CMDQ_EVENT_DISP_RDMA0_FRAME_DONE 414 +#define CMDQ_EVENT_DISP_POSTMASK0_FRAME_DONE 415 +#define CMDQ_EVENT_DISP_OVL0_FRAME_DONE 416 +#define CMDQ_EVENT_DISP_OVL0_2L_FRAME_DONE 417 +#define CMDQ_EVENT_DISP_GAMMA0_FRAME_DONE 418 +#define CMDQ_EVENT_DISP_DSC_WRAP0_CORE0_FRAME_DONE 420 +#define CMDQ_EVENT_DISP_DITHER0_FRAME_DONE 421 +#define CMDQ_EVENT_DISP_COLOR0_FRAME_DONE 422 +#define CMDQ_EVENT_DISP_CM0_FRAME_DONE 423 +#define CMDQ_EVENT_DISP_CCORR1_FRAME_DONE 424 +#define CMDQ_EVENT_DISP_CCORR0_FRAME_DONE 425 +#define CMDQ_EVENT_DISP_AAL0_FRAME_DONE 426 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_0 434 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_1 435 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_2 436 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_3 437 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_4 438 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_5 439 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_6 440 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_7 441 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_8 442 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_9 443 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_10 444 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_11 445 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_12 446 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_13 447 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_14 448 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_15 449 +#define CMDQ_EVENT_DSI0_TE_ENG_EVENT 450 +#define CMDQ_EVENT_DSI0_IRQ_ENG_EVENT 451 +#define CMDQ_EVENT_DSI0_DONE_ENG_EVENT 452 +#define CMDQ_EVENT_DISP_WDMA0_SW_RST_DONE_ENG_EVENT 453 +#define CMDQ_EVENT_DISP_SMIASSERT_ENG_EVENT 454 +#define CMDQ_EVENT_DISP_POSTMASK0_RST_DONE_ENG_EVENT 455 +#define CMDQ_EVENT_DISP_OVL0_RST_DONE_ENG_EVENT 456 +#define CMDQ_EVENT_DISP_OVL0_2L_RST_DONE_ENG_EVENT 457 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_0 458 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_1 459 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_2 460 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_3 461 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_4 462 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_5 463 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_6 464 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_7 465 +#define CMDQ_EVENT_OUT_EVENT_0 898 + +/* CMDQ sw tokens + * Following definitions are gce sw token which may use by clients + * event operation API. + * Note that token 512 to 639 may set secure + */ + +/* end of hw event and begin of sw token */ +#define CMDQ_MAX_HW_EVENT 512 + +/* Config thread notify trigger thread */ +#define CMDQ_SYNC_TOKEN_CONFIG_DIRTY 640 +/* Trigger thread notify config thread */ +#define CMDQ_SYNC_TOKEN_STREAM_EOF 641 +/* Block Trigger thread until the ESD check finishes. */ +#define CMDQ_SYNC_TOKEN_ESD_EOF 642 +#define CMDQ_SYNC_TOKEN_STREAM_BLOCK 643 +/* check CABC setup finish */ +#define CMDQ_SYNC_TOKEN_CABC_EOF 644 + +/* Notify normal CMDQ there are some secure task done + * MUST NOT CHANGE, this token sync with secure world + */ +#define CMDQ_SYNC_SECURE_THR_EOF 647 + +/* CMDQ use sw token */ +#define CMDQ_SYNC_TOKEN_USER_0 649 +#define CMDQ_SYNC_TOKEN_USER_1 650 +#define CMDQ_SYNC_TOKEN_POLL_MONITOR 651 +#define CMDQ_SYNC_TOKEN_TPR_LOCK 652 + +/* ISP sw token */ +#define CMDQ_SYNC_TOKEN_MSS 665 +#define CMDQ_SYNC_TOKEN_MSF 666 + +/* DISP sw token */ +#define CMDQ_SYNC_TOKEN_SODI 671 + +/* GPR access tokens (for register backup) + * There are 15 32-bit GPR, 3 GPR form a set + * (64-bit for address, 32-bit for value) + * MUST NOT CHANGE, these tokens sync with MDP + */ +#define CMDQ_SYNC_TOKEN_GPR_SET_0 700 +#define CMDQ_SYNC_TOKEN_GPR_SET_1 701 +#define CMDQ_SYNC_TOKEN_GPR_SET_2 702 +#define CMDQ_SYNC_TOKEN_GPR_SET_3 703 +#define CMDQ_SYNC_TOKEN_GPR_SET_4 704 + +/* Resource lock event to control resource in GCE thread */ +#define CMDQ_SYNC_RESOURCE_WROT0 710 +#define CMDQ_SYNC_RESOURCE_WROT1 711 + +/* event for gpr timer, used in sleep and poll with timeout */ +#define CMDQ_TOKEN_GPR_TIMER_R0 994 +#define CMDQ_TOKEN_GPR_TIMER_R1 995 +#define CMDQ_TOKEN_GPR_TIMER_R2 996 +#define CMDQ_TOKEN_GPR_TIMER_R3 997 +#define CMDQ_TOKEN_GPR_TIMER_R4 998 +#define CMDQ_TOKEN_GPR_TIMER_R5 999 +#define CMDQ_TOKEN_GPR_TIMER_R6 1000 +#define CMDQ_TOKEN_GPR_TIMER_R7 1001 +#define CMDQ_TOKEN_GPR_TIMER_R8 1002 +#define CMDQ_TOKEN_GPR_TIMER_R9 1003 +#define CMDQ_TOKEN_GPR_TIMER_R10 1004 +#define CMDQ_TOKEN_GPR_TIMER_R11 1005 +#define CMDQ_TOKEN_GPR_TIMER_R12 1006 +#define CMDQ_TOKEN_GPR_TIMER_R13 1007 +#define CMDQ_TOKEN_GPR_TIMER_R14 1008 +#define CMDQ_TOKEN_GPR_TIMER_R15 1009 + +#define CMDQ_EVENT_MAX 0x3FF +/* CMDQ sw tokens END */ + +#endif -- cgit v1.2.3 From 58919326e72f63c380dc3271dd1cc8bdf1bbe3e4 Mon Sep 17 00:00:00 2001 From: Kartik Date: Thu, 14 Apr 2022 13:05:56 +0530 Subject: dt-bindings: tegra186-hsp: add type for shared mailboxes Tegra234 supports sending/receiving 32-bit and 128-bit data over a shared mailbox. Based on the data size to be used, clients need to specify the type of shared mailbox in the device tree. Add a macro for 128-bit shared mailbox. Mailbox clients can use this macro as a flag in device tree to enable 128-bit data support for a shared mailbox. Signed-off-by: Kartik Acked-by: Rob Herring Signed-off-by: Jassi Brar --- include/dt-bindings/mailbox/tegra186-hsp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/mailbox/tegra186-hsp.h b/include/dt-bindings/mailbox/tegra186-hsp.h index 3bdec7a84d35..b9ccae2aa9e2 100644 --- a/include/dt-bindings/mailbox/tegra186-hsp.h +++ b/include/dt-bindings/mailbox/tegra186-hsp.h @@ -15,6 +15,11 @@ #define TEGRA_HSP_MBOX_TYPE_SS 0x2 #define TEGRA_HSP_MBOX_TYPE_AS 0x3 +/* + * These define the types of shared mailbox supported based on data size. + */ +#define TEGRA_HSP_MBOX_TYPE_SM_128BIT (1 << 8) + /* * These defines represent the bit associated with the given master ID in the * doorbell registers. -- cgit v1.2.3 From bb12dd42d20f5513a8d1da225232af0a0743fd79 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 24 Sep 2021 12:56:53 +0200 Subject: powerpc/powermac: constify device_node in of_irq_parse_oldworld() The of_irq_parse_oldworld() does not modify passed device_node so make it a pointer to const for safety. Drop the extern while modifying the line. Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210924105653.46963-2-krzysztof.kozlowski@canonical.com --- include/linux/of_irq.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index aaf219bd0354..83fccd0c9bba 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -20,12 +20,12 @@ typedef int (*of_irq_init_cb_t)(struct device_node *, struct device_node *); #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) extern unsigned int of_irq_workarounds; extern struct device_node *of_irq_dflt_pic; -extern int of_irq_parse_oldworld(struct device_node *device, int index, - struct of_phandle_args *out_irq); +int of_irq_parse_oldworld(const struct device_node *device, int index, + struct of_phandle_args *out_irq); #else /* CONFIG_PPC32 && CONFIG_PPC_PMAC */ #define of_irq_workarounds (0) #define of_irq_dflt_pic (NULL) -static inline int of_irq_parse_oldworld(struct device_node *device, int index, +static inline int of_irq_parse_oldworld(const struct device_node *device, int index, struct of_phandle_args *out_irq) { return -EINVAL; -- cgit v1.2.3 From cd705ea857fdd859a9df09e8adda4cb4c906e8a2 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Fri, 1 Apr 2022 23:40:29 +0200 Subject: lib: add generic polynomial calculation Some temperature and voltage sensors use a polynomial to convert between raw data points and actual temperature or voltage. The polynomial is usually the result of a curve fitting of the diode characteristic. The BT1 PVT hwmon driver already uses such a polynonmial calculation which is rather generic. Move it to lib/ so other drivers can reuse it. Signed-off-by: Michael Walle Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20220401214032.3738095-2-michael@walle.cc Signed-off-by: Guenter Roeck --- include/linux/polynomial.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/polynomial.h (limited to 'include') diff --git a/include/linux/polynomial.h b/include/linux/polynomial.h new file mode 100644 index 000000000000..9e074a0bb6fa --- /dev/null +++ b/include/linux/polynomial.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 BAIKAL ELECTRONICS, JSC + */ + +#ifndef _POLYNOMIAL_H +#define _POLYNOMIAL_H + +/* + * struct polynomial_term - one term descriptor of a polynomial + * @deg: degree of the term. + * @coef: multiplication factor of the term. + * @divider: distributed divider per each degree. + * @divider_leftover: divider leftover, which couldn't be redistributed. + */ +struct polynomial_term { + unsigned int deg; + long coef; + long divider; + long divider_leftover; +}; + +/* + * struct polynomial - a polynomial descriptor + * @total_divider: total data divider. + * @terms: polynomial terms, last term must have degree of 0 + */ +struct polynomial { + long total_divider; + struct polynomial_term terms[]; +}; + +long polynomial_calc(const struct polynomial *poly, long data); + +#endif -- cgit v1.2.3 From e5d21072054fbadf41cd56062a3a14e447e8c22b Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 11 May 2022 06:29:59 -0700 Subject: hwmon: Introduce hwmon_device_register_for_thermal The thermal subsystem registers a hwmon driver without providing chip or sysfs group information. This is for legacy reasons and would be difficult to change. At the same time, we want to enforce that chip information is provided when registering a hwmon device using hwmon_device_register_with_info(). To enable this, introduce a special API for use only by the thermal subsystem. Acked-by: Rafael J . Wysocki Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 4efaf06fd2b8..14325f93c6b2 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -450,6 +450,9 @@ hwmon_device_register_with_info(struct device *dev, const struct hwmon_chip_info *info, const struct attribute_group **extra_groups); struct device * +hwmon_device_register_for_thermal(struct device *dev, const char *name, + void *drvdata); +struct device * devm_hwmon_device_register_with_info(struct device *dev, const char *name, void *drvdata, const struct hwmon_chip_info *info, -- cgit v1.2.3 From 1359fcbe0f4aa2cd6ea684727a5a111eebeeed3a Mon Sep 17 00:00:00 2001 From: Ohad Sharabi Date: Wed, 23 Feb 2022 11:47:05 +0200 Subject: habanalabs: add DRAM default page size to HW info When using the device memory allocation API the user ought to know what is the default allocation page size. Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/habanalabs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 1d6b4f0c4159..ae2441521467 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -409,6 +409,7 @@ enum hl_server_type { * @dram_page_size: The DRAM physical page size. * @number_of_user_interrupts: The number of interrupts that are available to the userspace * application to use. Relevant for Gaudi2 and later. + * @device_mem_alloc_default_page_size: default page size used in device memory allocation. */ struct hl_info_hw_ip_info { __u64 sram_base_address; @@ -436,6 +437,8 @@ struct hl_info_hw_ip_info { __u32 reserved3; __u16 number_of_user_interrupts; __u16 pad2; + __u64 reserved4; + __u64 device_mem_alloc_default_page_size; }; struct hl_info_dram_usage { -- cgit v1.2.3 From 050a6f349a09d3cefb14f4114bfa047b2c5b2a65 Mon Sep 17 00:00:00 2001 From: Ohad Sharabi Date: Wed, 23 Feb 2022 13:37:08 +0200 Subject: habanalabs: add user API to get valid DRAM page sizes Future devices will support multiple device memory page sizes. In addition, an API for the user was added for it to be able to control the device memory allocation page size. This patch is a complementary patch to inform the user of the available page size supported by the device. Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/habanalabs.h | 63 +++++++++++++++++++++++++----------------- 1 file changed, 37 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index ae2441521467..f474e7fb018d 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -348,33 +348,35 @@ enum hl_server_type { * The address which accessing it caused the razwi. * Razwi initiator. * Razwi cause, was it a page fault or MMU access error. + * HL_INFO_DEV_MEM_ALLOC_PAGE_SIZES - Retrieve valid page sizes for device memory allocation */ -#define HL_INFO_HW_IP_INFO 0 -#define HL_INFO_HW_EVENTS 1 -#define HL_INFO_DRAM_USAGE 2 -#define HL_INFO_HW_IDLE 3 -#define HL_INFO_DEVICE_STATUS 4 -#define HL_INFO_DEVICE_UTILIZATION 6 -#define HL_INFO_HW_EVENTS_AGGREGATE 7 -#define HL_INFO_CLK_RATE 8 -#define HL_INFO_RESET_COUNT 9 -#define HL_INFO_TIME_SYNC 10 -#define HL_INFO_CS_COUNTERS 11 -#define HL_INFO_PCI_COUNTERS 12 -#define HL_INFO_CLK_THROTTLE_REASON 13 -#define HL_INFO_SYNC_MANAGER 14 -#define HL_INFO_TOTAL_ENERGY 15 -#define HL_INFO_PLL_FREQUENCY 16 -#define HL_INFO_POWER 17 -#define HL_INFO_OPEN_STATS 18 -#define HL_INFO_DRAM_REPLACED_ROWS 21 -#define HL_INFO_DRAM_PENDING_ROWS 22 -#define HL_INFO_LAST_ERR_OPEN_DEV_TIME 23 -#define HL_INFO_CS_TIMEOUT_EVENT 24 -#define HL_INFO_RAZWI_EVENT 25 - -#define HL_INFO_VERSION_MAX_LEN 128 -#define HL_INFO_CARD_NAME_MAX_LEN 16 +#define HL_INFO_HW_IP_INFO 0 +#define HL_INFO_HW_EVENTS 1 +#define HL_INFO_DRAM_USAGE 2 +#define HL_INFO_HW_IDLE 3 +#define HL_INFO_DEVICE_STATUS 4 +#define HL_INFO_DEVICE_UTILIZATION 6 +#define HL_INFO_HW_EVENTS_AGGREGATE 7 +#define HL_INFO_CLK_RATE 8 +#define HL_INFO_RESET_COUNT 9 +#define HL_INFO_TIME_SYNC 10 +#define HL_INFO_CS_COUNTERS 11 +#define HL_INFO_PCI_COUNTERS 12 +#define HL_INFO_CLK_THROTTLE_REASON 13 +#define HL_INFO_SYNC_MANAGER 14 +#define HL_INFO_TOTAL_ENERGY 15 +#define HL_INFO_PLL_FREQUENCY 16 +#define HL_INFO_POWER 17 +#define HL_INFO_OPEN_STATS 18 +#define HL_INFO_DRAM_REPLACED_ROWS 21 +#define HL_INFO_DRAM_PENDING_ROWS 22 +#define HL_INFO_LAST_ERR_OPEN_DEV_TIME 23 +#define HL_INFO_CS_TIMEOUT_EVENT 24 +#define HL_INFO_RAZWI_EVENT 25 +#define HL_INFO_DEV_MEM_ALLOC_PAGE_SIZES 26 + +#define HL_INFO_VERSION_MAX_LEN 128 +#define HL_INFO_CARD_NAME_MAX_LEN 16 /** * struct hl_info_hw_ip_info - hardware information on various IPs in the ASIC @@ -643,6 +645,15 @@ struct hl_info_razwi_event { __u8 pad[2]; }; +/** + * struct hl_info_dev_memalloc_page_sizes - valid page sizes in device mem alloc information. + * @page_order_bitmask: bitmap in which a set bit represents the order of the supported page size + * (e.g. 0x2100000 means that 1MB and 32MB pages are supported). + */ +struct hl_info_dev_memalloc_page_sizes { + __u64 page_order_bitmask; +}; + enum gaudi_dcores { HL_GAUDI_WS_DCORE, HL_GAUDI_WN_DCORE, -- cgit v1.2.3 From fdec56c1a416c6947b1db22617da15cb89f46c6c Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Thu, 3 Mar 2022 09:43:10 +0200 Subject: habanalabs: expose compute ctx status through info ioctl In order for the user to know if he can try and open device, we expose the compute ctx state. The user can now know if the context is used by another process or whether the device is still ongoing through cleanup or reset and will be available soon. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/habanalabs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index f474e7fb018d..ca2af5f98056 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -543,10 +543,15 @@ struct hl_pll_frequency_info { * struct hl_open_stats_info - device open statistics information * @open_counter: ever growing counter, increased on each successful dev open * @last_open_period_ms: duration (ms) device was open last time + * @is_compute_ctx_active: Whether there is an active compute context executing + * @compute_ctx_in_release: true if the current compute context is being released */ struct hl_open_stats_info { __u64 open_counter; __u64 last_open_period_ms; + __u8 is_compute_ctx_active; + __u8 compute_ctx_in_release; + __u8 pad[6]; }; /** -- cgit v1.2.3 From 5d1a0de2c778f369970dd50f6713e95068926a8b Mon Sep 17 00:00:00 2001 From: Ohad Sharabi Date: Sun, 10 Apr 2022 11:19:42 +0300 Subject: habanalabs: add prefetch flag to the MAP operation This patch let the user decide whether the translations done in the page tables will be fetched directly to the STLB right after the map. We want to let the user control whether to perform prefetch upon map operation. To do so a memory flag was added, to be used in the MAP ioctl, called HL_MEM_PREFETCH and if set- the mappings will be fetched directly to the STLB after map operation. Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/habanalabs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index ca2af5f98056..3576bf2b4841 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -1134,6 +1134,7 @@ union hl_wait_cs_args { #define HL_MEM_SHARED 0x2 #define HL_MEM_USERPTR 0x4 #define HL_MEM_FORCE_HINT 0x8 +#define HL_MEM_PREFETCH 0x40 /** * structure hl_mem_in - structure that handle input args for memory IOCTL -- cgit v1.2.3 From 422ef171038d4855ffe938137039a8f3b3e84293 Mon Sep 17 00:00:00 2001 From: Tal Cohen Date: Thu, 28 Apr 2022 13:45:18 +0300 Subject: habanalabs: add support for notification via eventfd The driver will be able to send notification events towards a user process, using user's registered event file descriptor. The driver uses the notification mechanism to inform the user about an occurred event. A user thread can wait until a notification is received from the driver. The driver stores the occurred event until the user reads it, using HL_INFO_GET_EVENTS - new ioctl opcode in the INFO ioctl. Gaudi specific implementation includes sending a notification on a TPC assertion event that is received from f/w. Signed-off-by: Tal Cohen Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/habanalabs.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 3576bf2b4841..52540d5b4fc9 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -349,6 +349,9 @@ enum hl_server_type { * Razwi initiator. * Razwi cause, was it a page fault or MMU access error. * HL_INFO_DEV_MEM_ALLOC_PAGE_SIZES - Retrieve valid page sizes for device memory allocation + * HL_INFO_REGISTER_EVENTFD - Register eventfd for event notifications. + * HL_INFO_UNREGISTER_EVENTFD - Unregister eventfd + * HL_INFO_GET_EVENTS - Retrieve the last occurred events */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 @@ -374,6 +377,9 @@ enum hl_server_type { #define HL_INFO_CS_TIMEOUT_EVENT 24 #define HL_INFO_RAZWI_EVENT 25 #define HL_INFO_DEV_MEM_ALLOC_PAGE_SIZES 26 +#define HL_INFO_REGISTER_EVENTFD 28 +#define HL_INFO_UNREGISTER_EVENTFD 29 +#define HL_INFO_GET_EVENTS 30 #define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 @@ -679,6 +685,7 @@ enum gaudi_dcores { * @period_ms: Period value, in milliseconds, for utilization rate in range 100ms - 1000ms in 100 ms * resolution. Currently not in use. * @pll_index: Index as defined in hl__pll_index enumeration. + * @eventfd: event file descriptor for event notifications. * @pad: Padding to 64 bit. */ struct hl_info_args { @@ -691,6 +698,7 @@ struct hl_info_args { __u32 ctx_id; __u32 period_ms; __u32 pll_index; + __u32 eventfd; }; __u32 pad; @@ -1390,6 +1398,13 @@ struct hl_debug_args { __u32 ctx_id; }; +/* + * Notifier event values - for the notification mechanism and the HL_INFO_GET_EVENTS command + * + * HL_NOTIFIER_EVENT_TPC_ASSERT - Indicates TPC assert event + */ +#define HL_NOTIFIER_EVENT_TPC_ASSERT (1 << 0) + /* * Various information operations such as: * - H/W IP information -- cgit v1.2.3 From cc4e7fa549cb69c18bc2ba7209df373ca06749e3 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 21 May 2022 13:10:53 +0200 Subject: net: qed: fix typos in comments Spelling mistakes (triple letters) in comments. Detected with the help of Coccinelle. Signed-off-by: Julia Lawall Signed-off-by: David S. Miller --- include/linux/qed/qed_fcoe_if.h | 4 ++-- include/linux/qed/qed_iscsi_if.h | 4 ++-- include/linux/qed/qed_nvmetcp_if.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h index 16752eca5cbd..90e3045b2dcb 100644 --- a/include/linux/qed/qed_fcoe_if.h +++ b/include/linux/qed/qed_fcoe_if.h @@ -76,7 +76,7 @@ void qed_fcoe_set_pf_params(struct qed_dev *cdev, * @fill_dev_info: fills FCoE specific information * @param cdev * @param info - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @register_ops: register FCoE operations * @param cdev * @param ops - specified using qed_iscsi_cb_ops @@ -96,7 +96,7 @@ void qed_fcoe_set_pf_params(struct qed_dev *cdev, * connection. * @param p_doorbell - qed will fill the address of the * doorbell. - * return 0 on sucesss, otherwise error value. + * return 0 on success, otherwise error value. * @release_conn: release a previously acquired fcoe connection * @param cdev * @param handle - the connection handle. diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h index 494cdc3cd840..fbf7973ae9ba 100644 --- a/include/linux/qed/qed_iscsi_if.h +++ b/include/linux/qed/qed_iscsi_if.h @@ -133,7 +133,7 @@ struct qed_iscsi_cb_ops { * @fill_dev_info: fills iSCSI specific information * @param cdev * @param info - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @register_ops: register iscsi operations * @param cdev * @param ops - specified using qed_iscsi_cb_ops @@ -152,7 +152,7 @@ struct qed_iscsi_cb_ops { * connection. * @param p_doorbell - qed will fill the address of the * doorbell. - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @release_conn: release a previously acquired iscsi connection * @param cdev * @param handle - the connection handle. diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 1d51df347560..bbfbfba51f37 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -132,7 +132,7 @@ struct nvmetcp_task_params { * connection. * @param p_doorbell - qed will fill the address of the * doorbell. - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @release_conn: release a previously acquired nvmetcp connection * @param cdev * @param handle - the connection handle. -- cgit v1.2.3 From a05754295e01f006a651eec759c5dbe682ef6cef Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 21 May 2022 08:45:22 +0100 Subject: rxrpc: Use refcount_t rather than atomic_t Move to using refcount_t rather than atomic_t for refcounts in rxrpc. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- include/trace/events/rxrpc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4a3ab0ed6e06..cdb28976641b 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -583,7 +583,7 @@ TRACE_EVENT(rxrpc_client, TP_fast_assign( __entry->conn = conn ? conn->debug_id : 0; __entry->channel = channel; - __entry->usage = conn ? atomic_read(&conn->usage) : -2; + __entry->usage = conn ? refcount_read(&conn->ref) : -2; __entry->op = op; __entry->cid = conn ? conn->proto.cid : 0; ), -- cgit v1.2.3 From ad25f5cb39872ca14bcbe00816ae65c22fe04b89 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 21 May 2022 08:45:28 +0100 Subject: rxrpc: Fix locking issue There's a locking issue with the per-netns list of calls in rxrpc. The pieces of code that add and remove a call from the list use write_lock() and the calls procfile uses read_lock() to access it. However, the timer callback function may trigger a removal by trying to queue a call for processing and finding that it's already queued - at which point it has a spare refcount that it has to do something with. Unfortunately, if it puts the call and this reduces the refcount to 0, the call will be removed from the list. Unfortunately, since the _bh variants of the locking functions aren't used, this can deadlock. ================================ WARNING: inconsistent lock state 5.18.0-rc3-build4+ #10 Not tainted -------------------------------- inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. ksoftirqd/2/25 [HC0[0]:SC1[1]:HE1:SE0] takes: ffff888107ac4038 (&rxnet->call_lock){+.?.}-{2:2}, at: rxrpc_put_call+0x103/0x14b {SOFTIRQ-ON-W} state was registered at: ... Possible unsafe locking scenario: CPU0 ---- lock(&rxnet->call_lock); lock(&rxnet->call_lock); *** DEADLOCK *** 1 lock held by ksoftirqd/2/25: #0: ffff8881008ffdb0 ((&call->timer)){+.-.}-{0:0}, at: call_timer_fn+0x5/0x23d Changes ======= ver #2) - Changed to using list_next_rcu() rather than rcu_dereference() directly. Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both") Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- include/linux/list.h | 10 ++++++++++ include/linux/seq_file.h | 4 ++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index c147eeb2d39d..57e8b559cdf6 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -605,6 +605,16 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_for_each(pos, head) \ for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) +/** + * list_for_each_rcu - Iterate over a list in an RCU-safe fashion + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + */ +#define list_for_each_rcu(pos, head) \ + for (pos = rcu_dereference((head)->next); \ + !list_is_head(pos, (head)); \ + pos = rcu_dereference(pos->next)) + /** * list_for_each_continue - continue iteration over a list * @pos: the &struct list_head to use as a loop cursor. diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 60820ab511d2..bd023dd38ae6 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -277,6 +277,10 @@ extern struct list_head *seq_list_start_head(struct list_head *head, extern struct list_head *seq_list_next(void *v, struct list_head *head, loff_t *ppos); +extern struct list_head *seq_list_start_rcu(struct list_head *head, loff_t pos); +extern struct list_head *seq_list_start_head_rcu(struct list_head *head, loff_t pos); +extern struct list_head *seq_list_next_rcu(void *v, struct list_head *head, loff_t *ppos); + /* * Helpers for iteration over hlist_head-s in seq_files */ -- cgit v1.2.3 From dc9fd093b2ebabc25a5d7d0dd5bdfdd6c878e0bf Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 21 May 2022 08:45:35 +0100 Subject: rxrpc: Automatically generate trace tag enums Automatically generate trace tag enums from the symbol -> string mapping tables rather than having the enums as well, thereby reducing duplicated data. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- include/trace/events/rxrpc.h | 261 +++++++------------------------------------ 1 file changed, 42 insertions(+), 219 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index cdb28976641b..66915b872a44 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -13,215 +13,6 @@ #include #include -/* - * Define enums for tracing information. - * - * These should all be kept sorted, making it easier to match the string - * mapping tables further on. - */ -#ifndef __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY -#define __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY - -enum rxrpc_skb_trace { - rxrpc_skb_cleaned, - rxrpc_skb_freed, - rxrpc_skb_got, - rxrpc_skb_lost, - rxrpc_skb_new, - rxrpc_skb_purged, - rxrpc_skb_received, - rxrpc_skb_rotated, - rxrpc_skb_seen, - rxrpc_skb_unshared, - rxrpc_skb_unshared_nomem, -}; - -enum rxrpc_local_trace { - rxrpc_local_got, - rxrpc_local_new, - rxrpc_local_processing, - rxrpc_local_put, - rxrpc_local_queued, -}; - -enum rxrpc_peer_trace { - rxrpc_peer_got, - rxrpc_peer_new, - rxrpc_peer_processing, - rxrpc_peer_put, -}; - -enum rxrpc_conn_trace { - rxrpc_conn_got, - rxrpc_conn_new_client, - rxrpc_conn_new_service, - rxrpc_conn_put_client, - rxrpc_conn_put_service, - rxrpc_conn_queued, - rxrpc_conn_reap_service, - rxrpc_conn_seen, -}; - -enum rxrpc_client_trace { - rxrpc_client_activate_chans, - rxrpc_client_alloc, - rxrpc_client_chan_activate, - rxrpc_client_chan_disconnect, - rxrpc_client_chan_pass, - rxrpc_client_chan_wait_failed, - rxrpc_client_cleanup, - rxrpc_client_discard, - rxrpc_client_duplicate, - rxrpc_client_exposed, - rxrpc_client_replace, - rxrpc_client_to_active, - rxrpc_client_to_idle, -}; - -enum rxrpc_call_trace { - rxrpc_call_connected, - rxrpc_call_error, - rxrpc_call_got, - rxrpc_call_got_kernel, - rxrpc_call_got_timer, - rxrpc_call_got_userid, - rxrpc_call_new_client, - rxrpc_call_new_service, - rxrpc_call_put, - rxrpc_call_put_kernel, - rxrpc_call_put_noqueue, - rxrpc_call_put_notimer, - rxrpc_call_put_timer, - rxrpc_call_put_userid, - rxrpc_call_queued, - rxrpc_call_queued_ref, - rxrpc_call_release, - rxrpc_call_seen, -}; - -enum rxrpc_transmit_trace { - rxrpc_transmit_await_reply, - rxrpc_transmit_end, - rxrpc_transmit_queue, - rxrpc_transmit_queue_last, - rxrpc_transmit_rotate, - rxrpc_transmit_rotate_last, - rxrpc_transmit_wait, -}; - -enum rxrpc_receive_trace { - rxrpc_receive_end, - rxrpc_receive_front, - rxrpc_receive_incoming, - rxrpc_receive_queue, - rxrpc_receive_queue_last, - rxrpc_receive_rotate, -}; - -enum rxrpc_recvmsg_trace { - rxrpc_recvmsg_cont, - rxrpc_recvmsg_data_return, - rxrpc_recvmsg_dequeue, - rxrpc_recvmsg_enter, - rxrpc_recvmsg_full, - rxrpc_recvmsg_hole, - rxrpc_recvmsg_next, - rxrpc_recvmsg_requeue, - rxrpc_recvmsg_return, - rxrpc_recvmsg_terminal, - rxrpc_recvmsg_to_be_accepted, - rxrpc_recvmsg_wait, -}; - -enum rxrpc_rtt_tx_trace { - rxrpc_rtt_tx_cancel, - rxrpc_rtt_tx_data, - rxrpc_rtt_tx_no_slot, - rxrpc_rtt_tx_ping, -}; - -enum rxrpc_rtt_rx_trace { - rxrpc_rtt_rx_cancel, - rxrpc_rtt_rx_lost, - rxrpc_rtt_rx_obsolete, - rxrpc_rtt_rx_ping_response, - rxrpc_rtt_rx_requested_ack, -}; - -enum rxrpc_timer_trace { - rxrpc_timer_begin, - rxrpc_timer_exp_ack, - rxrpc_timer_exp_hard, - rxrpc_timer_exp_idle, - rxrpc_timer_exp_keepalive, - rxrpc_timer_exp_lost_ack, - rxrpc_timer_exp_normal, - rxrpc_timer_exp_ping, - rxrpc_timer_exp_resend, - rxrpc_timer_expired, - rxrpc_timer_init_for_reply, - rxrpc_timer_init_for_send_reply, - rxrpc_timer_restart, - rxrpc_timer_set_for_ack, - rxrpc_timer_set_for_hard, - rxrpc_timer_set_for_idle, - rxrpc_timer_set_for_keepalive, - rxrpc_timer_set_for_lost_ack, - rxrpc_timer_set_for_normal, - rxrpc_timer_set_for_ping, - rxrpc_timer_set_for_resend, - rxrpc_timer_set_for_send, -}; - -enum rxrpc_propose_ack_trace { - rxrpc_propose_ack_client_tx_end, - rxrpc_propose_ack_input_data, - rxrpc_propose_ack_ping_for_check_life, - rxrpc_propose_ack_ping_for_keepalive, - rxrpc_propose_ack_ping_for_lost_ack, - rxrpc_propose_ack_ping_for_lost_reply, - rxrpc_propose_ack_ping_for_params, - rxrpc_propose_ack_processing_op, - rxrpc_propose_ack_respond_to_ack, - rxrpc_propose_ack_respond_to_ping, - rxrpc_propose_ack_retry_tx, - rxrpc_propose_ack_rotate_rx, - rxrpc_propose_ack_terminal_ack, -}; - -enum rxrpc_propose_ack_outcome { - rxrpc_propose_ack_subsume, - rxrpc_propose_ack_update, - rxrpc_propose_ack_use, -}; - -enum rxrpc_congest_change { - rxrpc_cong_begin_retransmission, - rxrpc_cong_cleared_nacks, - rxrpc_cong_new_low_nack, - rxrpc_cong_no_change, - rxrpc_cong_progress, - rxrpc_cong_retransmit_again, - rxrpc_cong_rtt_window_end, - rxrpc_cong_saw_nack, -}; - -enum rxrpc_tx_point { - rxrpc_tx_point_call_abort, - rxrpc_tx_point_call_ack, - rxrpc_tx_point_call_data_frag, - rxrpc_tx_point_call_data_nofrag, - rxrpc_tx_point_call_final_resend, - rxrpc_tx_point_conn_abort, - rxrpc_tx_point_rxkad_challenge, - rxrpc_tx_point_rxkad_response, - rxrpc_tx_point_reject, - rxrpc_tx_point_version_keepalive, - rxrpc_tx_point_version_reply, -}; - -#endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ - /* * Declare tracing information enums and their string mappings for display. */ @@ -451,6 +242,36 @@ enum rxrpc_tx_point { EM(rxrpc_tx_point_version_keepalive, "VerKeepalive") \ E_(rxrpc_tx_point_version_reply, "VerReply") +/* + * Generate enums for tracing information. + */ +#ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY + +#undef EM +#undef E_ +#define EM(a, b) a, +#define E_(a, b) a + +enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte); +enum rxrpc_client_trace { rxrpc_client_traces } __mode(byte); +enum rxrpc_congest_change { rxrpc_congest_changes } __mode(byte); +enum rxrpc_conn_trace { rxrpc_conn_traces } __mode(byte); +enum rxrpc_local_trace { rxrpc_local_traces } __mode(byte); +enum rxrpc_peer_trace { rxrpc_peer_traces } __mode(byte); +enum rxrpc_propose_ack_outcome { rxrpc_propose_ack_outcomes } __mode(byte); +enum rxrpc_propose_ack_trace { rxrpc_propose_ack_traces } __mode(byte); +enum rxrpc_receive_trace { rxrpc_receive_traces } __mode(byte); +enum rxrpc_recvmsg_trace { rxrpc_recvmsg_traces } __mode(byte); +enum rxrpc_rtt_rx_trace { rxrpc_rtt_rx_traces } __mode(byte); +enum rxrpc_rtt_tx_trace { rxrpc_rtt_tx_traces } __mode(byte); +enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); +enum rxrpc_timer_trace { rxrpc_timer_traces } __mode(byte); +enum rxrpc_transmit_trace { rxrpc_transmit_traces } __mode(byte); +enum rxrpc_tx_point { rxrpc_tx_points } __mode(byte); + +#endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ + /* * Export enum symbols via userspace. */ @@ -459,21 +280,21 @@ enum rxrpc_tx_point { #define EM(a, b) TRACE_DEFINE_ENUM(a); #define E_(a, b) TRACE_DEFINE_ENUM(a); -rxrpc_skb_traces; -rxrpc_local_traces; -rxrpc_conn_traces; -rxrpc_client_traces; rxrpc_call_traces; -rxrpc_transmit_traces; +rxrpc_client_traces; +rxrpc_congest_changes; +rxrpc_congest_modes; +rxrpc_conn_traces; +rxrpc_local_traces; +rxrpc_propose_ack_outcomes; +rxrpc_propose_ack_traces; rxrpc_receive_traces; rxrpc_recvmsg_traces; -rxrpc_rtt_tx_traces; rxrpc_rtt_rx_traces; +rxrpc_rtt_tx_traces; +rxrpc_skb_traces; rxrpc_timer_traces; -rxrpc_propose_ack_traces; -rxrpc_propose_ack_outcomes; -rxrpc_congest_modes; -rxrpc_congest_changes; +rxrpc_transmit_traces; rxrpc_tx_points; /* @@ -1574,6 +1395,8 @@ TRACE_EVENT(rxrpc_rx_discard_ack, __entry->call_ackr_prev) ); +#undef EM +#undef E_ #endif /* _TRACE_RXRPC_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 9a3dedcf18096e8f7f22b8777d78c4acfdea1651 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 21 May 2022 09:03:31 +0100 Subject: rxrpc: Fix decision on when to generate an IDLE ACK Fix the decision on when to generate an IDLE ACK by keeping a count of the number of packets we've received, but not yet soft-ACK'd, and the number of packets we've processed, but not yet hard-ACK'd, rather than trying to keep track of which DATA sequence numbers correspond to those points. We then generate an ACK when either counter exceeds 2. The counters are both cleared when we transcribe the information into any sort of ACK packet for transmission. IDLE and DELAY ACKs are skipped if both counters are 0 (ie. no change). Fixes: 805b21b929e2 ("rxrpc: Send an ACK after every few DATA packets we receive") Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- include/trace/events/rxrpc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4a3ab0ed6e06..1c714336b863 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -1509,7 +1509,7 @@ TRACE_EVENT(rxrpc_call_reset, __entry->call_serial = call->rx_serial; __entry->conn_serial = call->conn->hi_serial; __entry->tx_seq = call->tx_hard_ack; - __entry->rx_seq = call->ackr_seen; + __entry->rx_seq = call->rx_hard_ack; ), TP_printk("c=%08x %08x:%08x r=%08x/%08x tx=%08x rx=%08x", -- cgit v1.2.3 From c304eddcecfe2513ff98ce3ae97d1c196d82ba08 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 19 May 2022 13:20:54 -0700 Subject: net: wrap the wireless pointers in struct net_device in an ifdef Most protocol-specific pointers in struct net_device are under a respective ifdef. Wireless is the notable exception. Since there's a sizable number of custom-built kernels for datacenter workloads which don't build wireless it seems reasonable to ifdefy those pointers as well. While at it move IPv4 and IPv6 pointers up, those are special for obvious reasons. Acked-by: Johannes Berg Acked-by: Stefan Schmidt # ieee802154 Acked-by: Sven Eckelmann Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++-- include/net/cfg80211.h | 2 ++ include/net/cfg802154.h | 2 ++ 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1ce91cb8074a..f615a66c89e9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2119,6 +2119,8 @@ struct net_device { /* Protocol-specific pointers */ + struct in_device __rcu *ip_ptr; + struct inet6_dev __rcu *ip6_ptr; #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; #endif @@ -2131,16 +2133,18 @@ struct net_device { #if IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; #endif - struct in_device __rcu *ip_ptr; #if IS_ENABLED(CONFIG_DECNET) struct dn_dev __rcu *dn_ptr; #endif - struct inet6_dev __rcu *ip6_ptr; #if IS_ENABLED(CONFIG_AX25) void *ax25_ptr; #endif +#if IS_ENABLED(CONFIG_CFG80211) struct wireless_dev *ieee80211_ptr; +#endif +#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN) struct wpan_dev *ieee802154_ptr; +#endif #if IS_ENABLED(CONFIG_MPLS_ROUTING) struct mpls_dev __rcu *mpls_ptr; #endif diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cc8a9880b9d6..6d02e12e4702 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -8006,7 +8006,9 @@ int cfg80211_register_netdevice(struct net_device *dev); */ static inline void cfg80211_unregister_netdevice(struct net_device *dev) { +#if IS_ENABLED(CONFIG_CFG80211) cfg80211_unregister_wdev(dev->ieee80211_ptr); +#endif } /** diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 85f9e8417688..d8d8719315fd 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -373,6 +373,7 @@ struct wpan_dev { #define to_phy(_dev) container_of(_dev, struct wpan_phy, dev) +#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN) static inline int wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, const struct ieee802154_addr *daddr, @@ -383,6 +384,7 @@ wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, return wpan_dev->header_ops->create(skb, dev, daddr, saddr, len); } +#endif struct wpan_phy * wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size); -- cgit v1.2.3 From 97d6fb1b48f5e6f6d58028593defe8a23641b0b4 Mon Sep 17 00:00:00 2001 From: Yuezhang Mo Date: Tue, 12 Apr 2022 12:23:10 +0900 Subject: block: add sync_blockdev_range() sync_blockdev_range() is to support syncing multiple sectors with as few block device requests as possible, it is helpful to make the block device to give full play to its performance. Signed-off-by: Yuezhang Mo Suggested-by: Christoph Hellwig Reviewed-by: Andy Wu Reviewed-by: Aoyama Wataru Reviewed-by: Christoph Hellwig Reviewed-by: Jens Axboe Acked-by: Sungjong Seo Signed-off-by: Namjae Jeon --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60d016138997..331cc6918ee9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1547,6 +1547,7 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); +int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); void printk_all_partitions(void); -- cgit v1.2.3 From a72e23dd679c632bcf6ab47a3a1a58c1e777713a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 22 May 2022 00:37:40 +0300 Subject: net: dsa: felix: update bridge fwd mask from ocelot lib when changing tag_8021q CPU Add more logic to ocelot_port_{,un}set_dsa_8021q_cpu() from the ocelot switch lib by encapsulating the ocelot_apply_bridge_fwd_mask() call that felix used to have. This is necessary because the CPU port change procedure will also need to do this, and it's good to reduce code duplication by having an entry point in the ocelot switch lib that does all that is needed. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 3b8c5a54fb00..2c90a24ca064 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -880,7 +880,6 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled, void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state); u32 ocelot_get_dsa_8021q_cpu_mask(struct ocelot *ocelot); u32 ocelot_get_bridge_fwd_mask(struct ocelot *ocelot, int src_port); -void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot, bool joining); int ocelot_port_pre_bridge_flags(struct ocelot *ocelot, int port, struct switchdev_brport_flags val); void ocelot_port_bridge_flags(struct ocelot *ocelot, int port, -- cgit v1.2.3 From c295f9831f1db12330d6a28a1cb2bd2562535e37 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 22 May 2022 00:37:42 +0300 Subject: net: mscc: ocelot: switch from {,un}set to {,un}assign for tag_8021q CPU ports There is a desire for the felix driver to gain support for multiple tag_8021q CPU ports, but the current model prevents it. This is because ocelot_apply_bridge_fwd_mask() only takes into consideration whether a port is a tag_8021q CPU port, but not whose CPU port it is. We need a model where we can have a direct affinity between an ocelot port and a tag_8021q CPU port. This serves as the basis for multiple CPU ports. Declare a "dsa_8021q_cpu" backpointer in struct ocelot_port which encodes that affinity. Repurpose the "ocelot_set_dsa_8021q_cpu" API to "ocelot_assign_dsa_8021q_cpu" to express the change of paradigm. Note that this change makes the first practical use of the new ocelot_port->index field in ocelot_port_unassign_dsa_8021q_cpu(), where we need to remove the old tag_8021q CPU port from the reserved VLAN range. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 2c90a24ca064..5f88385a7748 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -654,6 +654,8 @@ struct ocelot_mirror { int to; }; +struct ocelot_port; + struct ocelot_port { struct ocelot *ocelot; @@ -662,6 +664,8 @@ struct ocelot_port { struct net_device *bond; struct net_device *bridge; + struct ocelot_port *dsa_8021q_cpu; + /* VLAN that untagged frames are classified to, on ingress */ const struct ocelot_bridge_vlan *pvid_vlan; @@ -865,8 +869,9 @@ void ocelot_deinit(struct ocelot *ocelot); void ocelot_init_port(struct ocelot *ocelot, int port); void ocelot_deinit_port(struct ocelot *ocelot, int port); -void ocelot_port_set_dsa_8021q_cpu(struct ocelot *ocelot, int port); -void ocelot_port_unset_dsa_8021q_cpu(struct ocelot *ocelot, int port); +void ocelot_port_assign_dsa_8021q_cpu(struct ocelot *ocelot, int port, int cpu); +void ocelot_port_unassign_dsa_8021q_cpu(struct ocelot *ocelot, int port); +u32 ocelot_port_assigned_dsa_8021q_cpu_mask(struct ocelot *ocelot, int port); /* DSA callbacks */ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data); @@ -878,7 +883,6 @@ void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs); int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled, struct netlink_ext_ack *extack); void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state); -u32 ocelot_get_dsa_8021q_cpu_mask(struct ocelot *ocelot); u32 ocelot_get_bridge_fwd_mask(struct ocelot *ocelot, int src_port); int ocelot_port_pre_bridge_flags(struct ocelot *ocelot, int port, struct switchdev_brport_flags val); -- cgit v1.2.3 From a4e044dc4c5b1e03f4195224c47108dc44122917 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 22 May 2022 00:37:43 +0300 Subject: net: dsa: felix: tag_8021q preparation for multiple CPU ports Update the VCAP filters to support multiple tag_8021q CPU ports. TX works using a filter for VLAN ID on the ingress of the CPU port, with a redirect and a VLAN pop action. This can be updated trivially by amending the ingress port mask of this rule to match on all tag_8021q CPU ports. RX works using a filter for ingress port on the egress of the CPU port, with a VLAN push action. Here we need to replicate these filters for each tag_8021q CPU port, and let them all have the same action. This means that the OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN() cookie needs to encode a unique value for every {user port, CPU port} pair it's given. Do this by encoding the CPU port in the upper 16 bits of the cookie, and the user port in the lower 16 bits. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot_vcap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index de26c992f821..c601a4598b0d 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -11,7 +11,7 @@ /* Cookie definitions for private VCAP filters installed by the driver. * Must be unique per VCAP block. */ -#define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port) (port) +#define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, upstream) ((upstream) << 16 | (port)) #define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port) (port) #define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port) (port) #define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) ((ocelot)->num_phys_ports + (port)) -- cgit v1.2.3 From a13e248ff90e81e9322406c0e618cf2168702f4e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Fri, 6 May 2022 18:08:11 +0200 Subject: landlock: Fix landlock_add_rule(2) documentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is not mandatory to pass a file descriptor obtained with the O_PATH flag. Also, replace rule's accesses with ruleset's accesses. Link: https://lore.kernel.org/r/20220506160820.524344-2-mic@digikod.net Cc: stable@vger.kernel.org Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 15c31abb0d76..21c8d58283c9 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -62,8 +62,9 @@ struct landlock_path_beneath_attr { */ __u64 allowed_access; /** - * @parent_fd: File descriptor, open with ``O_PATH``, which identifies - * the parent directory of a file hierarchy, or just a file. + * @parent_fd: File descriptor, preferably opened with ``O_PATH``, + * which identifies the parent directory of a file hierarchy, or just a + * file. */ __s32 parent_fd; /* -- cgit v1.2.3 From 100f59d964050020285f0c8264ce520f0c406c13 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Fri, 6 May 2022 18:10:56 +0200 Subject: LSM: Remove double path_rename hook calls for RENAME_EXCHANGE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to be able to identify a file exchange with renameat2(2) and RENAME_EXCHANGE, which will be useful for Landlock [1], propagate the rename flags to LSMs. This may also improve performance because of the switch from two set of LSM hook calls to only one, and because LSMs using this hook may optimize the double check (e.g. only one lock, reduce the number of path walks). AppArmor, Landlock and Tomoyo are updated to leverage this change. This should not change the current behavior (same check order), except (different level of) speed boosts. [1] https://lore.kernel.org/r/20220221212522.320243-1-mic@digikod.net Cc: James Morris Cc: Kentaro Takeda Cc: Serge E. Hallyn Acked-by: John Johansen Acked-by: Tetsuo Handa Reviewed-by: Paul Moore Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20220506161102.525323-7-mic@digikod.net --- include/linux/lsm_hook_defs.h | 2 +- include/linux/lsm_hooks.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index db924fe379c9..eafa1d2489fd 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -100,7 +100,7 @@ LSM_HOOK(int, 0, path_link, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) LSM_HOOK(int, 0, path_rename, const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, - struct dentry *new_dentry) + struct dentry *new_dentry, unsigned int flags) LSM_HOOK(int, 0, path_chmod, const struct path *path, umode_t mode) LSM_HOOK(int, 0, path_chown, const struct path *path, kuid_t uid, kgid_t gid) LSM_HOOK(int, 0, path_chroot, const struct path *path) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 419b5febc3ca..9acf5e368d73 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -358,6 +358,7 @@ * @old_dentry contains the dentry structure of the old link. * @new_dir contains the path structure for parent of the new link. * @new_dentry contains the dentry structure of the new link. + * @flags may contain rename options such as RENAME_EXCHANGE. * Return 0 if permission is granted. * @path_chmod: * Check for permission to change a mode of the file @path. The new -- cgit v1.2.3 From b91c3e4ea756b12b7d992529226edce1cfd854d7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Fri, 6 May 2022 18:10:57 +0200 Subject: landlock: Add support for file reparenting with LANDLOCK_ACCESS_FS_REFER MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a new LANDLOCK_ACCESS_FS_REFER access right to enable policy writers to allow sandboxed processes to link and rename files from and to a specific set of file hierarchies. This access right should be composed with LANDLOCK_ACCESS_FS_MAKE_* for the destination of a link or rename, and with LANDLOCK_ACCESS_FS_REMOVE_* for a source of a rename. This lift a Landlock limitation that always denied changing the parent of an inode. Renaming or linking to the same directory is still always allowed, whatever LANDLOCK_ACCESS_FS_REFER is used or not, because it is not considered a threat to user data. However, creating multiple links or renaming to a different parent directory may lead to privilege escalations if not handled properly. Indeed, we must be sure that the source doesn't gain more privileges by being accessible from the destination. This is handled by making sure that the source hierarchy (including the referenced file or directory itself) restricts at least as much the destination hierarchy. If it is not the case, an EXDEV error is returned, making it potentially possible for user space to copy the file hierarchy instead of moving or linking it. Instead of creating different access rights for the source and the destination, we choose to make it simple and consistent for users. Indeed, considering the previous constraint, it would be weird to require such destination access right to be also granted to the source (to make it a superset). Moreover, RENAME_EXCHANGE would also add to the confusion because of paths being both a source and a destination. See the provided documentation for additional details. New tests are provided with a following commit. Reviewed-by: Paul Moore Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20220506161102.525323-8-mic@digikod.net --- include/uapi/linux/landlock.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 21c8d58283c9..23df4e0e8ace 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -21,8 +21,14 @@ struct landlock_ruleset_attr { /** * @handled_access_fs: Bitmask of actions (cf. `Filesystem flags`_) * that is handled by this ruleset and should then be forbidden if no - * rule explicitly allow them. This is needed for backward - * compatibility reasons. + * rule explicitly allow them: it is a deny-by-default list that should + * contain as much Landlock access rights as possible. Indeed, all + * Landlock filesystem access rights that are not part of + * handled_access_fs are allowed. This is needed for backward + * compatibility reasons. One exception is the + * LANDLOCK_ACCESS_FS_REFER access right, which is always implicitly + * handled, but must still be explicitly handled to add new rules with + * this access right. */ __u64 handled_access_fs; }; @@ -112,6 +118,22 @@ struct landlock_path_beneath_attr { * - %LANDLOCK_ACCESS_FS_MAKE_FIFO: Create (or rename or link) a named pipe. * - %LANDLOCK_ACCESS_FS_MAKE_BLOCK: Create (or rename or link) a block device. * - %LANDLOCK_ACCESS_FS_MAKE_SYM: Create (or rename or link) a symbolic link. + * - %LANDLOCK_ACCESS_FS_REFER: Link or rename a file from or to a different + * directory (i.e. reparent a file hierarchy). This access right is + * available since the second version of the Landlock ABI. This is also the + * only access right which is always considered handled by any ruleset in + * such a way that reparenting a file hierarchy is always denied by default. + * To avoid privilege escalation, it is not enough to add a rule with this + * access right. When linking or renaming a file, the destination directory + * hierarchy must also always have the same or a superset of restrictions of + * the source hierarchy. If it is not the case, or if the domain doesn't + * handle this access right, such actions are denied by default with errno + * set to EXDEV. Linking also requires a LANDLOCK_ACCESS_FS_MAKE_* access + * right on the destination directory, and renaming also requires a + * LANDLOCK_ACCESS_FS_REMOVE_* access right on the source's (file or + * directory) parent. Otherwise, such actions are denied with errno set to + * EACCES. The EACCES errno prevails over EXDEV to let user space + * efficiently deal with an unrecoverable error. * * .. warning:: * @@ -137,6 +159,7 @@ struct landlock_path_beneath_attr { #define LANDLOCK_ACCESS_FS_MAKE_FIFO (1ULL << 10) #define LANDLOCK_ACCESS_FS_MAKE_BLOCK (1ULL << 11) #define LANDLOCK_ACCESS_FS_MAKE_SYM (1ULL << 12) +#define LANDLOCK_ACCESS_FS_REFER (1ULL << 13) /* clang-format on */ #endif /* _UAPI_LINUX_LANDLOCK_H */ -- cgit v1.2.3 From fb70bf124b051d4ded4ce57511dfec6d3ebf2b43 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 30 Mar 2022 10:30:54 -0400 Subject: NFSD: Instantiate a struct file when creating a regular NFSv4 file There have been reports of races that cause NFSv4 OPEN(CREATE) to return an error even though the requested file was created. NFSv4 does not provide a status code for this case. To mitigate some of these problems, reorganize the NFSv4 OPEN(CREATE) logic to allocate resources before the file is actually created, and open the new file while the parent directory is still locked. Two new APIs are added: + Add an API that works like nfsd_file_acquire() but does not open the underlying file. The OPEN(CREATE) path can use this API when it already has an open file. + Add an API that is kin to dentry_open(). NFSD needs to create a file and grab an open "struct file *" atomically. The alloc_empty_file() has to be done before the inode create. If it fails (for example, because the NFS server has exceeded its max_files limit), we avoid creating the file and can still return an error to the NFS client. BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=382 Signed-off-by: Chuck Lever Tested-by: JianHong Yin --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index aa6c1bbdb8c4..b848355b5e6c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2640,6 +2640,8 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt, name, flags, mode); } extern struct file * dentry_open(const struct path *, int, const struct cred *); +extern struct file *dentry_create(const struct path *path, int flags, + umode_t mode, const struct cred *cred); extern struct file * open_with_fake_path(const struct path *, int, struct inode*, const struct cred *); static inline struct file *file_clone_open(struct file *file) -- cgit v1.2.3 From 141e523914f72575915dd334fce3cef4fb0f1e91 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Mon, 12 Jul 2021 19:03:12 +0200 Subject: certs: Factor out the blacklist hash creation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Factor out the blacklist hash creation with the get_raw_hash() helper. This also centralize the "tbs" and "bin" prefixes and make them private, which help to manage them consistently. Cc: David Howells Cc: David S. Miller Cc: David Woodhouse Cc: Eric Snowberg Cc: Herbert Xu Cc: Jarkko Sakkinen Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20210712170313.884724-5-mic@digikod.net Signed-off-by: Jarkko Sakkinen --- include/keys/system_keyring.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h index 2419a735420f..91e080efb918 100644 --- a/include/keys/system_keyring.h +++ b/include/keys/system_keyring.h @@ -10,6 +10,13 @@ #include +enum blacklist_hash_type { + /* TBSCertificate hash */ + BLACKLIST_HASH_X509_TBS = 1, + /* Raw data hash */ + BLACKLIST_HASH_BINARY = 2, +}; + #ifdef CONFIG_SYSTEM_TRUSTED_KEYRING extern int restrict_link_by_builtin_trusted(struct key *keyring, @@ -54,13 +61,14 @@ static inline void __init set_machine_trusted_keys(struct key *keyring) extern struct pkcs7_message *pkcs7; #ifdef CONFIG_SYSTEM_BLACKLIST_KEYRING -extern int mark_hash_blacklisted(const char *hash); +extern int mark_hash_blacklisted(const u8 *hash, size_t hash_len, + enum blacklist_hash_type hash_type); extern int is_hash_blacklisted(const u8 *hash, size_t hash_len, - const char *type); + enum blacklist_hash_type hash_type); extern int is_binary_blacklisted(const u8 *hash, size_t hash_len); #else static inline int is_hash_blacklisted(const u8 *hash, size_t hash_len, - const char *type) + enum blacklist_hash_type hash_type) { return 0; } -- cgit v1.2.3 From fcd7c26901c83681532c6daac599e53d4df11738 Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Fri, 13 May 2022 16:57:00 +0200 Subject: KEYS: trusted: allow use of kernel RNG for key material The two existing trusted key sources don't make use of the kernel RNG, but instead let the hardware doing the sealing/unsealing also generate the random key material. However, both users and future backends may want to place less trust into the quality of the trust source's random number generator and instead reuse the kernel entropy pool, which can be seeded from multiple entropy sources. Make this possible by adding a new trusted.rng parameter, that will force use of the kernel RNG. In its absence, it's up to the trust source to decide, which random numbers to use, maintaining the existing behavior. Suggested-by: Jarkko Sakkinen Acked-by: Sumit Garg Acked-by: Pankaj Gupta Reviewed-by: David Gstir Reviewed-by: Pankaj Gupta Reviewed-by: Jarkko Sakkinen Tested-by: Pankaj Gupta Tested-by: Michael Walle # on ls1028a (non-E and E) Tested-by: John Ernberg # iMX8QXP Signed-off-by: Ahmad Fatoum Signed-off-by: Jarkko Sakkinen --- include/keys/trusted-type.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/keys/trusted-type.h b/include/keys/trusted-type.h index d89fa2579ac0..4eb64548a74f 100644 --- a/include/keys/trusted-type.h +++ b/include/keys/trusted-type.h @@ -64,7 +64,7 @@ struct trusted_key_ops { /* Unseal a key. */ int (*unseal)(struct trusted_key_payload *p, char *datablob); - /* Get a randomized key. */ + /* Optional: Get a randomized key. */ int (*get_random)(unsigned char *key, size_t key_len); /* Exit key interface. */ -- cgit v1.2.3 From 007c3ff11f38d83cc95b0f402e432cbf484e3c31 Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Fri, 13 May 2022 16:57:02 +0200 Subject: crypto: caam - add in-kernel interface for blob generator The NXP Cryptographic Acceleration and Assurance Module (CAAM) can be used to protect user-defined data across system reboot: - When the system is fused and boots into secure state, the master key is a unique never-disclosed device-specific key - random key is encrypted by key derived from master key - data is encrypted using the random key - encrypted data and its encrypted random key are stored alongside - This blob can now be safely stored in non-volatile memory On next power-on: - blob is loaded into CAAM - CAAM writes decrypted data either into memory or key register Add functions to realize encrypting and decrypting into memory alongside the CAAM driver. They will be used in a later commit as a source for the trusted key seal/unseal mechanism. Reviewed-by: David Gstir Reviewed-by: Pankaj Gupta Tested-by: Tim Harvey Tested-by: Matthias Schiffer Tested-by: Pankaj Gupta Tested-by: Michael Walle # on ls1028a (non-E and E) Tested-by: John Ernberg # iMX8QXP Signed-off-by: Steffen Trumtrar Signed-off-by: Ahmad Fatoum Signed-off-by: Jarkko Sakkinen --- include/soc/fsl/caam-blob.h | 103 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 103 insertions(+) create mode 100644 include/soc/fsl/caam-blob.h (limited to 'include') diff --git a/include/soc/fsl/caam-blob.h b/include/soc/fsl/caam-blob.h new file mode 100644 index 000000000000..937cac52f36d --- /dev/null +++ b/include/soc/fsl/caam-blob.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Pengutronix, Ahmad Fatoum + */ + +#ifndef __CAAM_BLOB_GEN +#define __CAAM_BLOB_GEN + +#include +#include + +#define CAAM_BLOB_KEYMOD_LENGTH 16 +#define CAAM_BLOB_OVERHEAD (32 + 16) +#define CAAM_BLOB_MAX_LEN 4096 + +struct caam_blob_priv; + +/** + * struct caam_blob_info - information for CAAM blobbing + * @input: pointer to input buffer (must be DMAable) + * @input_len: length of @input buffer in bytes. + * @output: pointer to output buffer (must be DMAable) + * @output_len: length of @output buffer in bytes. + * @key_mod: key modifier + * @key_mod_len: length of @key_mod in bytes. + * May not exceed %CAAM_BLOB_KEYMOD_LENGTH + */ +struct caam_blob_info { + void *input; + size_t input_len; + + void *output; + size_t output_len; + + const void *key_mod; + size_t key_mod_len; +}; + +/** + * caam_blob_gen_init - initialize blob generation + * Return: pointer to new &struct caam_blob_priv instance on success + * and ``ERR_PTR(-ENODEV)`` if CAAM has no hardware blobbing support + * or no job ring could be allocated. + */ +struct caam_blob_priv *caam_blob_gen_init(void); + +/** + * caam_blob_gen_exit - free blob generation resources + * @priv: instance returned by caam_blob_gen_init() + */ +void caam_blob_gen_exit(struct caam_blob_priv *priv); + +/** + * caam_process_blob - encapsulate or decapsulate blob + * @priv: instance returned by caam_blob_gen_init() + * @info: pointer to blobbing info describing key, blob and + * key modifier buffers. + * @encap: true for encapsulation, false for decapsulation + * + * Return: %0 and sets ``info->output_len`` on success and a negative + * error code otherwise. + */ +int caam_process_blob(struct caam_blob_priv *priv, + struct caam_blob_info *info, bool encap); + +/** + * caam_encap_blob - encapsulate blob + * @priv: instance returned by caam_blob_gen_init() + * @info: pointer to blobbing info describing input key, + * output blob and key modifier buffers. + * + * Return: %0 and sets ``info->output_len`` on success and + * a negative error code otherwise. + */ +static inline int caam_encap_blob(struct caam_blob_priv *priv, + struct caam_blob_info *info) +{ + if (info->output_len < info->input_len + CAAM_BLOB_OVERHEAD) + return -EINVAL; + + return caam_process_blob(priv, info, true); +} + +/** + * caam_decap_blob - decapsulate blob + * @priv: instance returned by caam_blob_gen_init() + * @info: pointer to blobbing info describing output key, + * input blob and key modifier buffers. + * + * Return: %0 and sets ``info->output_len`` on success and + * a negative error code otherwise. + */ +static inline int caam_decap_blob(struct caam_blob_priv *priv, + struct caam_blob_info *info) +{ + if (info->input_len < CAAM_BLOB_OVERHEAD || + info->output_len < info->input_len - CAAM_BLOB_OVERHEAD) + return -EINVAL; + + return caam_process_blob(priv, info, false); +} + +#endif -- cgit v1.2.3 From e9c5048c2de1913d0bcd589bc1487810c2e24bc1 Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Fri, 13 May 2022 16:57:03 +0200 Subject: KEYS: trusted: Introduce support for NXP CAAM-based trusted keys The Cryptographic Acceleration and Assurance Module (CAAM) is an IP core built into many newer i.MX and QorIQ SoCs by NXP. The CAAM does crypto acceleration, hardware number generation and has a blob mechanism for encapsulation/decapsulation of sensitive material. This blob mechanism depends on a device specific random 256-bit One Time Programmable Master Key that is fused in each SoC at manufacturing time. This key is unreadable and can only be used by the CAAM for AES encryption/decryption of user data. This makes it a suitable backend (source) for kernel trusted keys. Previous commits generalized trusted keys to support multiple backends and added an API to access the CAAM blob mechanism. Based on these, provide the necessary glue to use the CAAM for trusted keys. Reviewed-by: David Gstir Reviewed-by: Pankaj Gupta Reviewed-by: Jarkko Sakkinen Tested-by: Tim Harvey Tested-by: Matthias Schiffer Tested-by: Pankaj Gupta Tested-by: Michael Walle # on ls1028a (non-E and E) Tested-by: John Ernberg # iMX8QXP Signed-off-by: Ahmad Fatoum Signed-off-by: Jarkko Sakkinen --- include/keys/trusted_caam.h | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 include/keys/trusted_caam.h (limited to 'include') diff --git a/include/keys/trusted_caam.h b/include/keys/trusted_caam.h new file mode 100644 index 000000000000..73fe2f32f65e --- /dev/null +++ b/include/keys/trusted_caam.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Pengutronix, Ahmad Fatoum + */ + +#ifndef __CAAM_TRUSTED_KEY_H +#define __CAAM_TRUSTED_KEY_H + +extern struct trusted_key_ops trusted_key_caam_ops; + +#endif -- cgit v1.2.3 From bca1a1004615efe141fd78f360ecc48c60bc4ad5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20Ard=C3=B6?