From fa96b24204af42274ec13dfb2f2e6990d7510e55 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 5 Aug 2022 14:48:14 -0700 Subject: btf: Add a new kfunc flag which allows to mark a function to be sleepable This allows to declare a kfunc as sleepable and prevents its use in a non sleepable program. Signed-off-by: Benjamin Tissoires Co-developed-by: Yosry Ahmed Signed-off-by: Yosry Ahmed Signed-off-by: Hao Luo Link: https://lore.kernel.org/r/20220805214821.1058337-2-haoluo@google.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index cdb376d53238..976cbdd2981f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -49,6 +49,7 @@ * for this case. */ #define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */ +#define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ struct btf; struct btf_member; -- cgit v1.2.3 From c8996c98f703b09afe77a1d247dae691c9849dc1 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Aug 2022 08:08:02 +0200 Subject: bpf: Add BPF-helper for accessing CLOCK_TAI Commit 3dc6ffae2da2 ("timekeeping: Introduce fast accessor to clock tai") introduced a fast and NMI-safe accessor for CLOCK_TAI. Especially in time sensitive networks (TSN), where all nodes are synchronized by Precision Time Protocol (PTP), it's helpful to have the possibility to generate timestamps based on CLOCK_TAI instead of CLOCK_MONOTONIC. With a BPF helper for TAI in place, it becomes very convenient to correlate activity across different machines in the network. Use cases for such a BPF helper include functionalities such as Tx launch time (e.g. ETF and TAPRIO Qdiscs) and timestamping. Note: CLOCK_TAI is nothing new per se, only the NMI-safe variant of it is. Signed-off-by: Jesper Dangaard Brouer [Kurt: Wrote changelog and renamed helper] Signed-off-by: Kurt Kanzenbach Link: https://lore.kernel.org/r/20220809060803.5773-2-kurt@linutronix.de Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 20c26aed7896..a627a02cf8ab 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2349,6 +2349,7 @@ extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; +extern const struct bpf_func_proto bpf_ktime_get_tai_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; -- cgit v1.2.3 From 4dd48c6f1f83290d4bc61b43e61d86f8bc6c310e Mon Sep 17 00:00:00 2001 From: Artem Savkov Date: Wed, 10 Aug 2022 08:59:03 +0200 Subject: bpf: add destructive kfunc flag Add KF_DESTRUCTIVE flag for destructive functions. Functions with this flag set will require CAP_SYS_BOOT capabilities. Signed-off-by: Artem Savkov Link: https://lore.kernel.org/r/20220810065905.475418-2-asavkov@redhat.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 976cbdd2981f..ad93c2d9cc1c 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -49,7 +49,8 @@ * for this case. */ #define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */ -#define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ +#define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ +#define KF_DESTRUCTIVE (1 << 6) /* kfunc performs destructive actions */ struct btf; struct btf_member; -- cgit v1.2.3 From 0630f64d25a0f0a8c6a9ce9fde8750b3b561e6f5 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 15 Aug 2022 12:07:47 -0700 Subject: net: phy: broadcom: Implement suspend/resume for AC131 and BCM5241 Implement the suspend/resume procedure for the Broadcom AC131 and BCM5241 type of PHYs (10/100 only) by entering the standard power down followed by the proprietary standby mode in the auxiliary mode 4 shadow register. On resume, the PHY software reset is enough to make it come out of standby mode so we can utilize brcm_fet_config_init() as the resume hook. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6ff567ece34a..9e77165f3ef6 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -293,6 +293,7 @@ #define MII_BRCM_FET_SHDW_MC_FAME 0x4000 /* Force Auto MDIX enable */ #define MII_BRCM_FET_SHDW_AUXMODE4 0x1a /* Auxiliary mode 4 */ +#define MII_BRCM_FET_SHDW_AM4_STANDBY 0x0008 /* Standby enable */ #define MII_BRCM_FET_SHDW_AM4_LED_MASK 0x0003 #define MII_BRCM_FET_SHDW_AM4_LED_MODE1 0x0001 -- cgit v1.2.3 From e34cfee65ec891a319ce79797dda18083af33a76 Mon Sep 17 00:00:00 2001 From: Wong Vee Khee Date: Wed, 17 Aug 2022 14:43:24 +0800 Subject: stmmac: intel: remove unused 'has_crossts' flag The 'has_crossts' flag was not used anywhere in the stmmac driver, removing it from both header file and dwmac-intel driver. Signed-off-by: Wong Vee Khee Reviewed-by: Kurt Kanzenbach Link: https://lore.kernel.org/r/20220817064324.10025-1-veekhee@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/stmmac.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 8df475db88c0..fb2e88614f5d 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -257,7 +257,6 @@ struct plat_stmmacenet_data { u8 vlan_fail_q; unsigned int eee_usecs_rate; struct pci_dev *pdev; - bool has_crossts; int int_snapshot_num; int ext_snapshot_num; bool int_snapshot_en; -- cgit v1.2.3 From 24426654ed3ae83d1127511891fb782c54f49203 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 16 Aug 2022 23:17:17 -0700 Subject: bpf: net: Avoid sk_setsockopt() taking sk lock when called from bpf Most of the code in bpf_setsockopt(SOL_SOCKET) are duplicated from the sk_setsockopt(). The number of supported optnames are increasing ever and so as the duplicated code. One issue in reusing sk_setsockopt() is that the bpf prog has already acquired the sk lock. This patch adds a has_current_bpf_ctx() to tell if the sk_setsockopt() is called from a bpf prog. The bpf prog calling bpf_setsockopt() is either running in_task() or in_serving_softirq(). Both cases have the current->bpf_ctx initialized. Thus, the has_current_bpf_ctx() only needs to test !!current->bpf_ctx. This patch also adds sockopt_{lock,release}_sock() helpers for sk_setsockopt() to use. These helpers will test has_current_bpf_ctx() before acquiring/releasing the lock. They are in EXPORT_SYMBOL for the ipv6 module to use in a latter patch. Note on the change in sock_setbindtodevice(). sockopt_lock_sock() is done in sock_setbindtodevice() instead of doing the lock_sock in sock_bindtoindex(..., lock_sk = true). Reviewed-by: Stanislav Fomichev Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220817061717.4175589-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a627a02cf8ab..39bd36359c1e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1966,6 +1966,15 @@ static inline bool unprivileged_ebpf_enabled(void) return !sysctl_unprivileged_bpf_disabled; } +/* Not all bpf prog type has the bpf_ctx. + * For the bpf prog type that has initialized the bpf_ctx, + * this function can be used to decide if a kernel function + * is called by a bpf program. + */ +static inline bool has_current_bpf_ctx(void) +{ + return !!current->bpf_ctx; +} #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -2175,6 +2184,10 @@ static inline bool unprivileged_ebpf_enabled(void) return false; } +static inline bool has_current_bpf_ctx(void) +{ + return false; +} #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, -- cgit v1.2.3 From 5e61fe157a27afc7c0d4f7bcbceefdca536c015f Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 17 Aug 2022 14:32:52 +0200 Subject: net: phy: Introduce QUSGMII PHY mode The QUSGMII mode is a derivative of Cisco's USXGMII standard. This standard is pretty similar to SGMII, but allows for faster speeds, and has the build-in bits for Quad and Octa variants (like QSGMII). The main difference with SGMII/QSGMII is that USXGMII/QUSGMII re-uses the preamble to carry various information, named 'Extensions'. As of today, the USXGMII standard only mentions the "PCH" extension, which is used to convey timestamps, allowing in-band signaling of PTP timestamps without having to modify the frame itself. This commit adds support for that mode. When no extension is in use, it behaves exactly like QSGMII, although it's not compatible with QSGMII. Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 87638c55d844..9eeab9b9a74c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -115,6 +115,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_25GBASER: 25G BaseR * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN + * @PHY_INTERFACE_MODE_QUSGMII: Quad Universal SGMII * @PHY_INTERFACE_MODE_MAX: Book keeping * * Describes the interface between the MAC and PHY. @@ -152,6 +153,7 @@ typedef enum { PHY_INTERFACE_MODE_USXGMII, /* 10GBASE-KR - with Clause 73 AN */ PHY_INTERFACE_MODE_10GKR, + PHY_INTERFACE_MODE_QUSGMII, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -267,6 +269,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "10gbase-kr"; case PHY_INTERFACE_MODE_100BASEX: return "100base-x"; + case PHY_INTERFACE_MODE_QUSGMII: + return "qusgmii"; default: return "unknown"; } -- cgit v1.2.3 From c04ade27cb7b952b6b9b9a0efa0a6129cc63f2ae Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 17 Aug 2022 14:32:54 +0200 Subject: net: phy: Add helper to derive the number of ports from a phy mode Some phy modes such as QSGMII multiplex several MAC<->PHY links on one single physical interface. QSGMII used to be the only one supported, but other modes such as QUSGMII also carry multiple links. This helper allows getting the number of links that are multiplexed on a given interface. Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9eeab9b9a74c..7c49ab95441b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -968,6 +968,8 @@ struct phy_fixup { const char *phy_speed_to_str(int speed); const char *phy_duplex_to_str(unsigned int duplex); +int phy_interface_num_ports(phy_interface_t interface); + /* A structure for mapping a particular speed and duplex * combination to a particular SUPPORTED and ADVERTISED value */ -- cgit v1.2.3 From 1202cdd665315c525b5237e96e0bedc76d7e754f Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Wed, 17 Aug 2022 17:43:21 -0700 Subject: Remove DECnet support from kernel DECnet is an obsolete network protocol that receives more attention from kernel janitors than users. It belongs in computer protocol history museum not in Linux kernel. It has been "Orphaned" in kernel since 2010. The iproute2 support for DECnet was dropped in 5.0 release. The documentation link on Sourceforge says it is abandoned there as well. Leave the UAPI alone to keep userspace programs compiling. This means that there is still an empty neighbour table for AF_DECNET. The table of /proc/sys/net entries was updated to match current directories and reformatted to be alphabetical. Signed-off-by: Stephen Hemminger Acked-by: David Ahern Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ---- include/linux/netfilter.h | 5 ----- include/linux/netfilter_defs.h | 8 -------- 3 files changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1a3cb93c3dcc..64e8662632f8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1837,7 +1837,6 @@ enum netdev_ml_priv_type { * @tipc_ptr: TIPC specific data * @atalk_ptr: AppleTalk link * @ip_ptr: IPv4 specific data - * @dn_ptr: DECnet specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering @@ -2133,9 +2132,6 @@ struct net_device { #if IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; #endif -#if IS_ENABLED(CONFIG_DECNET) - struct dn_dev __rcu *dn_ptr; -#endif #if IS_ENABLED(CONFIG_AX25) void *ax25_ptr; #endif diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index c2c6f332fb90..d8817d381c14 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -243,11 +243,6 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, hook_head = rcu_dereference(net->nf.hooks_bridge[hook]); #endif break; -#if IS_ENABLED(CONFIG_DECNET) - case NFPROTO_DECNET: - hook_head = rcu_dereference(net->nf.hooks_decnet[hook]); - break; -#endif default: WARN_ON_ONCE(1); break; diff --git a/include/linux/netfilter_defs.h b/include/linux/netfilter_defs.h index 8dddfb151f00..a5f7bef1b3a4 100644 --- a/include/linux/netfilter_defs.h +++ b/include/linux/netfilter_defs.h @@ -7,14 +7,6 @@ /* in/out/forward only */ #define NF_ARP_NUMHOOKS 3 -/* max hook is NF_DN_ROUTE (6), also see uapi/linux/netfilter_decnet.h */ -#define NF_DN_NUMHOOKS 7 - -#if IS_ENABLED(CONFIG_DECNET) -/* Largest hook number + 1, see uapi/linux/netfilter_decnet.h */ -#define NF_MAX_HOOKS NF_DN_NUMHOOKS -#else #define NF_MAX_HOOKS NF_INET_NUMHOOKS -#endif #endif -- cgit v1.2.3 From 0ba985024ae7db226776725d9aa436b5c1c9fca2 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Sun, 21 Aug 2022 14:35:16 +0300 Subject: flow_dissector: Make 'bpf_flow_dissect' return the bpf program retcode Let 'bpf_flow_dissect' callers know the BPF program's retcode and act accordingly. Signed-off-by: Shmulik Ladkani Signed-off-by: Daniel Borkmann Reviewed-by: Stanislav Fomichev Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20220821113519.116765-2-shmulik.ladkani@gmail.com --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ca8afa382bf2..87921996175c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1460,8 +1460,8 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, unsigned int key_count); struct bpf_flow_dissector; -bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, - __be16 proto, int nhoff, int hlen, unsigned int flags); +u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, + __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, -- cgit v1.2.3 From dea6a4e17013382b20717664ebf3d7cc405e0952 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 23 Aug 2022 15:25:51 -0700 Subject: bpf: Introduce cgroup_{common,current}_func_proto Split cgroup_base_func_proto into the following: * cgroup_common_func_proto - common helpers for all cgroup hooks * cgroup_current_func_proto - common helpers for all cgroup hooks running in the process context (== have meaningful 'current'). Move bpf_{g,s}et_retval and other cgroup-related helpers into kernel/bpf/cgroup.c so they closer to where they are being used. Signed-off-by: Stanislav Fomichev Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220823222555.523590-2-sdf@google.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf-cgroup.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 2bd1b5f8de9b..57e9e109257e 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -414,6 +414,11 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr, int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); + +const struct bpf_func_proto * +cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); +const struct bpf_func_proto * +cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); #else static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } @@ -444,6 +449,18 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } +static inline const struct bpf_func_proto * +cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return NULL; +} + +static inline const struct bpf_func_proto * +cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return NULL; +} + static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( -- cgit v1.2.3 From bed89185af0de0d417e29ca1798df50f161b0231 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 23 Aug 2022 15:25:52 -0700 Subject: bpf: Use cgroup_{common,current}_func_proto in more hooks The following hooks are per-cgroup hooks but they are not using cgroup_{common,current}_func_proto, fix it: * BPF_PROG_TYPE_CGROUP_SKB (cg_skb) * BPF_PROG_TYPE_CGROUP_SOCK_ADDR (cg_sock_addr) * BPF_PROG_TYPE_CGROUP_SOCK (cg_sock) * BPF_PROG_TYPE_LSM+BPF_LSM_CGROUP Also: * move common func_proto's into cgroup func_proto handlers * make sure bpf_{g,s}et_retval are not accessible from recvmsg, getpeername and getsockname (return/errno is ignored in these places) * as a side effect, expose get_current_pid_tgid, get_current_comm_proto, get_current_ancestor_cgroup_id, get_cgroup_classid to more cgroup hooks Acked-by: Martin KaFai Lau Signed-off-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20220823222555.523590-3-sdf@google.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 39bd36359c1e..99fc7a64564f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2375,6 +2375,7 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto; +extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto; extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; -- cgit v1.2.3 From c205cc7534a97f2d6fbd2a23a94ed7c036c6e2aa Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 21 Aug 2022 13:18:58 +0800 Subject: net: skb: prevent the split of kfree_skb_reason() by gcc Sometimes, gcc will optimize the function by spliting it to two or more functions. In this case, kfree_skb_reason() is splited to kfree_skb_reason and kfree_skb_reason.part.0. However, the function/tracepoint trace_kfree_skb() in it needs the return address of kfree_skb_reason(). This split makes the call chains becomes: kfree_skb_reason() -> kfree_skb_reason.part.0 -> trace_kfree_skb() which makes the return address that passed to trace_kfree_skb() be kfree_skb(). Therefore, introduce '__fix_address', which is the combination of '__noclone' and 'noinline', and apply it to kfree_skb_reason() to prevent to from being splited or made inline. (Is it better to simply apply '__noclone oninline' to kfree_skb_reason? I'm thinking maybe other functions have the same problems) Meanwhile, wrap 'skb_unref()' with 'unlikely()', as the compiler thinks it is likely return true and splits kfree_skb_reason(). Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/compiler_attributes.h | 7 +++++++ include/linux/skbuff.h | 3 ++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 445e80517cab..fc93c9488c76 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -371,4 +371,11 @@ */ #define __weak __attribute__((__weak__)) +/* + * Used by functions that use '__builtin_return_address'. These function + * don't want to be splited or made inline, which can make + * the '__builtin_return_address' get unexpected address. + */ +#define __fix_address noinline __noclone + #endif /* __LINUX_COMPILER_ATTRIBUTES_H */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ca8afa382bf2..b51d07a727c9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1195,7 +1195,8 @@ static inline bool skb_unref(struct sk_buff *skb) return true; } -void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); +void __fix_address +kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason -- cgit v1.2.3 From 9d9d00ac29d0ef7ce426964de46fa6b380357d0a Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 23 Aug 2022 03:31:25 +0200 Subject: bpf: Fix reference state management for synchronous callbacks Currently, verifier verifies callback functions (sync and async) as if they will be executed once, (i.e. it explores execution state as if the function was being called once). The next insn to explore is set to start of subprog and the exit from nested frame is handled using curframe > 0 and prepare_func_exit. In case of async callback it uses a customized variant of push_stack simulating a kind of branch to set up custom state and execution context for the async callback. While this approach is simple and works when callback really will be executed only once, it is unsafe for all of our current helpers which are for_each style, i.e. they execute the callback multiple times. A callback releasing acquired references of the caller may do so multiple times, but currently verifier sees it as one call inside the frame, which then returns to caller. Hence, it thinks it released some reference that the cb e.g. got access through callback_ctx (register filled inside cb from spilled typed register on stack). Similarly, it may see that an acquire call is unpaired inside the callback, so the caller will copy the reference state of callback and then will have to release the register with new ref_obj_ids. But again, the callback may execute multiple times, but the verifier will only account for acquired references for a single symbolic execution of the callback, which will cause leaks. Note that for async callback case, things are different. While currently we have bpf_timer_set_callback which only executes it once, even for multiple executions it would be safe, as reference state is NULL and check_reference_leak would force program to release state before BPF_EXIT. The state is also unaffected by analysis for the caller frame. Hence async callback is safe. Since we want the reference state to be accessible, e.g. for pointers loaded from stack through callback_ctx's PTR_TO_STACK, we still have to copy caller's reference_state to callback's bpf_func_state, but we enforce that whatever references it adds to that reference_state has been released before it hits BPF_EXIT. This requires introducing a new callback_ref member in the reference state to distinguish between caller vs callee references. Hence, check_reference_leak now errors out if it sees we are in callback_fn and we have not released callback_ref refs. Since there can be multiple nested callbacks, like frame 0 -> cb1 -> cb2 etc. we need to also distinguish between whether this particular ref belongs to this callback frame or parent, and only error for our own, so we store state->frameno (which is always non-zero for callbacks). In short, callbacks can read parent reference_state, but cannot mutate it, to be able to use pointers acquired by the caller. They must only undo their changes (by releasing their own acquired_refs before BPF_EXIT) on top of caller reference_state before returning (at which point the caller and callback state will match anyway, so no need to copy it back to caller). Fixes: 69c087ba6225 ("bpf: Add bpf_for_each_map_elem() helper") Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220823013125.24938-1-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 2e3bad8640dc..1fdddbf3546b 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -212,6 +212,17 @@ struct bpf_reference_state { * is used purely to inform the user of a reference leak. */ int insn_idx; + /* There can be a case like: + * main (frame 0) + * cb (frame 1) + * func (frame 3) + * cb (frame 4) + * Hence for frame 4, if callback_ref just stored boolean, it would be + * impossible to distinguish nested callback refs. Hence store the + * frameno and compare that to callback_ref in check_reference_leak when + * exiting a callback function. + */ + int callback_ref; }; /* state of the program: -- cgit v1.2.3 From ea5cba269fb1fe22b84f4d01bb3d56320e6ffa3e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 16 Aug 2022 11:26:23 +0200 Subject: wifi: cfg80211/mac80211: check EHT capability size correctly For AP/non-AP the EHT MCS/NSS subfield size differs, the 4-octet subfield is only used for 20 MHz-only non-AP STA. Pass an argument around everywhere to be able to parse it properly. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 55e6f4ad0ca6..6f70394417ac 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2886,7 +2886,8 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) /* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */ static inline u8 ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap, - const struct ieee80211_eht_cap_elem_fixed *eht_cap) + const struct ieee80211_eht_cap_elem_fixed *eht_cap, + bool from_ap) { u8 count = 0; @@ -2907,7 +2908,10 @@ ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap, if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) count += 3; - return count ? count : 4; + if (count) + return count; + + return from_ap ? 3 : 4; } /* 802.11be EHT PPE Thresholds */ @@ -2943,7 +2947,8 @@ ieee80211_eht_ppe_size(u16 ppe_thres_hdr, const u8 *phy_cap_info) } static inline bool -ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len) +ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len, + bool from_ap) { const struct ieee80211_eht_cap_elem_fixed *elem = (const void *)data; u8 needed = sizeof(struct ieee80211_eht_cap_elem_fixed); @@ -2952,7 +2957,8 @@ ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len) return false; needed += ieee80211_eht_mcs_nss_size((const void *)he_capa, - (const void *)data); + (const void *)data, + from_ap); if (len < needed) return false; -- cgit v1.2.3 From d4ccaf58a8472123ac97e6db03932c375b5c45ba Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Wed, 24 Aug 2022 16:31:13 -0700 Subject: bpf: Introduce cgroup iter Cgroup_iter is a type of bpf_iter. It walks over cgroups in four modes: - walking a cgroup's descendants in pre-order. - walking a cgroup's descendants in post-order. - walking a cgroup's ancestors. - process only the given cgroup. When attaching cgroup_iter, one can set a cgroup to the iter_link created from attaching. This cgroup is passed as a file descriptor or cgroup id and serves as the starting point of the walk. If no cgroup is specified, the starting point will be the root cgroup v2. For walking descendants, one can specify the order: either pre-order or post-order. For walking ancestors, the walk starts at the specified cgroup and ends at the root. One can also terminate the walk early by returning 1 from the iter program. Note that because walking cgroup hierarchy holds cgroup_mutex, the iter program is called with cgroup_mutex held. Currently only one session is supported, which means, depending on the volume of data bpf program intends to send to user space, the number of cgroups that can be walked is limited. For example, given the current buffer size is 8 * PAGE_SIZE, if the program sends 64B data for each cgroup, assuming PAGE_SIZE is 4kb, the total number of cgroups that can be walked is 512. This is a limitation of cgroup_iter. If the output data is larger than the kernel buffer size, after all data in the kernel buffer is consumed by user space, the subsequent read() syscall will signal EOPNOTSUPP. In order to work around, the user may have to update their program to reduce the volume of data sent to output. For example, skip some uninteresting cgroups. In future, we may extend bpf_iter flags to allow customizing buffer size. Acked-by: Yonghong Song Acked-by: Tejun Heo Signed-off-by: Hao Luo Link: https://lore.kernel.org/r/20220824233117.1312810-2-haoluo@google.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 99fc7a64564f..9c1674973e03 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -48,6 +48,7 @@ struct mem_cgroup; struct module; struct bpf_func_state; struct ftrace_ops; +struct cgroup; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -1730,7 +1731,14 @@ int bpf_obj_get_user(const char __user *pathname, int flags); int __init bpf_iter_ ## target(args) { return 0; } struct bpf_iter_aux_info { + /* for map_elem iter */ struct bpf_map *map; + + /* for cgroup iter */ + struct { + struct cgroup *start; /* starting cgroup */ + enum bpf_cgroup_iter_order order; + } cgroup; }; typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, -- cgit v1.2.3 From b9030780971b56c0c455c3b66244efd96608846d Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Mon, 22 Aug 2022 16:32:43 +0200 Subject: netdev: Use try_cmpxchg in napi_if_scheduled_mark_missed Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old in napi_if_scheduled_mark_missed. x86 CMPXCHG instruction returns success in ZF flag, so this change saves a compare after cmpxchg (and related move instruction in front of cmpxchg). Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg fails, enabling further code simplifications. Cc: Eric Dumazet Cc: Paolo Abeni Signed-off-by: Uros Bizjak Link: https://lore.kernel.org/r/20220822143243.2798-1-ubizjak@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 64e8662632f8..8839abc1f941 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -546,8 +546,8 @@ static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) { unsigned long val, new; + val = READ_ONCE(n->state); do { - val = READ_ONCE(n->state); if (val & NAPIF_STATE_DISABLE) return true; @@ -555,7 +555,7 @@ static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) return false; new = val | NAPIF_STATE_MISSED; - } while (cmpxchg(&n->state, val, new) != val); + } while (!try_cmpxchg(&n->state, &val, new)); return true; } -- cgit v1.2.3 From 9c5d03d362519f36cd551aec596388f895c93d2d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Aug 2022 17:18:30 -0700 Subject: genetlink: start to validate reserved header bytes We had historically not checked that genlmsghdr.reserved is 0 on input which prevents us from using those precious bytes in the future. One use case would be to extend the cmd field, which is currently just 8 bits wide and 256 is not a lot of commands for some core families. To make sure that new families do the right thing by default put the onus of opting out of validation on existing families. Signed-off-by: Jakub Kicinski Acked-by: Paul Moore (NetLabel) Signed-off-by: David S. Miller --- include/linux/genl_magic_func.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 939b1a8f571b..4a4b387181ad 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -294,6 +294,7 @@ static struct genl_family ZZZ_genl_family __ro_after_init = { .ops = ZZZ_genl_ops, .n_ops = ARRAY_SIZE(ZZZ_genl_ops), .mcgrps = ZZZ_genl_mcgrps, + .resv_start_op = 42, /* drbd is currently the only user */ .n_mcgrps = ARRAY_SIZE(ZZZ_genl_mcgrps), .module = THIS_MODULE, }; -- cgit v1.2.3 From e8013f8edaa30e17fd583a326daff1fa86b75c82 Mon Sep 17 00:00:00 2001 From: Casper Andersson Date: Thu, 25 Aug 2022 11:28:35 +0200 Subject: ethernet: Add helpers to recognize addresses mapped to IP multicast IP multicast must sometimes be discriminated from non-IP multicast, e.g. when determining the forwarding behavior of a given group in the presence of multicast router ports on an offloaded bridge. Therefore, provide helpers to identify these groups. Signed-off-by: Casper Andersson Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 92b10e67d5f8..a541f0c4f146 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -428,6 +428,28 @@ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, return true; } +static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) +{ + u8 base[ETH_ALEN] = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; + u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; + + return ether_addr_equal_masked(addr, base, mask); +} + +static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) +{ + u8 base[ETH_ALEN] = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; + u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; + + return ether_addr_equal_masked(addr, base, mask); +} + +static inline bool ether_addr_is_ip_mcast(const u8 *addr) +{ + return ether_addr_is_ipv4_mcast(addr) || + ether_addr_is_ipv6_mcast(addr); +} + /** * ether_addr_to_u64 - Convert an Ethernet address into a u64 value. * @addr: Pointer to a six-byte array containing the Ethernet address -- cgit v1.2.3 From 690252f19f0e486abb8590b3a7a03d4e065d93d4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 25 Aug 2022 20:09:31 -0700 Subject: netlink: add support for ext_ack missing attributes There is currently no way to report via extack in a structured way that an attribute is missing. This leads to families resorting to string messages. Add a pair of attributes - @offset and @type for machine-readable way of reporting missing attributes. The @offset points to the nest which should have contained the attribute, @type is the expected nla_type. The offset will be skipped if the attribute is missing at the message level rather than inside a nest. User space should be able to figure out which attribute enum (AKA attribute space AKA attribute set) the nest pointed to by @offset is using. Reviewed-by: Johannes Berg Signed-off-by: Jakub Kicinski Signed-off-by: Paolo Abeni --- include/linux/netlink.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index bda1c385cffb..1619221c415c 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -71,6 +71,8 @@ netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg) * %NL_SET_ERR_MSG * @bad_attr: attribute with error * @policy: policy for a bad attribute + * @miss_type: attribute type which was missing + * @miss_nest: nest missing an attribute (%NULL if missing top level attr) * @cookie: cookie data to return to userspace (for success) * @cookie_len: actual cookie data length */ @@ -78,6 +80,8 @@ struct netlink_ext_ack { const char *_msg; const struct nlattr *bad_attr; const struct nla_policy *policy; + const struct nlattr *miss_nest; + u16 miss_type; u8 cookie[NETLINK_MAX_COOKIE_LEN]; u8 cookie_len; }; @@ -126,6 +130,15 @@ struct netlink_ext_ack { #define NL_SET_ERR_MSG_ATTR(extack, attr, msg) \ NL_SET_ERR_MSG_ATTR_POL(extack, attr, NULL, msg) +#define NL_SET_ERR_ATTR_MISS(extack, nest, type) do { \ + struct netlink_ext_ack *__extack = (extack); \ + \ + if (__extack) { \ + __extack->miss_nest = (nest); \ + __extack->miss_type = (type); \ + } \ +} while (0) + static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, u64 cookie) { -- cgit v1.2.3 From 45dca15759643806660e9285e6af8a1ba3c76c82 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 25 Aug 2022 20:09:32 -0700 Subject: netlink: add helpers for extack attr presence checking Being able to check attribute presence and set extack if not on one line is handy, add helpers. Reviewed-by: Johannes Berg Signed-off-by: Jakub Kicinski Signed-off-by: Paolo Abeni --- include/linux/netlink.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 1619221c415c..d51e041d2242 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -139,6 +139,17 @@ struct netlink_ext_ack { } \ } while (0) +#define NL_REQ_ATTR_CHECK(extack, nest, tb, type) ({ \ + struct nlattr **__tb = (tb); \ + u32 __attr = (type); \ + int __retval; \ + \ + __retval = !__tb[__attr]; \ + if (__retval) \ + NL_SET_ERR_ATTR_MISS((extack), (nest), __attr); \ + __retval; \ +}) + static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, u64 cookie) { -- cgit v1.2.3 From f9cad07b840ec8a8eb54928908d694b6e262631c Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 30 Aug 2022 18:32:47 +0300 Subject: thunderbolt: Show link type for XDomain connections too Following what we do for routers already, extend this to XDomain connections as well. This will show in sysfs whether the link is in USB4 or Thunderbolt mode. Signed-off-by: Mika Westerberg Signed-off-by: David S. Miller --- include/linux/thunderbolt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 9f442d73f3df..90cd08ab2f5d 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -187,6 +187,7 @@ void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir); * @device_name: Name of the device (or %NULL if not known) * @link_speed: Speed of the link in Gb/s * @link_width: Width of the link (1 or 2) + * @link_usb4: Downstream link is USB4 * @is_unplugged: The XDomain is unplugged * @needs_uuid: If the XDomain does not have @remote_uuid it will be * queried first @@ -234,6 +235,7 @@ struct tb_xdomain { const char *device_name; unsigned int link_speed; unsigned int link_width; + bool link_usb4; bool is_unplugged; bool needs_uuid; struct ida service_ids; -- cgit v1.2.3 From 977f1aa5e4d1942bc8012bf3f0e695008979ff4e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 31 Aug 2022 18:44:27 +0000 Subject: net: bql: add more documentation Add some documentation for netdev_tx_sent_queue() and netdev_tx_completed_queue() Stating that netdev_tx_completed_queue() must be called once per TX completion round is apparently not obvious for everybody. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eec35f9b6616..cfe41c053e11 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3353,6 +3353,16 @@ static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_qu #endif } +/** + * netdev_tx_sent_queue - report the number of bytes queued to a given tx queue + * @dev_queue: network device queue + * @bytes: number of bytes queued to the device queue + * + * Report the number of bytes queued for sending/completion to the network + * device hardware queue. @bytes should be a good approximation and should + * exactly match netdev_completed_queue() @bytes. + * This is typically called once per packet, from ndo_start_xmit(). + */ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, unsigned int bytes) { @@ -3398,13 +3408,14 @@ static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, } /** - * netdev_sent_queue - report the number of bytes queued to hardware - * @dev: network device - * @bytes: number of bytes queued to the hardware device queue + * netdev_sent_queue - report the number of bytes queued to hardware + * @dev: network device + * @bytes: number of bytes queued to the hardware device queue * - * Report the number of bytes queued for sending/completion to the network - * device hardware queue. @bytes should be a good approximation and should - * exactly match netdev_completed_queue() @bytes + * Report the number of bytes queued for sending/completion to the network + * device hardware queue#0. @bytes should be a good approximation and should + * exactly match netdev_completed_queue() @bytes. + * This is typically called once per packet, from ndo_start_xmit(). */ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes) { @@ -3419,6 +3430,15 @@ static inline bool __netdev_sent_queue(struct net_device *dev, xmit_more); } +/** + * netdev_tx_completed_queue - report number of packets/bytes at TX completion. + * @dev_queue: network device queue + * @pkts: number of packets (currently ignored) + * @bytes: number of bytes dequeued from the device queue + * + * Must be called at most once per TX completion round (and not per + * individual packet), so that BQL can adjust its limits appropriately. + */ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, unsigned int pkts, unsigned int bytes) { -- cgit v1.2.3 From c3f760ef128789252e7c4f10d3c1721422dceba9 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 31 Aug 2022 17:00:58 -0700 Subject: net: remove netif_tx_napi_add() All callers are now gone. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cfe41c053e11..f0068c1ff1df 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2569,8 +2569,6 @@ netif_napi_add_tx_weight(struct net_device *dev, netif_napi_add_weight(dev, napi, poll, weight); } -#define netif_tx_napi_add netif_napi_add_tx_weight - /** * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only * @dev: network device -- cgit v1.2.3 From dc84dbbcc97bfb47e0f2b175d816e601b2890c91 Mon Sep 17 00:00:00 2001 From: Shung-Hsi Yu Date: Wed, 31 Aug 2022 11:19:06 +0800 Subject: bpf, tnums: Warn against the usage of tnum_in(tnum_range(), ...) Commit a657182a5c51 ("bpf: Don't use tnum_range on array range checking for poke descriptors") has shown that using tnum_range() as argument to tnum_in() can lead to misleading code that looks like tight bound check when in fact the actual allowed range is much wider. Document such behavior to warn against its usage in general, and suggest some scenario where result can be trusted. Signed-off-by: Shung-Hsi Yu Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/984b37f9fdf7ac36831d2137415a4a915744c1b6.1661462653.git.daniel@iogearbox.net Link: https://www.openwall.com/lists/oss-security/2022/08/26/1 Link: https://lore.kernel.org/bpf/20220831031907.16133-3-shung-hsi.yu@suse.com Link: https://lore.kernel.org/bpf/20220831031907.16133-2-shung-hsi.yu@suse.com --- include/linux/tnum.h | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tnum.h b/include/linux/tnum.h index 498dbcedb451..1c3948a1d6ad 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -21,7 +21,12 @@ struct tnum { struct tnum tnum_const(u64 value); /* A completely unknown value */ extern const struct tnum tnum_unknown; -/* A value that's unknown except that @min <= value <= @max */ +/* An unknown value that is a superset of @min <= value <= @max. + * + * Could include values outside the range of [@min, @max]. + * For example tnum_range(0, 2) is represented by {0, 1, 2, *3*}, + * rather than the intended set of {0, 1, 2}. + */ struct tnum tnum_range(u64 min, u64 max); /* Arithmetic and logical ops */ @@ -73,7 +78,18 @@ static inline bool tnum_is_unknown(struct tnum a) */ bool tnum_is_aligned(struct tnum a, u64 size); -/* Returns true if @b represents a subset of @a. */ +/* Returns true if @b represents a subset of @a. + * + * Note that using tnum_range() as @a requires extra cautions as tnum_in() may + * return true unexpectedly due to tnum limited ability to represent tight + * range, e.g. + * + * tnum_in(tnum_range(0, 2), tnum_const(3)) == true + * + * As a rule of thumb, if @a is explicitly coded rather than coming from + * reg->var_off, it should be in form of tnum_const(), tnum_range(0, 2**n - 1), + * or tnum_range(2**n, 2**(n+1) - 1). + */ bool tnum_in(struct tnum a, struct tnum b); /* Formatting functions. These have snprintf-like semantics: they will write -- cgit v1.2.3 From 4ff09db1b79b98b4a2a7511571c640b76cab3beb Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 1 Sep 2022 17:28:02 -0700 Subject: bpf: net: Change sk_getsockopt() to take the sockptr_t argument This patch changes sk_getsockopt() to take the sockptr_t argument such that it can be used by bpf_getsockopt(SOL_SOCKET) in a latter patch. security_socket_getpeersec_stream() is not changed. It stays with the __user ptr (optval.user and optlen.user) to avoid changes to other security hooks. bpf_getsockopt(SOL_SOCKET) also does not support SO_PEERSEC. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220902002802.2888419-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 3 +-- include/linux/sockptr.h | 5 +++++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index a5f21dc3c432..527ae1d64e27 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -900,8 +900,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); void sk_reuseport_prog_free(struct bpf_prog *prog); int sk_detach_filter(struct sock *sk); -int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, - unsigned int len); +int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len); bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index d45902fb4cad..bae5e2369b4f 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -64,6 +64,11 @@ static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, return 0; } +static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) +{ + return copy_to_sockptr_offset(dst, 0, src, size); +} + static inline void *memdup_sockptr(sockptr_t src, size_t len) { void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); -- cgit v1.2.3 From 728f064cd7ebea8c182e99e6f152c8b4a0a6b071 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 1 Sep 2022 17:28:28 -0700 Subject: bpf: net: Change do_ip_getsockopt() to take the sockptr_t argument Similar to the earlier patch that changes sk_getsockopt() to take the sockptr_t argument. This patch also changes do_ip_getsockopt() to take the sockptr_t argument such that a latter patch can make bpf_getsockopt(SOL_IP) to reuse do_ip_getsockopt(). Note on the change in ip_mc_gsfget(). This function is to return an array of sockaddr_storage in optval. This function is shared between ip_get_mcast_msfilter() and compat_ip_get_mcast_msfilter(). However, the sockaddr_storage is stored at different offset of the optval because of the difference between group_filter and compat_group_filter. Thus, a new 'ss_offset' argument is added to ip_mc_gsfget(). Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220902002828.2890585-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/igmp.h | 4 ++-- include/linux/mroute.h | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 93c262ecbdc9..78890143f079 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -118,9 +118,9 @@ extern int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex); extern int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf,int ifindex); extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, - struct ip_msfilter __user *optval, int __user *optlen); + sockptr_t optval, sockptr_t optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, - struct sockaddr_storage __user *p); + sockptr_t optval, size_t offset); extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 6cbbfe94348c..80b8400ab8b2 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -17,7 +17,7 @@ static inline int ip_mroute_opt(int opt) } int ip_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); -int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); +int ip_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t); int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); int ip_mr_init(void); @@ -29,8 +29,8 @@ static inline int ip_mroute_setsockopt(struct sock *sock, int optname, return -ENOPROTOOPT; } -static inline int ip_mroute_getsockopt(struct sock *sock, int optname, - char __user *optval, int __user *optlen) +static inline int ip_mroute_getsockopt(struct sock *sk, int optname, + sockptr_t optval, sockptr_t optlen) { return -ENOPROTOOPT; } -- cgit v1.2.3 From 6dadbe4bac68309eb46ab0f30e8ff47a789df49a Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 1 Sep 2022 17:28:53 -0700 Subject: bpf: net: Change do_ipv6_getsockopt() to take the sockptr_t argument Similar to the earlier patch that changes sk_getsockopt() to take the sockptr_t argument . This patch also changes do_ipv6_getsockopt() to take the sockptr_t argument such that a latter patch can make bpf_getsockopt(SOL_IPV6) to reuse do_ipv6_getsockopt(). Note on the change in ip6_mc_msfget(). This function is to return an array of sockaddr_storage in optval. This function is shared between ipv6_get_msfilter() and compat_ipv6_get_msfilter(). However, the sockaddr_storage is stored at different offset of the optval because of the difference between group_filter and compat_group_filter. Thus, a new 'ss_offset' argument is added to ip6_mc_msfget(). Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220902002853.2892532-1-kafai@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/mroute6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index bc351a85ce9b..8f2b307fb124 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -27,7 +27,7 @@ struct sock; #ifdef CONFIG_IPV6_MROUTE extern int ip6_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); -extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *); +extern int ip6_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t); extern int ip6_mr_input(struct sk_buff *skb); extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); @@ -42,7 +42,7 @@ static inline int ip6_mroute_setsockopt(struct sock *sock, int optname, static inline int ip6_mroute_getsockopt(struct sock *sock, - int optname, char __user *optval, int __user *optlen) + int optname, sockptr_t optval, sockptr_t optlen) { return -ENOPROTOOPT; } -- cgit v1.2.3 From 4a502cf4d77e12119e7061a05d5789cd3129d185 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Fri, 2 Sep 2022 10:32:03 +0200 Subject: net: pcs: add new PCS driver for altera TSE PCS The Altera Triple Speed Ethernet has a SGMII/1000BaseC PCS that can be integrated in several ways. It can either be part of the TSE MAC's address space, accessed through 32 bits accesses on the mapped mdio device 0, or through a dedicated 16 bits register set. This driver allows using the TSE PCS outside of altera TSE's driver, since it can be used standalone by other MACs. Signed-off-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/pcs-altera-tse.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/linux/pcs-altera-tse.h (limited to 'include/linux') diff --git a/include/linux/pcs-altera-tse.h b/include/linux/pcs-altera-tse.h new file mode 100644 index 000000000000..92ab9f08e835 --- /dev/null +++ b/include/linux/pcs-altera-tse.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Bootlin + * + * Maxime Chevallier + */ + +#ifndef __LINUX_PCS_ALTERA_TSE_H +#define __LINUX_PCS_ALTERA_TSE_H + +struct phylink_pcs; +struct net_device; + +struct phylink_pcs *alt_tse_pcs_create(struct net_device *ndev, + void __iomem *pcs_base, int reg_width); + +#endif /* __LINUX_PCS_ALTERA_TSE_H */ -- cgit v1.2.3 From 8a2dd123f12f69e5373d3103da2c97fc36223e0c Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Mon, 29 Aug 2022 12:06:04 +0300 Subject: RDMA/mlx5: Move function mlx5_core_query_ib_ppcnt() to mlx5_ib This patch doesn't change any functionality, but move one function to mlx5_ib because it is not used by mlx5_core. The actual fix is in the next patch. Reviewed-by: Roi Dayan Signed-off-by: Chris Mi Link: https://lore.kernel.org/r/fd47b9138412bd94ed30f838026cbb4cf3878150.1661763871.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 76d7661e3e63..432bd202e2fe 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1079,8 +1079,6 @@ int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num); void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); -int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev, - u8 port_num, void *out, size_t sz); int mlx5_init_rl_table(struct mlx5_core_dev *dev); void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 05ad5d4581c3c1cc724fe50d4652833fb9f3037b Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Fri, 2 Sep 2022 18:02:39 -0400 Subject: net: phy: Add 1000BASE-KX interface mode Add 1000BASE-KX interface mode. This 1G backplane ethernet as described in clause 70. Clause 73 autonegotiation is mandatory, and only full duplex operation is supported. Although at the PMA level this interface mode is identical to 1000BASE-X, it uses a different form of in-band autonegation. This justifies a separate interface mode, since the interface mode (along with the MLO_AN_* autonegotiation mode) sets the type of autonegotiation which will be used on a link. This results in more than just electrical differences between the link modes. With regard to 1000BASE-X, 1000BASE-KX holds a similar position to SGMII: same signaling, but different autonegotiation. PCS drivers (which typically handle in-band autonegotiation) may only support 1000BASE-X, and not 1000BASE-KX. Similarly, the phy mode is used to configure serdes phys with phy_set_mode_ext. Due to the different electrical standards (SFI or XFI vs Clause 70), they will likely want to use different configuration. Adding a phy interface mode for 1000BASE-KX helps simplify configuration in these areas. Signed-off-by: Sean Anderson Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 7c49ab95441b..337230c135f7 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -116,6 +116,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_QUSGMII: Quad Universal SGMII + * @PHY_INTERFACE_MODE_1000BASEKX: 1000Base-KX - with Clause 73 AN * @PHY_INTERFACE_MODE_MAX: Book keeping * * Describes the interface between the MAC and PHY. @@ -154,6 +155,7 @@ typedef enum { /* 10GBASE-KR - with Clause 73 AN */ PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_QUSGMII, + PHY_INTERFACE_MODE_1000BASEKX, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -251,6 +253,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "trgmii"; case PHY_INTERFACE_MODE_1000BASEX: return "1000base-x"; + case PHY_INTERFACE_MODE_1000BASEKX: + return "1000base-kx"; case PHY_INTERFACE_MODE_2500BASEX: return "2500base-x"; case PHY_INTERFACE_MODE_5GBASER: -- cgit v1.2.3 From 7c8199e24fa09d2344ae0204527d55d7803e8409 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 2 Sep 2022 14:10:43 -0700 Subject: bpf: Introduce any context BPF specific memory allocator. Tracing BPF programs can attach to kprobe and fentry. Hence they run in unknown context where calling plain kmalloc() might not be safe. Front-end kmalloc() with minimal per-cpu cache of free elements. Refill this cache asynchronously from irq_work. BPF programs always run with migration disabled. It's safe to allocate from cache of the current cpu with irqs disabled. Free-ing is always done into bucket of the current cpu as well. irq_work trims extra free elements from buckets with kfree and refills them with kmalloc, so global kmalloc logic takes care of freeing objects allocated by one cpu and freed on another. struct bpf_mem_alloc supports two modes: - When size != 0 create kmem_cache and bpf_mem_cache for each cpu. This is typical bpf hash map use case when all elements have equal size. - When size == 0 allocate 11 bpf_mem_cache-s for each cpu, then rely on kmalloc/kfree. Max allocation size is 4096 in this case. This is bpf_dynptr and bpf_kptr use case. bpf_mem_alloc/bpf_mem_free are bpf specific 'wrappers' of kmalloc/kfree. bpf_mem_cache_alloc/bpf_mem_cache_free are 'wrappers' of kmem_cache_alloc/kmem_cache_free. The allocators are NMI-safe from bpf programs only. They are not NMI-safe in general. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Kumar Kartikeya Dwivedi Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220902211058.60789-2-alexei.starovoitov@gmail.com --- include/linux/bpf_mem_alloc.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 include/linux/bpf_mem_alloc.h (limited to 'include/linux') diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h new file mode 100644 index 000000000000..804733070f8d --- /dev/null +++ b/include/linux/bpf_mem_alloc.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#ifndef _BPF_MEM_ALLOC_H +#define _BPF_MEM_ALLOC_H +#include + +struct bpf_mem_cache; +struct bpf_mem_caches; + +struct bpf_mem_alloc { + struct bpf_mem_caches __percpu *caches; + struct bpf_mem_cache __percpu *cache; +}; + +int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size); +void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); + +/* kmalloc/kfree equivalent: */ +void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size); +void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); + +/* kmem_cache_alloc/free equivalent: */ +void *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma); +void bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr); + +#endif /* _BPF_MEM_ALLOC_H */ -- cgit v1.2.3 From 4ab67149f3c6e97c5c506a726f0ebdec38241679 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 2 Sep 2022 14:10:52 -0700 Subject: bpf: Add percpu allocation support to bpf_mem_alloc. Extend bpf_mem_alloc to cache free list of fixed size per-cpu allocations. Once such cache is created bpf_mem_cache_alloc() will return per-cpu objects. bpf_mem_cache_free() will free them back into global per-cpu pool after observing RCU grace period. per-cpu flavor of bpf_mem_alloc is going to be used by per-cpu hash maps. The free list cache consists of tuples { llist_node, per-cpu pointer } Unlike alloc_percpu() that returns per-cpu pointer the bpf_mem_cache_alloc() returns a pointer to per-cpu pointer and bpf_mem_cache_free() expects to receive it back. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Kumar Kartikeya Dwivedi Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220902211058.60789-11-alexei.starovoitov@gmail.com --- include/linux/bpf_mem_alloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index 804733070f8d..653ed1584a03 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -12,7 +12,7 @@ struct bpf_mem_alloc { struct bpf_mem_cache __percpu *cache; }; -int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size); +int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); /* kmalloc/kfree equivalent: */ -- cgit v1.2.3 From 9f2c6e96c65e6fa1aebef546be0c30a5895fcb37 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 2 Sep 2022 14:10:58 -0700 Subject: bpf: Optimize rcu_barrier usage between hash map and bpf_mem_alloc. User space might be creating and destroying a lot of hash maps. Synchronous rcu_barrier-s in a destruction path of hash map delay freeing of hash buckets and other map memory and may cause artificial OOM situation under stress. Optimize rcu_barrier usage between bpf hash map and bpf_mem_alloc: - remove rcu_barrier from hash map, since htab doesn't use call_rcu directly and there are no callback to wait for. - bpf_mem_alloc has call_rcu_in_progress flag that indicates pending callbacks. Use it to avoid barriers in fast path. - When barriers are needed copy bpf_mem_alloc into temp structure and wait for rcu barrier-s in the worker to let the rest of hash map freeing to proceed. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220902211058.60789-17-alexei.starovoitov@gmail.com --- include/linux/bpf_mem_alloc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index 653ed1584a03..3e164b8efaa9 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -3,6 +3,7 @@ #ifndef _BPF_MEM_ALLOC_H #define _BPF_MEM_ALLOC_H #include +#include struct bpf_mem_cache; struct bpf_mem_caches; @@ -10,6 +11,7 @@ struct bpf_mem_caches; struct bpf_mem_alloc { struct bpf_mem_caches __percpu *caches; struct bpf_mem_cache __percpu *cache; + struct work_struct work; }; int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu); -- cgit v1.2.3 From 720e6a435194fb5237833a4a7ec6aa60a78964a8 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 31 Aug 2022 08:26:46 -0700 Subject: bpf: Allow struct argument in trampoline based programs Allow struct argument in trampoline based programs where the struct size should be <= 16 bytes. In such cases, the argument will be put into up to 2 registers for bpf, x86_64 and arm64 architectures. To support arch-specific trampoline manipulation, add arg_flags for additional struct information about arguments in btf_func_model. Such information will be used in arch specific function arch_prepare_bpf_trampoline() to prepare argument access properly in trampoline. Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20220831152646.2078089-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9c1674973e03..4d32f125f4af 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -727,10 +727,14 @@ enum bpf_cgroup_storage_type { */ #define MAX_BPF_FUNC_REG_ARGS 5 +/* The argument is a structure. */ +#define BTF_FMODEL_STRUCT_ARG BIT(0) + struct btf_func_model { u8 ret_size; u8 nr_args; u8 arg_size[MAX_BPF_FUNC_ARGS]; + u8 arg_flags[MAX_BPF_FUNC_ARGS]; }; /* Restore arguments before returning from trampoline to let original function -- cgit v1.2.3 From be376df724aa3b7abdf79390eaab60c58a92f4f0 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 27 Aug 2022 04:49:03 +0200 Subject: wifi: brcmfmac: add 43439 SDIO ids and initialization Add HW and SDIO ids for use with the muRata 1YN (Cypress CYW43439). Add the firmware mapping structures for the CYW43439 chipset. The 43439 needs some things setup similar to the 43430 chipset. Signed-off-by: Marek Vasut Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220827024903.617294-1-marex@denx.de --- include/linux/mmc/sdio_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 53f0efa0bccf..74f9d9a6d330 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -74,6 +74,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 #define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4 #define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43439 0xa9af #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752 0xaae8 -- cgit v1.2.3 From a1be74c5384c4a47d91ab4af2ed854d3b7eaf763 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 5 Sep 2022 13:58:43 +0300 Subject: net/mlx5: Introduce ifc bits for page tracker Introduce ifc related stuff to enable using page tracker. A page tracker is a dirty page tracking object used by the device to report the tracking log. Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20220905105852.26398-2-yishaih@nvidia.com Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 83 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 82 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4acd5610e96b..06eab92b9fb3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -89,6 +89,7 @@ enum { MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d, MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS = 0x001c, MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018, + MLX5_OBJ_TYPE_PAGE_TRACK = 0x46, MLX5_OBJ_TYPE_MKEY = 0xff01, MLX5_OBJ_TYPE_QP = 0xff02, MLX5_OBJ_TYPE_PSV = 0xff03, @@ -1733,7 +1734,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_geneve_tlv_options[0x8]; u8 reserved_at_568[0x3]; u8 max_geneve_tlv_option_data_len[0x5]; - u8 reserved_at_570[0x10]; + u8 reserved_at_570[0x9]; + u8 adv_virtualization[0x1]; + u8 reserved_at_57a[0x6]; u8 reserved_at_580[0xb]; u8 log_max_dci_stream_channels[0x5]; @@ -11818,4 +11821,82 @@ struct mlx5_ifc_load_vhca_state_out_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_adv_virtualization_cap_bits { + u8 reserved_at_0[0x3]; + u8 pg_track_log_max_num[0x5]; + u8 pg_track_max_num_range[0x8]; + u8 pg_track_log_min_addr_space[0x8]; + u8 pg_track_log_max_addr_space[0x8]; + + u8 reserved_at_20[0x3]; + u8 pg_track_log_min_msg_size[0x5]; + u8 reserved_at_28[0x3]; + u8 pg_track_log_max_msg_size[0x5]; + u8 reserved_at_30[0x3]; + u8 pg_track_log_min_page_size[0x5]; + u8 reserved_at_38[0x3]; + u8 pg_track_log_max_page_size[0x5]; + + u8 reserved_at_40[0x7c0]; +}; + +struct mlx5_ifc_page_track_report_entry_bits { + u8 dirty_address_high[0x20]; + + u8 dirty_address_low[0x20]; +}; + +enum { + MLX5_PAGE_TRACK_STATE_TRACKING, + MLX5_PAGE_TRACK_STATE_REPORTING, + MLX5_PAGE_TRACK_STATE_ERROR, +}; + +struct mlx5_ifc_page_track_range_bits { + u8 start_address[0x40]; + + u8 length[0x40]; +}; + +struct mlx5_ifc_page_track_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; + + u8 state[0x4]; + u8 track_type[0x4]; + u8 log_addr_space_size[0x8]; + u8 reserved_at_90[0x3]; + u8 log_page_size[0x5]; + u8 reserved_at_98[0x3]; + u8 log_msg_size[0x5]; + + u8 reserved_at_a0[0x8]; + u8 reporting_qpn[0x18]; + + u8 reserved_at_c0[0x18]; + u8 num_ranges[0x8]; + + u8 reserved_at_e0[0x20]; + + u8 range_start_address[0x40]; + + u8 length[0x40]; + + struct mlx5_ifc_page_track_range_bits track_range[0]; +}; + +struct mlx5_ifc_create_page_track_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_page_track_bits obj_context; +}; + +struct mlx5_ifc_modify_page_track_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_page_track_bits obj_context; +}; + #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From 939838632b9119614128028eaea3b1d7bf29f16f Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 5 Sep 2022 13:58:44 +0300 Subject: net/mlx5: Query ADV_VIRTUALIZATION capabilities Query ADV_VIRTUALIZATION capabilities which provide information for advanced virtualization related features. Current capabilities refer to the page tracker object which is used for tracking the pages that are dirtied by the device. Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20220905105852.26398-3-yishaih@nvidia.com Signed-off-by: Leon Romanovsky --- include/linux/mlx5/device.