= Date: Thu, 31 Mar 2022 09:01:15 +0200 Subject: mailbox: forward the hrtimer if not queued and under a lock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit c7dacf5b0f32957b24ef29df1207dc2cd8307743, "mailbox: avoid timer start from callback" The previous commit was reverted since it lead to a race that caused the hrtimer to not be started at all. The check for hrtimer_active() in msg_submit() will return true if the callback function txdone_hrtimer() is currently running. This function could return HRTIMER_NORESTART and then the timer will not be restarted, and also msg_submit() will not start the timer. This will lead to a message actually being submitted but no timer will start to check for its compleation. The original fix that added checking hrtimer_active() was added to avoid a warning with hrtimer_forward. Looking in the kernel another solution to avoid this warning is to check hrtimer_is_queued() before calling hrtimer_forward_now() instead. This however requires a lock so the timer is not started by msg_submit() inbetween this check and the hrtimer_forward() call. Fixes: c7dacf5b0f32 ("mailbox: avoid timer start from callback") Signed-off-by: Björn Ardö Signed-off-by: Jassi Brar --- include/linux/mailbox_controller.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h index 36d6ce673503..6fee33cb52f5 100644 --- a/include/linux/mailbox_controller.h +++ b/include/linux/mailbox_controller.h @@ -83,6 +83,7 @@ struct mbox_controller { const struct of_phandle_args *sp); /* Internal to API */ struct hrtimer poll_hrt; + spinlock_t poll_hrt_lock; struct list_head node; }; -- cgit v1.2.3 From fe736565efb775620dbcf3c459c1cd80d3e868da Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 20 May 2022 16:57:53 -0700 Subject: bpf: Introduce bpf_arch_text_invalidate for bpf_prog_pack Introduce bpf_arch_text_invalidate and use it to fill unused part of the bpf_prog_pack with illegal instructions when a BPF program is freed. Fixes: 57631054fae6 ("bpf: Introduce bpf_prog_pack allocator") Fixes: 33c9805860e5 ("bpf: Introduce bpf_jit_binary_pack_[alloc|finalize|free]") Reported-by: Linus Torvalds Signed-off-by: Song Liu Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220520235758.1858153-4-song@kernel.org --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cc4d5e394031..a9b1875212f6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2365,6 +2365,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); void *bpf_arch_text_copy(void *dst, void *src, size_t len); +int bpf_arch_text_invalidate(void *dst, size_t len); struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); -- cgit v1.2.3 From 97e03f521050c092919591e668107b3d69c5f426 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 23 May 2022 14:07:07 -0700 Subject: bpf: Add verifier support for dynptrs This patch adds the bulk of the verifier work for supporting dynamic pointers (dynptrs) in bpf. A bpf_dynptr is opaque to the bpf program. It is a 16-byte structure defined internally as: struct bpf_dynptr_kern { void *data; u32 size; u32 offset; } __aligned(8); The upper 8 bits of *size* is reserved (it contains extra metadata about read-only status and dynptr type). Consequently, a dynptr only supports memory less than 16 MB. There are different types of dynptrs (eg malloc, ringbuf, ...). In this patchset, the most basic one, dynptrs to a bpf program's local memory, is added. For now only local memory that is of reg type PTR_TO_MAP_VALUE is supported. In the verifier, dynptr state information will be tracked in stack slots. When the program passes in an uninitialized dynptr (ARG_PTR_TO_DYNPTR | MEM_UNINIT), the stack slots corresponding to the frame pointer where the dynptr resides at are marked STACK_DYNPTR. For helper functions that take in initialized dynptrs (eg bpf_dynptr_read + bpf_dynptr_write which are added later in this patchset), the verifier enforces that the dynptr has been initialized properly by checking that their corresponding stack slots have been marked as STACK_DYNPTR. The 6th patch in this patchset adds test cases that the verifier should successfully reject, such as for example attempting to use a dynptr after doing a direct write into it inside the bpf program. Signed-off-by: Joanne Koong Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Acked-by: David Vernet Link: https://lore.kernel.org/bpf/20220523210712.3641569-2-joannelkoong@gmail.com --- include/linux/bpf.h | 28 ++++++++++++++++++++++++++++ include/linux/bpf_verifier.h | 18 ++++++++++++++++++ include/uapi/linux/bpf.h | 5 +++++ 3 files changed, 51 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a9b1875212f6..b26c8176b9e0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -392,10 +392,15 @@ enum bpf_type_flag { MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), + /* DYNPTR points to memory local to the bpf program. */ + DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; +#define DYNPTR_TYPE_FLAG_MASK DYNPTR_TYPE_LOCAL + /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) @@ -438,6 +443,7 @@ enum bpf_arg_type { ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ ARG_PTR_TO_KPTR, /* pointer to referenced kptr */ + ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */ __BPF_ARG_TYPE_MAX, /* Extended arg_types. */ @@ -2376,4 +2382,26 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 **bin_buf, u32 num_args); void bpf_bprintf_cleanup(void); +/* the implementation of the opaque uapi struct bpf_dynptr */ +struct bpf_dynptr_kern { + void *data; + /* Size represents the number of usable bytes of dynptr data. + * If for example the offset is at 4 for a local dynptr whose data is + * of type u64, the number of usable bytes is 4. + * + * The upper 8 bits are reserved. It is as follows: + * Bits 0 - 23 = size + * Bits 24 - 30 = dynptr type + * Bit 31 = whether dynptr is read-only + */ + u32 size; + u32 offset; +} __aligned(8); + +enum bpf_dynptr_type { + BPF_DYNPTR_TYPE_INVALID, + /* Points to memory that is local to the bpf program */ + BPF_DYNPTR_TYPE_LOCAL, +}; + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1f1e7f2ea967..af5b2135215e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -72,6 +72,18 @@ struct bpf_reg_state { u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */ + /* For dynptr stack slots */ + struct { + enum bpf_dynptr_type type; + /* A dynptr is 16 bytes so it takes up 2 stack slots. + * We need to track which slot is the first slot + * to protect against cases where the user may try to + * pass in an address starting at the second slot of the + * dynptr. + */ + bool first_slot; + } dynptr; + /* Max size from any of the above. */ struct { unsigned long raw1; @@ -174,9 +186,15 @@ enum bpf_stack_slot_type { STACK_SPILL, /* register spilled into stack */ STACK_MISC, /* BPF program wrote some data into this slot */ STACK_ZERO, /* BPF program wrote constant zero */ + /* A dynptr is stored in this stack slot. The type of dynptr + * is stored in bpf_stack_state->spilled_ptr.dynptr.type + */ + STACK_DYNPTR, }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ +#define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern) +#define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE) struct bpf_stack_state { struct bpf_reg_state spilled_ptr; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 56688bee20d9..610944cb3389 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6528,6 +6528,11 @@ struct bpf_timer { __u64 :64; } __attribute__((aligned(8))); +struct bpf_dynptr { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. -- cgit v1.2.3 From 263ae152e96253f40c2c276faad8629e096b3bad Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 23 May 2022 14:07:08 -0700 Subject: bpf: Add bpf_dynptr_from_mem for local dynptrs This patch adds a new api bpf_dynptr_from_mem: long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr); which initializes a dynptr to point to a bpf program's local memory. For now only local memory that is of reg type PTR_TO_MAP_VALUE is supported. Signed-off-by: Joanne Koong Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220523210712.3641569-3-joannelkoong@gmail.com --- include/uapi/linux/bpf.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 610944cb3389..9be3644457dd 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5178,6 +5178,17 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer. * Return * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr) + * Description + * Get a dynptr to local memory *data*. + * + * *data* must be a ptr to a map value. + * The maximum *size* supported is DYNPTR_MAX_SIZE. + * *flags* is currently unused. + * Return + * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE, + * -EINVAL if flags is not 0. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5377,6 +5388,7 @@ union bpf_attr { FN(kptr_xchg), \ FN(map_lookup_percpu_elem), \ FN(skc_to_mptcp_sock), \ + FN(dynptr_from_mem), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From bc34dee65a65e9c920c420005b8a43f2a721a458 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 23 May 2022 14:07:09 -0700 Subject: bpf: Dynptr support for ring buffers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, our only way of writing dynamically-sized data into a ring buffer is through bpf_ringbuf_output but this incurs an extra memcpy cost. bpf_ringbuf_reserve + bpf_ringbuf_commit avoids this extra memcpy, but it can only safely support reservation sizes that are statically known since the verifier cannot guarantee that the bpf program won’t access memory outside the reserved space. The bpf_dynptr abstraction allows for dynamically-sized ring buffer reservations without the extra memcpy. There are 3 new APIs: long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr); void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags); void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags); These closely follow the functionalities of the original ringbuf APIs. For example, all ringbuffer dynptrs that have been reserved must be either submitted or discarded before the program exits. Signed-off-by: Joanne Koong Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Acked-by: David Vernet Link: https://lore.kernel.org/bpf/20220523210712.3641569-4-joannelkoong@gmail.com --- include/linux/bpf.h | 15 ++++++++++++++- include/linux/bpf_verifier.h | 2 ++ include/uapi/linux/bpf.h | 35 +++++++++++++++++++++++++++++++++++ 3 files changed, 51 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b26c8176b9e0..c72321b6f306 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -395,11 +395,14 @@ enum bpf_type_flag { /* DYNPTR points to memory local to the bpf program. */ DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS), + /* DYNPTR points to a ringbuf record. */ + DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; -#define DYNPTR_TYPE_FLAG_MASK DYNPTR_TYPE_LOCAL +#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) @@ -2231,6 +2234,9 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; +extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto; +extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto; +extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto; extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; @@ -2402,6 +2408,13 @@ enum bpf_dynptr_type { BPF_DYNPTR_TYPE_INVALID, /* Points to memory that is local to the bpf program */ BPF_DYNPTR_TYPE_LOCAL, + /* Underlying data is a ringbuf record */ + BPF_DYNPTR_TYPE_RINGBUF, }; +void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, + enum bpf_dynptr_type type, u32 offset, u32 size); +void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); +int bpf_dynptr_check_size(u32 size); + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index af5b2135215e..e8439f6cbe57 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -100,6 +100,8 @@ struct bpf_reg_state { * for the purpose of tracking that it's freed. * For PTR_TO_SOCKET this is used to share which pointers retain the * same reference to the socket, to determine proper reference freeing. + * For stack slots that are dynptrs, this is used to track references to + * the dynptr to determine proper reference freeing. */ u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9be3644457dd..081a55540aa5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5189,6 +5189,38 @@ union bpf_attr { * Return * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE, * -EINVAL if flags is not 0. + * + * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr) + * Description + * Reserve *size* bytes of payload in a ring buffer *ringbuf* + * through the dynptr interface. *flags* must be 0. + * + * Please note that a corresponding bpf_ringbuf_submit_dynptr or + * bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the + * reservation fails. This is enforced by the verifier. + * Return + * 0 on success, or a negative error in case of failure. + * + * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags) + * Description + * Submit reserved ring buffer sample, pointed to by *data*, + * through the dynptr interface. This is a no-op if the dynptr is + * invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_submit'. + * Return + * Nothing. Always succeeds. + * + * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags) + * Description + * Discard reserved ring buffer sample through the dynptr + * interface. This is a no-op if the dynptr is invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_discard'. + * Return + * Nothing. Always succeeds. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5389,6 +5421,9 @@ union bpf_attr { FN(map_lookup_percpu_elem), \ FN(skc_to_mptcp_sock), \ FN(dynptr_from_mem), \ + FN(ringbuf_reserve_dynptr), \ + FN(ringbuf_submit_dynptr), \ + FN(ringbuf_discard_dynptr), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 13bbbfbea7598ea9f8d9c3d73bf053bb57f9c4b2 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 23 May 2022 14:07:10 -0700 Subject: bpf: Add bpf_dynptr_read and bpf_dynptr_write This patch adds two helper functions, bpf_dynptr_read and bpf_dynptr_write: long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset); long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len); The dynptr passed into these functions must be valid dynptrs that have been initialized. Signed-off-by: Joanne Koong Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220523210712.3641569-5-joannelkoong@gmail.com --- include/uapi/linux/bpf.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 081a55540aa5..efe2505650e6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5221,6 +5221,23 @@ union bpf_attr { * 'bpf_ringbuf_discard'. * Return * Nothing. Always succeeds. + * + * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset) + * Description + * Read *len* bytes from *src* into *dst*, starting from *offset* + * into *src*. + * Return + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *src*'s data, -EINVAL if *src* is an invalid dynptr. + * + * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len) + * Description + * Write *len* bytes from *src* into *dst*, starting from *offset* + * into *dst*. + * Return + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* + * is a read-only dynptr. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5424,6 +5441,8 @@ union bpf_attr { FN(ringbuf_reserve_dynptr), \ FN(ringbuf_submit_dynptr), \ FN(ringbuf_discard_dynptr), \ + FN(dynptr_read), \ + FN(dynptr_write), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 34d4ef5775f776ec4b0d53a02d588bf3195cada6 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 23 May 2022 14:07:11 -0700 Subject: bpf: Add dynptr data slices This patch adds a new helper function void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len); which returns a pointer to the underlying data of a dynptr. *len* must be a statically known value. The bpf program may access the returned data slice as a normal buffer (eg can do direct reads and writes), since the verifier associates the length with the returned pointer, and enforces that no out of bounds accesses occur. Signed-off-by: Joanne Koong Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20220523210712.3641569-6-joannelkoong@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 12 ++++++++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c72321b6f306..a7080c86fa76 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -488,6 +488,7 @@ enum bpf_return_type { RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM, + RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index efe2505650e6..f4009dbdf62d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5238,6 +5238,17 @@ union bpf_attr { * 0 on success, -E2BIG if *offset* + *len* exceeds the length * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* * is a read-only dynptr. + * + * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) + * Description + * Get a pointer to the underlying dynptr data. + * + * *len* must be a statically known value. The returned data slice + * is invalidated whenever the dynptr is invalidated. + * Return + * Pointer to the underlying dynptr data, NULL if the dynptr is + * read-only, if the dynptr is invalid, or if the offset and length + * is out of bounds. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5443,6 +5454,7 @@ union bpf_attr { FN(ringbuf_discard_dynptr), \ FN(dynptr_read), \ FN(dynptr_write), \ + FN(dynptr_data), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 5d7c854593a460706dacf8e1b16c9bdcb1c2d7bb Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 28 Mar 2022 08:26:48 +0200 Subject: livepatch: Remove klp_arch_set_pc() and asm/livepatch.h All three versions of klp_arch_set_pc() do exactly the same: they call ftrace_instruction_pointer_set(). Call ftrace_instruction_pointer_set() directly and remove klp_arch_set_pc(). As klp_arch_set_pc() was the only thing remaining in asm/livepatch.h on x86 and s390, remove asm/livepatch.h livepatch.h remains on powerpc but its content is exclusively used by powerpc specific code. Signed-off-by: Christophe Leroy Acked-by: Petr Mladek Acked-by: Peter Zijlstra (Intel) Acked-by: Miroslav Benes Signed-off-by: Petr Mladek --- include/linux/livepatch.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 2614247a9781..293e29960c6e 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -16,8 +16,6 @@ #if IS_ENABLED(CONFIG_LIVEPATCH) -#include - /* task patch states */ #define KLP_UNDEFINED -1 #define KLP_UNPATCHED 0 -- cgit v1.2.3 From 7b4537199a4a8480b8c3ba37a2d44765ce76cd9b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 13 May 2022 20:39:22 +0900 Subject: kbuild: link symbol CRCs at final link, removing CONFIG_MODULE_REL_CRCS include/{linux,asm-generic}/export.h defines a weak symbol, __crc_* as a placeholder. Genksyms writes the version CRCs into the linker script, which will be used for filling the __crc_* symbols. The linker script format depends on CONFIG_MODULE_REL_CRCS. If it is enabled, __crc_* holds the offset to the reference of CRC. It is time to get rid of this complexity. Now that modpost parses text files (.*.cmd) to collect all the CRCs, it can generate C code that will be linked to the vmlinux or modules. Generate a new C file, .vmlinux.export.c, which contains the CRCs of symbols exported by vmlinux. It is compiled and linked to vmlinux in scripts/link-vmlinux.sh. Put the CRCs of symbols exported by modules into the existing *.mod.c files. No additional build step is needed for modules. As before, *.mod.c are compiled and linked to *.ko in scripts/Makefile.modfinal. No linker magic is used here. The new C implementation works in the same way, whether CONFIG_RELOCATABLE is enabled or not. CONFIG_MODULE_REL_CRCS is no longer needed. Previously, Kbuild invoked additional $(LD) to update the CRCs in objects, but this step is unneeded too. Signed-off-by: Masahiro Yamada Tested-by: Nathan Chancellor Tested-by: Nicolas Schier Reviewed-by: Nicolas Schier Tested-by: Sedat Dilek # LLVM-14 (x86-64) --- include/asm-generic/export.h | 22 ++++++++-------------- include/linux/export-internal.h | 17 +++++++++++++++++ include/linux/export.h | 30 ++++++++---------------------- 3 files changed, 33 insertions(+), 36 deletions(-) create mode 100644 include/linux/export-internal.h (limited to 'include') diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h index 07a36a874dca..5e4b1f2369d2 100644 --- a/include/asm-generic/export.h +++ b/include/asm-generic/export.h @@ -2,6 +2,14 @@ #ifndef __ASM_GENERIC_EXPORT_H #define __ASM_GENERIC_EXPORT_H +/* + * This comment block is used by fixdep. Please do not remove. + * + * When CONFIG_MODVERSIONS is changed from n to y, all source files having + * EXPORT_SYMBOL variants must be re-compiled because genksyms is run as a + * side effect of the *.o build rule. + */ + #ifndef KSYM_FUNC #define KSYM_FUNC(x) x #endif @@ -12,9 +20,6 @@ #else #define KSYM_ALIGN 4 #endif -#ifndef KCRC_ALIGN -#define KCRC_ALIGN 4 -#endif .macro __put, val, name #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS @@ -43,17 +48,6 @@ __ksymtab_\name: __kstrtab_\name: .asciz "\name" .previous -#ifdef CONFIG_MODVERSIONS - .section ___kcrctab\sec+\name,"a" - .balign KCRC_ALIGN -#if defined(CONFIG_MODULE_REL_CRCS) - .long __crc_\name - . -#else - .long __crc_\name -#endif - .weak __crc_\name - .previous -#endif #endif .endm diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h new file mode 100644 index 000000000000..c2b1d4fd5987 --- /dev/null +++ b/include/linux/export-internal.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Please do not include this explicitly. + * This is used by C files generated by modpost. + */ + +#ifndef __LINUX_EXPORT_INTERNAL_H__ +#define __LINUX_EXPORT_INTERNAL_H__ + +#include +#include + +/* __used is needed to keep __crc_* for LTO */ +#define SYMBOL_CRC(sym, crc, sec) \ + u32 __section("___kcrctab" sec "+" #sym) __used __crc_##sym = crc + +#endif /* __LINUX_EXPORT_INTERNAL_H__ */ diff --git a/include/linux/export.h b/include/linux/export.h index 27d848712b90..565c5ffcb26f 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -11,6 +11,14 @@ * hackers place grumpy comments in header files. */ +/* + * This comment block is used by fixdep. Please do not remove. + * + * When CONFIG_MODVERSIONS is changed from n to y, all source files having + * EXPORT_SYMBOL variants must be re-compiled because genksyms is run as a + * side effect of the *.o build rule. + */ + #ifndef __ASSEMBLY__ #ifdef MODULE extern struct module __this_module; @@ -19,26 +27,6 @@ extern struct module __this_module; #define THIS_MODULE ((struct module *)0) #endif -#ifdef CONFIG_MODVERSIONS -/* Mark the CRC weak since genksyms apparently decides not to - * generate a checksums for some symbols */ -#if defined(CONFIG_MODULE_REL_CRCS) -#define __CRC_SYMBOL(sym, sec) \ - asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \ - " .weak __crc_" #sym " \n" \ - " .long __crc_" #sym " - . \n" \ - " .previous \n") -#else -#define __CRC_SYMBOL(sym, sec) \ - asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \ - " .weak __crc_" #sym " \n" \ - " .long __crc_" #sym " \n" \ - " .previous \n") -#endif -#else -#define __CRC_SYMBOL(sym, sec) -#endif - #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS #include /* @@ -85,7 +73,6 @@ struct kernel_symbol { /* * For every exported symbol, do the following: * - * - If applicable, place a CRC entry in the __kcrctab section. * - Put the name of the symbol and namespace (empty string "" for none) in * __ksymtab_strings. * - Place a struct kernel_symbol entry in the __ksymtab section. @@ -98,7 +85,6 @@ struct kernel_symbol { extern typeof(sym) sym; \ extern const char __kstrtab_##sym[]; \ extern const char __kstrtabns_##sym[]; \ - __CRC_SYMBOL(sym, sec); \ asm(" .section \"__ksymtab_strings\",\"aMS\",%progbits,1 \n" \ "__kstrtab_" #sym ": \n" \ " .asciz \"" #sym "\" \n" \ -- cgit v1.2.3 From 83567cee0472fb7b57cc6e931ab002aeb69a26d4 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 21 May 2022 13:11:36 +0200 Subject: RDMA/core: Fix typo in comment Spelling mistake (triple letters) in comment. Detected with the help of Coccinelle. Link: https://lore.kernel.org/r/20220521111145.81697-86-Julia.Lawall@inria.fr Signed-off-by: Julia Lawall Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index b0bc9de5e9a8..9c6317cf80d5 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -578,7 +578,7 @@ struct rdma_stat_desc { /** * struct rdma_hw_stats * @lock - Mutex to protect parallel write access to lifespan and values - * of counters, which are 64bits and not guaranteeed to be written + * of counters, which are 64bits and not guaranteed to be written * atomicaly on 32bits systems. * @timestamp - Used by the core code to track when the last update was * @lifespan - Used by the core code to determine how old the counters -- cgit v1.2.3 From 421cfe6596f6cb316991c02bf30a93bd81092853 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Thu, 19 May 2022 14:33:11 -0400 Subject: vfio: remove VFIO_GROUP_NOTIFY_SET_KVM Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to device_open. The first time a device is opened associate the group KVM with the device. This fixes a user-triggerable oops in GVT. Reviewed-by: Tony Krowiak Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Signed-off-by: Matthew Rosato Reviewed-by: Jason Gunthorpe Acked-by: Zhi Wang Link: https://lore.kernel.org/r/20220519183311.582380-2-mjrosato@linux.ibm.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 45b287826ce6..aa888cc51757 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -36,6 +36,8 @@ struct vfio_device { struct vfio_device_set *dev_set; struct list_head dev_set_list; unsigned int migration_flags; + /* Driver must reference the kvm during open_device or never touch it */ + struct kvm *kvm; /* Members below here are private, not for driver use */ refcount_t refcount; @@ -155,15 +157,11 @@ extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova, /* each type has independent events */ enum vfio_notify_type { VFIO_IOMMU_NOTIFY = 0, - VFIO_GROUP_NOTIFY = 1, }; /* events for VFIO_IOMMU_NOTIFY */ #define VFIO_IOMMU_NOTIFY_DMA_UNMAP BIT(0) -/* events for VFIO_GROUP_NOTIFY */ -#define VFIO_GROUP_NOTIFY_SET_KVM BIT(0) - extern int vfio_register_notifier(struct vfio_device *device, enum vfio_notify_type type, unsigned long *required_events, -- cgit v1.2.3 From eadb2f47a3ced5c64b23b90fd2a3463f63726066 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Mon, 23 May 2022 19:11:02 +0100 Subject: lockdown: also lock down previous kgdb use KGDB and KDB allow read and write access to kernel memory, and thus should be restricted during lockdown. An attacker with access to a serial port (for example, via a hypervisor console, which some cloud vendors provide over the network) could trigger the debugger so it is important that the debugger respect the lockdown mode when/if it is triggered. Fix this by integrating lockdown into kdb's existing permissions mechanism. Unfortunately kgdb does not have any permissions mechanism (although it certainly could be added later) so, for now, kgdb is simply and brutally disabled by immediately exiting the gdb stub without taking any action. For lockdowns established early in the boot (e.g. the normal case) then this should be fine but on systems where kgdb has set breakpoints before the lockdown is enacted than "bad things" will happen. CVE: CVE-2022-21499 Co-developed-by: Stephen Brennan Signed-off-by: Stephen Brennan Reviewed-by: Douglas Anderson Signed-off-by: Daniel Thompson Signed-off-by: Linus Torvalds --- include/linux/security.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/security.h b/include/linux/security.h index 25b3ef71f495..7fc4e9f49f54 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -121,10 +121,12 @@ enum lockdown_reason { LOCKDOWN_DEBUGFS, LOCKDOWN_XMON_WR, LOCKDOWN_BPF_WRITE_USER, + LOCKDOWN_DBG_WRITE_KERNEL, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, LOCKDOWN_BPF_READ_KERNEL, + LOCKDOWN_DBG_READ_KERNEL, LOCKDOWN_PERF, LOCKDOWN_TRACEFS, LOCKDOWN_XMON_RW, -- cgit v1.2.3 From e5499dd7253c8382d03f687f19a854adcc688357 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Wed, 25 May 2022 14:08:30 +0100 Subject: media: lirc: revert removal of unused feature flags Commit b2a90f4fcb14 ("media: lirc: remove unused lirc features") removed feature flags which were never implemented, but they are still used by the lirc daemon went built from source. Reinstate these symbols in order not to break the lirc build. Fixes: b2a90f4fcb14 ("media: lirc: remove unused lirc features") Link: https://lore.kernel.org/all/a0470450-ecfd-2918-e04a-7b57c1fd7694@kernel.org/ Reported-by: Jiri Slaby Cc: Mauro Carvalho Chehab Signed-off-by: Sean Young Signed-off-by: Linus Torvalds --- include/uapi/linux/lirc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h index 23b0f2c8ba81..8d7ca7c6af42 100644 --- a/include/uapi/linux/lirc.h +++ b/include/uapi/linux/lirc.h @@ -84,6 +84,13 @@ #define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK) #define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK) +/* + * Unused features. These features were never implemented, in tree or + * out of tree. These definitions are here so not to break the lircd build. + */ +#define LIRC_CAN_SET_REC_FILTER 0 +#define LIRC_CAN_NOTIFY_DECODE 0 + /*** IOCTL commands for lirc driver ***/ #define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32) -- cgit v1.2.3 From caa28984163cb63ea0be4cb8dbf05defdc7303f9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 25 May 2022 09:02:19 -0700 Subject: linux/types.h: reinstate "__bitwise__" macro for user space use Commit c724c866bb70 ("linux/types.h: remove unnecessary __bitwise__") was right that there are no users of __bitwise__ in the kernel, but it turns out there are user space users of it that do expect it. It is, after all, in the uapi directory, so user space usage is to be expected. Instead of reverting the commit completely, let's just clarify the situation so that it doesn't happen again, and have some in-code explanations for why that "__bitwise__" still exists. Reported-by: Jiri Slaby Cc: Bjorn Helgaas Link: https://lore.kernel.org/all/b5c0a68d-8387-4909-beea-f70ab9e6e3d5@kernel.org/ Signed-off-by: Linus Torvalds --- include/uapi/linux/types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h index c4dc597f3dcf..308433be33c2 100644 --- a/include/uapi/linux/types.h +++ b/include/uapi/linux/types.h @@ -26,6 +26,9 @@ #define __bitwise #endif +/* The kernel doesn't use this legacy form, but user space does */ +#define __bitwise__ __bitwise + typedef __u16 __bitwise __le16; typedef __u16 __bitwise __be16; typedef __u32 __bitwise __le32; -- cgit v1.2.3 From 185194f19134716f32b2ab04ac76cf93ea85706a Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 17 May 2022 09:58:14 +0300 Subject: include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion" Redefines __def_gfpflag_names array according to akpm@, willy@ and Joe Perches recommendations. Link: https://lkml.kernel.org/r/6f811e19-41c6-f3e8-fca6-23a19a62e313@openvz.org Fixes: fe573327ffb1 ("tracing: incorrect gfp_t conversion") Signed-off-by: Vasily Averin Cc: Matthew Wilcox Cc: Joe Perches Cc: Steven Rostedt Signed-off-by: Andrew Morton --- include/trace/events/mmflags.h | 84 +++++++++++++++++++++--------------------- 1 file changed, 43 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index fcb1ffb2cc8d..e87cb2b80ed3 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -13,49 +13,51 @@ * Thus most bits set go first. */ -#define __def_gfpflag_names \ - {(__force unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ - {(__force unsigned long)GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"}, \ - {(__force unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"},\ - {(__force unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ - {(__force unsigned long)GFP_USER, "GFP_USER"}, \ - {(__force unsigned long)GFP_KERNEL_ACCOUNT, "GFP_KERNEL_ACCOUNT"}, \ - {(__force unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ - {(__force unsigned long)GFP_NOFS, "GFP_NOFS"}, \ - {(__force unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ - {(__force unsigned long)GFP_NOIO, "GFP_NOIO"}, \ - {(__force unsigned long)GFP_NOWAIT, "GFP_NOWAIT"}, \ - {(__force unsigned long)GFP_DMA, "GFP_DMA"}, \ - {(__force unsigned long)__GFP_HIGHMEM, "__GFP_HIGHMEM"}, \ - {(__force unsigned long)GFP_DMA32, "GFP_DMA32"}, \ - {(__force unsigned long)__GFP_HIGH, "__GFP_HIGH"}, \ - {(__force unsigned long)__GFP_ATOMIC, "__GFP_ATOMIC"}, \ - {(__force unsigned long)__GFP_IO, "__GFP_IO"}, \ - {(__force unsigned long)__GFP_FS, "__GFP_FS"}, \ - {(__force unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ - {(__force unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ - {(__force unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ - {(__force unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ - {(__force unsigned long)__GFP_COMP, "__GFP_COMP"}, \ - {(__force unsigned long)__GFP_ZERO, "__GFP_ZERO"}, \ - {(__force unsigned long)__GFP_NOMEMALLOC, "__GFP_NOMEMALLOC"}, \ - {(__force unsigned long)__GFP_MEMALLOC, "__GFP_MEMALLOC"}, \ - {(__force unsigned long)__GFP_HARDWALL, "__GFP_HARDWALL"}, \ - {(__force unsigned long)__GFP_THISNODE, "__GFP_THISNODE"}, \ - {(__force unsigned long)__GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"}, \ - {(__force unsigned long)__GFP_MOVABLE, "__GFP_MOVABLE"}, \ - {(__force unsigned long)__GFP_ACCOUNT, "__GFP_ACCOUNT"}, \ - {(__force unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ - {(__force unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ - {(__force unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ - {(__force unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ - {(__force unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ +#define gfpflag_string(flag) {(__force unsigned long)flag, #flag} + +#define __def_gfpflag_names \ + gfpflag_string(GFP_TRANSHUGE), \ + gfpflag_string(GFP_TRANSHUGE_LIGHT), \ + gfpflag_string(GFP_HIGHUSER_MOVABLE), \ + gfpflag_string(GFP_HIGHUSER), \ + gfpflag_string(GFP_USER), \ + gfpflag_string(GFP_KERNEL_ACCOUNT), \ + gfpflag_string(GFP_KERNEL), \ + gfpflag_string(GFP_NOFS), \ + gfpflag_string(GFP_ATOMIC), \ + gfpflag_string(GFP_NOIO), \ + gfpflag_string(GFP_NOWAIT), \ + gfpflag_string(GFP_DMA), \ + gfpflag_string(__GFP_HIGHMEM), \ + gfpflag_string(GFP_DMA32), \ + gfpflag_string(__GFP_HIGH), \ + gfpflag_string(__GFP_ATOMIC), \ + gfpflag_string(__GFP_IO), \ + gfpflag_string(__GFP_FS), \ + gfpflag_string(__GFP_NOWARN), \ + gfpflag_string(__GFP_RETRY_MAYFAIL), \ + gfpflag_string(__GFP_NOFAIL), \ + gfpflag_string(__GFP_NORETRY), \ + gfpflag_string(__GFP_COMP), \ + gfpflag_string(__GFP_ZERO), \ + gfpflag_string(__GFP_NOMEMALLOC), \ + gfpflag_string(__GFP_MEMALLOC), \ + gfpflag_string(__GFP_HARDWALL), \ + gfpflag_string(__GFP_THISNODE), \ + gfpflag_string(__GFP_RECLAIMABLE), \ + gfpflag_string(__GFP_MOVABLE), \ + gfpflag_string(__GFP_ACCOUNT), \ + gfpflag_string(__GFP_WRITE), \ + gfpflag_string(__GFP_RECLAIM), \ + gfpflag_string(__GFP_DIRECT_RECLAIM), \ + gfpflag_string(__GFP_KSWAPD_RECLAIM), \ + gfpflag_string(__GFP_ZEROTAGS) #ifdef CONFIG_KASAN_HW_TAGS -#define __def_gfpflag_names_kasan , \ - {(__force unsigned long)__GFP_SKIP_ZERO, "__GFP_SKIP_ZERO"}, \ - {(__force unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ - {(__force unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} +#define __def_gfpflag_names_kasan , \ + gfpflag_string(__GFP_SKIP_ZERO), \ + gfpflag_string(__GFP_SKIP_KASAN_POISON), \ + gfpflag_string(__GFP_SKIP_KASAN_UNPOISON) #else #define __def_gfpflag_names_kasan #endif -- cgit v1.2.3 From e5c3f619a04d9e191de66d5f8e069367f73a6487 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 17 May 2022 09:55:51 +0300 Subject: include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace" Fix sparse warning about incorrect gfp_t cast. Link: https://lkml.kernel.org/r/001979f3-e978-0998-cbed-61a4a2ac87b8@openvz.org Fixes: f67bed134a05 ("percpu: improve percpu_alloc_percpu event trace") Signed-off-by: Vasily Averin Signed-off-by: Andrew Morton --- include/trace/events/percpu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/percpu.h b/include/trace/events/percpu.h index e989cefc0def..5b8211ca8950 100644 --- a/include/trace/events/percpu.h +++ b/include/trace/events/percpu.h @@ -28,7 +28,7 @@ TRACE_EVENT(percpu_alloc_percpu, __field( int, off ) __field( void __percpu *, ptr ) __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; @@ -40,7 +40,7 @@ TRACE_EVENT(percpu_alloc_percpu, __entry->off = off; __entry->ptr = ptr; __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", -- cgit v1.2.3 From 4934609dda03ec90ca5052deecbe455b09a44e21 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 23 May 2022 16:17:06 +0000 Subject: amt: fix typo in amt AMT_MSG_TEARDOWM is defined, But it should be AMT_MSG_TEARDOWN. Fixes: b9022b53adad ("amt: add control plane of amt interface") Signed-off-by: Taehee Yoo Signed-off-by: Jakub Kicinski --- include/net/amt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/amt.h b/include/net/amt.h index 7a4db8b903ee..0e40c3d64fcf 100644 --- a/include/net/amt.h +++ b/include/net/amt.h @@ -15,7 +15,7 @@ enum amt_msg_type { AMT_MSG_MEMBERSHIP_QUERY, AMT_MSG_MEMBERSHIP_UPDATE, AMT_MSG_MULTICAST_DATA, - AMT_MSG_TEARDOWM, + AMT_MSG_TEARDOWN, __AMT_MSG_MAX, }; -- cgit v1.2.3 From 50e35bd57c02a584442c0aa917787c858eabe80b Mon Sep 17 00:00:00 2001 From: pengfuyuan Date: Thu, 26 May 2022 14:27:57 +0800 Subject: video: fbdev: radeon: Fix spelling typo in comment Fix spelling typo in comment. Signed-off-by: pengfuyuan Signed-off-by: Helge Deller --- include/video/radeon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/video/radeon.h b/include/video/radeon.h index 005eae19ec09..72f94ccfa725 100644 --- a/include/video/radeon.h +++ b/include/video/radeon.h @@ -750,7 +750,7 @@ #define WAIT_DMA_GUI_IDLE (1 << 9) #define WAIT_2D_IDLECLEAN (1 << 16) -/* SURFACE_CNTL bit consants */ +/* SURFACE_CNTL bit constants */ #define SURF_TRANSLATION_DIS (1 << 8) #define NONSURF_AP0_SWP_16BPP (1 << 20) #define NONSURF_AP0_SWP_32BPP (1 << 21) -- cgit v1.2.3 From d534ca7128d7bf681ed6d462c09b9d6ffb3bed91 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 23 May 2022 11:24:31 -0400 Subject: drm/amdgpu: differentiate between LP and non-LP DDR memory Some applications want to know whether the memory is LP or not. Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 9a1d210d135d..d9d475d65c76 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -988,6 +988,8 @@ struct drm_amdgpu_info_vbios { #define AMDGPU_VRAM_TYPE_DDR4 8 #define AMDGPU_VRAM_TYPE_GDDR6 9 #define AMDGPU_VRAM_TYPE_DDR5 10 +#define AMDGPU_VRAM_TYPE_LPDDR4 11 +#define AMDGPU_VRAM_TYPE_LPDDR5 12 struct drm_amdgpu_info_device { /** PCI Device ID */ -- cgit v1.2.3 From fab2cc8335839867a3db38f195441b9c7c6460f6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 6 May 2022 13:08:34 +0200 Subject: drm/amdgpu: add AMDGPU_GEM_CREATE_DISCARDABLE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a AMDGPU_GEM_CREATE_DISCARDABLE flag to note that the content of a BO doesn't needs to be preserved during eviction. KFD was already using a similar functionality for SVM BOs so replace the internal flag with the new UAPI. Signed-off-by: Christian König Reviewed-by: Alex Deucher Reviewed-by: Marek Olšák Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index d9d475d65c76..a81bef5cfeaa 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -140,6 +140,10 @@ extern "C" { * not require GTT memory accounting */ #define AMDGPU_GEM_CREATE_PREEMPTIBLE (1 << 11) +/* Flag that BO can be discarded under memory pressure without keeping the + * content. + */ +#define AMDGPU_GEM_CREATE_DISCARDABLE (1 << 12) struct drm_amdgpu_gem_create_in { /** the requested memory size */ -- cgit v1.2.3 From b6c65a2c92aa880e8050a91ca83288b85fc32575 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 6 May 2022 13:11:41 +0200 Subject: drm/amdgpu: add AMDGPU_VM_NOALLOC v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the AMDGPU_VM_NOALLOC flag to let userspace control MALL allocation. v2: also add the flag to the allowed flags. Signed-off-by: Christian König Reviewed-by: Alex Deucher (v1) Reviewed-by: Marek Olšák Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index a81bef5cfeaa..18d3246d636e 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -533,6 +533,8 @@ struct drm_amdgpu_gem_op { #define AMDGPU_VM_MTYPE_UC (4 << 5) /* Use Read Write MTYPE instead of default MTYPE */ #define AMDGPU_VM_MTYPE_RW (5 << 5) +/* don't allocate MALL */ +#define AMDGPU_VM_PAGE_NOALLOC (1 << 9) struct drm_amdgpu_gem_va { /** GEM object handle */ -- cgit v1.2.3 From 43994049180704fd1faf78623fabd9a5cd443708 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 4 May 2022 12:36:31 +0900 Subject: kprobes: Fix build errors with CONFIG_KRETPROBES=n MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Max Filippov reported: When building kernel with CONFIG_KRETPROBES=n kernel/kprobes.c compilation fails with the following messages: kernel/kprobes.c: In function ‘recycle_rp_inst’: kernel/kprobes.c:1273:32: error: implicit declaration of function ‘get_kretprobe’ kernel/kprobes.c: In function ‘kprobe_flush_task’: kernel/kprobes.c:1299:35: error: ‘struct task_struct’ has no member named ‘kretprobe_instances’ This came from the commit d741bf41d7c7 ("kprobes: Remove kretprobe hash") which introduced get_kretprobe() and kretprobe_instances member in task_struct when CONFIG_KRETPROBES=y, but did not make recycle_rp_inst() and kprobe_flush_task() depending on CONFIG_KRETPORBES. Since those functions are only used for kretprobe, move those functions into #ifdef CONFIG_KRETPROBE area. Link: https://lkml.kernel.org/r/165163539094.74407.3838114721073251225.stgit@devnote2 Reported-by: Max Filippov Fixes: d741bf41d7c7 ("kprobes: Remove kretprobe hash") Cc: "Naveen N . Rao" Cc: Anil S Keshavamurthy Cc: "David S . Miller" Cc: Peter Zijlstra Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu Tested-by: Max Filippov Signed-off-by: Steven Rostedt (Google) --- include/linux/kprobes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 157168769fc2..55041d2f884d 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -424,7 +424,7 @@ void unregister_kretprobe(struct kretprobe *rp); int register_kretprobes(struct kretprobe **rps, int num); void unregister_kretprobes(struct kretprobe **rps, int num); -#ifdef CONFIG_KRETPROBE_ON_RETHOOK +#if defined(CONFIG_KRETPROBE_ON_RETHOOK) || !defined(CONFIG_KRETPROBES) #define kprobe_flush_task(tk) do {} while (0) #else void kprobe_flush_task(struct task_struct *tk); -- cgit v1.2.3 From 3a2bfec0b02f2226ff3376a5d2ff604d799bd7ea Mon Sep 17 00:00:00 2001 From: Li kunyu Date: Wed, 18 May 2022 10:36:40 +0800 Subject: ftrace: Remove return value of ftrace_arch_modify_*() All instances of the function ftrace_arch_modify_prepare() and ftrace_arch_modify_post_process() return zero. There's no point in checking their return value. Just have them be void functions. Link: https://lkml.kernel.org/r/20220518023639.4065-1-kunyu@nfschina.com Signed-off-by: Li kunyu Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 4816b7e11047..a5f74f6e7e4e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -449,8 +449,8 @@ static inline void stack_tracer_enable(void) { } #ifdef CONFIG_DYNAMIC_FTRACE -int ftrace_arch_code_modify_prepare(void); -int ftrace_arch_code_modify_post_process(void); +void ftrace_arch_code_modify_prepare(void); +void ftrace_arch_code_modify_post_process(void); enum ftrace_bug_type { FTRACE_BUG_UNKNOWN, -- cgit v1.2.3 From a54ce3703613e41fe1d98060b62ec09a3984dc28 Mon Sep 17 00:00:00 2001 From: Vincent Ray Date: Wed, 25 May 2022 17:17:46 -0700 Subject: net: sched: fixed barrier to prevent skbuff sticking in qdisc backlog In qdisc_run_begin(), smp_mb__before_atomic() used before test_bit() does not provide any ordering guarantee as test_bit() is not an atomic operation. This, added to the fact that the spin_trylock() call at the beginning of qdisc_run_begin() does not guarantee acquire semantics if it does not grab the lock, makes it possible for the following statement : if (test_bit(__QDISC_STATE_MISSED, &qdisc->state)) to be executed before an enqueue operation called before qdisc_run_begin(). As a result the following race can happen : CPU 1 CPU 2 qdisc_run_begin() qdisc_run_begin() /* true */ set(MISSED) . /* returns false */ . . /* sees MISSED = 1 */ . /* so qdisc not empty */ . __qdisc_run() . . . pfifo_fast_dequeue() ----> /* may be done here */ . | . clear(MISSED) | . . | . smp_mb __after_atomic(); | . . | . /* recheck the queue */ | . /* nothing => exit */ | enqueue(skb1) | . | qdisc_run_begin() | . | spin_trylock() /* fail */ | . | smp_mb__before_atomic() /* not enough */ | . ---- if (test_bit(MISSED)) return false; /* exit */ In the above scenario, CPU 1 and CPU 2 both try to grab the qdisc->seqlock at the same time. Only CPU 2 succeeds and enters the bypass code path, where it emits its skb then calls __qdisc_run(). CPU1 fails, sets MISSED and goes down the traditionnal enqueue() + dequeue() code path. But when executing qdisc_run_begin() for the second time, after enqueuing its skbuff, it sees the MISSED bit still set (by itself) and consequently chooses to exit early without setting it again nor trying to grab the spinlock again. Meanwhile CPU2 has seen MISSED = 1, cleared it, checked the queue and found it empty, so it returned. At the end of the sequence, we end up with skb1 enqueued in the backlog, both CPUs out of __dev_xmit_skb(), the MISSED bit not set, and no __netif_schedule() called made. skb1 will now linger in the qdisc until somebody later performs a full __qdisc_run(). Associated to the bypass capacity of the qdisc, and the ability of the TCP layer to avoid resending packets which it knows are still in the qdisc, this can lead to serious traffic "holes" in a TCP connection. We fix this by replacing the smp_mb__before_atomic() / test_bit() / set_bit() / smp_mb__after_atomic() sequence inside qdisc_run_begin() by a single test_and_set_bit() call, which is more concise and enforces the needed memory barriers. Fixes: 89837eb4b246 ("net: sched: add barrier to ensure correct ordering for lockless qdisc") Signed-off-by: Vincent Ray Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20220526001746.2437669-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/net/sch_generic.h | 36 ++++++++---------------------------- 1 file changed, 8 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 9bab396c1f3b..80973ce820f3 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -187,37 +187,17 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) if (spin_trylock(&qdisc->seqlock)) return true; - /* Paired with smp_mb__after_atomic() to make sure - * STATE_MISSED checking is synchronized with clearing - * in pfifo_fast_dequeue(). + /* No need to insist if the MISSED flag was already set. + * Note that test_and_set_bit() also gives us memory ordering + * guarantees wrt potential earlier enqueue() and below + * spin_trylock(), both of which are necessary to prevent races */ - smp_mb__before_atomic(); - - /* If the MISSED flag is set, it means other thread has - * set the MISSED flag before second spin_trylock(), so - * we can return false here to avoid multi cpus doing - * the set_bit() and second spin_trylock() concurrently. - */ - if (test_bit(__QDISC_STATE_MISSED, &qdisc->state)) + if (test_and_set_bit(__QDISC_STATE_MISSED, &qdisc->state)) return false; - /* Set the MISSED flag before the second spin_trylock(), - * if the second spin_trylock() return false, it means - * other cpu holding the lock will do dequeuing for us - * or it will see the MISSED flag set after releasing - * lock and reschedule the net_tx_action() to do the - * dequeuing. - */ - set_bit(__QDISC_STATE_MISSED, &qdisc->state); - - /* spin_trylock() only has load-acquire semantic, so use - * smp_mb__after_atomic() to ensure STATE_MISSED is set - * before doing the second spin_trylock(). - */ - smp_mb__after_atomic(); - - /* Retry again in case other CPU may not see the new flag - * after it releases the lock at the end of qdisc_run_end(). + /* Try to take the lock again to make sure that we will either + * grab it or the CPU that still has it will see MISSED set + * when testing it in qdisc_run_end() */ return spin_trylock(&qdisc->seqlock); } -- cgit v1.2.3 From 49f8b459fc1de5e3712b57c8ccefae9ec45270f8 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 24 May 2022 13:46:30 +0200 Subject: xen: switch gnttab_end_foreign_access() to take a struct page pointer Instead of a virtual kernel address use a pointer of the associated struct page as second parameter of gnttab_end_foreign_access(). Most users have that pointer available already and are creating the virtual address from it, risking problems in case the memory is located in highmem. gnttab_end_foreign_access() itself won't need to get the struct page from the address again. Suggested-by: Jan Beulich Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Signed-off-by: Juergen Gross --- include/xen/grant_table.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 7d0f2f0037b8..527c9907f99c 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -101,10 +101,10 @@ int gnttab_end_foreign_access_ref(grant_ref_t ref); * Eventually end access through the given grant reference, and once that * access has been ended, free the given page too. Access will be ended * immediately iff the grant entry is not in use, otherwise it will happen - * some time later. page may be 0, in which case no freeing will occur. + * some time later. page may be NULL, in which case no freeing will occur. * Note that the granted page might still be accessed (read or write) by the * other side after gnttab_end_foreign_access() returns, so even if page was - * specified as 0 it is not allowed to just reuse the page for other + * specified as NULL it is not allowed to just reuse the page for other * purposes immediately. gnttab_end_foreign_access() will take an additional * reference to the granted page in this case, which is dropped only after * the grant is no longer in use. @@ -112,7 +112,7 @@ int gnttab_end_foreign_access_ref(grant_ref_t ref); * gnttab_end_foreign_access() are done via alloc_pages_exact() (and freeing * via free_pages_exact()) in order to avoid high order pages. */ -void gnttab_end_foreign_access(grant_ref_t ref, unsigned long page); +void gnttab_end_foreign_access(grant_ref_t ref, struct page *page); /* * End access through the given grant reference, iff the grant entry is -- cgit v1.2.3 From 56b14ecec97f39118bf85c9ac2438c5a949509ed Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 20 May 2022 00:02:04 +0200 Subject: netfilter: conntrack: re-fetch conntrack after insertion In case the conntrack is clashing, insertion can free skb->_nfct and set skb->_nfct to the already-confirmed entry. This wasn't found before because the conntrack entry and the extension space used to free'd after an rcu grace period, plus the race needs events enabled to trigger. Reported-by: Fixes: 71d8c47fc653 ("netfilter: conntrack: introduce clash resolution on insertion race") Fixes: 2ad9d7747c10 ("netfilter: conntrack: free extension area immediately") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 6406cfee34c2..37866c8386e2 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -58,8 +58,13 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) int ret = NF_ACCEPT; if (ct) { - if (!nf_ct_is_confirmed(ct)) + if (!nf_ct_is_confirmed(ct)) { ret = __nf_conntrack_confirm(skb); + + if (ret == NF_ACCEPT) + ct = (struct nf_conn *)skb_nfct(skb); + } + if (ret == NF_ACCEPT && nf_ct_ecache_exist(ct)) nf_ct_deliver_cached_events(ct); } -- cgit v1.2.3 From 656d054e0a15ec327bd82801ccd58201e59f6896 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 2 May 2022 12:30:20 +0200 Subject: jump_label,noinstr: Avoid instrumentation for JUMP_LABEL=n builds When building x86_64 with JUMP_LABEL=n it's possible for instrumentation to sneak into noinstr: vmlinux.o: warning: objtool: exit_to_user_mode+0x14: call to static_key_count.constprop.0() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_exit_to_user_mode+0x2d: call to static_key_count.constprop.0() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_exit_to_user_mode+0x1b: call to static_key_count.constprop.0() leaves .noinstr.text section Switch to arch_ prefixed atomic to avoid the explicit instrumentation. Reported-by: kernel test robot Signed-off-by: Peter Zijlstra (Intel) --- include/linux/jump_label.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 107751cc047b..bf1eef337a07 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -256,9 +256,9 @@ extern void static_key_disable_cpuslocked(struct static_key *key); #include #include -static inline int static_key_count(struct static_key *key) +static __always_inline int static_key_count(struct static_key *key) { - return atomic_read(&key->enabled); + return arch_atomic_read(&key->enabled); } static __always_inline void jump_label_init(void) -- cgit v1.2.3 From 620f8d3bd3d5e82dff8cc591c831827d4beeae2e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 7 May 2022 13:35:37 +0200 Subject: context_tracking: Always inline empty stubs Because GCC is seriously challenged.. vmlinux.o: warning: objtool: enter_from_user_mode+0x85: call to context_tracking_enabled() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0x8f: call to context_tracking_enabled() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode_prepare+0x85: call to context_tracking_enabled() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_enter_from_user_mode+0x85: call to context_tracking_enabled() leaves .noinstr.text section Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Link: https://lkml.kernel.org/r/20220526105958.134113388@infradead.org --- include/linux/context_tracking_state.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 65a60d3313b0..ae1e63e26947 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -46,10 +46,10 @@ static __always_inline bool context_tracking_in_user(void) return __this_cpu_read(context_tracking.state) == CONTEXT_USER; } #else -static inline bool context_tracking_in_user(void) { return false; } -static inline bool context_tracking_enabled(void) { return false; } -static inline bool context_tracking_enabled_cpu(int cpu) { return false; } -static inline bool context_tracking_enabled_this_cpu(void) { return false; } +static __always_inline bool context_tracking_in_user(void) { return false; } +static __always_inline bool context_tracking_enabled(void) { return false; } +static __always_inline bool context_tracking_enabled_cpu(int cpu) { return false; } +static __always_inline bool context_tracking_enabled_this_cpu(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING */ #endif -- cgit v1.2.3 From b9684a71fca793213378dd410cd11675d973eaa1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 May 2022 07:58:06 +0200 Subject: block, loop: support partitions without scanning Historically we did distinguish between a flag that surpressed partition scanning, and a combinations of the minors variable and another flag if any partitions were supported. This was generally confusing and doesn't make much sense, but some corner case uses of the loop driver actually do want to support manually added partitions on a device that does not actively scan for partitions. To make things worsee the loop driver also wants to dynamically toggle the scanning for partitions on a live gendisk, which makes the disk->flags updates non-atomic. Introduce a new GD_SUPPRESS_PART_SCAN bit in disk->state that disables just scanning for partitions, and toggle that instead of GENHD_FL_NO_PART in the loop driver. Fixes: 1ebe2e5f9d68 ("block: remove GENHD_FL_EXT_DEVT") Reported-by: Ming Lei Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20220527055806.1972352-1-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index afad3d1d0dac..691b4c15b8ce 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -147,6 +147,7 @@ struct gendisk { #define GD_DEAD 2 #define GD_NATIVE_CAPACITY 3 #define GD_ADDED 4 +#define GD_SUPPRESS_PART_SCAN 5 struct mutex open_mutex; /* open/close mutex */ unsigned open_partitions; /* number of open partitions */ -- cgit v1.2.3 From 3e35142ef99fe6b4fe5d834ad43ee13cca10a2dc Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Thu, 19 May 2022 14:42:37 +0530 Subject: kexec_file: drop weak attribute from arch_kexec_apply_relocations[_add] Since commit d1bcae833b32f1 ("ELF: Don't generate unused section symbols") [1], binutils (v2.36+) started dropping section symbols that it thought were unused. This isn't an issue in general, but with kexec_file.c, gcc is placing kexec_arch_apply_relocations[_add] into a separate .text.unlikely section and the section symbol ".text.unlikely" is being dropped. Due to this, recordmcount is unable to find a non-weak symbol in .text.unlikely to generate a relocation record against. Address this by dropping the weak attribute from these functions. Instead, follow the existing pattern of having architectures #define the name of the function they want to override in their headers. [1] https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=d1bcae833b32f1 [akpm@linux-foundation.org: arch/s390/include/asm/kexec.h needs linux/module.h] Link: https://lkml.kernel.org/r/20220519091237.676736-1-naveen.n.rao@linux.vnet.ibm.com Signed-off-by: Michael Ellerman Signed-off-by: Naveen N. Rao Cc: "Eric W. Biederman" Cc: Signed-off-by: Andrew Morton --- include/linux/kexec.h | 46 ++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 38 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 58d1b58a971e..fcd5035209f1 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -193,14 +193,6 @@ void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, unsigned long buf_len); void *arch_kexec_kernel_image_load(struct kimage *image); -int arch_kexec_apply_relocations_add(struct purgatory_info *pi, - Elf_Shdr *section, - const Elf_Shdr *relsec, - const Elf_Shdr *symtab); -int arch_kexec_apply_relocations(struct purgatory_info *pi, - Elf_Shdr *section, - const Elf_Shdr *relsec, - const Elf_Shdr *symtab); int arch_kimage_file_post_load_cleanup(struct kimage *image); #ifdef CONFIG_KEXEC_SIG int arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, @@ -229,6 +221,44 @@ extern int crash_exclude_mem_range(struct crash_mem *mem, unsigned long long mend); extern int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map, void **addr, unsigned long *sz); + +#ifndef arch_kexec_apply_relocations_add +/* + * arch_kexec_apply_relocations_add - apply relocations of type RELA + * @pi: Purgatory to be relocated. + * @section: Section relocations applying to. + * @relsec: Section containing RELAs. + * @symtab: Corresponding symtab. + * + * Return: 0 on success, negative errno on error. + */ +static inline int +arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section, + const Elf_Shdr *relsec, const Elf_Shdr *symtab) +{ + pr_err("RELA relocation unsupported.\n"); + return -ENOEXEC; +} +#endif + +#ifndef arch_kexec_apply_relocations +/* + * arch_kexec_apply_relocations - apply relocations of type REL + * @pi: Purgatory to be relocated. + * @section: Section relocations applying to. + * @relsec: Section containing RELs. + * @symtab: Corresponding symtab. + * + * Return: 0 on success, negative errno on error. + */ +static inline int +arch_kexec_apply_relocations(struct purgatory_info *pi, Elf_Shdr *section, + const Elf_Shdr *relsec, const Elf_Shdr *symtab) +{ + pr_err("REL relocation unsupported.\n"); + return -ENOEXEC; +} +#endif #endif /* CONFIG_KEXEC_FILE */ #ifdef CONFIG_KEXEC_ELF -- cgit v1.2.3 From 9f186f9e5fa9ebdaef909fd45f825a6ce281f13c Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 19 May 2022 20:50:26 +0800 Subject: mm/swapfile: unuse_pte can map random data if swap read fails Patch series "A few fixup patches for mm", v4. This series contains a few patches to avoid mapping random data if swap read fails and fix lost swap bits in unuse_pte. Also we free hwpoison and swapin error entry in madvise_free_pte_range and so on. More details can be found in the respective changelogs. This patch (of 5): There is a bug in unuse_pte(): when swap page happens to be unreadable, page filled with random data is mapped into user address space. In case of error, a special swap entry indicating swap read fails is set to the page table. So the swapcache page can be freed and the user won't end up with a permanently mounted swap because a sector is bad. And if the page is accessed later, the user process will be killed so that corrupted data is never consumed. On the other hand, if the page is never accessed, the user won't even notice it. Link: https://lkml.kernel.org/r/20220519125030.21486-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20220519125030.21486-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Acked-by: David Hildenbrand Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: Vlastimil Babka Cc: David Howells Cc: NeilBrown Cc: Alistair Popple Cc: Suren Baghdasaryan Cc: Peter Xu Cc: Ralph Campbell Cc: Naoya Horiguchi Signed-off-by: Andrew Morton --- include/linux/swap.h | 7 ++++++- include/linux/swapops.h | 10 ++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index f3ae17b43f20..0c0fed1b348f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -55,6 +55,10 @@ static inline int current_is_kswapd(void) * actions on faults. */ +#define SWP_SWAPIN_ERROR_NUM 1 +#define SWP_SWAPIN_ERROR (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ + SWP_MIGRATION_NUM + SWP_DEVICE_NUM + \ + SWP_PTE_MARKER_NUM) /* * PTE markers are used to persist information onto PTEs that are mapped with * file-backed memories. As its name "PTE" hints, it should only be applied to @@ -120,7 +124,8 @@ static inline int current_is_kswapd(void) #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - SWP_PTE_MARKER_NUM) + SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ + SWP_PTE_MARKER_NUM - SWP_SWAPIN_ERROR_NUM) /* * Magic header for a swap area. The first part of the union is diff --git a/include/linux/swapops.h b/include/linux/swapops.h index fe220df499f1..f24775b41880 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -108,6 +108,16 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) return xa_mk_value(entry.val); } +static inline swp_entry_t make_swapin_error_entry(struct page *page) +{ + return swp_entry(SWP_SWAPIN_ERROR, page_to_pfn(page)); +} + +static inline int is_swapin_error_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_SWAPIN_ERROR; +} + #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { -- cgit v1.2.3 From 1c563432588dbffa71e67ca6e37c826f9fa86e04 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 24 May 2022 10:15:25 -0700 Subject: mm: fix is_pinnable_page against a cma page Pages in the CMA area could have MIGRATE_ISOLATE as well as MIGRATE_CMA so the current is_pinnable_page() could miss CMA pages which have MIGRATE_ISOLATE. It ends up pinning CMA pages as longterm for the pin_user_pages() API so CMA allocations keep failing until the pin is released. CPU 0 CPU 1 - Task B cma_alloc alloc_contig_range pin_user_pages_fast(FOLL_LONGTERM) change pageblock as MIGRATE_ISOLATE internal_get_user_pages_fast lockless_pages_from_mm gup_pte_range try_grab_folio is_pinnable_page return true; So, pinned the page successfully. page migration failure with pinned page .. .. After 30 sec unpin_user_page(page) CMA allocation succeeded after 30 sec. The CMA allocation path protects the migration type change race using zone->lock but what GUP path need to know is just whether the page is on CMA area or not rather than exact migration type. Thus, we don't need zone->lock but just checks migration type in either of (MIGRATE_ISOLATE and MIGRATE_CMA). Adding the MIGRATE_ISOLATE check in is_pinnable_page could cause rejecting of pinning pages on MIGRATE_ISOLATE pageblocks even though it's neither CMA nor movable zone if the page is temporarily unmovable. However, such a migration failure by unexpected temporal refcount holding is general issue, not only come from MIGRATE_ISOLATE and the MIGRATE_ISOLATE is also transient state like other temporal elevated refcount problem. Link: https://lkml.kernel.org/r/20220524171525.976723-1-minchan@kernel.org Signed-off-by: Minchan Kim Reviewed-by: John Hubbard Acked-by: Paul E. McKenney Cc: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/mm.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index de32c0383387..93a46ff33dc2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1594,8 +1594,13 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, #ifdef CONFIG_MIGRATION static inline bool is_pinnable_page(struct page *page) { - return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) || - is_zero_pfn(page_to_pfn(page)); +#ifdef CONFIG_CMA + int mt = get_pageblock_migratetype(page); + + if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) + return false; +#endif + return !