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index b5f58fd37a0f..5b41b9fb3d48 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1200,6 +1200,7 @@ enum mlx5_cap_type { MLX5_CAP_DEV_SHAMPO = 0x1d, MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, + MLX5_CAP_ADV_VIRTUALIZATION = 0x26, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1365,6 +1366,14 @@ enum mlx5_qcam_feature_groups { MLX5_GET(port_selection_cap, \ mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->max, cap) +#define MLX5_CAP_ADV_VIRTUALIZATION(mdev, cap) \ + MLX5_GET(adv_virtualization_cap, \ + mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->cur, cap) + +#define MLX5_CAP_ADV_VIRTUALIZATION_MAX(mdev, cap) \ + MLX5_GET(adv_virtualization_cap, \ + mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->max, cap) + #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) -- cgit v1.2.3 From d1b2234b7fbf94348901bed4ea8d015c8a819d02 Mon Sep 17 00:00:00 2001 From: Lior Nahmanson Date: Mon, 5 Sep 2022 22:21:16 -0700 Subject: net/mlx5: Removed esp_id from struct mlx5_flow_act esp_id is no longer in used Signed-off-by: Lior Nahmanson Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 8e73c377da2c..920cbc9524ad 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -245,7 +245,6 @@ struct mlx5_flow_act { struct mlx5_pkt_reformat *pkt_reformat; union { u32 ipsec_obj_id; - uintptr_t esp_id; }; u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; -- cgit v1.2.3 From e227ee990bf974f655ec3132b496409990f6634b Mon Sep 17 00:00:00 2001 From: Lior Nahmanson Date: Mon, 5 Sep 2022 22:21:17 -0700 Subject: net/mlx5: Generalize Flow Context for new crypto fields In order to support MACsec offload (and maybe some other crypto features in the future), generalize flow action parameters / defines to be used by crypto offlaods other than IPsec. The following changes made: ipsec_obj_id field at flow action context was changed to crypto_obj_id, intreduced a new crypto_type field where IPsec is the default zero type for backward compatibility. Action ipsec_decrypt was changed to crypto_decrypt. Action ipsec_encrypt was changed to crypto_encrypt. IPsec offload code was updated accordingly for backward compatibility. Signed-off-by: Lior Nahmanson Reviewed-by: Raed Salem Signed-off-by: Raed Salem Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 7 ++++--- include/linux/mlx5/mlx5_ifc.h | 12 ++++++++---- 2 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 920cbc9524ad..e62d50acb6bd 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -243,9 +243,10 @@ struct mlx5_flow_act { u32 action; struct mlx5_modify_hdr *modify_hdr; struct mlx5_pkt_reformat *pkt_reformat; - union { - u32 ipsec_obj_id; - }; + struct mlx5_flow_act_crypto_params { + u8 type; + u32 obj_id; + } crypto; u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4acd5610e96b..5758218cb3fa 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3310,8 +3310,8 @@ enum { MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH = 0x100, MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2 = 0x400, MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800, - MLX5_FLOW_CONTEXT_ACTION_IPSEC_DECRYPT = 0x1000, - MLX5_FLOW_CONTEXT_ACTION_IPSEC_ENCRYPT = 0x2000, + MLX5_FLOW_CONTEXT_ACTION_CRYPTO_DECRYPT = 0x1000, + MLX5_FLOW_CONTEXT_ACTION_CRYPTO_ENCRYPT = 0x2000, MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO = 0x4000, }; @@ -3321,6 +3321,10 @@ enum { MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT = 0x2, }; +enum { + MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_IPSEC = 0x0, +}; + struct mlx5_ifc_vlan_bits { u8 ethtype[0x10]; u8 prio[0x3]; @@ -3374,7 +3378,7 @@ struct mlx5_ifc_flow_context_bits { u8 extended_destination[0x1]; u8 reserved_at_81[0x1]; u8 flow_source[0x2]; - u8 reserved_at_84[0x4]; + u8 encrypt_decrypt_type[0x4]; u8 destination_list_size[0x18]; u8 reserved_at_a0[0x8]; @@ -3386,7 +3390,7 @@ struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_vlan_bits push_vlan_2; - u8 ipsec_obj_id[0x20]; + u8 encrypt_decrypt_obj_id[0x20]; u8 reserved_at_140[0xc0]; struct mlx5_ifc_fte_match_param_bits match_value; -- cgit v1.2.3 From 8385c51ff5bceb92f7401138e16b0a617ca2ab02 Mon Sep 17 00:00:00 2001 From: Lior Nahmanson Date: Mon, 5 Sep 2022 22:21:18 -0700 Subject: net/mlx5: Introduce MACsec Connect-X offload hardware bits and structures Add MACsec offload related IFC structs, layouts and enumerations. Signed-off-by: Lior Nahmanson Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 4 ++ include/linux/mlx5/mlx5_ifc.h | 99 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 101 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index b5f58fd37a0f..2927810f172b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1198,6 +1198,7 @@ enum mlx5_cap_type { MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, MLX5_CAP_DEV_SHAMPO = 0x1d, + MLX5_CAP_MACSEC = 0x1f, MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, /* NUM OF CAP Types */ @@ -1446,6 +1447,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_DEV_SHAMPO(mdev, cap)\ MLX5_GET(shampo_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_SHAMPO], cap) +#define MLX5_CAP_MACSEC(mdev, cap)\ + MLX5_GET(macsec_cap, (mdev)->caps.hca[MLX5_CAP_MACSEC]->cur, cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5758218cb3fa..8decbf9a7bdd 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -82,6 +82,7 @@ enum { MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM), MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11), MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13), + MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39), }; enum { @@ -449,7 +450,12 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_60[0x2]; u8 reformat_insert[0x1]; u8 reformat_remove[0x1]; - u8 reserver_at_64[0x14]; + u8 macsec_encrypt[0x1]; + u8 macsec_decrypt[0x1]; + u8 reserved_at_66[0x2]; + u8 reformat_add_macsec[0x1]; + u8 reformat_remove_macsec[0x1]; + u8 reserved_at_6a[0xe]; u8 log_max_ft_num[0x8]; u8 reserved_at_80[0x10]; @@ -611,7 +617,11 @@ struct mlx5_ifc_fte_match_set_misc2_bits { u8 metadata_reg_a[0x20]; - u8 reserved_at_1a0[0x60]; + u8 reserved_at_1a0[0x8]; + + u8 macsec_syndrome[0x8]; + + u8 reserved_at_1b0[0x50]; }; struct mlx5_ifc_fte_match_set_misc3_bits { @@ -1276,6 +1286,24 @@ struct mlx5_ifc_ipsec_cap_bits { u8 reserved_at_30[0x7d0]; }; +struct mlx5_ifc_macsec_cap_bits { + u8 macsec_epn[0x1]; + u8 reserved_at_1[0x2]; + u8 macsec_crypto_esp_aes_gcm_256_encrypt[0x1]; + u8 macsec_crypto_esp_aes_gcm_128_encrypt[0x1]; + u8 macsec_crypto_esp_aes_gcm_256_decrypt[0x1]; + u8 macsec_crypto_esp_aes_gcm_128_decrypt[0x1]; + u8 reserved_at_7[0x4]; + u8 log_max_macsec_offload[0x5]; + u8 reserved_at_10[0x10]; + + u8 min_log_macsec_full_replay_window[0x8]; + u8 max_log_macsec_full_replay_window[0x8]; + u8 reserved_at_30[0x10]; + + u8 reserved_at_40[0x7c0]; +}; + enum { MLX5_WQ_TYPE_LINKED_LIST = 0x0, MLX5_WQ_TYPE_CYCLIC = 0x1, @@ -3295,6 +3323,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_device_mem_cap_bits device_mem_cap; struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap; struct mlx5_ifc_shampo_cap_bits shampo_cap; + struct mlx5_ifc_macsec_cap_bits macsec_cap; u8 reserved_at_0[0x8000]; }; @@ -3323,6 +3352,7 @@ enum { enum { MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_IPSEC = 0x0, + MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_MACSEC = 0x1, }; struct mlx5_ifc_vlan_bits { @@ -6320,6 +6350,8 @@ enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, + MLX5_REFORMAT_TYPE_ADD_MACSEC = 0x11, + MLX5_REFORMAT_TYPE_DEL_MACSEC = 0x12, }; struct mlx5_ifc_alloc_packet_reformat_context_in_bits { @@ -11475,6 +11507,7 @@ enum { MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13, MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20, MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24, + MLX5_GENERAL_OBJECT_TYPES_MACSEC = 0x27, }; enum { @@ -11525,6 +11558,67 @@ struct mlx5_ifc_modify_ipsec_obj_in_bits { struct mlx5_ifc_ipsec_obj_bits ipsec_object; }; +struct mlx5_ifc_macsec_aso_bits { + u8 valid[0x1]; + u8 reserved_at_1[0x1]; + u8 mode[0x2]; + u8 window_size[0x2]; + u8 soft_lifetime_arm[0x1]; + u8 hard_lifetime_arm[0x1]; + u8 remove_flow_enable[0x1]; + u8 epn_event_arm[0x1]; + u8 reserved_at_a[0x16]; + + u8 remove_flow_packet_count[0x20]; + + u8 remove_flow_soft_lifetime[0x20]; + + u8 reserved_at_60[0x80]; + + u8 mode_parameter[0x20]; + + u8 replay_protection_window[8][0x20]; +}; + +struct mlx5_ifc_macsec_offload_obj_bits { + u8 modify_field_select[0x40]; + + u8 confidentiality_en[0x1]; + u8 reserved_at_41[0x1]; + u8 esn_en[0x1]; + u8 esn_overlap[0x1]; + u8 reserved_at_44[0x2]; + u8 confidentiality_offset[0x2]; + u8 reserved_at_48[0x4]; + u8 aso_return_reg[0x4]; + u8 reserved_at_50[0x10]; + + u8 esn_msb[0x20]; + + u8 reserved_at_80[0x8]; + u8 dekn[0x18]; + + u8 reserved_at_a0[0x20]; + + u8 sci[0x40]; + + u8 reserved_at_100[0x8]; + u8 macsec_aso_access_pd[0x18]; + + u8 reserved_at_120[0x60]; + + u8 salt[3][0x20]; + + u8 reserved_at_1e0[0x20]; + + struct mlx5_ifc_macsec_aso_bits macsec_aso; +}; + +struct mlx5_ifc_create_macsec_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_macsec_offload_obj_bits macsec_object; +}; + struct mlx5_ifc_encryption_key_obj_bits { u8 modify_field_select[0x40]; @@ -11642,6 +11736,7 @@ enum { enum { MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_TLS = 0x1, MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_IPSEC = 0x2, + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_MACSEC = 0x4, }; struct mlx5_ifc_tls_static_params_bits { -- cgit v1.2.3 From ee534d7f81ba9cec028580f91429b3dc29b90c7f Mon Sep 17 00:00:00 2001 From: Lior Nahmanson Date: Mon, 5 Sep 2022 22:21:20 -0700 Subject: net/mlx5: Add MACsec Tx tables support to fs_core Changed EGRESS_KERNEL namespace to EGRESS_IPSEC and add new namespace for MACsec TX. This namespace should be the last namespace for transmitted packets. Signed-off-by: Lior Nahmanson Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index e62d50acb6bd..53d186774206 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -92,7 +92,8 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_SNIFFER_RX, MLX5_FLOW_NAMESPACE_SNIFFER_TX, MLX5_FLOW_NAMESPACE_EGRESS, - MLX5_FLOW_NAMESPACE_EGRESS_KERNEL, + MLX5_FLOW_NAMESPACE_EGRESS_IPSEC, + MLX5_FLOW_NAMESPACE_EGRESS_MACSEC, MLX5_FLOW_NAMESPACE_RDMA_RX, MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL, MLX5_FLOW_NAMESPACE_RDMA_TX, -- cgit v1.2.3 From e467b283ffd50cf15b84c73eef68787e257eaed5 Mon Sep 17 00:00:00 2001 From: Lior Nahmanson Date: Mon, 5 Sep 2022 22:21:21 -0700 Subject: net/mlx5e: Add MACsec TX steering rules Tx flow steering consists of two flow tables (FTs). The first FT (crypto table) has two fixed rules: One default miss rule so non MACsec offloaded packets bypass the MACSec tables, another rule to make sure that MACsec key exchange (MKE) traffic passes unencrypted as expected (matched of ethertype). On each new MACsec offload flow, a new MACsec rule is added. This rule is matched on metadata_reg_a (which contains the id of the flow) and invokes the MACsec offload action on match. The second FT (check table) has two fixed rules: One rule for verifying that the previous offload actions were finished successfully and packet need to be transmitted. Another default rule for dropping packets that were failed in the offload actions. The MACsec FTs should be created on demand when the first MACsec rule is added and destroyed when the last MACsec rule is deleted. Signed-off-by: Lior Nahmanson Reviewed-by: Raed Salem Signed-off-by: Raed Salem Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/qp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 8bda3ba5b109..be640c749d5e 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -252,6 +252,7 @@ enum { enum { MLX5_ETH_WQE_FT_META_IPSEC = BIT(0), + MLX5_ETH_WQE_FT_META_MACSEC = BIT(1), }; struct mlx5_wqe_eth_seg { -- cgit v1.2.3 From 15d187e285b3d5f4fe0328c09566355c1e387ff6 Mon Sep 17 00:00:00 2001 From: Lior Nahmanson Date: Mon, 5 Sep 2022 22:21:24 -0700 Subject: net/mlx5: Add MACsec Rx tables support to fs_core Add new namespace for MACsec RX flows. Encrypted MACsec packets should be first decrypted and stripped from MACsec header and then continues with the kernel's steering pipeline. Signed-off-by: Lior Nahmanson Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 53d186774206..c7a91981cd5a 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -79,6 +79,7 @@ static inline void build_leftovers_ft_param(int *priority, enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_BYPASS, + MLX5_FLOW_NAMESPACE_KERNEL_RX_MACSEC, MLX5_FLOW_NAMESPACE_LAG, MLX5_FLOW_NAMESPACE_OFFLOADS, MLX5_FLOW_NAMESPACE_ETHTOOL, -- cgit v1.2.3 From 95f2f26f3cac06cfc046d2b29e60719d7848ea54 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 6 Sep 2022 17:12:58 +0200 Subject: bpf: split btf_check_subprog_arg_match in two btf_check_subprog_arg_match() was used twice in verifier.c: - when checking for the type mismatches between a (sub)prog declaration and BTF - when checking the call of a subprog to see if the provided arguments are correct and valid This is problematic when we check if the first argument of a program (pointer to ctx) is correctly accessed: To be able to ensure we access a valid memory in the ctx, the verifier assumes the pointer to context is not null. This has the side effect of marking the program accessing the entire context, even if the context is never dereferenced. For example, by checking the context access with the current code, the following eBPF program would fail with -EINVAL if the ctx is set to null from the userspace: ``` SEC("syscall") int prog(struct my_ctx *args) { return 0; } ``` In that particular case, we do not want to actually check that the memory is correct while checking for the BTF validity, but we just want to ensure that the (sub)prog definition matches the BTF we have. So split btf_check_subprog_arg_match() in two so we can actually check for the memory used when in a call, and ignore that part when not. Note that a further patch is in preparation to disentangled btf_check_func_arg_match() from these two purposes, and so right now we just add a new hack around that by adding a boolean to this function. Signed-off-by: Benjamin Tissoires Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220906151303.2780789-3-benjamin.tissoires@redhat.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4d32f125f4af..3cf161cfd396 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1947,6 +1947,8 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, struct bpf_reg_state; int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); +int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *regs); int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs, -- cgit v1.2.3 From eb1f7f71c126c8fd50ea81af98f97c4b581ea4ae Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 6 Sep 2022 17:13:02 +0200 Subject: bpf/verifier: allow kfunc to return an allocated mem For drivers (outside of network), the incoming data is not statically defined in a struct. Most of the time the data buffer is kzalloc-ed and thus we can not rely on eBPF and BTF to explore the data. This commit allows to return an arbitrary memory, previously allocated by the driver. An interesting extra point is that the kfunc can mark the exported memory region as read only or read/write. So, when a kfunc is not returning a pointer to a struct but to a plain type, we can consider it is a valid allocated memory assuming that: - one of the arguments is either called rdonly_buf_size or rdwr_buf_size - and this argument is a const from the caller point of view We can then use this parameter as the size of the allocated memory. The memory is either read-only or read-write based on the name of the size parameter. Acked-by: Kumar Kartikeya Dwivedi Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20220906151303.2780789-7-benjamin.tissoires@redhat.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 9 ++++++++- include/linux/bpf_verifier.h | 2 ++ include/linux/btf.h | 10 ++++++++++ 3 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3cf161cfd396..79883f883ff3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1944,6 +1944,13 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, const char *func_name, struct btf_func_model *m); +struct bpf_kfunc_arg_meta { + u64 r0_size; + bool r0_rdonly; + int ref_obj_id; + u32 flags; +}; + struct bpf_reg_state; int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); @@ -1952,7 +1959,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs, - u32 kfunc_flags); + struct bpf_kfunc_arg_meta *meta); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *reg); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1fdddbf3546b..8fbc1d05281e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -598,6 +598,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, struct bpf_attach_target_info *tgt_info); void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab); +int mark_chain_precision(struct bpf_verifier_env *env, int regno); + #define BPF_BASE_TYPE_MASK GENMASK(BPF_BASE_TYPE_BITS - 1, 0) /* extract base type from bpf_{arg, return, reg}_type. */ diff --git a/include/linux/btf.h b/include/linux/btf.h index ad93c2d9cc1c..1fcc833a8690 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -441,4 +441,14 @@ static inline int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dt } #endif +static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) +{ + if (!btf_type_is_ptr(t)) + return false; + + t = btf_type_skip_modifiers(btf, t->type, NULL); + + return btf_type_is_struct(t); +} + #endif -- cgit v1.2.3 From 448325199f574d33824dbf9121efb03558412966 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sun, 4 Sep 2022 22:41:14 +0200 Subject: bpf: Add copy_map_value_long to copy to remote percpu memory bpf_long_memcpy is used while copying to remote percpu regions from BPF syscall and helpers, so that the copy is atomic at word size granularity. This might not be possible when you copy from map value hosting kptrs from or to percpu maps, as the alignment or size in disjoint regions may not be multiple of word size. Hence, to avoid complicating the copy loop, we only use bpf_long_memcpy when special fields are not present, otherwise use normal memcpy to copy the disjoint regions. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220904204145.3089-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 52 +++++++++++++++++++++++++++++++++------------------- 1 file changed, 33 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 79883f883ff3..6a73e94821c4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -280,14 +280,33 @@ static inline void check_and_init_map_value(struct bpf_map *map, void *dst) } } -/* 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) +/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and + * forced to use 'long' read/writes to try to atomically copy long counters. + * Best-effort only. No barriers here, since it _will_ race with concurrent + * updates from BPF programs. Called from bpf syscall and mostly used with + * size 8 or 16 bytes, so ask compiler to inline it. + */ +static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) +{ + const long *lsrc = src; + long *ldst = dst; + + size /= sizeof(long); + while (size--) + *ldst++ = *lsrc++; +} + +/* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ +static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, bool long_memcpy) { u32 curr_off = 0; int i; if (likely(!map->off_arr)) { - memcpy(dst, src, map->value_size); + if (long_memcpy) + bpf_long_memcpy(dst, src, round_up(map->value_size, 8)); + else + memcpy(dst, src, map->value_size); return; } @@ -299,6 +318,17 @@ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) } memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off); } + +static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) +{ + __copy_map_value(map, dst, src, false); +} + +static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src) +{ + __copy_map_value(map, dst, src, true); +} + void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); @@ -1827,22 +1857,6 @@ int bpf_get_file_flag(int flags); int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); -/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and - * forced to use 'long' read/writes to try to atomically copy long counters. - * Best-effort only. No barriers here, since it _will_ race with concurrent - * updates from BPF programs. Called from bpf syscall and mostly used with - * size 8 or 16 bytes, so ask compiler to inline it. - */ -static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) -{ - const long *lsrc = src; - long *ldst = dst; - - size /= sizeof(long); - while (size--) - *ldst++ = *lsrc++; -} - /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr); -- cgit v1.2.3 From cc48755808c646666436745b35629c3f0d05e165 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sun, 4 Sep 2022 22:41:16 +0200 Subject: bpf: Add zero_map_value to zero map value with special fields We need this helper to skip over special fields (bpf_spin_lock, bpf_timer, kptrs) while zeroing a map value. Use the same logic as copy_map_value but memset instead of memcpy. Currently, the code zeroing map value memory does not have to deal with special fields, hence this is a prerequisite for introducing such support. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220904204145.3089-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6a73e94821c4..48ae05099f36 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -329,6 +329,25 @@ static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src __copy_map_value(map, dst, src, true); } +static inline void zero_map_value(struct bpf_map *map, void *dst) +{ + u32 curr_off = 0; + int i; + + if (likely(!map->off_arr)) { + memset(dst, 0, map->value_size); + return; + } + + for (i = 0; i < map->off_arr->cnt; i++) { + u32 next_off = map->off_arr->field_off[i]; + + memset(dst + curr_off, 0, next_off - curr_off); + curr_off += map->off_arr->field_sz[i]; + } + memset(dst + curr_off, 0, map->value_size - curr_off); +} + void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); -- cgit v1.2.3 From b239da34203f49c40b5d656220c39647c3ff0b3c Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sun, 4 Sep 2022 22:41:28 +0200 Subject: bpf: Add helper macro bpf_for_each_reg_in_vstate For a lot of use cases in future patches, we will want to modify the state of registers part of some same 'group' (e.g. same ref_obj_id). It won't just be limited to releasing reference state, but setting a type flag dynamically based on certain actions, etc. Hence, we need a way to easily pass a callback to the function that iterates over all registers in current bpf_verifier_state in all frames upto (and including) the curframe. While in C++ we would be able to easily use a lambda to pass state and the callback together, sadly we aren't using C++ in the kernel. The next best thing to avoid defining a function for each case seems like statement expressions in GNU C. The kernel already uses them heavily, hence they can passed to the macro in the style of a lambda. The statement expression will then be substituted in the for loop bodies. Variables __state and __reg are set to current bpf_func_state and reg for each invocation of the expression inside the passed in verifier state. Then, convert mark_ptr_or_null_regs, clear_all_pkt_pointers, release_reference, find_good_pkt_pointers, find_equal_scalars to use bpf_for_each_reg_in_vstate. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220904204145.3089-16-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 8fbc1d05281e..b49a349cc6ae 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -348,6 +348,27 @@ struct bpf_verifier_state { iter < frame->allocated_stack / BPF_REG_SIZE; \ iter++, reg = bpf_get_spilled_reg(iter, frame)) +/* Invoke __expr over regsiters in __vst, setting __state and __reg */ +#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ + ({ \ + struct bpf_verifier_state *___vstate = __vst; \ + int ___i, ___j; \ + for (___i = 0; ___i <= ___vstate->curframe; ___i++) { \ + struct bpf_reg_state *___regs; \ + __state = ___vstate->frame[___i]; \ + ___regs = __state->regs; \ + for (___j = 0; ___j < MAX_BPF_REG; ___j++) { \ + __reg = &___regs[___j]; \ + (void)(__expr); \ + } \ + bpf_for_each_spilled_reg(___j, __state, __reg) { \ + if (!__reg) \ + continue; \ + (void)(__expr); \ + } \ + } \ + }) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; -- cgit v1.2.3 From bb5721f063ba63cd54cc5916881a706c21e6abc6 Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Mon, 5 Sep 2022 09:21:25 -0700 Subject: mfd: ocelot: Add helper to get regmap from a resource Several ocelot-related modules are designed for MMIO / regmaps. As such, they often use a combination of devm_platform_get_and_ioremap_resource() and devm_regmap_init_mmio(). Operating in an MFD might be different, in that it could be memory mapped, or it could be SPI, I2C... In these cases a fallback to use IORESOURCE_REG instead of IORESOURCE_MEM becomes necessary. When this happens, there's redundant logic that needs to be implemented in every driver. In order to avoid this redundancy, utilize a single function that, if the MFD scenario is enabled, will perform this fallback logic. Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Reviewed-by: Andy Shevchenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20220905162132.2943088-2-colin.foster@in-advantage.com --- include/linux/mfd/ocelot.h | 62 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) create mode 100644 include/linux/mfd/ocelot.h (limited to 'include/linux') diff --git a/include/linux/mfd/ocelot.h b/include/linux/mfd/ocelot.h new file mode 100644 index 000000000000..dd72073d2d4f --- /dev/null +++ b/include/linux/mfd/ocelot.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2022 Innovative Advantage Inc. */ + +#ifndef _LINUX_MFD_OCELOT_H +#define _LINUX_MFD_OCELOT_H + +#include +#include +#include +#include +#include +#include + +struct resource; + +static inline struct regmap * +ocelot_regmap_from_resource_optional(struct platform_device *pdev, + unsigned int index, + const struct regmap_config *config) +{ + struct device *dev = &pdev->dev; + struct resource *res; + void __iomem *regs; + + /* + * Don't use _get_and_ioremap_resource() here, since that will invoke + * prints of "invalid resource" which will simply add confusion. + */ + res = platform_get_resource(pdev, IORESOURCE_MEM, index); + if (res) { + regs = devm_ioremap_resource(dev, res); + if (IS_ERR(regs)) + return ERR_CAST(regs); + return devm_regmap_init_mmio(dev, regs, config); + } + + /* + * Fall back to using REG and getting the resource from the parent + * device, which is possible in an MFD configuration + */ + if (dev->parent) { + res = platform_get_resource(pdev, IORESOURCE_REG, index); + if (!res) + return NULL; + + return dev_get_regmap(dev->parent, res->name); + } + + return NULL; +} + +static inline struct regmap * +ocelot_regmap_from_resource(struct platform_device *pdev, unsigned int index, + const struct regmap_config *config) +{ + struct regmap *map; + + map = ocelot_regmap_from_resource_optional(pdev, index, config); + return map ?: ERR_PTR(-ENOENT); +} + +#endif -- cgit v1.2.3 From 39f7d0832c28a6a31abb5b7363e7b1ba0714fe18 Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Mon, 5 Sep 2022 09:21:30 -0700 Subject: resource: add define macro for register address resources DEFINE_RES_ macros have been created for the commonly used resource types, but not IORESOURCE_REG. Add the macro so it can be used in a similar manner to all other resource types. Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Reviewed-by: Andy Shevchenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20220905162132.2943088-7-colin.foster@in-advantage.com --- include/linux/ioport.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 616b683563a9..8a76dca9deee 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -172,6 +172,11 @@ enum { #define DEFINE_RES_MEM(_start, _size) \ DEFINE_RES_MEM_NAMED((_start), (_size), NULL) +#define DEFINE_RES_REG_NAMED(_start, _size, _name) \ + DEFINE_RES_NAMED((_start), (_size), (_name), IORESOURCE_REG) +#define DEFINE_RES_REG(_start, _size) \ + DEFINE_RES_REG_NAMED((_start), (_size), NULL) + #define DEFINE_RES_IRQ_NAMED(_irq, _name) \ DEFINE_RES_NAMED((_irq), 1, (_name), IORESOURCE_IRQ) #define DEFINE_RES_IRQ(_irq) \ -- cgit v1.2.3 From d4f7bdb2ed7bf320a8772258fdc257655d225afb Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Wed, 7 Sep 2022 10:40:37 -0600 Subject: bpf: Add stub for btf_struct_access() Add corresponding unimplemented stub for when CONFIG_BPF_SYSCALL=n Signed-off-by: Daniel Xu Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/4021398e884433b1fef57a4d28361bb9fcf1bd05.1662568410.git.dxu@dxuuu.xyz Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 48ae05099f36..54178b9e9c3a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2211,6 +2211,15 @@ static inline struct bpf_prog *bpf_prog_by_id(u32 id) return ERR_PTR(-ENOTSUPP); } +static inline int btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) +{ + return -EACCES; +} + static inline const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { -- cgit v1.2.3 From 1bfe26fb082724be453e4d7fd9bb358e3ba669b2 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Thu, 8 Sep 2022 16:07:16 -0700 Subject: bpf: Add verifier support for custom callback return range Verifier logic to confirm that a callback function returns 0 or 1 was added in commit 69c087ba6225b ("bpf: Add bpf_for_each_map_elem() helper"). At the time, callback return value was only used to continue or stop iteration. In order to support callbacks with a broader return value range, such as those added in rbtree series[0] and others, add a callback_ret_range to bpf_func_state. Verifier's helpers which set in_callback_fn will also set the new field, which the verifier will later use to check return value bounds. Default to tnum_range(0, 0) instead of using tnum_unknown as a sentinel value as the latter would prevent the valid range (0, U64_MAX) being used. Previous global default tnum_range(0, 1) is explicitly set for extant callback helpers. The change to global default was made after discussion around this patch in rbtree series [1], goal here is to make it more obvious that callback_ret_range should be explicitly set. [0]: lore.kernel.org/bpf/20220830172759.4069786-1-davemarchevsky@fb.com/ [1]: lore.kernel.org/bpf/20220830172759.4069786-2-davemarchevsky@fb.com/ Signed-off-by: Dave Marchevsky Reviewed-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20220908230716.2751723-1-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b49a349cc6ae..e197f8fb27e2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -248,6 +248,7 @@ struct bpf_func_state { */ u32 async_entry_cnt; bool in_callback_fn; + struct tnum callback_ret_range; bool in_async_callback_fn; /* The following fields should be last. See copy_func_state() */ -- cgit v1.2.3 From 96a7457a14d9cf98cf58de1e26c03180e0f28141 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 12 Sep 2022 19:07:19 +0200 Subject: can: skb: unify skb CAN frame identification helpers Replace open coded checks for sk_buffs containing Classical CAN and CAN FD frame structures as a preparation for CAN XL support. With the added length check the unintended processing of CAN XL frames having the CANXL_XLF bit set can be suppressed even when the skb->len fits to non CAN XL frames. The CAN_RAW socket needs a rework to use these helpers. Therefore the use of these helpers is postponed to the CAN_RAW CAN XL integration. The J1939 protocol gets a check for Classical CAN frames too. Acked-by: Vincent Mailhol Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20220912170725.120748-2-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/linux/can/skb.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index 182749e858b3..27ebfc28510f 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -97,10 +97,20 @@ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) return nskb; } +static inline bool can_is_can_skb(const struct sk_buff *skb) +{ + struct can_frame *cf = (struct can_frame *)skb->data; + + /* the CAN specific type of skb is identified by its data length */ + return (skb->len == CAN_MTU && cf->len <= CAN_MAX_DLEN); +} + static inline bool can_is_canfd_skb(const struct sk_buff *skb) { + struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + /* the CAN specific type of skb is identified by its data length */ - return skb->len == CANFD_MTU; + return (skb->len == CANFD_MTU && cfd->len <= CANFD_MAX_DLEN); } #endif /* !_CAN_SKB_H */ -- cgit v1.2.3 From 467ef4c7b9d1c22ee64342804bf92549d765df14 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 12 Sep 2022 19:07:20 +0200 Subject: can: skb: add skb CAN frame data length helpers Add two helpers to retrieve the data length from CAN sk_buffs and prepare the length information to be a uint16 value for the CAN XL support. Acked-by: Vincent Mailhol Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20220912170725.120748-3-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/linux/can/skb.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index 27ebfc28510f..ddffc2fc008c 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -20,7 +20,8 @@ void can_flush_echo_skb(struct net_device *dev); int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx, unsigned int frame_len); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, - u8 *len_ptr, unsigned int *frame_len_ptr); + unsigned int *len_ptr, + unsigned int *frame_len_ptr); unsigned int __must_check can_get_echo_skb(struct net_device *dev, unsigned int idx, unsigned int *frame_len_ptr); @@ -113,4 +114,25 @@ static inline bool can_is_canfd_skb(const struct sk_buff *skb) return (skb->len == CANFD_MTU && cfd->len <= CANFD_MAX_DLEN); } +/* get length element value from can[fd]_frame structure */ +static inline unsigned int can_skb_get_len_val(struct sk_buff *skb) +{ + const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + + return cfd->len; +} + +/* get needed data length inside CAN frame for all frame types (RTR aware) */ +static inline unsigned int can_skb_get_data_len(struct sk_buff *skb) +{ + unsigned int len = can_skb_get_len_val(skb); + const struct can_frame *cf = (struct can_frame *)skb->data; + + /* RTR frames have an actual length of zero */ + if (can_is_can_skb(skb) && cf->can_id & CAN_RTR_FLAG) + return 0; + + return len; +} + #endif /* !_CAN_SKB_H */ -- cgit v1.2.3 From fb08cba12b52cba4366e858932307649dc5304e2 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 12 Sep 2022 19:07:23 +0200 Subject: can: canxl: update CAN infrastructure for CAN XL frames - add new ETH_P_CANXL ethernet protocol type - update skb checks for CAN XL - add alloc_canxl_skb() which now needs a data length parameter - introduce init_can_skb_reserve() to reduce code duplication Acked-by: Vincent Mailhol Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20220912170725.120748-6-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/linux/can/skb.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index ddffc2fc008c..1abc25a8d144 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -30,6 +30,9 @@ void can_free_echo_skb(struct net_device *dev, unsigned int idx, struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); struct sk_buff *alloc_canfd_skb(struct net_device *dev, struct canfd_frame **cfd); +struct sk_buff *alloc_canxl_skb(struct net_device *dev, + struct canxl_frame **cxl, + unsigned int data_len); struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf); bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb); @@ -114,11 +117,29 @@ static inline bool can_is_canfd_skb(const struct sk_buff *skb) return (skb->len == CANFD_MTU && cfd->len <= CANFD_MAX_DLEN); } -/* get length element value from can[fd]_frame structure */ +static inline bool can_is_canxl_skb(const struct sk_buff *skb) +{ + const struct canxl_frame *cxl = (struct canxl_frame *)skb->data; + + if (skb->len < CANXL_HDR_SIZE + CANXL_MIN_DLEN || skb->len > CANXL_MTU) + return false; + + /* this also checks valid CAN XL data length boundaries */ + if (skb->len != CANXL_HDR_SIZE + cxl->len) + return false; + + return cxl->flags & CANXL_XLF; +} + +/* get length element value from can[|fd|xl]_frame structure */ static inline unsigned int can_skb_get_len_val(struct sk_buff *skb) { + const struct canxl_frame *cxl = (struct canxl_frame *)skb->data; const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + if (can_is_canxl_skb(skb)) + return cxl->len; + return cfd->len; } -- cgit v1.2.3 From ebf87fc728502244550eaf8819fc785e2014b2ad Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 12 Sep 2022 19:07:24 +0200 Subject: can: dev: add CAN XL support to virtual CAN Make use of new can_skb_get_data_len() helper. Add support for variable CANXL MTU using the new can_is_canxl_dev_mtu(). Acked-by: Vincent Mailhol Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20220912170725.120748-7-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index c3e50e537e39..58f5431a5559 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -147,6 +147,11 @@ static inline u32 can_get_static_ctrlmode(struct can_priv *priv) return priv->ctrlmode & ~priv->ctrlmode_supported; } +static inline bool can_is_canxl_dev_mtu(unsigned int mtu) +{ + return (mtu >= CANXL_MIN_MTU && mtu <= CANXL_MAX_MTU); +} + void can_setup(struct net_device *dev); struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, -- cgit v1.2.3 From 47e34cb74d376ddfeaef94abb1d6dfb3c905ee51 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Mon, 12 Sep 2022 08:45:44 -0700 Subject: bpf: Add verifier check for BPF_PTR_POISON retval and arg BPF_PTR_POISON was added in commit c0a5a21c25f37 ("bpf: Allow storing referenced kptr in map") to denote a bpf_func_proto btf_id which the verifier will replace with a dynamically-determined btf_id at verification time. This patch adds verifier 'poison' functionality to BPF_PTR_POISON in order to prepare for expanded use of the value to poison ret- and arg-btf_id in ongoing work, namely rbtree and linked list patchsets [0, 1]. Specifically, when the verifier checks helper calls, it assumes that BPF_PTR_POISON'ed ret type will be replaced with a valid type before - or in lieu of - the default ret_btf_id logic. Similarly for arg btf_id. If poisoned btf_id reaches default handling block for either, consider this a verifier internal error and fail verification. Otherwise a helper w/ poisoned btf_id but no verifier logic replacing the type will cause a crash as the invalid pointer is dereferenced. Also move BPF_PTR_POISON to existing include/linux/posion.h header and remove unnecessary shift. [0]: lore.kernel.org/bpf/20220830172759.4069786-1-davemarchevsky@fb.com [1]: lore.kernel.org/bpf/20220904204145.3089-1-memxor@gmail.com Signed-off-by: Dave Marchevsky Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220912154544.1398199-1-davemarchevsky@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/poison.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/poison.h b/include/linux/poison.h index d62ef5a6b4e9..2d3249eb0e62 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -81,4 +81,7 @@ /********** net/core/page_pool.c **********/ #define PP_SIGNATURE (0x40 + POISON_POINTER_DELTA) +/********** kernel/bpf/ **********/ +#define BPF_PTR_POISON ((void *)(0xeB9FUL + POISON_POINTER_DELTA)) + #endif -- cgit v1.2.3 From 7187440dd7c45fd8b6dd4f3ff56b03ca4aa1bbd2 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 8 Sep 2022 15:20:23 +0300 Subject: iov_iter: use "maxpages" parameter This was intended to be "maxpages" instead of INT_MAX. There is only one caller and it passes INT_MAX so this does not affect runtime. Fixes: b93235e68921 ("tls: cap the output scatter list to something reasonable") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- include/linux/uio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 5896af36199c..2e3134b14ffd 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -298,7 +298,7 @@ iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) shorted = iov_iter_count(i) - max_bytes; iov_iter_truncate(i, max_bytes); } - npages = iov_iter_npages(i, INT_MAX); + npages = iov_iter_npages(i, maxpages); if (shorted) iov_iter_reexpand(i, iov_iter_count(i) + shorted); -- cgit v1.2.3 From bfeb7e399bacae4ee46ad978f5fce3e47f0978d6 Mon Sep 17 00:00:00 2001 From: Yauheni Kaliuta Date: Mon, 5 Sep 2022 12:01:49 +0300 Subject: bpf: Use bpf_capable() instead of CAP_SYS_ADMIN for blinding decision The full CAP_SYS_ADMIN requirement for blinding looks too strict nowadays. These days given unprivileged BPF is disabled by default, the main users for constant blinding coming from unprivileged in particular via cBPF -> eBPF migration (e.g. old-style socket filters). Signed-off-by: Yauheni Kaliuta Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220831090655.156434-1-ykaliuta@redhat.com Link: https://lore.kernel.org/bpf/20220905090149.61221-1-ykaliuta@redhat.com --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 527ae1d64e27..75335432fcbc 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1099,7 +1099,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) return false; if (!bpf_jit_harden) return false; - if (bpf_jit_harden == 1 && capable(CAP_SYS_ADMIN)) + if (bpf_jit_harden == 1 && bpf_capable()) return false; return true; -- cgit v1.2.3 From ceea991a019c57a1fb0edd12a5f836a0fa431aee Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 3 Sep 2022 15:11:54 +0200 Subject: bpf: Move bpf_dispatcher function out of ftrace locations The dispatcher function is attached/detached to trampoline by dispatcher update function. At the same time it's available as ftrace attachable function. After discussion [1] the proposed solution is to use compiler attributes to alter bpf_dispatcher_##name##_func function: - remove it from being instrumented with __no_instrument_function__ attribute, so ftrace has no track of it - but still generate 5 nop instructions with patchable_function_entry(5) attribute, which are expected by bpf_arch_text_poke used by dispatcher update function Enabling HAVE_DYNAMIC_FTRACE_NO_PATCHABLE option for x86, so __patchable_function_entries functions are not part of ftrace/mcount locations. Adding attributes to bpf_dispatcher_XXX function on x86_64 so it's kept out of ftrace locations and has 5 byte nop generated at entry. These attributes need to be arch specific as pointed out by Ilya Leoshkevic in here [2]. The dispatcher image is generated only for x86_64 arch, so the code can stay as is for other archs. [1] https://lore.kernel.org/bpf/20220722110811.124515-1-jolsa@kernel.org/ [2] https://lore.kernel.org/bpf/969a14281a7791c334d476825863ee449964dd0c.camel@linux.ibm.com/ Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Jiri Olsa Signed-off-by: Daniel Borkmann Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/bpf/20220903131154.420467-3-jolsa@kernel.org --- include/linux/bpf.