(is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page))); } #else static inline bool is_pinnable_page(struct page *page) -- cgit v1.2.3 From 98d40e76652e9aeb3aec4065f600d633ed335e94 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 24 May 2022 07:56:30 +0200 Subject: block: document BLK_STS_AGAIN usage BLK_STS_AGAIN should only be used if RQF_NOWAIT is set and the bio would block. So we'd better document that to avoid accidental misuse. Signed-off-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220524055631.85480-2-hare@suse.de Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 40e815400611..8b38367d1bc7 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -105,6 +105,10 @@ typedef u16 blk_short_t; /* hack for device mapper, don't use elsewhere: */ #define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) +/* + * BLK_STS_AGAIN should only be returned if RQF_NOWAIT is set + * and the bio would block (cf bio_wouldblock_error()) + */ #define BLK_STS_AGAIN ((__force blk_status_t)12) /* -- cgit v1.2.3 From e2e530867245d051dc7800b0d07193b3e581f5b9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 May 2022 14:15:30 +0200 Subject: blk-mq: remove the done argument to blk_execute_rq_nowait Let the caller set it together with the end_io_data instead of passing a pointless argument. Note the the target code did in fact already set it and then just overrode it again by calling blk_execute_rq_nowait. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Kanchan Joshi Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220524121530.943123-4-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 9f07061418db..e2d9daf7e8dd 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -969,8 +969,7 @@ int blk_rq_unmap_user(struct bio *); int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); int blk_rq_append_bio(struct request *rq, struct bio *bio); -void blk_execute_rq_nowait(struct request *rq, bool at_head, - rq_end_io_fn *end_io); +void blk_execute_rq_nowait(struct request *rq, bool at_head); blk_status_t blk_execute_rq(struct request *rq, bool at_head); struct req_iterator { -- cgit v1.2.3 From 47f15561b69e226bfc034e94ff6dbec51a4662af Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 28 May 2022 11:08:48 -0700 Subject: drm: fix EDID struct for old ARM OABI format When building the kernel for arm with the "-mabi=apcs-gnu" option, gcc will force alignment of all structures and unions to a word boundary (see also STRUCTURE_SIZE_BOUNDARY and the "-mstructure-size-boundary=XX" option if you're a gcc person), even when the members of said structures do not want or need said alignment. This completely messes up the structure alignment of 'struct edid' on those targets, because even though all the embedded structures are marked with "__attribute__((packed))", the unions that contain them are not. This was exposed by commit f1e4c916f97f ("drm/edid: add EDID block count and size helpers"), but the bug is pre-existing. That commit just made the structure layout problem cause a build failure due to the addition of the BUILD_BUG_ON(sizeof(*edid) != EDID_LENGTH); sanity check in drivers/gpu/drm/drm_edid.c:edid_block_data(). This legacy union alignment should probably not be used in the first place, but we can fix the layout by adding the packed attribute to the union entries even when each member is already packed and it shouldn't matter in a sane build environment. You can see this issue with a trivial test program: union { struct { char c[5]; }; struct { char d; unsigned e; } __attribute__((packed)); } a = { "1234" }; where building this with a normal "gcc -S" will result in the expected 5-byte size of said union: .type a, @object .size a, 5 but with an ARM compiler and the old ABI: arm-linux-gnu-gcc -mabi=apcs-gnu -mfloat-abi=soft -S t.c you get .type a, %object .size a, 8 instead, because even though each member of the union is packed, the union itself still gets aligned. This was reported by Sudip for the spear3xx_defconfig target. Link: https://lore.kernel.org/lkml/YpCUzStDnSgQLNFN@debian/ Reported-by: Sudip Mukherjee Acked-by: Arnd Bergmann Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: Daniel Vetter Signed-off-by: Linus Torvalds --- include/drm/drm_edid.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index c3204a58fb09..b2756753370b 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -121,7 +121,7 @@ struct detailed_data_monitor_range { u8 supported_scalings; u8 preferred_refresh; } __attribute__((packed)) cvt; - } formula; + } __attribute__((packed)) formula; } __attribute__((packed)); struct detailed_data_wpindex { @@ -154,7 +154,7 @@ struct detailed_non_pixel { struct detailed_data_wpindex color; struct std_timing timings[6]; struct cvt_timing cvt[4]; - } data; + } __attribute__((packed)) data; } __attribute__((packed)); #define EDID_DETAIL_EST_TIMINGS 0xf7 @@ -172,7 +172,7 @@ struct detailed_timing { union { struct detailed_pixel_timing pixel_data; struct detailed_non_pixel other_data; - } data; + } __attribute__((packed)) data; } __attribute__((packed)); #define DRM_EDID_INPUT_SERRATION_VSYNC (1 << 0) -- cgit v1.2.3 From a7c41b4687f5902af70cd559806990930c8a307b Mon Sep 17 00:00:00 2001 From: Xiaoguang Wang Date: Mon, 30 May 2022 21:15:20 +0800 Subject: io_uring: let IORING_OP_FILES_UPDATE support choosing fixed file slots One big issue with the file registration feature is that it needs user space apps to maintain free slot info about io_uring's fixed file table, which really is a burden for development. io_uring now supports choosing free file slot for user space apps by using IORING_FILE_INDEX_ALLOC flag in accept, open, and socket operations, but they need the app to use direct accept or direct open, which not all apps are prepared to use yet. To support apps that still need real fds, make use of the registration feature easier. Let IORING_OP_FILES_UPDATE support choosing fixed file slots, which will store picked fixed files slots in fd array and let cqe return the number of slots allocated. Suggested-by: Hao Xu Signed-off-by: Xiaoguang Wang [axboe: move flag to uapi io_uring header, change goto to break, init] Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 53e7dae92e42..776e0278f9dd 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -47,6 +47,7 @@ struct io_uring_sqe { __u32 unlink_flags; __u32 hardlink_flags; __u32 xattr_flags; + __u32 close_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -258,6 +259,11 @@ enum io_uring_op { */ #define IORING_ACCEPT_MULTISHOT (1U << 0) +/* + * close flags, store in sqe->close_flags + */ +#define IORING_CLOSE_FD_AND_FILE_SLOT (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ -- cgit v1.2.3 From 3e0b8f529c10037ae0b369fc892e524eae5a5485 Mon Sep 17 00:00:00 2001 From: Arun Ajith S Date: Mon, 30 May 2022 10:14:14 +0000 Subject: net/ipv6: Expand and rename accept_unsolicited_na to accept_untracked_na RFC 9131 changes default behaviour of handling RX of NA messages when the corresponding entry is absent in the neighbour cache. The current implementation is limited to accept just unsolicited NAs. However, the RFC is more generic where it also accepts solicited NAs. Both types should result in adding a STALE entry for this case. Expand accept_untracked_na behaviour to also accept solicited NAs to be compliant with the RFC and rename the sysctl knob to accept_untracked_na. Fixes: f9a2fb73318e ("net/ipv6: Introduce accept_unsolicited_na knob to implement router-side changes for RFC9131") Signed-off-by: Arun Ajith S Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20220530101414.65439-1-aajith@arista.com Signed-off-by: Paolo Abeni --- include/linux/ipv6.h | 2 +- include/uapi/linux/ipv6.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 38c8203d52cb..37dfdcfcdd54 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -61,7 +61,7 @@ struct ipv6_devconf { __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; __s32 drop_unsolicited_na; - __s32 accept_unsolicited_na; + __s32 accept_untracked_na; struct ipv6_stable_secret { bool initialized; struct in6_addr secret; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 549ddeaf788b..03cdbe798fe3 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -194,7 +194,7 @@ enum { DEVCONF_IOAM6_ID, DEVCONF_IOAM6_ID_WIDE, DEVCONF_NDISC_EVICT_NOCARRIER, - DEVCONF_ACCEPT_UNSOLICITED_NA, + DEVCONF_ACCEPT_UNTRACKED_NA, DEVCONF_MAX }; -- cgit v1.2.3 From 13b00b135665c92065a27c0c39dd97e0f380bd4f Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 18 May 2022 16:38:00 +0300 Subject: vdpa: Add support for querying vendor statistics Allows to read vendor statistics of a vdpa device. The specific statistics data are received from the upstream driver in the form of an (attribute name, attribute value) pairs. An example of statistics for mlx5_vdpa device are: received_desc - number of descriptors received by the virtqueue completed_desc - number of descriptors completed by the virtqueue A descriptor using indirect buffers is still counted as 1. In addition, N chained descriptors are counted correctly N times as one would expect. A new callback was added to vdpa_config_ops which provides the means for the vdpa driver to return statistics results. The interface allows for reading all the supported virtqueues, including the control virtqueue if it exists. Below are some examples taken from mlx5_vdpa which are introduced in the following patch: 1. Read statistics for the virtqueue at index 1 $ vdpa dev vstats show vdpa-a qidx 1 vdpa-a: queue_type tx queue_index 1 received_desc 3844836 completed_desc 3844836 2. Read statistics for the virtqueue at index 32 $ vdpa dev vstats show vdpa-a qidx 32 vdpa-a: queue_type control_vq queue_index 32 received_desc 62 completed_desc 62 3. Read statisitics for the virtqueue at index 0 with json output $ vdpa -j dev vstats show vdpa-a qidx 0 {"vstats":{"vdpa-a":{ "queue_type":"rx","queue_index":0,"name":"received_desc","value":417776,\ "name":"completed_desc","value":417548}}} 4. Read statistics for the virtqueue at index 0 with preety json output $ vdpa -jp dev vstats show vdpa-a qidx 0 { "vstats": { "vdpa-a": { "queue_type": "rx", "queue_index": 0, "name": "received_desc", "value": 417776, "name": "completed_desc", "value": 417548 } } } Signed-off-by: Eli Cohen Message-Id: <20220518133804.1075129-3-elic@nvidia.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 3 +++ include/uapi/linux/vdpa.h | 6 ++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 8943a209202e..2ae8443331e1 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -276,6 +276,9 @@ struct vdpa_config_ops { const struct vdpa_vq_state *state); int (*get_vq_state)(struct vdpa_device *vdev, u16 idx, struct vdpa_vq_state *state); + int (*get_vendor_vq_stats)(struct vdpa_device *vdev, u16 idx, + struct sk_buff *msg, + struct netlink_ext_ack *extack); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* vq irq is not expected to be changed once DRIVER_OK is set */ diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 1061d8d2d09d..25c55cab3d7c 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -18,6 +18,7 @@ enum vdpa_command { VDPA_CMD_DEV_DEL, VDPA_CMD_DEV_GET, /* can dump */ VDPA_CMD_DEV_CONFIG_GET, /* can dump */ + VDPA_CMD_DEV_VSTATS_GET, }; enum vdpa_attr { @@ -46,6 +47,11 @@ enum vdpa_attr { VDPA_ATTR_DEV_NEGOTIATED_FEATURES, /* u64 */ VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, /* u32 */ VDPA_ATTR_DEV_SUPPORTED_FEATURES, /* u64 */ + + VDPA_ATTR_DEV_QUEUE_INDEX, /* u32 */ + VDPA_ATTR_DEV_VENDOR_ATTR_NAME, /* string */ + VDPA_ATTR_DEV_VENDOR_ATTR_VALUE, /* u64 */ + /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From a6a51adc6e8aafebfe0c4beb80e99694ea562b40 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 18 May 2022 16:38:02 +0300 Subject: net/vdpa: Use readers/writers semaphore instead of cf_mutex Replace cf_mutex with rw_semaphore to reflect the fact that some calls could be called concurrently but can suffice with read lock. Suggested-by: Si-Wei Liu Signed-off-by: Eli Cohen Message-Id: <20220518133804.1075129-5-elic@nvidia.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 2ae8443331e1..2cb14847831e 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -66,7 +66,7 @@ struct vdpa_mgmt_dev; * @dma_dev: the actual device that is performing DMA * @driver_override: driver name to force a match * @config: the configuration ops for this device. - * @cf_mutex: Protects get and set access to configuration layout. + * @cf_lock: Protects get and set access to configuration layout. * @index: device index * @features_valid: were features initialized? for legacy guests * @use_va: indicate whether virtual address must be used by this device @@ -79,7 +79,7 @@ struct vdpa_device { struct device *dma_dev; const char *driver_override; const struct vdpa_config_ops *config; - struct mutex cf_mutex; /* Protects get/set config */ + struct rw_semaphore cf_lock; /* Protects get/set config */ unsigned int index; bool features_valid; bool use_va; @@ -398,10 +398,10 @@ static inline int vdpa_reset(struct vdpa_device *vdev) const struct vdpa_config_ops *ops = vdev->config; int ret; - mutex_lock(&vdev->cf_mutex); + down_write(&vdev->cf_lock); vdev->features_valid = false; ret = ops->reset(vdev); - mutex_unlock(&vdev->cf_mutex); + up_write(&vdev->cf_lock); return ret; } @@ -420,9 +420,9 @@ static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) { int ret; - mutex_lock(&vdev->cf_mutex); + down_write(&vdev->cf_lock); ret = vdpa_set_features_unlocked(vdev, features); - mutex_unlock(&vdev->cf_mutex); + up_write(&vdev->cf_lock); return ret; } -- cgit v1.2.3 From 1892a3d425bf525ac98d6d3534035e6ed2bfab50 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 18 May 2022 16:38:03 +0300 Subject: vdpa/mlx5: Add support for reading descriptor statistics Implement the get_vq_stats calback of vdpa_config_ops to return the statistics for a virtqueue. The statistics are provided as vendor specific statistics where the driver provides a pair of attribute name and attribute value. Currently supported are received descriptors and completed descriptors. Signed-off-by: Eli Cohen Message-Id: <20220518133804.1075129-6-elic@nvidia.com> Signed-off-by: Michael S. Tsirkin --- include/linux/mlx5/mlx5_ifc.h | 1 + include/linux/mlx5/mlx5_ifc_vdpa.h | 39 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 78b3d3465dd7..2a8334bb5f82 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -87,6 +87,7 @@ enum { enum { MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b, MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d, + MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS = 0x001c, MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018, MLX5_OBJ_TYPE_MKEY = 0xff01, MLX5_OBJ_TYPE_QP = 0xff02, diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h index 1a9c9d94cb59..4414ed5b6ed2 100644 --- a/include/linux/mlx5/mlx5_ifc_vdpa.h +++ b/include/linux/mlx5/mlx5_ifc_vdpa.h @@ -165,4 +165,43 @@ struct mlx5_ifc_modify_virtio_net_q_out_bits { struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; }; +struct mlx5_ifc_virtio_q_counters_bits { + u8 modify_field_select[0x40]; + u8 reserved_at_40[0x40]; + u8 received_desc[0x40]; + u8 completed_desc[0x40]; + u8 error_cqes[0x20]; + u8 bad_desc_errors[0x20]; + u8 exceed_max_chain[0x20]; + u8 invalid_buffer[0x20]; + u8 reserved_at_180[0x280]; +}; + +struct mlx5_ifc_create_virtio_q_counters_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_virtio_q_counters_bits virtio_q_counters; +}; + +struct mlx5_ifc_create_virtio_q_counters_out_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_virtio_q_counters_bits virtio_q_counters; +}; + +struct mlx5_ifc_destroy_virtio_q_counters_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; +}; + +struct mlx5_ifc_destroy_virtio_q_counters_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits hdr; +}; + +struct mlx5_ifc_query_virtio_q_counters_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; +}; + +struct mlx5_ifc_query_virtio_q_counters_out_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_virtio_q_counters_bits counters; +}; + #endif /* __MLX5_IFC_VDPA_H_ */ -- cgit v1.2.3 From 175d493c3c3e09a3abaa843068fae0f0ad42c47e Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:41 +0530 Subject: vhost: move the backend feature bits to vhost_types.h We should store feature bits in vhost_types.h as what has been done for e.g VHOST_F_LOG_ALL. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-2-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 5 ----- include/uapi/linux/vhost_types.h | 5 +++++ 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 5d99e7c242a2..8f7b4a95d6f9 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -89,11 +89,6 @@ /* Set or get vhost backend capability */ -/* Use message type V2 */ -#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 -/* IOTLB can accept batching hints */ -#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 - #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index f7f6a3a28977..76ee7016c501 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -153,4 +153,9 @@ struct vhost_vdpa_iova_range { /* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ #define VHOST_NET_F_VIRTIO_NET_HDR 27 +/* Use message type V2 */ +#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 +/* IOTLB can accept batching hints */ +#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 + #endif -- cgit v1.2.3 From d4821902e43453b85b31329441a9f6ac071228a8 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:45 +0530 Subject: vdpa: introduce virtqueue groups This patch introduces virtqueue groups to vDPA device. The virtqueue group is the minimal set of virtqueues that must share an address space. And the address space identifier could only be attached to a specific virtqueue group. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-6-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 2cb14847831e..e4e53574183e 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -85,6 +85,7 @@ struct vdpa_device { bool use_va; u32 nvqs; struct vdpa_mgmt_dev *mdev; + unsigned int ngroups; }; /** @@ -172,6 +173,10 @@ struct vdpa_map_file { * for the device * @vdev: vdpa device * Returns virtqueue algin requirement + * @get_vq_group: Get the group id for a specific virtqueue + * @vdev: vdpa device + * @idx: virtqueue index + * Returns u32: group id for this virtqueue * @get_device_features: Get virtio features supported by the device * @vdev: vdpa device * Returns the virtio features support by the @@ -286,6 +291,7 @@ struct vdpa_config_ops { /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); + u32 (*get_vq_group)(struct vdpa_device *vdev, u16 idx); u64 (*get_device_features)(struct vdpa_device *vdev); int (*set_driver_features)(struct vdpa_device *vdev, u64 features); u64 (*get_driver_features)(struct vdpa_device *vdev); @@ -318,6 +324,7 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, + unsigned int ngroups, size_t size, const char *name, bool use_va); @@ -328,17 +335,18 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, * @member: the name of struct vdpa_device within the @dev_struct * @parent: the parent device * @config: the bus operations that is supported by this device + * @ngroups: the number of virtqueue groups supported by this device * @name: name of the vdpa device * @use_va: indicate whether virtual address must be used by this device * * Return allocated data structure or ERR_PTR upon error */ -#define vdpa_alloc_device(dev_struct, member, parent, config, name, use_va) \ - container_of(__vdpa_alloc_device( \ - parent, config, \ +#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, name, use_va) \ + container_of((__vdpa_alloc_device( \ + parent, config, ngroups, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va), \ + dev_struct, member)), name, use_va)), \ dev_struct, member) int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); -- cgit v1.2.3 From db9adcbf4286ad1c1fca091a870db6e49bb0df07 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:46 +0530 Subject: vdpa: multiple address spaces support This patches introduces the multiple address spaces support for vDPA device. This idea is to identify a specific address space via an dedicated identifier - ASID. During vDPA device allocation, vDPA device driver needs to report the number of address spaces supported by the device then the DMA mapping ops of the vDPA device needs to be extended to support ASID. This helps to isolate the environments for the virtqueue that will not be assigned directly. E.g in the case of virtio-net, the control virtqueue will not be assigned directly to guest. As a start, simply claim 1 virtqueue groups and 1 address spaces for all vDPA devices. And vhost-vDPA will simply reject the device with more than 1 virtqueue groups or address spaces. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-7-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index e4e53574183e..1515748e84ff 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -69,6 +69,8 @@ struct vdpa_mgmt_dev; * @cf_lock: Protects get and set access to configuration layout. * @index: device index * @features_valid: were features initialized? for legacy guests + * @ngroups: the number of virtqueue groups + * @nas: the number of address spaces * @use_va: indicate whether virtual address must be used by this device * @nvqs: maximum number of supported virtqueues * @mdev: management device pointer; caller must setup when registering device as part @@ -86,6 +88,7 @@ struct vdpa_device { u32 nvqs; struct vdpa_mgmt_dev *mdev; unsigned int ngroups; + unsigned int nas; }; /** @@ -241,6 +244,7 @@ struct vdpa_map_file { * Needed for device that using device * specific DMA translation (on-chip IOMMU) * @vdev: vdpa device + * @asid: address space identifier * @iotlb: vhost memory mapping to be * used by the vDPA * Returns integer: success (0) or error (< 0) @@ -249,6 +253,7 @@ struct vdpa_map_file { * specific DMA translation (on-chip IOMMU) * and preferring incremental map. * @vdev: vdpa device + * @asid: address space identifier * @iova: iova to be mapped * @size: size of the area * @pa: physical address for the map @@ -260,6 +265,7 @@ struct vdpa_map_file { * specific DMA translation (on-chip IOMMU) * and preferring incremental unmap. * @vdev: vdpa device + * @asid: address space identifier * @iova: iova to be unmapped * @size: size of the area * Returns integer: success (0) or error (< 0) @@ -313,10 +319,12 @@ struct vdpa_config_ops { struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); /* DMA ops */ - int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb); - int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size, - u64 pa, u32 perm, void *opaque); - int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size); + int (*set_map)(struct vdpa_device *vdev, unsigned int asid, + struct vhost_iotlb *iotlb); + int (*dma_map)(struct vdpa_device *vdev, unsigned int asid, + u64 iova, u64 size, u64 pa, u32 perm, void *opaque); + int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid, + u64 iova, u64 size); /* Free device resources */ void (*free)(struct vdpa_device *vdev); @@ -324,7 +332,7 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - unsigned int ngroups, + unsigned int ngroups, unsigned int nas, size_t size, const char *name, bool use_va); @@ -336,17 +344,19 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, * @parent: the parent device * @config: the bus operations that is supported by this device * @ngroups: the number of virtqueue groups supported by this device + * @nas: the number of address spaces * @name: name of the vdpa device * @use_va: indicate whether virtual address must be used by this device * * Return allocated data structure or ERR_PTR upon error */ -#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, name, use_va) \ +#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, nas, \ + name, use_va) \ container_of((__vdpa_alloc_device( \ - parent, config, ngroups, \ - sizeof(dev_struct) + \ + parent, config, ngroups, nas, \ + (sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va)), \ + dev_struct, member))), name, use_va)), \ dev_struct, member) int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); -- cgit v1.2.3 From 46d554b1bcd19133401d2d5c0728b85e7bfd1358 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:47 +0530 Subject: vdpa: introduce config operations for associating ASID to a virtqueue group This patch introduces a new bus operation to allow the vDPA bus driver to associate an ASID to a virtqueue group. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-8-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 1515748e84ff..f336d253db3d 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -240,6 +240,12 @@ struct vdpa_map_file { * @vdev: vdpa device * Returns the iova range supported by * the device. + * @set_group_asid: Set address space identifier for a + * virtqueue group + * @vdev: vdpa device + * @group: virtqueue group + * @asid: address space id for this group + * Returns integer: success (0) or error (< 0) * @set_map: Set device memory mapping (optional) * Needed for device that using device * specific DMA translation (on-chip IOMMU) @@ -325,6 +331,8 @@ struct vdpa_config_ops { u64 iova, u64 size, u64 pa, u32 perm, void *opaque); int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid, u64 iova, u64 size); + int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group, + unsigned int asid); /* Free device resources */ void (*free)(struct vdpa_device *vdev); -- cgit v1.2.3 From 1cb108994c6830cc6a6e066ad7d9a22ef59fa167 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:48 +0530 Subject: vhost_iotlb: split out IOTLB initialization This patch splits out IOTLB initialization to make sure it could be reused by external modules. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-9-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vhost_iotlb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/vhost_iotlb.h b/include/linux/vhost_iotlb.h index 2d0e2f52f938..e79a40838998 100644 --- a/include/linux/vhost_iotlb.h +++ b/include/linux/vhost_iotlb.h @@ -36,6 +36,8 @@ int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last, u64 addr, unsigned int perm); void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last); +void vhost_iotlb_init(struct vhost_iotlb *iotlb, unsigned int limit, + unsigned int flags); struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags); void vhost_iotlb_free(struct vhost_iotlb *iotlb); void vhost_iotlb_reset(struct vhost_iotlb *iotlb); -- cgit v1.2.3 From 91233ad711866f4e375742d84ef3ed6aab9daa96 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:49 +0530 Subject: vhost: support ASID in IOTLB API This patches allows userspace to send ASID based IOTLB message to vhost. This idea is to use the reserved u32 field in the existing V2 IOTLB message. Vhost device should advertise this capability via VHOST_BACKEND_F_IOTLB_ASID backend feature. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-10-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost_types.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index 76ee7016c501..634cee485abb 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -87,7 +87,7 @@ struct vhost_msg { struct vhost_msg_v2 { __u32 type; - __u32 reserved; + __u32 asid; union { struct vhost_iotlb_msg iotlb; __u8 padding[64]; @@ -157,5 +157,9 @@ struct vhost_vdpa_iova_range { #define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 /* IOTLB can accept batching hints */ #define VHOST_BACKEND_F_IOTLB_BATCH 0x2 +/* IOTLB can accept address space identifier through V2 type of IOTLB + * message + */ +#define VHOST_BACKEND_F_IOTLB_ASID 0x3 #endif -- cgit v1.2.3 From 3ace88bd37436abc84906312146fe5158a469142 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:51 +0530 Subject: vhost-vdpa: introduce uAPI to get the number of virtqueue groups Follows the vDPA support for multiple address spaces, this patch introduce uAPI for the userspace to know the number of virtqueue groups supported by the vDPA device. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-12-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 8f7b4a95d6f9..61317c61d768 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -145,11 +145,13 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) - /* Get the config size */ #define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) /* Get the count of all virtqueues */ #define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) + #endif -- cgit v1.2.3 From a0c95f201170bd559737d3cdc8a950aea62f29c6 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:52 +0530 Subject: vhost-vdpa: introduce uAPI to get the number of address spaces This patch introduces the uAPI for getting the number of address spaces supported by this vDPA device. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-13-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 61317c61d768..51322008901a 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -154,4 +154,6 @@ /* Get the number of virtqueue groups. */ #define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) +/* Get the number of address spaces. */ +#define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int) #endif -- cgit v1.2.3 From 2d1fcb7758e49fd9caf150f3c70804b95b2ce80c Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:53 +0530 Subject: vhost-vdpa: uAPI to get virtqueue group id Follows the support for virtqueue group in vDPA. This patches introduces uAPI to get the virtqueue group ID for a specific virtqueue in vhost-vdpa. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-14-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 51322008901a..668914c87f74 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -156,4 +156,12 @@ /* Get the number of address spaces. */ #define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int) + +/* Get the group for a virtqueue: read index, write group in num, + * The virtqueue index is stored in the index field of + * vhost_vring_state. The group for this specific virtqueue is + * returned via num field of vhost_vring_state. + */ +#define VHOST_VDPA_GET_VRING_GROUP _IOWR(VHOST_VIRTIO, 0x7B, \ + struct vhost_vring_state) #endif -- cgit v1.2.3 From 84d7c8fd3aade2fe79313003ed06ede431ec2a6d Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:54 +0530 Subject: vhost-vdpa: introduce uAPI to set group ASID Follows the vDPA support for associating ASID to a specific virtqueue group. This patch adds a uAPI to support setting them from userspace. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-15-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 668914c87f74..cab645d4a645 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -164,4 +164,11 @@ */ #define VHOST_VDPA_GET_VRING_GROUP _IOWR(VHOST_VIRTIO, 0x7B, \ struct vhost_vring_state) +/* Set the ASID for a virtqueue group. The group index is stored in + * the index field of vhost_vring_state, the ASID associated with this + * group is stored at num field of vhost_vring_state. + */ +#define VHOST_VDPA_SET_GROUP_ASID _IOW(VHOST_VIRTIO, 0x7C, \ + struct vhost_vring_state) + #endif -- cgit v1.2.3 From ffbda8e9df10d1784d5427ec199e7d8308e3763f Mon Sep 17 00:00:00 2001 From: Cindy Lu Date: Fri, 29 Apr 2022 17:10:30 +0800 Subject: vdpa/vp_vdpa : add vdpa tool support in vp_vdpa this patch is to add the support for vdpa tool in vp_vdpa here is the example steps modprobe vp_vdpa modprobe vhost_vdpa echo 0000:00:06.0>/sys/bus/pci/drivers/virtio-pci/unbind echo 1af4 1041 > /sys/bus/pci/drivers/vp-vdpa/new_id vdpa dev add name vdpa1 mgmtdev pci/0000:00:06.0 Signed-off-by: Cindy Lu Message-Id: <20220429091030.547434-1-lulu@redhat.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/vdpa.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index f336d253db3d..15af802d41c4 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -492,7 +492,7 @@ struct vdpa_mgmtdev_ops { struct vdpa_mgmt_dev { struct device *device; const struct vdpa_mgmtdev_ops *ops; - const struct virtio_device_id *id_table; + struct virtio_device_id *id_table; u64 config_attr_mask; struct list_head list; u64 supported_features; -- cgit v1.2.3 From 48b69959a8559db5df78661d9c6d5138c2f20871 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 27 May 2022 14:01:14 +0800 Subject: virtio: introduce config op to synchronize vring callbacks This patch introduces new virtio config op to vring callbacks. Transport specific method is required to make sure the write before this function is visible to the vring_interrupt() that is called after the return of this function. For the transport that doesn't provide synchronize_vqs(), use synchornize_rcu() which synchronize with IRQ implicitly as a fallback. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: "Paul E. McKenney" Cc: Marc Zyngier Cc: Halil Pasic Cc: Cornelia Huck Cc: Vineeth Vijayan Cc: Peter Oberparleiter Cc: linux-s390@vger.kernel.org Reviewed-by: Cornelia Huck Signed-off-by: Jason Wang Message-Id: <20220527060120.20964-4-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo Reviewed-by: Stefano Garzarella --- include/linux/virtio_config.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index b341dd62aa4d..25be018810a7 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -57,6 +57,11 @@ struct virtio_shm_region { * include a NULL entry for vqs unused by driver * Returns 0 on success or error status * @del_vqs: free virtqueues found by find_vqs(). + * @synchronize_cbs: synchronize with the virtqueue callbacks (optional) + * The function guarantees that all memory operations on the + * queue before it are visible to the vring_interrupt() that is + * called after it. + * vdev: the virtio_device * @get_features: get the array of feature bits for this device. * vdev: the virtio_device * Returns the first 64 feature bits (all we currently need). @@ -89,6 +94,7 @@ struct virtio_config_ops { const char * const names[], const bool *ctx, struct irq_affinity *desc); void (*del_vqs)(struct virtio_device *); + void (*synchronize_cbs)(struct virtio_device *); u64 (*get_features)(struct virtio_device *vdev); int (*finalize_features)(struct virtio_device *vdev); const char *(*bus_name)(struct virtio_device *vdev); @@ -217,6 +223,25 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, desc); } +/** + * virtio_synchronize_cbs - synchronize with virtqueue callbacks + * @vdev: the device + */ +static inline +void virtio_synchronize_cbs(struct virtio_device *dev) +{ + if (dev->config->synchronize_cbs) { + dev->config->synchronize_cbs(dev); + } else { + /* + * A best effort fallback to synchronize with + * interrupts, preemption and softirq disabled + * regions. See comment above synchronize_rcu(). + */ + synchronize_rcu(); + } +} + /** * virtio_device_ready - enable vq use in probe function * @vdev: the device -- cgit v1.2.3 From be83f04d2529e8dc4273efdd1ccf7b7502741071 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 27 May 2022 14:01:18 +0800 Subject: virtio: allow to unbreak virtqueue This patch allows the new introduced __virtio_break_device() to unbreak the virtqueue. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: "Paul E. McKenney" Cc: Marc Zyngier Cc: Halil Pasic Cc: Cornelia Huck Cc: Vineeth Vijayan Cc: Peter Oberparleiter Cc: linux-s390@vger.kernel.org Signed-off-by: Jason Wang Message-Id: <20220527060120.20964-8-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo --- include/linux/virtio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 5464f398912a..d8fdf170637c 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -131,6 +131,7 @@ void unregister_virtio_device(struct virtio_device *dev); bool is_virtio_device(struct device *dev); void virtio_break_device(struct virtio_device *dev); +void __virtio_unbreak_device(struct virtio_device *dev); void virtio_config_changed(struct virtio_device *dev); #ifdef CONFIG_PM_SLEEP -- cgit v1.2.3 From 8b4ec69d7e098a7ddf832e1e7840de53ed474c77 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 27 May 2022 14:01:19 +0800 Subject: virtio: harden vring IRQ This is a rework on the previous IRQ hardening that is done for virtio-pci where several drawbacks were found and were reverted: 1) try to use IRQF_NO_AUTOEN which is not friendly to affinity managed IRQ that is used by some device such as virtio-blk 2) done only for PCI transport The vq->broken is re-used in this patch for implementing the IRQ hardening. The vq->broken is set to true during both initialization and reset. And the vq->broken is set to false in virtio_device_ready(). Then vring_interrupt() can check and return when vq->broken is true. And in this case, switch to return IRQ_NONE to let the interrupt core aware of such invalid interrupt to prevent IRQ storm. The reason of using a per queue variable instead of a per device one is that we may need it for per queue reset hardening in the future. Note that the hardening is only done for vring interrupt since the config interrupt hardening is already done in commit 22b7050a024d7 ("virtio: defer config changed notifications"). But the method that is used by config interrupt can't be reused by the vring interrupt handler because it uses spinlock to do the synchronization which is expensive. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: "Paul E. McKenney" Cc: Marc Zyngier Cc: Halil Pasic Cc: Cornelia Huck Cc: Vineeth Vijayan Cc: Peter Oberparleiter Cc: linux-s390@vger.kernel.org Signed-off-by: Jason Wang Message-Id: <20220527060120.20964-9-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo --- include/linux/virtio_config.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 25be018810a7..d4edfd7d91bb 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -256,6 +256,26 @@ void virtio_device_ready(struct virtio_device *dev) unsigned status = dev->config->get_status(dev); BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); + + /* + * The virtio_synchronize_cbs() makes sure vring_interrupt() + * will see the driver specific setup if it sees vq->broken + * as false (even if the notifications come before DRIVER_OK). + */ + virtio_synchronize_cbs(dev); + __virtio_unbreak_device(dev); + /* + * The transport should ensure the visibility of vq->broken + * before setting DRIVER_OK. See the comments for the transport + * specific set_status() method. + * + * A well behaved device will only notify a virtqueue after + * DRIVER_OK, this means the device should "see" the coherenct + * memory write that set vq->broken as false which is done by + * the driver when it sees DRIVER_OK, then the following + * driver's vring_interrupt() will see vq->broken as false so + * we won't lose any notification. + */ dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK); } -- cgit v1.2.3 From 619e9e14ba3c97a80776c0b5a68a01caa41dd148 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 27 May 2022 14:01:20 +0800 Subject: virtio: use WARN_ON() to warning illegal status value We used to use BUG_ON() in virtio_device_ready() to detect illegal status value, this seems sub-optimal since the value is under the control of the device. Switch to use WARN_ON() instead. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: "Paul E. McKenney" Cc: Marc Zyngier Cc: Halil Pasic Cc: Cornelia Huck Cc: Vineeth Vijayan Cc: Peter Oberparleiter Cc: linux-s390@vger.kernel.org Signed-off-by: Jason Wang Message-Id: <20220527060120.20964-10-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo --- include/linux/virtio_config.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index d4edfd7d91bb..9a36051ceb76 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -255,7 +255,7 @@ void virtio_device_ready(struct virtio_device *dev) { unsigned status = dev->config->get_status(dev); - BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); + WARN_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); /* * The virtio_synchronize_cbs() makes sure vring_interrupt() -- cgit v1.2.3 From 3fc2a9e89b3508a5cc0c324f26d7b4740ba8c456 Mon Sep 17 00:00:00 2001 From: Changcheng Liu Date: Tue, 26 Apr 2022 21:28:14 +0800 Subject: net/mlx5: correct ECE offset in query qp output ECE field should be after opt_param_mask in query qp output. Fixes: 6b646a7e4af6 ("net/mlx5: Add ability to read and write ECE options") Signed-off-by: Changcheng Liu Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 78b3d3465dd7..2cd7d611e7b3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5176,12 +5176,11 @@ struct mlx5_ifc_query_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x20]; - u8 ece[0x20]; + u8 reserved_at_40[0x40]; u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; -- cgit v1.2.3 From c3ed222745d9ad7b69299b349a64ba533c64a34f Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Sat, 14 May 2022 07:05:13 -0400 Subject: NFSv4: Fix free of uninitialized nfs4_label on referral lookup. Send along the already-allocated fattr along with nfs4_fs_locations, and drop the memcpy of fattr. We end up growing two more allocations, but this fixes up a crash as: PID: 790 TASK: ffff88811b43c000 CPU: 0 COMMAND: "ls" #0 [ffffc90000857920] panic at ffffffff81b9bfde #1 [ffffc900008579c0] do_trap at ffffffff81023a9b #2 [ffffc90000857a10] do_error_trap at ffffffff81023b78 #3 [ffffc90000857a58] exc_stack_segment at ffffffff81be1f45 #4 [ffffc90000857a80] asm_exc_stack_segment at ffffffff81c009de #5 [ffffc90000857b08] nfs_lookup at ffffffffa0302322 [nfs] #6 [ffffc90000857b70] __lookup_slow at ffffffff813a4a5f #7 [ffffc90000857c60] walk_component at ffffffff813a86c4 #8 [ffffc90000857cb8] path_lookupat at ffffffff813a9553 #9 [ffffc90000857cf0] filename_lookup at ffffffff813ab86b Suggested-by: Trond Myklebust Fixes: 9558a007dbc3 ("NFS: Remove the label from the nfs4_lookup_res struct") Signed-off-by: Benjamin Coddington Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 4a8ba84f848e..0e3aa0f5f324 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1222,7 +1222,7 @@ struct nfs4_fs_location { #define NFS4_FS_LOCATIONS_MAXENTRIES 10 struct nfs4_fs_locations { - struct nfs_fattr fattr; + struct nfs_fattr *fattr; const struct nfs_server *server; struct nfs4_pathname fs_path; int nlocations; -- cgit v1.2.3 From 118f09eda21d392e1eeb9f8a4bee044958cccf20 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 25 May 2022 12:12:59 -0400 Subject: NFSv4.1 mark qualified async operations as MOVEABLE tasks Mark async operations such as RENAME, REMOVE, COMMIT MOVEABLE for the nfsv4.1+ sessions. Fixes: 85e39feead948 ("NFSv4.1 identify and mark RPC tasks that can move between transports") Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 157d2bd6b241..ea2f7e6b1b0b 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -287,4 +287,5 @@ struct nfs_server { #define NFS_CAP_XATTR (1U << 28) #define NFS_CAP_READ_PLUS (1U << 29) #define NFS_CAP_FS_LOCATIONS (1U << 30) +#define NFS_CAP_MOVEABLE (1U << 31) #endif -- cgit v1.2.3 From 2e8728c955ce0624b958eee6e030a37aca3a5d86 Mon Sep 17 00:00:00 2001 From: Guoju Fang Date: Sat, 28 May 2022 18:16:28 +0800 Subject: net: sched: add barrier to fix packet stuck problem for lockless qdisc In qdisc_run_end(), the spin_unlock() only has store-release semantic, which guarantees all earlier memory access are visible before it. But the subsequent test_bit() has no barrier semantics so may be reordered ahead of the spin_unlock(). The store-load reordering may cause a packet stuck problem. The concurrent operations can be described as below, CPU 0 | CPU 1 qdisc_run_end() | qdisc_run_begin() . | . ----> /* may be reorderd here */ | . | . | . | spin_unlock() | set_bit() | . | smp_mb__after_atomic() ---- test_bit() | spin_trylock() . | . Consider the following sequence of events: CPU 0 reorder test_bit() ahead and see MISSED = 0 CPU 1 calls set_bit() CPU 1 calls spin_trylock() and return fail CPU 0 executes spin_unlock() At the end of the sequence, CPU 0 calls spin_unlock() and does nothing because it see MISSED = 0. The skb on CPU 1 has beed enqueued but no one take it, until the next cpu pushing to the qdisc (if ever ...) will notice and dequeue it. This patch fix this by adding one explicit barrier. As spin_unlock() and test_bit() ordering is a store-load ordering, a full memory barrier smp_mb() is needed here. Fixes: a90c57f2cedd ("net: sched: fix packet stuck problem for lockless qdisc") Signed-off-by: Guoju Fang Link: https://lore.kernel.org/r/20220528101628.120193-1-gjfang@linux.alibaba.com Signed-off-by: Jakub Kicinski --- include/net/sch_generic.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 80973ce820f3..d6cf5116b5f9 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -209,6 +209,12 @@ static inline void qdisc_run_end(struct Qdisc *qdisc) if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); + /* spin_unlock() only has store-release semantic. The unlock + * and test_bit() ordering is a store-load ordering, so a full + * memory barrier is needed here. + */ + smp_mb(); + if (unlikely(test_bit(__QDISC_STATE_MISSED, &qdisc->state))) __netif_schedule(qdisc); -- cgit v1.2.3 From 41925b105e345ebc84cedb64f59d20cb14a62613 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 30 May 2022 10:26:34 +0200 Subject: xen: replace xen_remap() with memremap() xen_remap() is used to establish mappings for frames not under direct control of the kernel: for Xenstore and console ring pages, and for grant pages of non-PV guests. Today xen_remap() is defined to use ioremap() on x86 (doing uncached mappings), and ioremap_cache() on Arm (doing cached mappings). Uncached mappings for those use cases are bad for performance, so they should be avoided if possible. As all use cases of xen_remap() don't require uncached mappings (the mapped area is always physical RAM), a mapping using the standard WB cache mode is fine. As sparse is flagging some of the xen_remap() use cases to be not appropriate for iomem(), as the result is not annotated with the __iomem modifier, eliminate xen_remap() completely and replace all use cases with memremap() specifying the MEMREMAP_WB caching mode. xen_unmap() can be replaced with memunmap(). Reported-by: kernel test robot Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Acked-by: Stefano Stabellini Link: https://lore.kernel.org/r/20220530082634.6339-1-jgross@suse.com Signed-off-by: Juergen Gross --- include/xen/arm/page.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h index ac1b65470563..f831cfeca000 100644 --- a/include/xen/arm/page.h +++ b/include/xen/arm/page.h @@ -109,9 +109,6 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) return __set_phys_to_machine(pfn, mfn); } -#define xen_remap(cookie, size) ioremap_cache((cookie), (size)) -#define xen_unmap(cookie) iounmap((cookie)) - bool xen_arch_need_swiotlb(struct device *dev, phys_addr_t phys, dma_addr_t dev_addr); -- cgit v1.2.3 From c4caa500ffebf64795d1c0f6f9d6f179b502c6b7 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 31 May 2022 14:37:27 +0800 Subject: bonding: guard ns_targets by CONFIG_IPV6 Guard ns_targets in struct bond_params by CONFIG_IPV6, which could save 256 bytes if IPv6 not configed. Also add this protection for function bond_is_ip6_target_ok() and bond_get_targets_ip6(). Remove the IS_ENABLED() check for bond_opts[] as this will make BOND_OPT_NS_TARGETS uninitialized if CONFIG_IPV6 not enabled. Add a dummy bond_option_ns_ip6_targets_set() for this situation. Fixes: 4e24be018eb9 ("bonding: add new parameter ns_targets") Signed-off-by: Hangbin Liu Acked-by: Jonathan Toppins Link: https://lore.kernel.org/r/20220531063727.224043-1-liuhangbin@gmail.com Signed-off-by: Paolo Abeni --- include/net/bonding.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/bonding.h b/include/net/bonding.h index b14f4c0b4e9e..cb904d356e31 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -149,7 +149,9 @@ struct bond_params { struct reciprocal_value reciprocal_packets_per_slave; u16 ad_actor_sys_prio; u16 ad_user_port_key; +#if IS_ENABLED(CONFIG_IPV6) struct in6_addr ns_targets[BOND_MAX_NS_TARGETS]; +#endif /* 2 bytes of padding : see ether_addr_equal_64bits() */ u8 ad_actor_system[ETH_ALEN + 2]; @@ -503,12 +505,14 @@ static inline int bond_is_ip_target_ok(__be32 addr) return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); } +#if IS_ENABLED(CONFIG_IPV6) static inline int bond_is_ip6_target_ok(struct in6_addr *addr) { return !ipv6_addr_any(addr) && !ipv6_addr_loopback(addr) && !ipv6_addr_is_multicast(addr); } +#endif /* Get the oldest arp which we've received on this slave for bond's * arp_targets. @@ -746,6 +750,7 @@ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) return -1; } +#if IS_ENABLED(CONFIG_IPV6) static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip) { int i; @@ -758,6 +763,7 @@ static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr return -1; } +#endif /* exported from bond_main.c */ extern unsigned int bond_net_id; -- cgit v1.2.3 From 597b89d30b42dcc8e6b262e6876b42dde66f97f0 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Mon, 16 May 2022 11:52:51 +0300 Subject: gpu: host1x: Add context bus The context bus is a "dummy" bus that contains struct devices that correspond to IOMMU contexts assigned through Host1x to processes. Even when host1x itself is built as a module, the bus is registered in built-in code so that the built-in ARM SMMU driver is able to reference it. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- include/linux/host1x_context_bus.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/host1x_context_bus.h (limited to 'include') diff --git a/include/linux/host1x_context_bus.h b/include/linux/host1x_context_bus.h new file mode 100644 index 000000000000..72462737a6db --- /dev/null +++ b/include/linux/host1x_context_bus.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2021, NVIDIA Corporation. All rights reserved. + */ + +#ifndef __LINUX_HOST1X_CONTEXT_BUS_H +#define __LINUX_HOST1X_CONTEXT_BUS_H + +#include + +#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS +extern struct bus_type host1x_context_device_bus_type; +#endif + +#endif -- cgit v1.2.3 From 662ce1dc9caf493c309200edbe38d186f1ea20d0 Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Wed, 1 Jun 2022 15:55:25 -0700 Subject: delayacct: track delays from write-protect copy Delay accounting does not track the delay of write-protect copy. When tasks trigger many write-protect copys(include COW and unsharing of anonymous pages[1]), it may spend a amount of time waiting for them. To get the delay of tasks in write-protect copy, could help users to evaluate the impact of using KSM or fork() or GUP. Also update tools/accounting/getdelays.c: / # ./getdelays -dl -p 231 print delayacct stats ON listen forever PID 231 CPU count real total virtual total delay total delay average 6247 1859000000 2154070021 1674255063 0.268ms IO count delay total delay average 0 0 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 0 0 0ms COMPACT count delay total delay average 3 72758 0ms WPCOPY count delay total delay average 3635 271567604 0ms [1] commit 31cc5bc4af70("mm: support GUP-triggered unsharing of anonymous pages") Link: https://lkml.kernel.org/r/20220409014342.2505532-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Reviewed-by: David Hildenbrand Reviewed-by: Jiang Xuexin Reviewed-by: Ran Xiaokai Reviewed-by: wangyong Cc: Jonathan Corbet Cc: Balbir Singh Cc: Mike Kravetz Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- include/linux/delayacct.h | 28 ++++++++++++++++++++++++++++ include/uapi/linux/taskstats.h | 6 +++++- 2 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 6b16a6930a19..58aea2d7385c 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -45,9 +45,13 @@ struct task_delay_info { u64 compact_start; u64 compact_delay; /* wait for memory compact */ + u64 wpcopy_start; + u64 wpcopy_delay; /* wait for write-protect copy */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ u32 compact_count; /* total count of memory compact */ + u32 wpcopy_count; /* total count of write-protect copy */ }; #endif @@ -75,6 +79,8 @@ extern void __delayacct_swapin_start(void); extern void __delayacct_swapin_end(void); extern void __delayacct_compact_start(void); extern void __delayacct_compact_end(void); +extern void __delayacct_wpcopy_start(void); +extern void __delayacct_wpcopy_end(void); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -191,6 +197,24 @@ static inline void delayacct_compact_end(void) __delayacct_compact_end(); } +static inline void delayacct_wpcopy_start(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_wpcopy_start(); +} + +static inline void delayacct_wpcopy_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_wpcopy_end(); +} + #else static inline void delayacct_init(void) {} @@ -225,6 +249,10 @@ static inline void delayacct_compact_start(void) {} static inline void delayacct_compact_end(void) {} +static inline void delayacct_wpcopy_start(void) +{} +static inline void delayacct_wpcopy_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 736154171489..a7f5b11a8f1b 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 12 +#define TASKSTATS_VERSION 13 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -194,6 +194,10 @@ struct taskstats { __u64 ac_exe_dev; /* program binary device ID */ __u64 ac_exe_inode; /* program binary inode number */ /* v12 end */ + + /* v13: Delay waiting for write-protect copy */ + __u64 wpcopy_count; + __u64 wpcopy_delay_total; }; -- cgit v1.2.3 From 8d3398ba2a0d1e25690f830192b7834acab003ec Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 31 May 2022 11:43:45 +0200 Subject: socket: Don't use u8 type in uapi socket.h Use plain 255 instead, which also avoid introducing an additional header dependency on Fixes: 26859240e4ee ("txhash: Add socket option to control TX hash rethink behavior") Signed-off-by: Tobias Klauser Link: https://lore.kernel.org/r/20220531094345.13801-1-tklauser@distanz.ch Signed-off-by: Jakub Kicinski --- include/uapi/linux/socket.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index 51d6bb2f6765..d3fcd3b5ec53 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -31,7 +31,7 @@ struct __kernel_sockaddr_storage { #define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK) -#define SOCK_TXREHASH_DEFAULT ((u8)-1) +#define SOCK_TXREHASH_DEFAULT 255 #define SOCK_TXREHASH_DISABLED 0 #define SOCK_TXREHASH_ENABLED 1 -- cgit v1.2.3 From b6d9014a3335194590abdd2a2471ef5147a67645 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 30 May 2022 18:40:06 +0200 Subject: netfilter: nf_tables: delete flowtable hooks via transaction list Remove inactive bool field in nft_hook object that was introduced in abadb2f865d7 ("netfilter: nf_tables: delete devices from flowtable"). Move stale flowtable hooks to transaction list instead. Deleting twice the same device does not result in ENOENT. Fixes: abadb2f865d7 ("netfilter: nf_tables: delete devices from flowtable") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 20af9d3557b9..279ae0fff7ad 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1090,7 +1090,6 @@ struct nft_stats { struct nft_hook { struct list_head list; - bool inactive; struct nf_hook_ops ops; struct rcu_head rcu; }; -- cgit v1.2.3 From 7d8a3a477b3e25ada8dc71d22048c2ea417209a0 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Mon, 30 May 2022 23:21:58 +0800 Subject: ax25: Fix ax25 session cleanup problems There are session cleanup problems in ax25_release() and ax25_disconnect(). If we setup a session and then disconnect, the disconnected session is still in "LISTENING" state that is shown below. Active AX.25 sockets Dest Source Device State Vr/Vs Send-Q Recv-Q DL9SAU-4 DL9SAU-3 ??? LISTENING 000/000 0 0 DL9SAU-3 DL9SAU-4 ??? LISTENING 000/000 0 0 The first reason is caused by del_timer_sync() in ax25_release(). The timers of ax25 are used for correct session cleanup. If we use ax25_release() to close ax25 sessions and ax25_dev is not null, the del_timer_sync() functions in ax25_release() will execute. As a result, the sessions could not be cleaned up correctly, because the timers have stopped. In order to solve this problem, this patch adds a device_up flag in ax25_dev in order to judge whether the device is up. If there are sessions to be cleaned up, the del_timer_sync() in ax25_release() will not execute. What's more, we add ax25_cb_del() in ax25_kill_by_device(), because the timers have been stopped and there are no functions that could delete ax25_cb if we do not call ax25_release(). Finally, we reorder the position of ax25_list_lock in ax25_cb_del() in order to synchronize among different functions that call ax25_cb_del(). The second reason is caused by improper check in ax25_disconnect(). The incoming ax25 sessions which ax25->sk is null will close heartbeat timer, because the check "if(!ax25->sk || ..)" is satisfied. As a result, the session could not be cleaned up properly. In order to solve this problem, this patch changes the improper check to "if(ax25->sk && ..)" in ax25_disconnect(). What`s more, the ax25_disconnect() may be called twice, which is not necessary. For example, ax25_kill_by_device() calls ax25_disconnect() and sets ax25->state to AX25_STATE_0, but ax25_release() calls ax25_disconnect() again. In order to solve this problem, this patch add a check in ax25_release(). If the flag of ax25->sk equals to SOCK_DEAD, the ax25_disconnect() in ax25_release() should not be executed. Fixes: 82e31755e55f ("ax25: Fix UAF bugs in ax25 timers") Fixes: 8a367e74c012 ("ax25: Fix segfault after sock connection timeout") Reported-and-tested-by: Thomas Osterried Signed-off-by: Duoming Zhou Link: https://lore.kernel.org/r/20220530152158.108619-1-duoming@zju.edu.cn Signed-off-by: Paolo Abeni --- include/net/ax25.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ax25.h b/include/net/ax25.h index 0f9790c455bb..a427a05672e2 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -228,6 +228,7 @@ typedef struct ax25_dev { ax25_dama_info dama; #endif refcount_t refcount; + bool device_up; } ax25_dev; typedef struct ax25_cb { -- cgit v1.2.3 From 8cc5b032240ae5220b62c689c20459d3e1825b2d Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Wed, 1 Jun 2022 01:00:17 +0000 Subject: binder: fix sender_euid type in uapi header The {pid,uid}_t fields of struct binder_transaction were recently replaced to use kernel types in commit 169adc2b6b3c ("android/binder.h: add linux/android/binder(fs).h to UAPI compile-test coverage"). However, using __kernel_uid_t here breaks backwards compatibility in architectures using 16-bits for this type, since glibc and some others still expect a 32-bit uid_t. Instead, let's use __kernel_uid32_t which avoids this compatibility problem. Fixes: 169adc2b6b3c ("android/binder.h: add linux/android/binder(fs).h to UAPI compile-test coverage") Reported-by: Christopher Ferris Signed-off-by: Carlos Llamas Acked-by: Todd Kjos Signed-off-by: Arnd Bergmann --- include/uapi/linux/android/binder.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 11157fae8a8e..688bcdaeed53 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -289,7 +289,7 @@ struct binder_transaction_data { /* General information about the transaction. */ __u32 flags; __kernel_pid_t sender_pid; - __kernel_uid_t sender_euid; + __kernel_uid32_t sender_euid; binder_size_t data_size; /* number of bytes of data */ binder_size_t offsets_size; /* number of bytes of offsets */ -- cgit v1.2.3 From 22296a5c0cd35aaf62e1af3266f82cdf6b0b9b78 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 2 Jun 2022 09:18:58 -0700 Subject: net: add debug info to __skb_pull() While analyzing yet another syzbot report, I found the following patch very useful. It allows to better understand what went wrong. This debug info is only enabled if CONFIG_DEBUG_NET=y, which is the case for syzbot builds. Signed-off-by: Eric Dumazet Acked-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index da96f0d3e753..d3d10556f0fa 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2696,7 +2696,14 @@ void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { skb->len -= len; - BUG_ON(skb->len < skb->data_len); + if (unlikely(skb->len < skb->data_len)) { +#if defined(CONFIG_DEBUG_NET) + skb->len += len; + pr_err("__skb_pull(len=%u)\n", len); + skb_dump(KERN_ERR, skb, false); +#endif + BUG(); + } return skb->data += len; } -- cgit v1.2.3 From 08145b087e4481458f6075f3af58021a3cf8a940 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 31 May 2022 18:04:10 +0800 Subject: LoongArch: Add ELF-related definitions Add ELF-related definitions for LoongArch, including: EM_LOONGARCH, KEXEC_ARCH_LOONGARCH, AUDIT_ARCH_LOONGARCH32, AUDIT_ARCH_LOONGARCH64 and NT_LOONGARCH_*. Reviewed-by: WANG Xuerui Reviewed-by: Jiaxun Yang Signed-off-by: Huacai Chen --- include/uapi/linux/audit.h | 2 ++ include/uapi/linux/elf-em.h | 1 + include/uapi/linux/elf.h | 5 +++++ include/uapi/linux/kexec.h | 1 + 4 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 8eda133ca4c1..7c1dc818b1d5 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -439,6 +439,8 @@ enum { #define AUDIT_ARCH_UNICORE (EM_UNICORE|__AUDIT_ARCH_LE) #define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) #define AUDIT_ARCH_XTENSA (EM_XTENSA) +#define AUDIT_ARCH_LOONGARCH32 (EM_LOONGARCH|__AUDIT_ARCH_LE) +#define AUDIT_ARCH_LOONGARCH64 (EM_LOONGARCH|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) #define AUDIT_PERM_EXEC 1 #define AUDIT_PERM_WRITE 2 diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h index f47e853546fa..ef38c2bc5ab7 100644 --- a/include/uapi/linux/elf-em.h +++ b/include/uapi/linux/elf-em.h @@ -51,6 +51,7 @@ #define EM_RISCV 243 /* RISC-V */ #define EM_BPF 247 /* Linux BPF - in-kernel virtual machine */ #define EM_CSKY 252 /* C-SKY */ +#define EM_LOONGARCH 258 /* LoongArch */ #define EM_FRV 0x5441 /* Fujitsu FR-V */ /* diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index c4abd09c3da9..2b9f5e9985e5 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -438,6 +438,11 @@ typedef struct elf64_shdr { #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ #define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */ #define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */ +#define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ +#define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */ +#define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */ +#define NT_LOONGARCH_LASX 0xa03 /* LoongArch Loongson Advanced SIMD Extension registers */ +#define NT_LOONGARCH_LBT 0xa04 /* LoongArch Loongson Binary Translation registers */ /* Note types with note name "GNU" */ #define NT_GNU_PROPERTY_TYPE_0 5 diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index fb7e2ef60825..981016e05cfa 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -43,6 +43,7 @@ #define KEXEC_ARCH_MIPS ( 8 << 16) #define KEXEC_ARCH_AARCH64 (183 << 16) #define KEXEC_ARCH_RISCV (243 << 16) +#define KEXEC_ARCH_LOONGARCH (258 << 16) /* The artificial cap on the number of segments passed to kexec_load. */ #define KEXEC_SEGMENT_MAX 16 -- cgit v1.2.3 From 439057ec3b748b1ff61855d09859f369493e22d8 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 31 May 2022 18:04:10 +0800 Subject: LoongArch: Add writecombine support for drm LoongArch maintains cache coherency in hardware, but its WUC attribute (Weak-ordered UnCached, which is similar to WC) is out of the scope of cache coherency machanism. This means WUC can only used for write-only memory regions. Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Reviewed-by: WANG Xuerui Reviewed-by: Jiaxun Yang Signed-off-by: Huacai Chen --- include/drm/drm_cache.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h index 22deb216b59c..08e0e3ffad13 100644 --- a/include/drm/drm_cache.h +++ b/include/drm/drm_cache.h @@ -67,6 +67,14 @@ static inline bool drm_arch_can_wc_memory(void) * optimization entirely for ARM and arm64. */ return false; +#elif defined(CONFIG_LOONGARCH) + /* + * LoongArch maintains cache coherency in hardware, but its WUC attribute + * (Weak-ordered UnCached, which is similar to WC) is out of the scope of + * cache coherency machanism. This means WUC can only used for write-only + * memory regions. + */ + return false; #else return true; #endif -- cgit v1.2.3 From 46859ac8af52ae599e1b51992ddef3eb43f295fc Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 31 May 2022 18:04:12 +0800 Subject: LoongArch: Add multi-processor (SMP) support LoongArch-based procesors have 4, 8 or 16 cores per package. This patch adds multi-processor (SMP) support for LoongArch. Reviewed-by: WANG Xuerui Reviewed-by: Jiaxun Yang Signed-off-by: Huacai Chen --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index b66c5f389159..19f0dbfdd7fe 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -130,6 +130,7 @@ enum cpuhp_state { CPUHP_ZCOMP_PREPARE, CPUHP_TIMERS_PREPARE, CPUHP_MIPS_SOC_PREPARE, + CPUHP_LOONGARCH_SOC_PREPARE, CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, CPUHP_BRINGUP_CPU, -- cgit v1.2.3 From 6d7131bd52b3e0dd068a0067e5584b3f36cf17eb Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 11 Apr 2022 17:05:55 +0200 Subject: include/linux/find: Fix documentation The order of the arguments in function documentation doesn't fit the implementation. Change the documentation so that it corresponds to the code. This prevent people to get confused when reading the documentation. Signed-off-by: Anna-Maria Behnsen Reviewed-by: Andy Shevchenko Signed-off-by: Yury Norov --- include/linux/find.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/find.h b/include/linux/find.h index 5bb6db213bcb..424ef67d4a42 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -21,8 +21,8 @@ extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long siz /** * find_next_bit - find the next set bit in a memory region * @addr: The address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. @@ -50,8 +50,8 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, * find_next_and_bit - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. @@ -79,8 +79,8 @@ unsigned long find_next_and_bit(const unsigned long *addr1, /** * find_next_zero_bit - find the next cleared bit in a memory region * @addr: The address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number of the next zero bit * If no bits are zero, returns @size. -- cgit v1.2.3 From e041e0ac53dd52d2d201aa87edc3adaca1085299 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 28 Apr 2022 13:51:12 -0700 Subject: lib/bitmap: extend comment for bitmap_(from,to)_arr32() On LE systems bitmaps are naturally ordered, therefore we can potentially use bitmap_copy routines when converting from 32-bit arrays, even if host system is 64-bit. But it may lead to out-of-bond access due to unsafe typecast, and the bitmap_(from,to)_arr32 comment doesn't explain that clearly CC: Alexander Gordeev CC: Andy Shevchenko CC: Christian Borntraeger CC: Claudio Imbrenda CC: David Hildenbrand CC: Heiko Carstens CC: Janosch Frank CC: Rasmus Villemoes CC: Sven Schnelle CC: Vasily Gorbik Signed-off-by: Yury Norov --- include/linux/bitmap.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 7dba0847510c..afcf7b8dddd1 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -264,8 +264,12 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, } /* - * On 32-bit systems bitmaps are represented as u32 arrays internally, and - * therefore conversion is not needed when copying data from/to arrays of u32. + * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 + * machines the order of hi and lo parts of numbers match the bitmap structure. + * In both cases conversion is not needed when copying data from/to arrays of + * u32. But in LE64 case, typecast in bitmap_copy_clear_tail() may lead + * to out-of-bound access. To avoid that, both LE and BE variants of 64-bit + * architectures are not using bitmap_copy_clear_tail(). */ #if BITS_PER_LONG == 64 void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, -- cgit v1.2.3 From 0a97953fd2210d0ac8eb5c76f8bd08fb53b6d3d6 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 28 Apr 2022 13:51:13 -0700 Subject: lib: add bitmap_{from,to}_arr64 Manipulating 64-bit arrays with bitmap functions is potentially dangerous because on 32-bit BE machines the order of halfwords doesn't match. Another issue is that compiler may throw a warning about out-of-boundary access. This patch adds bitmap_{from,to}_arr64 functions in addition to existing bitmap_{from,to}_arr32. CC: Alexander Gordeev CC: Andy Shevchenko CC: Christian Borntraeger CC: Claudio Imbrenda CC: David Hildenbrand CC: Heiko Carstens CC: Janosch Frank CC: Rasmus Villemoes CC: Sven Schnelle CC: Vasily Gorbik Signed-off-by: Yury Norov --- include/linux/bitmap.h | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index afcf7b8dddd1..71147b7d721b 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -72,6 +72,8 @@ struct device; * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region * bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst * bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst + * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst + * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start * @@ -285,6 +287,22 @@ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, (const unsigned long *) (bitmap), (nbits)) #endif +/* + * On 64-bit systems bitmaps are represented as u64 arrays internally. On LE32 + * machines the order of hi and lo parts of numbers match the bitmap structure. + * In both cases conversion is not needed when copying data from/to arrays of + * u64. + */ +#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN) +void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits); +void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits); +#else +#define bitmap_from_arr64(bitmap, buf, nbits) \ + bitmap_copy_clear_tail((unsigned long *)(bitmap), (const unsigned long *)(buf), (nbits)) +#define bitmap_to_arr64(buf, bitmap, nbits) \ + bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits)) +#endif + static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { @@ -518,10 +536,7 @@ static inline void bitmap_next_set_region(unsigned long *bitmap, */ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) { - dst[0] = mask & ULONG_MAX; - - if (sizeof(mask) > sizeof(unsigned long)) - dst[1] = mask >> 32; + bitmap_from_arr64(dst, &mask, 64); } /** -- cgit v1.2.3 From 005f17007f47495dbbb659aa5db7e581065d16e7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 18 May 2022 13:52:22 -0700 Subject: bitmap: Fix return values to be unsigned Both nodemask and bitmap routines had mixed return values that provided potentially signed return values that could never happen. This was leading to the compiler getting confusing about the range of possible return values (it was thinking things could be negative where they could not be). In preparation for fixing nodemask, fix all the bitmap routines that should be returning unsigned (or bool) values. Cc: Yury Norov Cc: Rasmus Villemoes Cc: Christophe de Dinechin Cc: Alexey Dobriyan Cc: Andy Shevchenko Cc: Andrew Morton Cc: Zhen Lei Signed-off-by: Kees Cook Signed-off-by: Yury Norov --- include/linux/bitmap.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 71147b7d721b..2e6cd5681040 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -134,8 +134,8 @@ unsigned long *devm_bitmap_zalloc(struct device *dev, * lib/bitmap.c provides these functions: */ -int __bitmap_equal(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); +bool __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); bool __pure __bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, const unsigned long *src3, @@ -159,10 +159,10 @@ int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits); -int __bitmap_intersects(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -int __bitmap_subset(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); +bool __bitmap_intersects(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +bool __bitmap_subset(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); void __bitmap_set(unsigned long *map, unsigned int start, int len); void __bitmap_clear(unsigned long *map, unsigned int start, int len); @@ -353,8 +353,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) -static inline int bitmap_equal(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static inline bool bitmap_equal(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); @@ -384,8 +384,9 @@ static inline bool bitmap_or_equal(const unsigned long *src1, return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); } -static inline int bitmap_intersects(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static inline bool bitmap_intersects(const unsigned long *src1, + const unsigned long *src2, + unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; @@ -393,8 +394,8 @@ static inline int bitmap_intersects(const unsigned long *src1, return __bitmap_intersects(src1, src2, nbits); } -static inline int bitmap_subset(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static inline bool bitmap_subset(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); -- cgit v1.2.3 From 0dfe54071d7c828a02917b595456bfde1afdddc9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 18 May 2022 13:52:23 -0700 Subject: nodemask: Fix return values to be unsigned MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The nodemask routines had mixed return values that provided potentially signed return values that could never happen. This was leading to the compiler getting confusing about the range of possible return values (it was thinking things could be negative where they could not be). Fix all the nodemask routines that should be returning unsigned (or bool) values. Silences: mm/swapfile.c: In function ‘setup_swap_info’: mm/swapfile.c:2291:47: error: array subscript -1 is below array bounds of ‘struct plist_node[]’ [-Werror=array-bounds] 2291 | p->avail_lists[i].prio = 1; | ~~~~~~~~~~~~~~^~~ In file included from mm/swapfile.c:16: ./include/linux/swap.h:292:27: note: while referencing ‘avail_lists’ 292 | struct plist_node avail_lists[]; /* | ^~~~~~~~~~~ Reported-by: Christophe de Dinechin Link: https://lore.kernel.org/lkml/20220414150855.2407137-3-dinechin@redhat.com/ Cc: Alexey Dobriyan Cc: Yury Norov Cc: Andy Shevchenko Cc: Rasmus Villemoes Cc: Andrew Morton Cc: Zhen Lei Signed-off-by: Kees Cook Signed-off-by: Yury Norov --- include/linux/nodemask.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 567c3ddba2c4..2c39663c3407 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -42,11 +42,11 @@ * void nodes_shift_right(dst, src, n) Shift right * void nodes_shift_left(dst, src, n) Shift left * - * int first_node(mask) Number lowest set bit, or MAX_NUMNODES - * int next_node(node, mask) Next node past 'node', or MAX_NUMNODES - * int next_node_in(node, mask) Next node past 'node', or wrap to first, + * unsigned int first_node(mask) Number lowest set bit, or MAX_NUMNODES + * unsigend int next_node(node, mask) Next node past 'node', or MAX_NUMNODES + * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first, * or MAX_NUMNODES - * int first_unset_node(mask) First node not set in mask, or + * unsigned int first_unset_node(mask) First node not set in mask, or * MAX_NUMNODES * * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set @@ -153,7 +153,7 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) -static inline int __node_test_and_set(int node, nodemask_t *addr) +static inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } @@ -200,7 +200,7 @@ static inline void __nodes_complement(nodemask_t *dstp, #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) -static inline int __nodes_equal(const nodemask_t *src1p, +static inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); @@ -208,7 +208,7 @@ static inline int __nodes_equal(const nodemask_t *src1p, #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) -static inline int __nodes_intersects(const nodemask_t *src1p, +static inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); @@ -216,20 +216,20 @@ static inline int __nodes_intersects(const nodemask_t *src1p, #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) -static inline int __nodes_subset(const nodemask_t *src1p, +static inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) -static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits) +static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) -static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits) +static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } @@ -260,15 +260,15 @@ static inline void __nodes_shift_left(nodemask_t *dstp, > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) -static inline int __first_node(const nodemask_t *srcp) +static inline unsigned int __first_node(const nodemask_t *srcp) { - return min_t(int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); + return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) -static inline int __next_node(int n, const nodemask_t *srcp) +static inline unsigned int __next_node(int n, const nodemask_t *srcp) { - return min_t(int,MAX_NUMNODES,find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); + return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } /* @@ -276,7 +276,7 @@ static inline int __next_node(int n, const nodemask_t *srcp) * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) -int __next_node_in(int node, const nodemask_t *srcp); +unsigned int __next_node_in(int node, const nodemask_t *srcp); static inline void init_nodemask_of_node(nodemask_t *mask, int node) { @@ -296,9 +296,9 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node) }) #define first_unset_node(mask) __first_unset_node(&(mask)) -static inline int __first_unset_node(const nodemask_t *maskp) +static inline unsigned int __first_unset_node(const nodemask_t *maskp) { - return min_t(int,MAX_NUMNODES, + return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); } @@ -436,11 +436,11 @@ static inline int num_node_state(enum node_states state) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) -static inline int next_online_node(int nid) +static inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } -static inline int next_memory_node(int nid) +static inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } -- cgit v1.2.3 From e1cff7002b716bd0b5f5f4afd4273c99aa8644be Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 5 Jun 2022 11:51:48 -0700 Subject: bluetooth: don't use bitmaps for random flag accesses The bluetooth code uses our bitmap infrastructure for the two bits (!) of connection setup flags, and in the process causes odd problems when it converts between a bitmap and just the regular values of said bits. It's completely pointless to do things like bitmap_to_arr32() to convert a bitmap into a u32. It shoudln't have been a bitmap in the first place. The reason to use bitmaps is if you have arbitrary number of bits you want to manage (not two!), or if you rely on the atomicity guarantees of the bitmap setting and clearing. The code could use an "atomic_t" and use "atomic_or/andnot()" to set and clear the bit values, but considering that it then copies the bitmaps around with "bitmap_to_arr32()" and friends, there clearly cannot be a lot of atomicity requirements. So just use a regular integer. In the process, this avoids the warnings about erroneous use of bitmap_from_u64() which were triggered on 32-bit architectures when conversion from a u64 would access two words (and, surprise, surprise, only one word is needed - and indeed overkill - for a 2-bit bitmap). That was always problematic, but the compiler seems to notice it and warn about the invalid pattern only after commit 0a97953fd221 ("lib: add bitmap_{from,to}_arr64") changed the exact implementation details of 'bitmap_from_u64()', as reported by Sudip Mukherjee and Stephen Rothwell. Fixes: fe92ee6425a2 ("Bluetooth: hci_core: Rework hci_conn_params flags") Link: https://lore.kernel.org/all/YpyJ9qTNHJzz0FHY@debian/ Link: https://lore.kernel.org/all/20220606080631.0c3014f2@canb.auug.org.au/ Link: https://lore.kernel.org/all/20220605162537.1604762-1-yury.norov@gmail.com/ Reported-by: Stephen Rothwell Reported-by: Sudip Mukherjee Reviewed-by: Yury Norov Cc: Luiz Augusto von Dentz Cc: Marcel Holtmann Signed-off-by: Linus Torvalds --- include/net/bluetooth/hci_core.h | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 5a52a2018b56..c0ea2a4892b1 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -155,21 +155,18 @@ struct bdaddr_list_with_irk { u8 local_irk[16]; }; +/* Bitmask of connection flags */ enum hci_conn_flags { - HCI_CONN_FLAG_REMOTE_WAKEUP, - HCI_CONN_FLAG_DEVICE_PRIVACY, - - __HCI_CONN_NUM_FLAGS, + HCI_CONN_FLAG_REMOTE_WAKEUP = 1, + HCI_CONN_FLAG_DEVICE_PRIVACY = 2, }; - -/* Make sure number of flags doesn't exceed sizeof(current_flags) */ -static_assert(__HCI_CONN_NUM_FLAGS < 32); +typedef u8 hci_conn_flags_t; struct bdaddr_list_with_flags { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; - DECLARE_BITMAP(flags, __HCI_CONN_NUM_FLAGS); + hci_conn_flags_t flags; }; struct bt_uuid { @@ -576,7 +573,7 @@ struct hci_dev { struct rfkill *rfkill; DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); - DECLARE_BITMAP(conn_flags, __HCI_CONN_NUM_FLAGS); + hci_conn_flags_t conn_flags; __s8 adv_tx_power; __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; @@ -775,7 +772,7 @@ struct hci_conn_params { struct hci_conn *conn; bool explicit_connect; - DECLARE_BITMAP(flags, __HCI_CONN_NUM_FLAGS); + hci_conn_flags_t flags; u8 privacy_mode; }; -- cgit v1.2.3 From a734510fa8b4e61e6a37176f0da01f4c55fa52de Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 25 May 2022 13:49:42 +0200 Subject: ata: libata: drop 'sas_last_tag' Unused now. Fixes: 4f1a22ee7b57 ("libata: Improve ATA queued command allocation") Cc: John Garry Signed-off-by: Hannes Reinecke Reviewed-by: John Garry Signed-off-by: Damien Le Moal --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 732de9014626..0f2a59c9c735 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -822,7 +822,6 @@ struct ata_port { struct ata_queued_cmd qcmd[ATA_MAX_QUEUE + 1]; u64 qc_active; int nr_active_links; /* #links with active qcs */ - unsigned int sas_last_tag; /* track next tag hw expects */ struct ata_link link; /* host default link */ struct ata_link *slave_link; /* see ata_slave_link_init() */ -- cgit v1.2.3 From 2130a790ca49763f724ec45cf93b9dd765e2023e Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 2 Jun 2022 15:05:26 +0200 Subject: kernel: add platform_has() infrastructure Add a simple infrastructure for setting, resetting and querying platform feature flags. Flags can be either global or architecture specific. Signed-off-by: Juergen Gross Reviewed-by: Oleksandr Tyshchenko Tested-by: Oleksandr Tyshchenko # Arm64 only Reviewed-by: Christoph Hellwig Acked-by: Borislav Petkov Signed-off-by: Juergen Gross --- include/asm-generic/Kbuild | 1 + include/asm-generic/platform-feature.h | 8 ++++++++ include/linux/platform-feature.h | 15 +++++++++++++++ 3 files changed, 24 insertions(+) create mode 100644 include/asm-generic/platform-feature.h create mode 100644 include/linux/platform-feature.h (limited to 'include') diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index 302506bbc2a4..8e47d483b524 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -44,6 +44,7 @@ mandatory-y += msi.h mandatory-y += pci.h mandatory-y += percpu.h mandatory-y += pgalloc.h +mandatory-y += platform-feature.h mandatory-y += preempt.h mandatory-y += rwonce.h mandatory-y += sections.h diff --git a/include/asm-generic/platform-feature.h b/include/asm-generic/platform-feature.h new file mode 100644 index 000000000000..4b0af3d51588 --- /dev/null +++ b/include/asm-generic/platform-feature.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_GENERIC_PLATFORM_FEATURE_H +#define _ASM_GENERIC_PLATFORM_FEATURE_H + +/* Number of arch specific feature flags. */ +#define PLATFORM_ARCH_FEAT_N 0 + +#endif /* _ASM_GENERIC_PLATFORM_FEATURE_H */ diff --git a/include/linux/platform-feature.h b/include/linux/platform-feature.h new file mode 100644 index 000000000000..6ed859928b97 --- /dev/null +++ b/include/linux/platform-feature.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _PLATFORM_FEATURE_H +#define _PLATFORM_FEATURE_H + +#include +#include + +/* The platform features are starting with the architecture specific ones. */ +#define PLATFORM_FEAT_N (0 + PLATFORM_ARCH_FEAT_N) + +void platform_set(unsigned int feature); +void platform_clear(unsigned int feature); +bool platform_has(unsigned int feature); + +#endif /* _PLATFORM_FEATURE_H */ -- cgit v1.2.3 From 3f9dfbebdc48cebfbda738f6f3d1dbf6d7232f90 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 6 Jun 2022 08:09:16 +0200 Subject: virtio: replace arch_has_restricted_virtio_memory_access() Instead of using arch_has_restricted_virtio_memory_access() together with CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS, replace those with platform_has() and a new platform feature PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS. Signed-off-by: Juergen Gross Reviewed-by: Oleksandr Tyshchenko Tested-by: Oleksandr Tyshchenko # Arm64 only Reviewed-by: Christoph Hellwig Acked-by: Borislav Petkov --- include/linux/platform-feature.h | 6 +++++- include/linux/virtio_config.h | 9 --------- 2 files changed, 5 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/platform-feature.h b/include/linux/platform-feature.h index 6ed859928b97..b2f48be999fa 100644 --- a/include/linux/platform-feature.h +++ b/include/linux/platform-feature.h @@ -6,7 +6,11 @@ #include /* The platform features are starting with the architecture specific ones. */ -#define PLATFORM_FEAT_N (0 + PLATFORM_ARCH_FEAT_N) + +/* Used to enable platform specific DMA handling for virtio devices. */ +#define PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS (0 + PLATFORM_ARCH_FEAT_N) + +#define PLATFORM_FEAT_N (1 + PLATFORM_ARCH_FEAT_N) void platform_set(unsigned int feature); void platform_clear(unsigned int feature); diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 9a36051ceb76..49c7c32815f1 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -604,13 +604,4 @@ static inline void virtio_cwrite64(struct virtio_device *vdev, _r; \ }) -#ifdef CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS -int arch_has_restricted_virtio_memory_access(void); -#else -static inline int arch_has_restricted_virtio_memory_access(void) -{ - return 0; -} -#endif /* CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS */ - #endif /* _LINUX_VIRTIO_CONFIG_H */ -- cgit v1.2.3 From 9bf22421dc8a69cade3c994771637e9693ff0216 Mon Sep 17 00:00:00 2001 From: Oleksandr Tyshchenko Date: Thu, 2 Jun 2022 22:23:46 +0300 Subject: arm/xen: Introduce xen_setup_dma_ops() This patch introduces new helper and places it in new header. The helper's purpose is to assign any Xen specific DMA ops in a single place. For now, we deal with xen-swiotlb DMA ops only. The one of the subsequent commits in current series will add xen-grant DMA ops case. Also re-use the xen_swiotlb_detect() check on Arm32. Signed-off-by: Oleksandr Tyshchenko Reviewed-by: Stefano Stabellini [For arm64] Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/1654197833-25362-2-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/arm/xen-ops.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/xen/arm/xen-ops.h (limited to 'include') diff --git a/include/xen/arm/xen-ops.h b/include/xen/arm/xen-ops.h new file mode 100644 index 000000000000..288deb1c3ac9 --- /dev/null +++ b/include/xen/arm/xen-ops.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ARM_XEN_OPS_H +#define _ASM_ARM_XEN_OPS_H + +#include + +static inline void xen_setup_dma_ops(struct device *dev) +{ +#ifdef CONFIG_XEN + if (xen_swiotlb_detect()) + dev->dma_ops = &xen_swiotlb_dma_ops; +#endif +} + +#endif /* _ASM_ARM_XEN_OPS_H */ -- cgit v1.2.3 From 02a9e681a3f7998074f39ec265080bf934871530 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 2 Jun 2022 22:23:47 +0300 Subject: xen/grants: support allocating consecutive grants For support of virtio via grant mappings in rare cases larger mappings using consecutive grants are needed. Support those by adding a bitmap of free grants. As consecutive grants will be needed only in very rare cases (e.g. when configuring a virtio device with a multi-page ring), optimize for the normal case of non-consecutive allocations. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/1654197833-25362-3-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/grant_table.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 527c9907f99c..e279be353e3f 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -127,10 +127,14 @@ int gnttab_try_end_foreign_access(grant_ref_t ref); */ int gnttab_alloc_grant_references(u16 count, grant_ref_t *pprivate_head); +int gnttab_alloc_grant_reference_seq(unsigned int count, grant_ref_t *first); + void gnttab_free_grant_reference(grant_ref_t ref); void gnttab_free_grant_references(grant_ref_t head); +void gnttab_free_grant_reference_seq(grant_ref_t head, unsigned int count); + int gnttab_empty_grant_references(const grant_ref_t *pprivate_head); int gnttab_claim_grant_reference(grant_ref_t *pprivate_head); -- cgit v1.2.3 From d6aca3504c7ded5f4f46957e3685b9344d9743dd Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 2 Jun 2022 22:23:48 +0300 Subject: xen/grant-dma-ops: Add option to restrict memory access under Xen Introduce Xen grant DMA-mapping layer which contains special DMA-mapping routines for providing grant references as DMA addresses to be used by frontends (e.g. virtio) in Xen guests. Add the needed functionality by providing a special set of DMA ops handling the needed grant operations for the I/O pages. The subsequent commit will introduce the use case for xen-grant DMA ops layer to enable using virtio devices in Xen guests in a safe manner. Signed-off-by: Juergen Gross Signed-off-by: Oleksandr Tyshchenko Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/1654197833-25362-4-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/xen-ops.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index c7c1b46ff4cd..afd586d717a4 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -214,4 +214,12 @@ static inline void xen_preemptible_hcall_end(void) { } #endif /* CONFIG_XEN_PV && !CONFIG_PREEMPTION */ +#ifdef CONFIG_XEN_GRANT_DMA_OPS +void xen_grant_setup_dma_ops(struct device *dev); +#else +static inline void xen_grant_setup_dma_ops(struct device *dev) +{ +} +#endif /* CONFIG_XEN_GRANT_DMA_OPS */ + #endif /* INCLUDE_XEN_OPS_H */ -- cgit v1.2.3 From fa1f57421e0b1c57843902c89728f823abc32f02 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 2 Jun 2022 22:23:49 +0300 Subject: xen/virtio: Enable restricted memory access using Xen grant mappings In order to support virtio in Xen guests add a config option XEN_VIRTIO enabling the user to specify whether in all Xen guests virtio should be able to access memory via Xen grant mappings only on the host side. Also set PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS feature from the guest initialization code on Arm and x86 if CONFIG_XEN_VIRTIO is enabled. Signed-off-by: Juergen Gross Signed-off-by: Oleksandr Tyshchenko Reviewed-by: Stefano Stabellini Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/1654197833-25362-5-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/xen.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/xen/xen.h b/include/xen/xen.h index a99bab817523..0780a81e140d 100644 --- a/include/xen/xen.h +++ b/include/xen/xen.h @@ -52,6 +52,14 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, extern u64 xen_saved_max_mem_size; #endif +#include + +static inline void xen_set_restricted_virtio_memory_access(void) +{ + if (IS_ENABLED(CONFIG_XEN_VIRTIO) && xen_domain()) + platform_set(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS); +} + #ifdef CONFIG_XEN_UNPOPULATED_ALLOC int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages); void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages); -- cgit v1.2.3 From 625ab90ecdf7770bda7ae21c4d5c938aa9b43bb4 Mon Sep 17 00:00:00 2001 From: Oleksandr Tyshchenko Date: Thu, 2 Jun 2022 22:23:52 +0300 Subject: xen/grant-dma-ops: Retrieve the ID of backend's domain for DT devices Use the presence of "iommus" property pointed to the IOMMU node with recently introduced "xen,grant-dma" compatible as a clear indicator of enabling Xen grant mappings scheme for that device and read the ID of Xen domain where the corresponding backend is running. The domid (domain ID) is used as an argument to the Xen grant mapping APIs. To avoid the deferred probe timeout which takes place after reusing generic IOMMU device tree bindings (because the IOMMU device never becomes available) enable recently introduced stub IOMMU driver by selecting XEN_GRANT_DMA_IOMMU. Also introduce xen_is_grant_dma_device() to check whether xen-grant DMA ops need to be set for a passed device. Remove the hardcoded domid 0 in xen_grant_setup_dma_ops(). Signed-off-by: Oleksandr Tyshchenko Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/1654197833-25362-8-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/xen-ops.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index afd586d717a4..80546960f8b7 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -216,10 +216,15 @@ static inline void xen_preemptible_hcall_end(void) { } #ifdef CONFIG_XEN_GRANT_DMA_OPS void xen_grant_setup_dma_ops(struct device *dev); +bool xen_is_grant_dma_device(struct device *dev); #else static inline void xen_grant_setup_dma_ops(struct device *dev) { } +static inline bool xen_is_grant_dma_device(struct device *dev) +{ + return false; +} #endif /* CONFIG_XEN_GRANT_DMA_OPS */ #endif /* INCLUDE_XEN_OPS_H */ -- cgit v1.2.3 From fea981610c25173e6e5d63ccd4fce49739663ab0 Mon Sep 17 00:00:00 2001 From: Oleksandr Tyshchenko Date: Thu, 2 Jun 2022 22:23:53 +0300 Subject: arm/xen: Assign xen-grant DMA ops for xen-grant DMA devices By assigning xen-grant DMA ops we will restrict memory access for passed device using Xen grant mappings. This is needed for using any virtualized device (e.g. virtio) in Xen guests in a safe manner. Please note, for the virtio devices the XEN_VIRTIO config should be enabled (it forces ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS). Signed-off-by: Oleksandr Tyshchenko Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/1654197833-25362-9-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/arm/xen-ops.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/xen/arm/xen-ops.h b/include/xen/arm/xen-ops.h index 288deb1c3ac9..b0766a660338 100644 --- a/include/xen/arm/xen-ops.h +++ b/include/xen/arm/xen-ops.h @@ -3,11 +3,14 @@ #define _ASM_ARM_XEN_OPS_H #include +#include static inline void xen_setup_dma_ops(struct device *dev) { #ifdef CONFIG_XEN - if (xen_swiotlb_detect()) + if (xen_is_grant_dma_device(dev)) + xen_grant_setup_dma_ops(dev); + else if (xen_swiotlb_detect()) dev->dma_ops = &xen_swiotlb_dma_ops; #endif } -- cgit v1.2.3 From 3a41c64d9c1185a2f3a184015e2a9b78bfc99c71 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 6 Jun 2022 17:31:29 +0200 Subject: netfilter: nf_tables: bail out early if hardware offload is not supported If user requests for NFT_CHAIN_HW_OFFLOAD, then check if either device provides the .ndo_setup_tc interface or there is an indirect flow block that has been registered. Otherwise, bail out early from the preparation phase. Moreover, validate that family == NFPROTO_NETDEV and hook is NF_NETDEV_INGRESS. Fixes: c9626a2cbdb2 ("netfilter: nf_tables: add hardware offload support") Signed-off-by: Pablo Neira Ayuso --- include/net/flow_offload.h | 1 + include/net/netfilter/nf_tables_offload.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 021778a7e1af..6484095a8c01 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -612,5 +612,6 @@ int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, enum tc_setup_type type, void *data, struct flow_block_offload *bo, void (*cleanup)(struct flow_block_cb *block_cb)); +bool flow_indr_dev_exists(void); #endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index 797147843958..3568b6a2f5f0 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -92,7 +92,7 @@ int nft_flow_rule_offload_commit(struct net *net); NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \ memset(&(__reg)->mask, 0xff, (__reg)->len); -int nft_chain_offload_priority(struct nft_base_chain *basechain); +bool nft_chain_offload_support(const struct nft_base_chain *basechain); int nft_offload_init(void); void nft_offload_exit(void); -- cgit v1.2.3 From 77991645952c21962a095910c51fe0f73d35bf91 Mon Sep 17 00:00:00 2001 From: Roger Knecht Date: Sat, 21 May 2022 14:47:45 +0200 Subject: crc-itu-t: fix typo in CRC ITU-T polynomial comment The code comment says that the polynomial is x^16 + x^12 + x^15 + 1, but the correct polynomial is x^16 + x^12 + x^5 + 1. Quoting from page 2 in the ITU-T V.41 specification [1]: 2 Encoding and checking process The service bits and information bits, taken in conjunction, correspond to the coefficients of a message polynomial having terms from x^(n-1) (n = total number of bits in a block or sequence) down to x^16. This polynomial is divided, modulo 2, by the generating polynomial x^16 + x^12 + x^5 + 1. The hex (truncated) polynomial 0x1021 and CRC code implementation are correct, however. [1] https://www.itu.int/rec/T-REC-V.41-198811-I/en Signed-off-by: Roger Knecht Acked-by: Randy Dunlap Signed-off-by: Jason A. Donenfeld --- include/linux/crc-itu-t.