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 54178b9e9c3a..e0dbe0c0a17e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -977,7 +977,14 @@ int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs); }, \ } +#ifdef CONFIG_X86_64 +#define BPF_DISPATCHER_ATTRIBUTES __attribute__((patchable_function_entry(5))) +#else +#define BPF_DISPATCHER_ATTRIBUTES +#endif + #define DEFINE_BPF_DISPATCHER(name) \ + notrace BPF_DISPATCHER_ATTRIBUTES \ noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ -- cgit v1.2.3 From e63efbcaba7d6f6846b1c2ec5cf259249b9ed88f Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Fri, 16 Sep 2022 17:02:46 +0100 Subject: wifi: brcmfmac: pcie: Read Apple OTP information On Apple platforms, the One Time Programmable ROM in the Broadcom chips contains information about the specific board design (module, vendor, version) that is required to select the correct NVRAM file. Parse this OTP ROM and extract the required strings. Note that the user OTP offset/size is per-chip. This patch does not add any chips yet. Reviewed-by: Arend van Spriel Signed-off-by: Hector Martin Signed-off-by: Russell King (Oracle) Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/E1oZDni-0077aM-I6@rmk-PC.armlinux.org.uk --- include/linux/bcma/bcma_driver_chipcommon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index e3314f746bfa..2d94c30ed439 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -271,6 +271,7 @@ #define BCMA_CC_SROM_CONTROL_OP_WRDIS 0x40000000 #define BCMA_CC_SROM_CONTROL_OP_WREN 0x60000000 #define BCMA_CC_SROM_CONTROL_OTPSEL 0x00000010 +#define BCMA_CC_SROM_CONTROL_OTP_PRESENT 0x00000020 #define BCMA_CC_SROM_CONTROL_LOCK 0x00000008 #define BCMA_CC_SROM_CONTROL_SIZE_MASK 0x00000006 #define BCMA_CC_SROM_CONTROL_SIZE_1K 0x00000000 -- cgit v1.2.3 From db01868bf2e919a10551066d54cf4bef5dd5a01e Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 11 Sep 2022 04:06:57 +0300 Subject: net: introduce iterators over synced hw addresses Some network drivers use __dev_mc_sync()/__dev_uc_sync() and therefore program the hardware only with addresses with a non-zero sync_cnt. Some of the above drivers also need to save/restore the address filtering lists when certain events happen, and they need to walk through the struct net_device :: uc and struct net_device :: mc lists. But these lists contain unsynced addresses too. To keep the appearance of an elementary form of data encapsulation, provide iterators through these lists that only look at entries with a non-zero sync_cnt, instead of filtering entries out from device drivers. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f0068c1ff1df..9f42fc871c3b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -253,11 +253,17 @@ struct netdev_hw_addr_list { #define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc) #define netdev_for_each_uc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->uc) +#define netdev_for_each_synced_uc_addr(_ha, _dev) \ + netdev_for_each_uc_addr((_ha), (_dev)) \ + if ((_ha)->sync_cnt) #define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc) #define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc) #define netdev_for_each_mc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->mc) +#define netdev_for_each_synced_mc_addr(_ha, _dev) \ + netdev_for_each_mc_addr((_ha), (_dev)) \ + if ((_ha)->sync_cnt) struct hh_cache { unsigned int hh_len; -- cgit v1.2.3 From 256dea9134c38fcc409ec7ea6a1eb67829b563bc Mon Sep 17 00:00:00 2001 From: Ronak Jain Date: Wed, 14 Sep 2022 18:03:15 +0530 Subject: firmware: xilinx: add support for sd/gem config Add new APIs in firmware to configure SD/GEM registers. Internally it calls PM IOCTL for below SD/GEM register configuration: - SD/EMMC select - SD slot type - SD base clock - SD 8 bit support - SD fixed config - GEM SGMII Mode - GEM fixed config Signed-off-by: Ronak Jain Signed-off-by: Radhey Shyam Pandey Reviewed-by: Claudiu Beznea Signed-off-by: Jakub Kicinski --- include/linux/firmware/xlnx-zynqmp.h | 45 ++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 9f50dacbf7d6..76d2b3ebad84 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -153,6 +153,9 @@ enum pm_ioctl_id { /* Runtime feature configuration */ IOCTL_SET_FEATURE_CONFIG = 26, IOCTL_GET_FEATURE_CONFIG = 27, + /* Dynamic SD/GEM configuration */ + IOCTL_SET_SD_CONFIG = 30, + IOCTL_SET_GEM_CONFIG = 31, }; enum pm_query_id { @@ -399,6 +402,30 @@ enum pm_feature_config_id { PM_FEATURE_EXTWDT_VALUE = 4, }; +/** + * enum pm_sd_config_type - PM SD configuration. + * @SD_CONFIG_EMMC_SEL: To set SD_EMMC_SEL in CTRL_REG_SD and SD_SLOTTYPE + * @SD_CONFIG_BASECLK: To set SD_BASECLK in SD_CONFIG_REG1 + * @SD_CONFIG_8BIT: To set SD_8BIT in SD_CONFIG_REG2 + * @SD_CONFIG_FIXED: To set fixed config registers + */ +enum pm_sd_config_type { + SD_CONFIG_EMMC_SEL = 1, + SD_CONFIG_BASECLK = 2, + SD_CONFIG_8BIT = 3, + SD_CONFIG_FIXED = 4, +}; + +/** + * enum pm_gem_config_type - PM GEM configuration. + * @GEM_CONFIG_SGMII_MODE: To set GEM_SGMII_MODE in GEM_CLK_CTRL register + * @GEM_CONFIG_FIXED: To set fixed config registers + */ +enum pm_gem_config_type { + GEM_CONFIG_SGMII_MODE = 1, + GEM_CONFIG_FIXED = 2, +}; + /** * struct zynqmp_pm_query_data - PM query data * @qid: query ID @@ -475,6 +502,9 @@ 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); int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset); +int zynqmp_pm_set_sd_config(u32 node, enum pm_sd_config_type config, u32 value); +int zynqmp_pm_set_gem_config(u32 node, enum pm_gem_config_type config, + u32 value); #else static inline int zynqmp_pm_get_api_version(u32 *version) { @@ -745,6 +775,21 @@ static inline int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset) { return -ENODEV; } + +static inline int zynqmp_pm_set_sd_config(u32 node, + enum pm_sd_config_type config, + u32 value) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_set_gem_config(u32 node, + enum pm_gem_config_type config, + u32 value) +{ + return -ENODEV; +} + #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 17df341d35265c8e14d71a48886fc7dcf92ef8a1 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 11 Sep 2022 13:39:01 +0200 Subject: headers: Remove some left-over license text Remove a left-over from commit 2874c5fd2842 ("treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152") There is no need for an empty "License:". Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/0e5ff727626b748238f4b78932f81572143d8f0b.1662896317.git.christophe.jaillet@wanadoo.fr Signed-off-by: Jakub Kicinski --- include/linux/if_pppol2tp.h | 2 -- include/linux/if_pppox.h | 2 -- 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_pppol2tp.h b/include/linux/if_pppol2tp.h index 96d40942e5a3..c87efd333faa 100644 --- a/include/linux/if_pppol2tp.h +++ b/include/linux/if_pppol2tp.h @@ -4,8 +4,6 @@ * * This file supplies definitions required by the PPP over L2TP driver * (l2tp_ppp.c). All version information wrt this file is located in l2tp_ppp.c - * - * License: */ #ifndef __LINUX_IF_PPPOL2TP_H #define __LINUX_IF_PPPOL2TP_H diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index 69e813bcb947..ff3beda1312c 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -5,8 +5,6 @@ * * This file supplies definitions required by the PPP over Ethernet driver * (pppox.c). All version information wrt this file is located in pppox.c - * - * License: */ #ifndef __LINUX_IF_PPPOX_H #define __LINUX_IF_PPPOX_H -- cgit v1.2.3 From fdf214978a71b2749d26f6da2b1d51d9ac23831d Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Tue, 20 Sep 2022 08:15:24 -0600 Subject: bpf: Move nf_conn extern declarations to filter.h We're seeing the following new warnings on netdev/build_32bit and netdev/build_allmodconfig_warn CI jobs: ../net/core/filter.c:8608:1: warning: symbol 'nf_conn_btf_access_lock' was not declared. Should it be static? ../net/core/filter.c:8611:5: warning: symbol 'nfct_bsa' was not declared. Should it be static? Fix by ensuring extern declaration is present while compiling filter.o. Fixes: 864b656f82cc ("bpf: Add support for writing to nf_conn:mark") Signed-off-by: Daniel Xu Link: https://lore.kernel.org/r/2bd2e0283df36d8a4119605878edb1838d144174.1663683114.git.dxu@dxuuu.xyz Signed-off-by: Martin KaFai Lau --- include/linux/filter.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 75335432fcbc..98e28126c24b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -567,6 +567,12 @@ struct sk_filter { DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); +extern struct mutex nf_conn_btf_access_lock; +extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, u32 *next_btf_id, + enum bpf_type_flag *flag); + typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, const struct bpf_insn *insnsi, unsigned int (*bpf_func)(const void *, -- cgit v1.2.3 From 583c1f420173f7d84413a1a1fbf5109d798b4faa Mon Sep 17 00:00:00 2001 From: David Vernet Date: Mon, 19 Sep 2022 19:00:57 -0500 Subject: bpf: Define new BPF_MAP_TYPE_USER_RINGBUF map type We want to support a ringbuf map type where samples are published from user-space, to be consumed by BPF programs. BPF currently supports a kernel -> user-space circular ring buffer via the BPF_MAP_TYPE_RINGBUF map type. We'll need to define a new map type for user-space -> kernel, as none of the helpers exported for BPF_MAP_TYPE_RINGBUF will apply to a user-space producer ring buffer, and we'll want to add one or more helper functions that would not apply for a kernel-producer ring buffer. This patch therefore adds a new BPF_MAP_TYPE_USER_RINGBUF map type definition. The map type is useless in its current form, as there is no way to access or use it for anything until we one or more BPF helpers. A follow-on patch will therefore add a new helper function that allows BPF programs to run callbacks on samples that are published to the ring buffer. Signed-off-by: David Vernet Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220920000100.477320-2-void@manifault.com --- include/linux/bpf_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 2b9112b80171..2c6a4f2562a7 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -126,6 +126,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_USER_RINGBUF, user_ringbuf_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) -- cgit v1.2.3 From 20571567384428dfc9fe5cf9f2e942e1df13c2dd Mon Sep 17 00:00:00 2001 From: David Vernet Date: Mon, 19 Sep 2022 19:00:58 -0500 Subject: bpf: Add bpf_user_ringbuf_drain() helper In a prior change, we added a new BPF_MAP_TYPE_USER_RINGBUF map type which will allow user-space applications to publish messages to a ring buffer that is consumed by a BPF program in kernel-space. In order for this map-type to be useful, it will require a BPF helper function that BPF programs can invoke to drain samples from the ring buffer, and invoke callbacks on those samples. This change adds that capability via a new BPF helper function: bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags) BPF programs may invoke this function to run callback_fn() on a series of samples in the ring buffer. callback_fn() has the following signature: long callback_fn(struct bpf_dynptr *dynptr, void *context); Samples are provided to the callback in the form of struct bpf_dynptr *'s, which the program can read using BPF helper functions for querying struct bpf_dynptr's. In order to support bpf_ringbuf_drain(), a new PTR_TO_DYNPTR register type is added to the verifier to reflect a dynptr that was allocated by a helper function and passed to a BPF program. Unlike PTR_TO_STACK dynptrs which are allocated on the stack by a BPF program, PTR_TO_DYNPTR dynptrs need not use reference tracking, as the BPF helper is trusted to properly free the dynptr before returning. The verifier currently only supports PTR_TO_DYNPTR registers that are also DYNPTR_TYPE_LOCAL. Note that while the corresponding user-space libbpf logic will be added in a subsequent patch, this patch does contain an implementation of the .map_poll() callback for BPF_MAP_TYPE_USER_RINGBUF maps. This .map_poll() callback guarantees that an epoll-waiting user-space producer will receive at least one event notification whenever at least one sample is drained in an invocation of bpf_user_ringbuf_drain(), provided that the function is not invoked with the BPF_RB_NO_WAKEUP flag. If the BPF_RB_FORCE_WAKEUP flag is provided, a wakeup notification is sent even if no sample was drained. Signed-off-by: David Vernet Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220920000100.477320-3-void@manifault.com --- include/linux/bpf.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e0dbe0c0a17e..33e543b86e1a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -451,7 +451,7 @@ 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 points to a kernel-produced ringbuf record. */ DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), /* Size is known at compile time. */ @@ -656,6 +656,7 @@ enum bpf_reg_type { PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_FUNC, /* reg points to a bpf program function */ + PTR_TO_DYNPTR, /* reg points to a dynptr */ __BPF_REG_TYPE_MAX, /* Extended reg_types. */ @@ -1394,6 +1395,11 @@ struct bpf_array { #define BPF_MAP_CAN_READ BIT(0) #define BPF_MAP_CAN_WRITE BIT(1) +/* Maximum number of user-producer ring buffer samples that can be drained in + * a call to bpf_user_ringbuf_drain(). + */ +#define BPF_MAX_USER_RINGBUF_SAMPLES (128 * 1024) + static inline u32 bpf_map_flags_to_cap(struct bpf_map *map) { u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); @@ -2495,6 +2501,7 @@ extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_copy_from_user_task_proto; extern const struct bpf_func_proto bpf_set_retval_proto; extern const struct bpf_func_proto bpf_get_retval_proto; +extern const struct bpf_func_proto bpf_user_ringbuf_drain_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -2639,7 +2646,7 @@ 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 */ + /* Underlying data is a kernel-produced ringbuf record */ BPF_DYNPTR_TYPE_RINGBUF, }; -- cgit v1.2.3 From b8d31762a0ae6861e1115302ee338560d853e317 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Tue, 20 Sep 2022 09:59:42 +0200 Subject: btf: Allow dynamic pointer parameters in kfuncs Allow dynamic pointers (struct bpf_dynptr_kern *) to be specified as parameters in kfuncs. Also, ensure that dynamic pointers passed as argument are valid and initialized, are a pointer to the stack, and of the type local. More dynamic pointer types can be supported in the future. To properly detect whether a parameter is of the desired type, introduce the stringify_struct() macro to compare the returned structure name with the desired name. In addition, protect against structure renames, by halting the build with BUILD_BUG_ON(), so that developers have to revisit the code. To check if a dynamic pointer passed to the kfunc is valid and initialized, and if its type is local, export the existing functions is_dynptr_reg_valid_init() and is_dynptr_type_expected(). Cc: Joanne Koong Cc: Kumar Kartikeya Dwivedi Signed-off-by: Roberto Sassu Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220920075951.929132-5-roberto.sassu@huaweicloud.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 5 +++++ include/linux/btf.h | 9 +++++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e197f8fb27e2..9e1e6965f407 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -593,6 +593,11 @@ int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); +bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, + struct bpf_reg_state *reg); +bool is_dynptr_type_expected(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + enum bpf_arg_type arg_type); /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, diff --git a/include/linux/btf.h b/include/linux/btf.h index 1fcc833a8690..f9aababc5d78 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -52,6 +52,15 @@ #define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ #define KF_DESTRUCTIVE (1 << 6) /* kfunc performs destructive actions */ +/* + * Return the name of the passed struct, if exists, or halt the build if for + * example the structure gets renamed. In this way, developers have to revisit + * the code using that structure name, and update it accordingly. + */ +#define stringify_struct(x) \ + ({ BUILD_BUG_ON(sizeof(struct x) < 0); \ + __stringify(x); }) + struct btf; struct btf_member; struct btf_type; -- cgit v1.2.3 From 51df4865718540f51bb5d3e552c50dc88e1333d6 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Tue, 20 Sep 2022 09:59:43 +0200 Subject: bpf: Export bpf_dynptr_get_size() Export bpf_dynptr_get_size(), so that kernel code dealing with eBPF dynamic pointers can obtain the real size of data carried by this data structure. Signed-off-by: Roberto Sassu Reviewed-by: Joanne Koong Acked-by: KP Singh Acked-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220920075951.929132-6-roberto.sassu@huaweicloud.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 33e543b86e1a..6535fb1e21b9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2654,6 +2654,7 @@ 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); +u32 bpf_dynptr_get_size(struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_LSM void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); -- cgit v1.2.3 From 90fd8f26edd47942203639bf3a5dde8fa1931a0e Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Tue, 20 Sep 2022 09:59:44 +0200 Subject: KEYS: Move KEY_LOOKUP_ to include/linux/key.h and define KEY_LOOKUP_ALL In preparation for the patch that introduces the bpf_lookup_user_key() eBPF kfunc, move KEY_LOOKUP_ definitions to include/linux/key.h, to be able to validate the kfunc parameters. Add them to enum key_lookup_flag, so that all the current ones and the ones defined in the future are automatically exported through BTF and available to eBPF programs. Also, add KEY_LOOKUP_ALL to the enum, with the logical OR of currently defined flags as value, to facilitate checking whether a variable contains only those flags. Signed-off-by: Roberto Sassu Acked-by: Jarkko Sakkinen Link: https://lore.kernel.org/r/20220920075951.929132-7-roberto.sassu@huaweicloud.com Signed-off-by: Alexei Starovoitov --- include/linux/key.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index 7febc4881363..d27477faf00d 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -88,6 +88,12 @@ enum key_need_perm { KEY_DEFER_PERM_CHECK, /* Special: permission check is deferred */ }; +enum key_lookup_flag { + KEY_LOOKUP_CREATE = 0x01, + KEY_LOOKUP_PARTIAL = 0x02, + KEY_LOOKUP_ALL = (KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL), +}; + struct seq_file; struct user_struct; struct signal_struct; -- cgit v1.2.3 From f3cf4134c5c6c47b9b5c7aa3cb2d67e107887a7b Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Tue, 20 Sep 2022 09:59:45 +0200 Subject: bpf: Add bpf_lookup_*_key() and bpf_key_put() kfuncs Add the bpf_lookup_user_key(), bpf_lookup_system_key() and bpf_key_put() kfuncs, to respectively search a key with a given key handle serial number and flags, obtain a key from a pre-determined ID defined in include/linux/verification.h, and cleanup. Introduce system_keyring_id_check() to validate the keyring ID parameter of bpf_lookup_system_key(). Signed-off-by: Roberto Sassu Acked-by: Kumar Kartikeya Dwivedi Acked-by: Song Liu Link: https://lore.kernel.org/r/20220920075951.929132-8-roberto.sassu@huaweicloud.