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/crc-itu-t.h b/include/linux/crc-itu-t.h index a4367051e192..2f991a427ade 100644 --- a/include/linux/crc-itu-t.h +++ b/include/linux/crc-itu-t.h @@ -4,7 +4,7 @@ * * Implements the standard CRC ITU-T V.41: * Width 16 - * Poly 0x1021 (x^16 + x^12 + x^15 + 1) + * Poly 0x1021 (x^16 + x^12 + x^5 + 1) * Init 0 */ -- cgit v1.2.3 From c4f135d643823a869becfa87539f7820ef9d5bfa Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Wed, 1 Jun 2022 16:32:47 +0900 Subject: workqueue: Wrap flush_workqueue() using a macro Since flush operation synchronously waits for completion, flushing system-wide WQs (e.g. system_wq) might introduce possibility of deadlock due to unexpected locking dependency. Tejun Heo commented at [1] that it makes no sense at all to call flush_workqueue() on the shared WQs as the caller has no idea what it's gonna end up waiting for. Although there is flush_scheduled_work() which flushes system_wq WQ with "Think twice before calling this function! It's very easy to get into trouble if you don't take great care." warning message, syzbot found a circular locking dependency caused by flushing system_wq WQ [2]. Therefore, let's change the direction to that developers had better use their local WQs if flush_scheduled_work()/flush_workqueue(system_*_wq) is inevitable. Steps for converting system-wide WQs into local WQs are explained at [3], and a conversion to stop flushing system-wide WQs is in progress. Now we want some mechanism for preventing developers who are not aware of this conversion from again start flushing system-wide WQs. Since I found that WARN_ON() is complete but awkward approach for teaching developers about this problem, let's use __compiletime_warning() for incomplete but handy approach. For completeness, we will also insert WARN_ON() into __flush_workqueue() after all in-tree users stopped calling flush_scheduled_work(). Link: https://lore.kernel.org/all/YgnQGZWT%2Fn3VAITX@slm.duckdns.org/ [1] Link: https://syzkaller.appspot.com/bug?extid=bde0f89deacca7c765b8 [2] Link: https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp [3] Signed-off-by: Tetsuo Handa Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 64 +++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 56 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 7fee9b6cfede..e1f1c8b1121b 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -445,7 +445,7 @@ extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork); -extern void flush_workqueue(struct workqueue_struct *wq); +extern void __flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); @@ -563,15 +563,23 @@ static inline bool schedule_work(struct work_struct *work) return queue_work(system_wq, work); } +/* + * Detect attempt to flush system-wide workqueues at compile time when possible. + * + * See https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp + * for reasons and steps for converting system-wide workqueues into local workqueues. + */ +extern void __warn_flushing_systemwide_wq(void) + __compiletime_warning("Please avoid flushing system-wide workqueues."); + /** * flush_scheduled_work - ensure that any scheduled work has run to completion. * * Forces execution of the kernel-global workqueue and blocks until its * completion. * - * Think twice before calling this function! It's very easy to get into - * trouble if you don't take great care. Either of the following situations - * will lead to deadlock: + * It's very easy to get into trouble if you don't take great care. + * Either of the following situations will lead to deadlock: * * One of the work items currently on the workqueue needs to acquire * a lock held by your code or its caller. @@ -586,11 +594,51 @@ static inline bool schedule_work(struct work_struct *work) * need to know that a particular work item isn't queued and isn't running. * In such cases you should use cancel_delayed_work_sync() or * cancel_work_sync() instead. + * + * Please stop calling this function! A conversion to stop flushing system-wide + * workqueues is in progress. This function will be removed after all in-tree + * users stopped calling this function. */ -static inline void flush_scheduled_work(void) -{ - flush_workqueue(system_wq); -} +/* + * The background of commit 771c035372a036f8 ("deprecate the + * '__deprecated' attribute warnings entirely and for good") is that, + * since Linus builds all modules between every single pull he does, + * the standard kernel build needs to be _clean_ in order to be able to + * notice when new problems happen. Therefore, don't emit warning while + * there are in-tree users. + */ +#define flush_scheduled_work() \ +({ \ + if (0) \ + __warn_flushing_systemwide_wq(); \ + __flush_workqueue(system_wq); \ +}) + +/* + * Although there is no longer in-tree caller, for now just emit warning + * in order to give out-of-tree callers time to update. + */ +#define flush_workqueue(wq) \ +({ \ + struct workqueue_struct *_wq = (wq); \ + \ + if ((__builtin_constant_p(_wq == system_wq) && \ + _wq == system_wq) || \ + (__builtin_constant_p(_wq == system_highpri_wq) && \ + _wq == system_highpri_wq) || \ + (__builtin_constant_p(_wq == system_long_wq) && \ + _wq == system_long_wq) || \ + (__builtin_constant_p(_wq == system_unbound_wq) && \ + _wq == system_unbound_wq) || \ + (__builtin_constant_p(_wq == system_freezable_wq) && \ + _wq == system_freezable_wq) || \ + (__builtin_constant_p(_wq == system_power_efficient_wq) && \ + _wq == system_power_efficient_wq) || \ + (__builtin_constant_p(_wq == system_freezable_power_efficient_wq) && \ + _wq == system_freezable_power_efficient_wq)) \ + __warn_flushing_systemwide_wq(); \ + __flush_workqueue(_wq); \ +}) /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay -- cgit v1.2.3 From 873a400938b31a1e443c4d94b560b78300787540 Mon Sep 17 00:00:00 2001 From: Wonhyuk Yang Date: Wed, 4 May 2022 11:32:03 +0900 Subject: workqueue: Fix type of cpu in trace event The trace event "workqueue_queue_work" use unsigned int type for req_cpu, cpu. This casue confusing cpu number like below log. $ cat /sys/kernel/debug/tracing/trace cat-317 [001] ...: workqueue_queue_work: ... req_cpu=8192 cpu=4294967295 So, change unsigned type to signed type in the trace event. After applying this patch, cpu number will be printed as -1 instead of 4294967295 as folllows. $ cat /sys/kernel/debug/tracing/trace cat-1338 [002] ...: workqueue_queue_work: ... req_cpu=8192 cpu=-1 Cc: Baik Song An Cc: Hong Yeon Kim Cc: Taeung Song Cc: linuxgeek@linuxgeek.io Signed-off-by: Wonhyuk Yang Signed-off-by: Tejun Heo --- include/trace/events/workqueue.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index 6154a2e72bce..262d52021c23 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -22,7 +22,7 @@ struct pool_workqueue; */ TRACE_EVENT(workqueue_queue_work, - TP_PROTO(unsigned int req_cpu, struct pool_workqueue *pwq, + TP_PROTO(int req_cpu, struct pool_workqueue *pwq, struct work_struct *work), TP_ARGS(req_cpu, pwq, work), @@ -31,8 +31,8 @@ TRACE_EVENT(workqueue_queue_work, __field( void *, work ) __field( void *, function) __string( workqueue, pwq->wq->name) - __field( unsigned int, req_cpu ) - __field( unsigned int, cpu ) + __field( int, req_cpu ) + __field( int, cpu ) ), TP_fast_assign( @@ -43,7 +43,7 @@ TRACE_EVENT(workqueue_queue_work, __entry->cpu = pwq->pool->cpu; ), - TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%u cpu=%u", + TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%d cpu=%d", __entry->work, __entry->function, __get_str(workqueue), __entry->req_cpu, __entry->cpu) ); -- cgit v1.2.3 From 62ed448cc53b654036f7d7f3c99f299d79ad14c3 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 7 Jun 2022 16:47:58 -0400 Subject: SUNRPC: Optimize xdr_reserve_space() Transitioning between encode buffers is quite infrequent. It happens about 1 time in 400 calls to xdr_reserve_space(), measured on NFSD with a typical build/test workload. Force the compiler to remove that code from xdr_reserve_space(), which is a hot path on both the server and the client. This change reduces the size of xdr_reserve_space() from 10 cache lines to 2 when compiled with -Os. Signed-off-by: Chuck Lever Reviewed-by: J. Bruce Fields --- include/linux/sunrpc/xdr.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 4417f667c757..5860f32e3958 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -243,7 +243,7 @@ extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes); -extern void xdr_commit_encode(struct xdr_stream *xdr); +extern void __xdr_commit_encode(struct xdr_stream *xdr); extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len); extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen); extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, @@ -306,6 +306,20 @@ xdr_reset_scratch_buffer(struct xdr_stream *xdr) xdr_set_scratch_buffer(xdr, NULL, 0); } +/** + * xdr_commit_encode - Ensure all data is written to xdr->buf + * @xdr: pointer to xdr_stream + * + * Handle encoding across page boundaries by giving the caller a + * temporary location to write to, then later copying the data into + * place. __xdr_commit_encode() does that copying. + */ +static inline void xdr_commit_encode(struct xdr_stream *xdr) +{ + if (unlikely(xdr->scratch.iov_len)) + __xdr_commit_encode(xdr); +} + /** * xdr_stream_remaining - Return the number of bytes remaining in the stream * @xdr: pointer to struct xdr_stream -- cgit v1.2.3 From f93431c86b631bbca5614c66f966bf3ddb3c2803 Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Tue, 7 Jun 2022 20:00:27 +0800 Subject: ipv6: Fix signed integer overflow in __ip6_append_data Resurrect ubsan overflow checks and ubsan report this warning, fix it by change the variable [length] type to size_t. UBSAN: signed-integer-overflow in net/ipv6/ip6_output.c:1489:19 2147479552 + 8567 cannot be represented in type 'int' CPU: 0 PID: 253 Comm: err Not tainted 5.16.0+ #1 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x214/0x230 show_stack+0x30/0x78 dump_stack_lvl+0xf8/0x118 dump_stack+0x18/0x30 ubsan_epilogue+0x18/0x60 handle_overflow+0xd0/0xf0 __ubsan_handle_add_overflow+0x34/0x44 __ip6_append_data.isra.48+0x1598/0x1688 ip6_append_data+0x128/0x260 udpv6_sendmsg+0x680/0xdd0 inet6_sendmsg+0x54/0x90 sock_sendmsg+0x70/0x88 ____sys_sendmsg+0xe8/0x368 ___sys_sendmsg+0x98/0xe0 __sys_sendmmsg+0xf4/0x3b8 __arm64_sys_sendmmsg+0x34/0x48 invoke_syscall+0x64/0x160 el0_svc_common.constprop.4+0x124/0x300 do_el0_svc+0x44/0xc8 el0_svc+0x3c/0x1e8 el0t_64_sync_handler+0x88/0xb0 el0t_64_sync+0x16c/0x170 Changes since v1: -Change the variable [length] type to unsigned, as Eric Dumazet suggested. Changes since v2: -Don't change exthdrlen type in ip6_make_skb, as Paolo Abeni suggested. Changes since v3: -Don't change ulen type in udpv6_sendmsg and l2tp_ip6_sendmsg, as Jakub Kicinski suggested. Reported-by: Hulk Robot Signed-off-by: Wang Yufen Link: https://lore.kernel.org/r/20220607120028.845916-1-wangyufen@huawei.com Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 5b38bf1a586b..de9dcc5652c4 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1063,7 +1063,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags); @@ -1079,7 +1079,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); -- cgit v1.2.3 From d5a37b19983725d2045588cfa3a4699f5b39ae26 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Jun 2022 08:34:07 +0200 Subject: block: remove bioset_init_from_src Unused now, and the interface never really made a whole lot of sense to start with. Signed-off-by: Christoph Hellwig Signed-off-by: Mike Snitzer --- include/linux/bio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 1cf3738ef1ea..992ee987f273 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -403,7 +403,6 @@ enum { extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); -extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask, -- cgit v1.2.3 From 00d1f546470d89e072dd3cda12b5c794341e7268 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 9 Jun 2022 12:19:01 +0800 Subject: vdpa: make get_vq_group and set_group_asid optional This patch makes get_vq_group and set_group_asid optional. This is needed to unbreak the vDPA parent that doesn't support multiple address spaces. Cc: Gautam Dawar Fixes: aaca8373c4b1 ("vhost-vdpa: support ASID based IOTLB API") Signed-off-by: Jason Wang Message-Id: <20220609041901.2029-1-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 4700a88a28f6..7b4a13d3bd91 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -178,7 +178,8 @@ struct vdpa_map_file { * for the device * @vdev: vdpa device * Returns virtqueue algin requirement - * @get_vq_group: Get the group id for a specific virtqueue + * @get_vq_group: Get the group id for a specific + * virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index * Returns u32: group id for this virtqueue @@ -243,7 +244,7 @@ struct vdpa_map_file { * Returns the iova range supported by * the device. * @set_group_asid: Set address space identifier for a - * virtqueue group + * virtqueue group (optional) * @vdev: vdpa device * @group: virtqueue group * @asid: address space id for this group -- cgit v1.2.3 From 69a37a8ba1b408a1c7616494aa7018e4b3844cbe Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 8 Jun 2022 15:18:34 -0400 Subject: mm/huge_memory: Fix xarray node memory leak If xas_split_alloc() fails to allocate the necessary nodes to complete the xarray entry split, it sets the xa_state to -ENOMEM, which xas_nomem() then interprets as "Please allocate more memory", not as "Please free any unnecessary memory" (which was the intended outcome). It's confusing to use xas_nomem() to free memory in this context, so call xas_destroy() instead. Reported-by: syzbot+9e27a75a8c24f3fe75c1@syzkaller.appspotmail.com Fixes: 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache") Cc: stable@vger.kernel.org Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/xarray.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 72feab5ea8d4..c29e11b2c073 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1508,6 +1508,7 @@ void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); +void xas_destroy(struct xa_state *); void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); -- cgit v1.2.3 From 334f6f53abcf57782bd2fe81da1cbd893e4ef05c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 9 Jun 2022 09:13:57 -0400 Subject: mm: Add kernel-doc for folio->mlock_count Fix "./include/linux/mm_types.h:279: warning: Function parameter or member 'mlock_count' not described in 'folio'". Also neaten the html by hiding the anon struct. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mm_types.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index b34ff2cdbc4f..c29ab4c0cd5c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -227,6 +227,7 @@ struct page { * struct folio - Represents a contiguous set of bytes. * @flags: Identical to the page flags. * @lru: Least Recently Used list; tracks how recently this folio was used. + * @mlock_count: Number of times this folio has been pinned by mlock(). * @mapping: The file this page belongs to, or refers to the anon_vma for * anonymous memory. * @index: Offset within the file, in units of pages. For anonymous memory, @@ -255,10 +256,14 @@ struct folio { unsigned long flags; union { struct list_head lru; + /* private: avoid cluttering the output */ struct { void *__filler; + /* public: */ unsigned int mlock_count; + /* private: */ }; + /* public: */ }; struct address_space *mapping; pgoff_t index; -- cgit v1.2.3 From 874c8ca1e60b2c564a48f7e7acc40d328d5c8733 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 9 Jun 2022 21:46:04 +0100 Subject: netfs: Fix gcc-12 warning by embedding vfs inode in netfs_i_context While randstruct was satisfied with using an open-coded "void *" offset cast for the netfs_i_context <-> inode casting, __builtin_object_size() as used by FORTIFY_SOURCE was not as easily fooled. This was causing the following complaint[1] from gcc v12: In file included from include/linux/string.h:253, from include/linux/ceph/ceph_debug.h:7, from fs/ceph/inode.c:2: In function 'fortify_memset_chk', inlined from 'netfs_i_context_init' at include/linux/netfs.h:326:2, inlined from 'ceph_alloc_inode' at fs/ceph/inode.c:463:2: include/linux/fortify-string.h:242:25: warning: call to '__write_overflow_field' declared with attribute warning: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Wattribute-warning] 242 | __write_overflow_field(p_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix this by embedding a struct inode into struct netfs_i_context (which should perhaps be renamed to struct netfs_inode). The struct inode vfs_inode fields are then removed from the 9p, afs, ceph and cifs inode structs and vfs_inode is then simply changed to "netfs.inode" in those filesystems. Further, rename netfs_i_context to netfs_inode, get rid of the netfs_inode() function that converted a netfs_i_context pointer to an inode pointer (that can now be done with &ctx->inode) and rename the netfs_i_context() function to netfs_inode() (which is now a wrapper around container_of()). Most of the changes were done with: perl -p -i -e 's/vfs_inode/netfs.inode/'g \ `git grep -l 'vfs_inode' -- fs/{9p,afs,ceph,cifs}/*.[ch]` Kees suggested doing it with a pair structure[2] and a special declarator to insert that into the network filesystem's inode wrapper[3], but I think it's cleaner to embed it - and then it doesn't matter if struct randomisation reorders things. Dave Chinner suggested using a filesystem-specific VFS_I() function in each filesystem to convert that filesystem's own inode wrapper struct into the VFS inode struct[4]. Version #2: - Fix a couple of missed name changes due to a disabled cifs option. - Rename nfs_i_context to nfs_inode - Use "netfs" instead of "nic" as the member name in per-fs inode wrapper structs. [ This also undoes commit 507160f46c55 ("netfs: gcc-12: temporarily disable '-Wattribute-warning' for now") that is no longer needed ] Fixes: bc899ee1c898 ("netfs: Add a netfs inode context") Reported-by: Jeff Layton Signed-off-by: David Howells Reviewed-by: Jeff Layton Reviewed-by: Kees Cook Reviewed-by: Xiubo Li cc: Jonathan Corbet cc: Eric Van Hensbergen cc: Latchesar Ionkov cc: Dominique Martinet cc: Christian Schoenebeck cc: Marc Dionne cc: Ilya Dryomov cc: Steve French cc: William Kucharski cc: "Matthew Wilcox (Oracle)" cc: Dave Chinner cc: linux-doc@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: samba-technical@lists.samba.org cc: linux-fsdevel@vger.kernel.org cc: linux-hardening@vger.kernel.org Link: https://lore.kernel.org/r/d2ad3a3d7bdd794c6efb562d2f2b655fb67756b9.camel@kernel.org/ [1] Link: https://lore.kernel.org/r/20220517210230.864239-1-keescook@chromium.org/ [2] Link: https://lore.kernel.org/r/20220518202212.2322058-1-keescook@chromium.org/ [3] Link: https://lore.kernel.org/r/20220524101205.GI2306852@dread.disaster.area/ [4] Link: https://lore.kernel.org/r/165296786831.3591209.12111293034669289733.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/165305805651.4094995.7763502506786714216.stgit@warthog.procyon.org.uk # v2 Signed-off-by: Linus Torvalds --- include/linux/netfs.h | 41 ++++++++++++++++------------------------- 1 file changed, 16 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 77fa6a61706a..6dbb4c9ce50d 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -119,9 +119,10 @@ typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error, bool was_async); /* - * Per-inode description. This must be directly after the inode struct. + * Per-inode context. This wraps the VFS inode. */ -struct netfs_i_context { +struct netfs_inode { + struct inode inode; /* The VFS inode */ const struct netfs_request_ops *ops; #if IS_ENABLED(CONFIG_FSCACHE) struct fscache_cookie *cache; @@ -256,7 +257,7 @@ struct netfs_cache_ops { * boundary as appropriate. */ enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, - loff_t i_size); + loff_t i_size); /* Prepare a write operation, working out what part of the write we can * actually do. @@ -288,45 +289,35 @@ extern void netfs_put_subrequest(struct netfs_io_subrequest *subreq, extern void netfs_stats_show(struct seq_file *); /** - * netfs_i_context - Get the netfs inode context from the inode + * netfs_inode - Get the netfs inode context from the inode * @inode: The inode to query * * Get the netfs lib inode context from the network filesystem's inode. The * context struct is expected to directly follow on from the VFS inode struct. */ -static inline struct netfs_i_context *netfs_i_context(struct inode *inode) +static inline struct netfs_inode *netfs_inode(struct inode *inode) { - return (void *)inode + sizeof(*inode); + return container_of(inode, struct netfs_inode, inode); } /** - * netfs_inode - Get the netfs inode from the inode context - * @ctx: The context to query - * - * Get the netfs inode from the netfs library's inode context. The VFS inode - * is expected to directly precede the context struct. - */ -static inline struct inode *netfs_inode(struct netfs_i_context *ctx) -{ - return (void *)ctx - sizeof(struct inode); -} - -/** - * netfs_i_context_init - Initialise a netfs lib context + * netfs_inode_init - Initialise a netfslib inode context * @inode: The inode with which the context is associated * @ops: The netfs's operations list * * Initialise the netfs library context struct. This is expected to follow on * directly from the VFS inode struct. */ -static inline void netfs_i_context_init(struct inode *inode, - const struct netfs_request_ops *ops) +static inline void netfs_inode_init(struct inode *inode, + const struct netfs_request_ops *ops) { - struct netfs_i_context *ctx = netfs_i_context(inode); + struct netfs_inode *ctx = netfs_inode(inode); - memset(ctx, 0, sizeof(*ctx)); ctx->ops = ops; ctx->remote_i_size = i_size_read(inode); +#if IS_ENABLED(CONFIG_FSCACHE) + ctx->cache = NULL; +#endif } /** @@ -338,7 +329,7 @@ static inline void netfs_i_context_init(struct inode *inode, */ static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size) { - struct netfs_i_context *ctx = netfs_i_context(inode); + struct netfs_inode *ctx = netfs_inode(inode); ctx->remote_i_size = new_i_size; } @@ -352,7 +343,7 @@ static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size) static inline struct fscache_cookie *netfs_i_cookie(struct inode *inode) { #if IS_ENABLED(CONFIG_FSCACHE) - struct netfs_i_context *ctx = netfs_i_context(inode); + struct netfs_inode *ctx = netfs_inode(inode); return ctx->cache; #else return NULL; -- cgit v1.2.3 From b489a6e5871690735752f8875f411e4d0cd8e5df Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 8 Jun 2022 18:34:25 +0300 Subject: tls: Rename TLS_INFO_ZC_SENDFILE to TLS_INFO_ZC_TX To embrace possible future optimizations of TLS, rename zerocopy sendfile definitions to more generic ones: * setsockopt: TLS_TX_ZEROCOPY_SENDFILE- > TLS_TX_ZEROCOPY_RO * sock_diag: TLS_INFO_ZC_SENDFILE -> TLS_INFO_ZC_RO_TX RO stands for readonly and emphasizes that the application shouldn't modify the data being transmitted with zerocopy to avoid potential disconnection. Fixes: c1318b39c7d3 ("tls: Add opt-in zerocopy mode of sendfile()") Signed-off-by: Maxim Mikityanskiy Link: https://lore.kernel.org/r/20220608153425.3151146-1-maximmi@nvidia.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/tls.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index ac39328eabe7..bb8f80812b0b 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -39,7 +39,7 @@ /* TLS socket options */ #define TLS_TX 1 /* Set transmit parameters */ #define TLS_RX 2 /* Set receive parameters */ -#define TLS_TX_ZEROCOPY_SENDFILE 3 /* transmit zerocopy sendfile */ +#define TLS_TX_ZEROCOPY_RO 3 /* TX zerocopy (only sendfile now) */ /* Supported versions */ #define TLS_VERSION_MINOR(ver) ((ver) & 0xFF) @@ -161,7 +161,7 @@ enum { TLS_INFO_CIPHER, TLS_INFO_TXCONF, TLS_INFO_RXCONF, - TLS_INFO_ZC_SENDFILE, + TLS_INFO_ZC_RO_TX, __TLS_INFO_MAX, }; #define TLS_INFO_MAX (__TLS_INFO_MAX - 1) -- cgit v1.2.3 From 39e0f991a62ed5efabd20711a7b6e7da92603170 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 7 Jun 2022 17:00:16 +0200 Subject: random: mark bootloader randomness code as __init add_bootloader_randomness() and the variables it touches are only used during __init and not after, so mark these as __init. At the same time, unexport this, since it's only called by other __init code that's built-in. Cc: stable@vger.kernel.org Fixes: 428826f5358c ("fdt: add support for rng-seed") Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index fae0c84027fd..223b4bd584e7 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -13,7 +13,7 @@ struct notifier_block; void add_device_randomness(const void *buf, size_t len); -void add_bootloader_randomness(const void *buf, size_t len); +void __init add_bootloader_randomness(const void *buf, size_t len); void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; void add_interrupt_randomness(int irq) __latent_entropy; -- cgit v1.2.3 From e052a478a7daeca67664f7addd308ff51dd40654 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 8 Jun 2022 10:31:25 +0200 Subject: random: remove rng_has_arch_random() With arch randomness being used by every distro and enabled in defconfigs, the distinction between rng_has_arch_random() and rng_is_initialized() is now rather small. In fact, the places where they differ are now places where paranoid users and system builders really don't want arch randomness to be used, in which case we should respect that choice, or places where arch randomness is known to be broken, in which case that choice is all the more important. So this commit just removes the function and its one user. Reviewed-by: Petr Mladek # for vsprintf.c Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 223b4bd584e7..20e389a14e5c 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -74,7 +74,6 @@ static inline unsigned long get_random_canary(void) int __init random_init(const char *command_line); bool rng_is_initialized(void); -bool rng_has_arch_random(void); int wait_for_random_bytes(void); /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). -- cgit v1.2.3 From e81fb4198e27925b151aad1450e0fd607d6733f8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 9 Jun 2022 15:04:01 -0700 Subject: netfs: Further cleanups after struct netfs_inode wrapper introduced Change the signature of netfs helper functions to take a struct netfs_inode pointer rather than a struct inode pointer where appropriate, thereby relieving the need for the network filesystem to convert its internal inode format down to the VFS inode only for netfslib to bounce it back up. For type safety, it's better not to do that (and it's less typing too). Give netfs_write_begin() an extra argument to pass in a pointer to the netfs_inode struct rather than deriving it internally from the file pointer. Note that the ->write_begin() and ->write_end() ops are intended to be replaced in the future by netfslib code that manages this without the need to call in twice for each page. netfs_readpage() and similar are intended to be pointed at directly by the address_space_operations table, so must stick to the signature dictated by the function pointers there. Changes ======= - Updated the kerneldoc comments and documentation [DH]. Signed-off-by: David Howells cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/CAHk-=wgkwKyNmNdKpQkqZ6DnmUL-x9hp0YBnUGjaPFEAdxDTbw@mail.gmail.com/ --- include/linux/netfs.h | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 6dbb4c9ce50d..a62739f3726b 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -277,7 +277,8 @@ struct netfs_cache_ops { struct readahead_control; extern void netfs_readahead(struct readahead_control *); int netfs_read_folio(struct file *, struct folio *); -extern int netfs_write_begin(struct file *, struct address_space *, +extern int netfs_write_begin(struct netfs_inode *, + struct file *, struct address_space *, loff_t, unsigned int, struct folio **, void **); @@ -302,19 +303,17 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode) /** * netfs_inode_init - Initialise a netfslib inode context - * @inode: The inode with which the context is associated + * @inode: The netfs inode to initialise * @ops: The netfs's operations list * * Initialise the netfs library context struct. This is expected to follow on * directly from the VFS inode struct. */ -static inline void netfs_inode_init(struct inode *inode, +static inline void netfs_inode_init(struct netfs_inode *ctx, const struct netfs_request_ops *ops) { - struct netfs_inode *ctx = netfs_inode(inode); - ctx->ops = ops; - ctx->remote_i_size = i_size_read(inode); + ctx->remote_i_size = i_size_read(&ctx->inode); #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif @@ -322,28 +321,25 @@ static inline void netfs_inode_init(struct inode *inode, /** * netfs_resize_file - Note that a file got resized - * @inode: The inode being resized + * @ctx: The netfs inode being resized * @new_i_size: The new file size * * Inform the netfs lib that a file got resized so that it can adjust its state. */ -static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size) +static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size) { - struct netfs_inode *ctx = netfs_inode(inode); - ctx->remote_i_size = new_i_size; } /** * netfs_i_cookie - Get the cache cookie from the inode - * @inode: The inode to query + * @ctx: The netfs inode to query * * Get the caching cookie (if enabled) from the network filesystem's inode. */ -static inline struct fscache_cookie *netfs_i_cookie(struct inode *inode) +static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx) { #if IS_ENABLED(CONFIG_FSCACHE) - struct netfs_inode *ctx = netfs_inode(inode); return ctx->cache; #else return NULL; -- cgit v1.2.3 From 40a81101202300df7db273f77dda9fbe6271b1d2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 25 Feb 2022 11:19:14 +0000 Subject: netfs: Rename the netfs_io_request cleanup op and give it an op pointer The netfs_io_request cleanup op is now always in a position to be given a pointer to a netfs_io_request struct, so this can be passed in instead of the mapping and private data arguments (both of which are included in the struct). So rename the ->cleanup op to ->free_request (to match ->init_request) and pass in the I/O pointer. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com --- include/linux/netfs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index a62739f3726b..097cdd644665 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -206,7 +206,9 @@ struct netfs_io_request { */ struct netfs_request_ops { int (*init_request)(struct netfs_io_request *rreq, struct file *file); + void (*free_request)(struct netfs_io_request *rreq); int (*begin_cache_operation)(struct netfs_io_request *rreq); + void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); void (*issue_read)(struct netfs_io_subrequest *subreq); @@ -214,7 +216,6 @@ struct netfs_request_ops { int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio *folio, void **_fsdata); void (*done)(struct netfs_io_request *rreq); - void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; /* -- cgit v1.2.3 From 8bee9dd953b69c634d1c9a3241a8b357469ad4aa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Fri, 10 Jun 2022 01:41:10 +0200 Subject: workqueue: Switch to new kerneldoc syntax for named variable macro argument MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The syntax without dots is available since commit 43756e347f21 ("scripts/kernel-doc: Add support for named variable macro arguments"). The same HTML output is produced with and without this patch. Signed-off-by: Jonathan Neuschäfer Acked-by: Tejun Heo Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index e1f1c8b1121b..62e75dd40d9a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -406,7 +406,7 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) - * @args...: args for @fmt + * @args: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are -- cgit v1.2.3