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 8 ++++++++ include/linux/verification.h | 8 ++++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6535fb1e21b9..a1435b019aca 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2664,4 +2664,12 @@ static inline void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) {} static inline void bpf_cgroup_atype_put(int cgroup_atype) {} #endif /* CONFIG_BPF_LSM */ +struct key; + +#ifdef CONFIG_KEYS +struct bpf_key { + struct key *key; + bool has_ref; +}; +#endif /* CONFIG_KEYS */ #endif /* _LINUX_BPF_H */ diff --git a/include/linux/verification.h b/include/linux/verification.h index a655923335ae..f34e50ebcf60 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -17,6 +17,14 @@ #define VERIFY_USE_SECONDARY_KEYRING ((struct key *)1UL) #define VERIFY_USE_PLATFORM_KEYRING ((struct key *)2UL) +static inline int system_keyring_id_check(u64 id) +{ + if (id > (unsigned long)VERIFY_USE_PLATFORM_KEYRING) + return -EINVAL; + + return 0; +} + /* * The use to which an asymmetric key is being put. */ -- cgit v1.2.3 From 05b24ff9b2cfabfcfd951daaa915a036ab53c9e1 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 16 Sep 2022 09:19:14 +0200 Subject: bpf: Prevent bpf program recursion for raw tracepoint probes We got report from sysbot [1] about warnings that were caused by bpf program attached to contention_begin raw tracepoint triggering the same tracepoint by using bpf_trace_printk helper that takes trace_printk_lock lock. Call Trace: ? trace_event_raw_event_bpf_trace_printk+0x5f/0x90 bpf_trace_printk+0x2b/0xe0 bpf_prog_a9aec6167c091eef_prog+0x1f/0x24 bpf_trace_run2+0x26/0x90 native_queued_spin_lock_slowpath+0x1c6/0x2b0 _raw_spin_lock_irqsave+0x44/0x50 bpf_trace_printk+0x3f/0xe0 bpf_prog_a9aec6167c091eef_prog+0x1f/0x24 bpf_trace_run2+0x26/0x90 native_queued_spin_lock_slowpath+0x1c6/0x2b0 _raw_spin_lock_irqsave+0x44/0x50 bpf_trace_printk+0x3f/0xe0 bpf_prog_a9aec6167c091eef_prog+0x1f/0x24 bpf_trace_run2+0x26/0x90 native_queued_spin_lock_slowpath+0x1c6/0x2b0 _raw_spin_lock_irqsave+0x44/0x50 bpf_trace_printk+0x3f/0xe0 bpf_prog_a9aec6167c091eef_prog+0x1f/0x24 bpf_trace_run2+0x26/0x90 native_queued_spin_lock_slowpath+0x1c6/0x2b0 _raw_spin_lock_irqsave+0x44/0x50 __unfreeze_partials+0x5b/0x160 ... The can be reproduced by attaching bpf program as raw tracepoint on contention_begin tracepoint. The bpf prog calls bpf_trace_printk helper. Then by running perf bench the spin lock code is forced to take slow path and call contention_begin tracepoint. Fixing this by skipping execution of the bpf program if it's already running, Using bpf prog 'active' field, which is being currently used by trampoline programs for the same reason. Moving bpf_prog_inc_misses_counter to syscall.c because trampoline.c is compiled in just for CONFIG_BPF_JIT option. Reviewed-by: Stanislav Fomichev Reported-by: syzbot+2251879aa068ad9c960d@syzkaller.appspotmail.com [1] https://lore.kernel.org/bpf/YxhFe3EwqchC%2FfYf@krava/T/#t Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20220916071914.7156-1-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a1435b019aca..edd43edb27d6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2042,6 +2042,8 @@ static inline bool has_current_bpf_ctx(void) { return !!current->bpf_ctx; } + +void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -2264,6 +2266,10 @@ static inline bool has_current_bpf_ctx(void) { return false; } + +static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog) +{ +} #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, -- cgit v1.2.3 From de84a090d99a3b991bd89cd86a94b65d15bd1bbe Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 20 Sep 2022 12:11:21 +0200 Subject: net: ethernet: mtk_eth_wed: add wed support for mt7986 chipset Introduce Wireless Etherne Dispatcher support on transmission side for mt7986 chipset Tested-by: Daniel Golle Co-developed-by: Bo Jiao Signed-off-by: Bo Jiao Co-developed-by: Sujuan Chen Signed-off-by: Sujuan Chen Signed-off-by: Lorenzo Bianconi Signed-off-by: Paolo Abeni --- include/linux/soc/mediatek/mtk_wed.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index 7e00cca06709..592221a7149b 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -14,6 +14,7 @@ struct mtk_wdma_desc; struct mtk_wed_ring { struct mtk_wdma_desc *desc; dma_addr_t desc_phys; + u32 desc_size; int size; u32 reg_base; @@ -45,10 +46,17 @@ struct mtk_wed_device { struct pci_dev *pci_dev; u32 wpdma_phys; + u32 wpdma_int; + u32 wpdma_mask; + u32 wpdma_tx; + u32 wpdma_txfree; u16 token_start; unsigned int nbuf; + u8 tx_tbit[MTK_WED_TX_QUEUES]; + u8 txfree_tbit; + 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); -- cgit v1.2.3 From 2b2ba3ecb2411c5e2a0d670be5e9ded2c93351e9 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 20 Sep 2022 12:11:22 +0200 Subject: net: ethernet: mtk_eth_wed: add axi bus support Other than pcie bus, introduce support for axi bus to mtk wed driver. Axi bus is used to connect mt7986-wmac soc chip available on mt7986 device. Tested-by: Daniel Golle Co-developed-by: Bo Jiao Signed-off-by: Bo Jiao Co-developed-by: Sujuan Chen Signed-off-by: Sujuan Chen Signed-off-by: Lorenzo Bianconi Signed-off-by: Paolo Abeni --- include/linux/soc/mediatek/mtk_wed.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index 592221a7149b..4450c8b7a1cb 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -11,6 +11,11 @@ struct mtk_wed_hw; struct mtk_wdma_desc; +enum mtk_wed_bus_tye { + MTK_WED_BUS_PCIE, + MTK_WED_BUS_AXI, +}; + struct mtk_wed_ring { struct mtk_wdma_desc *desc; dma_addr_t desc_phys; @@ -43,7 +48,11 @@ struct mtk_wed_device { /* filled by driver: */ struct { - struct pci_dev *pci_dev; + union { + struct platform_device *platform_dev; + struct pci_dev *pci_dev; + }; + enum mtk_wed_bus_tye bus_type; u32 wpdma_phys; u32 wpdma_int; -- cgit v1.2.3 From 21803630c4ffb433bab2951fbe0ee7b8dbcc8bcb Mon Sep 17 00:00:00 2001 From: Emeel Hakim Date: Wed, 21 Sep 2022 11:10:46 -0700 Subject: net/mlx5: Fix fields name prefix in MACsec Fix ifc fields name to be consistent with the device spec document. Fixes: 8385c51ff5bc ("net/mlx5: Introduce MACsec Connect-X offload hardware bits and structures") Signed-off-by: Emeel Hakim Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 8decbf9a7bdd..da0ed11fcebd 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -11585,15 +11585,15 @@ struct mlx5_ifc_macsec_offload_obj_bits { u8 confidentiality_en[0x1]; u8 reserved_at_41[0x1]; - u8 esn_en[0x1]; - u8 esn_overlap[0x1]; + u8 epn_en[0x1]; + u8 epn_overlap[0x1]; u8 reserved_at_44[0x2]; u8 confidentiality_offset[0x2]; u8 reserved_at_48[0x4]; u8 aso_return_reg[0x4]; u8 reserved_at_50[0x10]; - u8 esn_msb[0x20]; + u8 epn_msb[0x20]; u8 reserved_at_80[0x8]; u8 dekn[0x18]; -- cgit v1.2.3 From 23cc83c6ca87c9a4da62b9ddf4d0fc09f3054f81 Mon Sep 17 00:00:00 2001 From: Emeel Hakim Date: Wed, 21 Sep 2022 11:10:49 -0700 Subject: net/mlx5: Add ifc bits for MACsec extended packet number (EPN) and replay protection Add ifc bits related to advanced steering operations (ASO) and general object modify for macsec to use as part of offloading EPN and replay protection features. Reviewed-by: Raed Salem Signed-off-by: Emeel Hakim Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index da0ed11fcebd..bd577b99b146 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -11558,6 +11558,20 @@ struct mlx5_ifc_modify_ipsec_obj_in_bits { struct mlx5_ifc_ipsec_obj_bits ipsec_object; }; +enum { + MLX5_MACSEC_ASO_REPLAY_PROTECTION = 0x1, +}; + +enum { + MLX5_MACSEC_ASO_REPLAY_WIN_32BIT = 0x0, + MLX5_MACSEC_ASO_REPLAY_WIN_64BIT = 0x1, + MLX5_MACSEC_ASO_REPLAY_WIN_128BIT = 0x2, + MLX5_MACSEC_ASO_REPLAY_WIN_256BIT = 0x3, +}; + +#define MLX5_MACSEC_ASO_INC_SN 0x2 +#define MLX5_MACSEC_ASO_REG_C_4_5 0x2 + struct mlx5_ifc_macsec_aso_bits { u8 valid[0x1]; u8 reserved_at_1[0x1]; @@ -11619,6 +11633,21 @@ struct mlx5_ifc_create_macsec_obj_in_bits { struct mlx5_ifc_macsec_offload_obj_bits macsec_object; }; +struct mlx5_ifc_modify_macsec_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_macsec_offload_obj_bits macsec_object; +}; + +enum { + MLX5_MODIFY_MACSEC_BITMASK_EPN_OVERLAP = BIT(0), + MLX5_MODIFY_MACSEC_BITMASK_EPN_MSB = BIT(1), +}; + +struct mlx5_ifc_query_macsec_obj_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + struct mlx5_ifc_macsec_offload_obj_bits macsec_object; +}; + struct mlx5_ifc_encryption_key_obj_bits { u8 modify_field_select[0x40]; -- cgit v1.2.3 From 4411a6c0abd3e55b4a4fb9432b3a0553f12337c2 Mon Sep 17 00:00:00 2001 From: Emeel Hakim Date: Wed, 21 Sep 2022 11:10:53 -0700 Subject: net/mlx5e: Support MACsec offload extended packet number (EPN) MACsec EPN splits the packet number (PN) into two 32-bits fields, epn_lsb (32 least significant bits (LSBs) of PN) and epn_msb (32 most significant bits (MSBs) of PN). Epn_msb bits are managed by SW and for that HW is required to send an object change event of type EPN event notifying the SW to update the epn_msb in addition, once epn_msb is updated SW update HW with the new epn_msb value for HW to perform replay protection. To prevent HW from stopping while handling the event, SW manages another bit for HW called epn_overlap, HW uses the latter to get an indication regarding how to read the epn_msb value correctly while still receiving packets. Add epn event handling that updates the epn_overlap and epn_msb for every 2^31 packets according to the following logic: if epn_lsb crosses 2^31 (half sequence number wraparound) upon HW relevant event, SW updates the esn_overlap value to OLD (value = 1). When the epn_lsb crosses 2^32 (full sequence number wraparound) upon HW relevant event, SW updates the esn_overlap to NEW (value = 0) and increment the esn_msb. When using MACsec EPN a salt and short secure channel id (ssci) needs to be provided by the user, when offloading EPN need to pass this salt and ssci to the HW to be used in the initial vector (IV) calculations. Reviewed-by: Raed Salem Signed-off-by: Emeel Hakim Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Reported-by: kernel test robot Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/device.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 2927810f172b..dcd60fb9e6b4 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -325,6 +325,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR = 0x10, MLX5_EVENT_TYPE_WQ_ACCESS_ERROR = 0x11, MLX5_EVENT_TYPE_SRQ_CATAS_ERROR = 0x12, + MLX5_EVENT_TYPE_OBJECT_CHANGE = 0x27, MLX5_EVENT_TYPE_INTERNAL_ERROR = 0x08, MLX5_EVENT_TYPE_PORT_CHANGE = 0x09, @@ -699,6 +700,12 @@ struct mlx5_eqe_temp_warning { __be64 sensor_warning_lsb; } __packed; +struct mlx5_eqe_obj_change { + u8 rsvd0[2]; + __be16 obj_type; + __be32 obj_id; +} __packed; + #define SYNC_RST_STATE_MASK 0xf enum sync_rst_state_type { @@ -737,6 +744,7 @@ union ev_data { struct mlx5_eqe_xrq_err xrq_err; struct mlx5_eqe_sync_fw_update sync_fw_update; struct mlx5_eqe_vhca_state vhca_state; + struct mlx5_eqe_obj_change obj_change; } __packed; struct mlx5_eqe { -- cgit v1.2.3 From 72bc36956f73ac54f19a7ac7302fb274069bec18 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Tue, 20 Sep 2022 18:12:28 -0400 Subject: net: phylink: Document MAC_(A)SYM_PAUSE This documents the possible MLO_PAUSE_* settings which can result from different combinations of MAC_(A)SYM_PAUSE. Special note is paid to settings which can result from user configuration (MLO_PAUSE_AN). The autonegotiation results are more-or-less a direct consequence of IEEE 802.3 Table 28B-2. Signed-off-by: Sean Anderson Signed-off-by: David S. Miller --- include/linux/phylink.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 6d06896fc20d..1f997e14bf80 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -21,6 +21,35 @@ enum { MLO_AN_FIXED, /* Fixed-link mode */ MLO_AN_INBAND, /* In-band protocol */ + /* MAC_SYM_PAUSE and MAC_ASYM_PAUSE are used when configuring our + * autonegotiation advertisement. They correspond to the PAUSE and + * ASM_DIR bits defined by 802.3, respectively. + * + * The following table lists the values of tx_pause and rx_pause which + * might be requested in mac_link_up. The exact values depend on either + * the results of autonegotation (if MLO_PAUSE_AN is set) or user + * configuration (if MLO_PAUSE_AN is not set). + * + * MAC_SYM_PAUSE MAC_ASYM_PAUSE MLO_PAUSE_AN tx_pause/rx_pause + * ============= ============== ============ ================== + * 0 0 0 0/0 + * 0 0 1 0/0 + * 0 1 0 0/0, 0/1, 1/0, 1/1 + * 0 1 1 0/0, 1/0 + * 1 0 0 0/0, 1/1 + * 1 0 1 0/0, 1/1 + * 1 1 0 0/0, 0/1, 1/0, 1/1 + * 1 1 1 0/0, 0/1, 1/1 + * + * If you set MAC_ASYM_PAUSE, the user may request any combination of + * tx_pause and rx_pause. You do not have to support these + * combinations. + * + * However, you should support combinations of tx_pause and rx_pause + * which might be the result of autonegotation. For example, don't set + * MAC_SYM_PAUSE unless your device can support tx_pause and rx_pause + * at the same time. + */ MAC_SYM_PAUSE = BIT(0), MAC_ASYM_PAUSE = BIT(1), MAC_10HD = BIT(2), -- cgit v1.2.3 From 606116529ab2d12e93bf751f74ed50a621b46846 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Tue, 20 Sep 2022 18:12:29 -0400 Subject: net: phylink: Export phylink_caps_to_linkmodes This function is convenient for MAC drivers. They can use it to add or remove particular link modes based on capabilities (such as if half duplex is not supported for a particular interface mode). Signed-off-by: Sean Anderson Signed-off-by: David S. Miller --- include/linux/phylink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 1f997e14bf80..7cf26d7a522d 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -547,6 +547,7 @@ void pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); #endif +void phylink_caps_to_linkmodes(unsigned long *linkmodes, unsigned long caps); void phylink_get_linkmodes(unsigned long *linkmodes, phy_interface_t interface, unsigned long mac_capabilities); void phylink_generic_validate(struct phylink_config *config, -- cgit v1.2.3 From 3e6eab8f3ef93cd78cd4b67f497ef6035eb073ad Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Tue, 20 Sep 2022 18:12:30 -0400 Subject: net: phylink: Generate caps and convert to linkmodes separately If we call phylink_caps_to_linkmodes directly from phylink_get_linkmodes, it is difficult to re-use this functionality in MAC drivers. This is because MAC drivers must then work with an ethtool linkmode bitmap, instead of with mac capabilities. Instead, let the caller of phylink_get_linkmodes do the conversion. To reflect this change, rename the function to phylink_get_capabilities. Signed-off-by: Sean Anderson Signed-off-by: David S. Miller --- include/linux/phylink.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 7cf26d7a522d..cc039ae7e80c 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -548,8 +548,8 @@ void pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, #endif void phylink_caps_to_linkmodes(unsigned long *linkmodes, unsigned long caps); -void phylink_get_linkmodes(unsigned long *linkmodes, phy_interface_t interface, - unsigned long mac_capabilities); +unsigned long phylink_get_capabilities(phy_interface_t interface, + unsigned long mac_capabilities); void phylink_generic_validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); -- cgit v1.2.3 From 0c3e10cb44232833a50cb8e3e784c432906a60c1 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Tue, 20 Sep 2022 18:12:31 -0400 Subject: net: phy: Add support for rate matching This adds support for rate matching (also known as rate adaptation) to the phy subsystem. The general idea is that the phy interface runs at one speed, and the MAC throttles the rate at which it sends packets to the link speed. There's a good overview of several techniques for achieving this at [1]. This patch adds support for three: pause-frame based (such as in Aquantia phys), CRS-based (such as in 10PASS-TS and 2BASE-TL), and open-loop-based (such as in 10GBASE-W). This patch makes a few assumptions and a few non assumptions about the types of rate matching available. First, it assumes that different phys may use different forms of rate matching. Second, it assumes that phys can use rate matching for any of their supported link speeds (e.g. if a phy supports 10BASE-T and XGMII, then it can adapt XGMII to 10BASE-T). Third, it does not assume that all interface modes will use the same form of rate matching. Fourth, it does not assume that all phy devices will support rate matching (even if some do). Relaxing or strengthening these (non-)assumptions could result in a different API. For example, if all interface modes were assumed to use the same form of rate matching, then a bitmask of interface modes supportting rate matching would suffice. For some better visibility into the process, the current rate matching mode is exposed as part of the ethtool ksettings. For the moment, only read access is supported. I'm not sure what userspace might want to configure yet (disable it altogether, disable just one mode, specify the mode to use, etc.). For the moment, since only pause-based rate adaptation support is added in the next few commits, rate matching can be disabled altogether by adjusting the advertisement. 802.3 calls this feature "rate adaptation" in clause 49 (10GBASE-R) and "rate matching" in clause 61 (10PASS-TL and 2BASE-TS). Aquantia also calls this feature "rate adaptation". I chose "rate matching" because it is shorter, and because Russell doesn't think "adaptation" is correct in this context. Signed-off-by: Sean Anderson Signed-off-by: David S. Miller --- include/linux/phy.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 337230c135f7..9c66f357f489 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -280,7 +280,6 @@ static inline const char *phy_modes(phy_interface_t interface) } } - #define PHY_INIT_TIMEOUT 100000 #define PHY_FORCE_TIMEOUT 10 @@ -574,6 +573,7 @@ struct macsec_ops; * @lp_advertising: Current link partner advertised linkmodes * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited * @autoneg: Flag autoneg being used + * @rate_matching: Current rate matching mode * @link: Current link state * @autoneg_complete: Flag auto negotiation of the link has completed * @mdix: Current crossover @@ -641,6 +641,8 @@ struct phy_device { unsigned irq_suspended:1; unsigned irq_rerun:1; + int rate_matching; + enum phy_state state; u32 dev_flags; @@ -805,6 +807,21 @@ struct phy_driver { */ int (*get_features)(struct phy_device *phydev); + /** + * @get_rate_matching: Get the supported type of rate matching for a + * particular phy interface. This is used by phy consumers to determine + * whether to advertise lower-speed modes for that interface. It is + * assumed that if a rate matching mode is supported on an interface, + * then that interface's rate can be adapted to all slower link speeds + * supported by the phy. If iface is %PHY_INTERFACE_MODE_NA, and the phy + * supports any kind of rate matching for any interface, then it must + * return that rate matching mode (preferring %RATE_MATCH_PAUSE to + * %RATE_MATCH_CRS). If the interface is not supported, this should + * return %RATE_MATCH_NONE. + */ + int (*get_rate_matching)(struct phy_device *phydev, + phy_interface_t iface); + /* PHY Power Management */ /** @suspend: Suspend the hardware, saving state if needed */ int (*suspend)(struct phy_device *phydev); @@ -971,6 +988,7 @@ struct phy_fixup { const char *phy_speed_to_str(int speed); const char *phy_duplex_to_str(unsigned int duplex); +const char *phy_rate_matching_to_str(int rate_matching); int phy_interface_num_ports(phy_interface_t interface); @@ -1687,6 +1705,8 @@ int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); +int phy_get_rate_matching(struct phy_device *phydev, + phy_interface_t iface); void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); -- cgit v1.2.3 From ae0e4bb2a0e0e434e9f98fb4994093ec2ee71997 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Tue, 20 Sep 2022 18:12:32 -0400 Subject: net: phylink: Adjust link settings based on rate matching If the phy is configured to use pause-based rate matching, ensure that the link is full duplex with pause frame reception enabled. As suggested, if pause-based rate matching is enabled by the phy, then pause reception is unconditionally enabled. The interface duplex is determined based on the rate matching type. When rate matching is enabled, so is the speed. We assume the maximum interface speed is used. This is only relevant for MLO_AN_PHY. For MLO_AN_INBAND, the MAC/PCS's view of the interface speed will be used. Although there are no RATE_ADAPT_CRS phys in-tree, it has been added for comparison (and the implementation is quite simple). Co-developed-by: Russell King Signed-off-by: Sean Anderson Signed-off-by: David S. Miller --- include/linux/phylink.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index cc039ae7e80c..5c99c21e42b5 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -88,6 +88,10 @@ static inline bool phylink_autoneg_inband(unsigned int mode) * @speed: link speed, one of the SPEED_* constants. * @duplex: link duplex mode, one of DUPLEX_* constants. * @pause: link pause state, described by MLO_PAUSE_* constants. + * @rate_matching: rate matching being performed, one of the RATE_MATCH_* + * constants. If rate matching is taking place, then the speed/duplex of + * the medium link mode (@speed and @duplex) and the speed/duplex of the phy + * interface mode (@interface) are different. * @link: true if the link is up. * @an_enabled: true if autonegotiation is enabled/desired. * @an_complete: true if autonegotiation has completed. @@ -99,6 +103,7 @@ struct phylink_link_state { int speed; int duplex; int pause; + int rate_matching; unsigned int link:1; unsigned int an_enabled:1; unsigned int an_complete:1; -- cgit v1.2.3 From b7e9294885b610791fcebc799bf2a9e219446fd6 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Tue, 20 Sep 2022 18:12:33 -0400 Subject: net: phylink: Adjust advertisement based on rate matching This adds support for adjusting the advertisement for pause-based rate matching. This may result in a lossy link, since the final link settings are not adjusted. Asymmetric pause support is necessary. It would be possible for a MAC supporting only symmetric pause to use pause-based rate adaptation, but only if pause reception was enabled as well. Signed-off-by: Sean Anderson Signed-off-by: David S. Miller --- include/linux/phylink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 5c99c21e42b5..664dd409feb9 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -554,7 +554,8 @@ void pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, void phylink_caps_to_linkmodes(unsigned long *linkmodes, unsigned long caps); unsigned long phylink_get_capabilities(phy_interface_t interface, - unsigned long mac_capabilities); + unsigned long mac_capabilities, + int rate_matching); void phylink_generic_validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); -- cgit v1.2.3 From bf7a87f1075f67c286f794519f0fedfa8b0b18cc Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 26 Sep 2022 17:33:35 +0200 Subject: kprobes: Add new KPROBE_FLAG_ON_FUNC_ENTRY kprobe flag Adding KPROBE_FLAG_ON_FUNC_ENTRY kprobe flag to indicate that attach address is on function entry. This is used in following changes in get_func_ip helper to return correct function address. Acked-by: Masami Hiramatsu (Google) Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20220926153340.1621984-2-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/kprobes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 55041d2f884d..a0b92be98984 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -103,6 +103,7 @@ struct kprobe { * this flag is only for optimized_kprobe. */ #define KPROBE_FLAG_FTRACE 8 /* probe is using ftrace */ +#define KPROBE_FLAG_ON_FUNC_ENTRY 16 /* probe is on the function entry */ /* Has this kprobe gone ? */ static inline bool kprobe_gone(struct kprobe *p) -- cgit v1.2.3 From 19c02415da2345d0dda2b5c4495bc17cc14b18b5 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 26 Sep 2022 11:47:38 -0700 Subject: bpf: use bpf_prog_pack for bpf_dispatcher Allocate bpf_dispatcher with bpf_prog_pack_alloc so that bpf_dispatcher can share pages with bpf programs. arch_prepare_bpf_dispatcher() is updated to provide a RW buffer as working area for arch code to write to. This also fixes CPA W^X warnning like: CPA refuse W^X violation: 8000000000000163 -> 0000000000000163 range: ... Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20220926184739.3512547-2-song@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 ++- include/linux/filter.h | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index edd43edb27d6..9ae155c75014 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -946,6 +946,7 @@ struct bpf_dispatcher { struct bpf_dispatcher_prog progs[BPF_DISPATCHER_MAX]; int num_progs; void *image; + void *rw_image; u32 image_off; struct bpf_ksym ksym; }; @@ -964,7 +965,7 @@ int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampolin struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); -int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs); +int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs); #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ diff --git a/include/linux/filter.h b/include/linux/filter.h index 98e28126c24b..efc42a6e3aed 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1023,6 +1023,8 @@ extern long bpf_jit_limit_max; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); +void bpf_jit_fill_hole_with_zero(void *area, unsigned int size); + struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, @@ -1035,6 +1037,9 @@ void bpf_jit_free(struct bpf_prog *fp); struct bpf_binary_header * bpf_jit_binary_pack_hdr(const struct bpf_prog *fp); +void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns); +void bpf_prog_pack_free(struct bpf_binary_header *hdr); + static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { return list_empty(&fp->aux->ksym.lnode) || -- cgit v1.2.3 From 5b0d1c7bd5722467960829af51d523f5a6ffd848 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 26 Sep 2022 11:47:39 -0700 Subject: bpf: Enforce W^X for bpf trampoline Mark the trampoline as RO+X after arch_prepare_bpf_trampoline, so that the trampoine follows W^X rule strictly. This will turn off warnings like CPA refuse W^X violation: 8000000000000163 -> 0000000000000163 range: ... Also remove bpf_jit_alloc_exec_page(), since it is not used any more. Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20220926184739.3512547-3-song@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9ae155c75014..5161fac0513f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1008,7 +1008,6 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ -void *bpf_jit_alloc_exec_page(void); void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); -- cgit v1.2.3 From 976a859c9c68fdf160379bfc154431489f318292 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Wed, 7 Sep 2022 16:36:23 -0700 Subject: net/mlx5: Expose NPPS related registers Add management capability bits indicating firmware may support N pulses per second. Add corresponding fields in MTPPS register. Signed-off-by: Aya Levin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 06eab92b9fb3..e929b0dcd985 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9792,7 +9792,9 @@ struct mlx5_ifc_pcam_reg_bits { struct mlx5_ifc_mcam_enhanced_features_bits { u8 reserved_at_0[0x5d]; u8 mcia_32dwords[0x1]; - u8 reserved_at_5e[0xc]; + u8 out_pulse_duration_ns[0x1]; + u8 npps_period[0x1]; + u8 reserved_at_60[0xa]; u8 reset_state[0x1]; u8 ptpcyc2realtime_modify[0x1]; u8 reserved_at_6c[0x2]; @@ -10292,7 +10294,12 @@ struct mlx5_ifc_mtpps_reg_bits { u8 reserved_at_18[0x4]; u8 cap_max_num_of_pps_out_pins[0x4]; - u8 reserved_at_20[0x24]; + u8 reserved_at_20[0x13]; + u8 cap_log_min_npps_period[0x5]; + u8 reserved_at_38[0x3]; + u8 cap_log_min_out_pulse_duration_ns[0x5]; + + u8 reserved_at_40[0x4]; u8 cap_pin_3_mode[0x4]; u8 reserved_at_48[0x4]; u8 cap_pin_2_mode[0x4]; @@ -10311,7 +10318,9 @@ struct mlx5_ifc_mtpps_reg_bits { u8 cap_pin_4_mode[0x4]; u8 field_select[0x20]; - u8 reserved_at_a0[0x60]; + u8 reserved_at_a0[0x20]; + + u8 npps_period[0x40]; u8 enable[0x1]; u8 reserved_at_101[0xb]; @@ -10320,7 +10329,8 @@ struct mlx5_ifc_mtpps_reg_bits { u8 pin_mode[0x4]; u8 pin[0x8]; - u8 reserved_at_120[0x20]; + u8 reserved_at_120[0x2]; + u8 out_pulse_duration_ns[0x1e]; u8 time_stamp[0x40]; -- cgit v1.2.3 From f0462bc3e9024e9738fcd1a026456238317d84c7 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Wed, 7 Sep 2022 16:36:24 -0700 Subject: net/mlx5: Add support for NPPS with real time mode Add support for setting NPPS. NPPS is currently available in REAL_TIME_CLOCK mode only. In addition allow the user to set the pulse duration. When NPPS pulse duration is not set explicitly by the user, driver set it to 50% of the NPPS period. Signed-off-by: Aya Levin Reviewed-by: Eran Ben Elisha Reviewed-by: Saeed Mahameed Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 954af9cafb1d..481506376344 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -698,6 +698,8 @@ struct mlx5_pps { struct work_struct out_work; u64 start[MAX_PIN_NUM]; u8 enabled; + u64 min_npps_period; + u64 min_out_pulse_duration_ns; }; struct mlx5_timer { -- cgit v1.2.3 From 8d1ac895fff96a228db20db92243e93687659ef7 Mon Sep 17 00:00:00 2001 From: "Liu, Changcheng" Date: Wed, 7 Sep 2022 16:36:25 -0700 Subject: net/mlx5: add IFC bits for bypassing port select flow table port_select_flow_table_bypass - When set, device supports bypass port select flow table. active_port - Bitmask indicates the current active ports in PORT_SELECT_FT LAG. MLX5_SET_HCA_CAP_OP_MODE_PORT_SELECTION - op_mod to operate PORT_SELECTION_Capabilities. Signed-off-by: Liu, Changcheng Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index e929b0dcd985..b7f4e93df0f2 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -68,6 +68,7 @@ enum { MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, MLX5_SET_HCA_CAP_OP_MOD_ROCE = 0x4, + MLX5_SET_HCA_CAP_OP_MODE_PORT_SELECTION = 0x25, }; enum { @@ -814,7 +815,9 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_port_selection_cap_bits { u8 reserved_at_0[0x10]; u8 port_select_flow_table[0x1]; - u8 reserved_at_11[0xf]; + u8 reserved_at_11[0x1]; + u8 port_select_flow_table_bypass[0x1]; + u8 reserved_at_13[0xd]; u8 reserved_at_20[0x1e0]; @@ -10933,7 +10936,9 @@ struct mlx5_ifc_lagc_bits { u8 reserved_at_18[0x5]; u8 lag_state[0x3]; - u8 reserved_at_20[0x14]; + u8 reserved_at_20[0xc]; + u8 active_port[0x4]; + u8 reserved_at_30[0x4]; u8 tx_remap_affinity_2[0x4]; u8 reserved_at_38[0x4]; u8 tx_remap_affinity_1[0x4]; -- cgit v1.2.3 From a83bb5df2ac604ab418fbe0a8720f55de46652eb Mon Sep 17 00:00:00 2001 From: "Liu, Changcheng" Date: Wed, 7 Sep 2022 16:36:26 -0700 Subject: RDMA/mlx5: Don't set tx affinity when lag is in hash mode In hash mode, without setting tx affinity explicitly, the port select flow table decides which port is used for the traffic. If port_select_flow_table_bypass capability is supported and tx affinity is set explicitly for QP/TIS, they will be added into the explicit affinity table in FW to check which port is used for the traffic. 1. The overloaded explicit affinity table may affect performance. To avoid this, do not set tx affinity explicitly by default. 2. The packets of the same flow need to be transmitted on the same port. Because the packets of the same flow use different QPs in slow & fast path, it shouldn't set tx affinity explicitly for these QPs. Signed-off-by: Liu, Changcheng Reviewed-by: Mark Bloch Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 481506376344..9114caceb2b5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1153,6 +1153,7 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev); bool mlx5_lag_is_roce(struct mlx5_core_dev *dev); bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev); bool mlx5_lag_is_active(struct mlx5_core_dev *dev); +bool mlx5_lag_mode_is_hash(struct mlx5_core_dev *dev); bool mlx5_lag_is_master(struct mlx5_core_dev *dev); bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev); struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 66af4fe37119dbf6a82078949a82e625155777ef Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Wed, 7 Sep 2022 16:36:30 -0700 Subject: net/mlx5: Remove unused functions Remove functions which are no longer used in the driver: mlx5e_ipsec_is_tx_flow mlx5_health_flush get_cqe_enhanced_num_mini_cqes get_cqe_l3_hdr_type mlx5_health_flush mlx5_fs_is_ipsec_flow _mlx5_fs_is_outer_ipproto_flow mlx5_fs_is_outer_tcp_flow mlx5_fs_is_outer_udp_flow mlx5_fs_is_vxlan_flow mlx5_fs_is_outer_ipsec_flow Signed-off-by: Gal Pressman Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 11 ---------- include/linux/mlx5/driver.h | 1 - include/linux/mlx5/fs_helpers.h | 48 ----------------------------------------- 3 files changed, 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 5b41b9fb3d48..753753f3ce12 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -874,12 +874,6 @@ static inline u8 get_cqe_opcode(struct mlx5_cqe64 *cqe) return cqe->op_own >> 4; } -static inline u8 get_cqe_enhanced_num_mini_cqes(struct mlx5_cqe64 *cqe) -{ - /* num_of_mini_cqes is zero based */ - return get_cqe_opcode(cqe) + 1; -} - static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) { return (cqe->lro.tcppsh_abort_dupack >> 6) & 1; @@ -890,11 +884,6 @@ static inline u8 get_cqe_l4_hdr_type(struct mlx5_cqe64 *cqe) return (cqe->l4_l3_hdr_type >> 4) & 0x7; } -static inline u8 get_cqe_l3_hdr_type(struct mlx5_cqe64 *cqe) -{ - return (cqe->l4_l3_hdr_type >> 2) & 0x3; -} - static inline bool cqe_is_tunneled(struct mlx5_cqe64 *cqe) { return cqe->tls_outer_l3_tunneled & 0x1; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 9114caceb2b5..52f34fe47049 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1018,7 +1018,6 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); -void mlx5_health_flush(struct mlx5_core_dev *dev); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/fs_helpers.h b/include/linux/mlx5/fs_helpers.h index 9db21cd0e92c..bc5125bc0561 100644 --- a/include/linux/mlx5/fs_helpers.h +++ b/include/linux/mlx5/fs_helpers.h @@ -38,46 +38,6 @@ #define MLX5_FS_IPV4_VERSION 4 #define MLX5_FS_IPV6_VERSION 6 -static inline bool mlx5_fs_is_ipsec_flow(const u32 *match_c) -{ - void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c, - misc_parameters); - - return MLX5_GET(fte_match_set_misc, misc_params_c, outer_esp_spi); -} - -static inline bool _mlx5_fs_is_outer_ipproto_flow(const u32 *match_c, - const u32 *match_v, u8 match) -{ - const void *headers_c = MLX5_ADDR_OF(fte_match_param, match_c, - outer_headers); - const void *headers_v = MLX5_ADDR_OF(fte_match_param, match_v, - outer_headers); - - return MLX5_GET(fte_match_set_lyr_2_4, headers_c, ip_protocol) == 0xff && - MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol) == match; -} - -static inline bool mlx5_fs_is_outer_tcp_flow(const u32 *match_c, - const u32 *match_v) -{ - return _mlx5_fs_is_outer_ipproto_flow(match_c, match_v, IPPROTO_TCP); -} - -static inline bool mlx5_fs_is_outer_udp_flow(const u32 *match_c, - const u32 *match_v) -{ - return _mlx5_fs_is_outer_ipproto_flow(match_c, match_v, IPPROTO_UDP); -} - -static inline bool mlx5_fs_is_vxlan_flow(const u32 *match_c) -{ - void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c, - misc_parameters); - - return MLX5_GET(fte_match_set_misc, misc_params_c, vxlan_vni); -} - static inline bool _mlx5_fs_is_outer_ipv_flow(struct mlx5_core_dev *mdev, const u32 *match_c, const u32 *match_v, int version) @@ -131,12 +91,4 @@ mlx5_fs_is_outer_ipv6_flow(struct mlx5_core_dev *mdev, const u32 *match_c, MLX5_FS_IPV6_VERSION); } -static inline bool mlx5_fs_is_outer_ipsec_flow(const u32 *match_c) -{ - void *misc_params_c = - MLX5_ADDR_OF(fte_match_param, match_c, misc_parameters); - - return MLX5_GET(fte_match_set_misc, misc_params_c, outer_esp_spi); -} - #endif -- cgit v1.2.3 From b53ff37fcd5c7038d9dd000dcf682575a8f47999 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Wed, 7 Sep 2022 16:36:31 -0700 Subject: net/mlx5: Remove unused structs Remove structs which are no longer used in the driver: mlx5dr_cmd_qp_create_attr mlx5_fs_dr_ns mlx5_pas Signed-off-by: Gal Pressman Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 52f34fe47049..949feb7f889f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -857,11 +857,6 @@ struct mlx5_cmd_work_ent { refcount_t refcnt; }; -struct mlx5_pas { - u64 pa; - u8 log_sz; -}; - enum phy_port_state { MLX5_AAA_111 }; -- cgit v1.2.3 From 9175d8103780084e70bc89f2040ea62dc30f6f60 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 7 Sep 2022 16:36:32 -0700 Subject: net/mlx5: Remove from FPGA IFC file not-needed definitions Move IP layout bits definitions to be close to the place that actually uses it, together with removal extra defines that not in-use. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 16 ++++++++++++++++ include/linux/mlx5/mlx5_ifc_fpga.h | 24 ------------------------ 2 files changed, 16 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b7f4e93df0f2..c25f2ce75734 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -478,6 +478,22 @@ struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 reserved_at_6[0x1a]; }; +struct mlx5_ifc_ipv4_layout_bits { + u8 reserved_at_0[0x60]; + + u8 ipv4[0x20]; +}; + +struct mlx5_ifc_ipv6_layout_bits { + u8 ipv6[16][0x8]; +}; + +union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { + struct mlx5_ifc_ipv6_layout_bits ipv6_layout; + struct mlx5_ifc_ipv4_layout_bits ipv4_layout; + u8 reserved_at_0[0x80]; +}; + struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 smac_47_16[0x20]; diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index 45c7c0d67635..0596472923ad 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -32,30 +32,6 @@ #ifndef MLX5_IFC_FPGA_H #define MLX5_IFC_FPGA_H -struct mlx5_ifc_ipv4_layout_bits { - u8 reserved_at_0[0x60]; - - u8 ipv4[0x20]; -}; - -struct mlx5_ifc_ipv6_layout_bits { - u8 ipv6[16][0x8]; -}; - -union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { - struct mlx5_ifc_ipv6_layout_bits ipv6_layout; - struct mlx5_ifc_ipv4_layout_bits ipv4_layout; - u8 reserved_at_0[0x80]; -}; - -enum { - MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX = 0x2c9, -}; - -enum { - MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC = 0x2, -}; - struct mlx5_ifc_fpga_shell_caps_bits { u8 max_num_qps[0x10]; u8 reserved_at_10[0x8]; -- cgit v1.2.3 From f0d74c4da1f060d2a66976193712a5e6abd361f5 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Mon, 26 Sep 2022 11:49:53 -0700 Subject: bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com --- include/linux/bpf.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5161fac0513f..0f3eaf3ed98c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1796,6 +1796,27 @@ int bpf_obj_get_user(const char __user *pathname, int flags); extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } +/* + * The task type of iterators. + * + * For BPF task iterators, they can be parameterized with various + * parameters to visit only some of tasks. + * + * BPF_TASK_ITER_ALL (default) + * Iterate over resources of every task. + * + * BPF_TASK_ITER_TID + * Iterate over resources of a task/tid. + * + * BPF_TASK_ITER_TGID + * Iterate over resources of every task of a process / task group. + */ +enum bpf_iter_task_type { + BPF_TASK_ITER_ALL = 0, + BPF_TASK_ITER_TID, + BPF_TASK_ITER_TGID, +}; + struct bpf_iter_aux_info { /* for map_elem iter */ struct bpf_map *map; @@ -1805,6 +1826,10 @@ struct bpf_iter_aux_info { struct cgroup *start; /* starting cgroup */ enum bpf_cgroup_iter_order order; } cgroup; + struct { + enum bpf_iter_task_type type; + u32 pid; + } task; }; typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, -- cgit v1.2.3 From 6eaab4dfdd30ea8fb0dd4ee04940676c12b728e8 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 23 Sep 2022 17:39:01 +0100 Subject: net: introduce struct ubuf_info_msgzc We're going to split struct ubuf_info and leave there only mandatory fields. Users are free to extend it. Add struct ubuf_info_msgzc, which will be an extended version for MSG_ZEROCOPY and some other users. It duplicates of struct ubuf_info for now and will be removed in a couple of patches. Signed-off-by: Pavel Begunkov Acked-by: Paolo Abeni Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f15d5b62539b..fd7dcb977fdf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -554,7 +554,28 @@ struct ubuf_info { } mmp; }; +struct ubuf_info_msgzc { + struct ubuf_info ubuf; + + union { + struct { + unsigned long desc; + void *ctx; + }; + struct { + u32 id; + u16 len; + u16 zerocopy:1; + u32 bytelen; + }; + }; + + struct mmpin mmp; +}; + #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) +#define uarg_to_msgzc(ubuf_ptr) container_of((ubuf_ptr), struct ubuf_info_msgzc, \ + ubuf) int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); -- cgit v1.2.3 From e7d2b510165fff6bedc9cca88c071ad846850c74 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 23 Sep 2022 17:39:04 +0100 Subject: net: shrink struct ubuf_info We can benefit from a smaller struct ubuf_info, so leave only mandatory fields and let users to decide how they want to extend it. Convert MSG_ZEROCOPY to struct ubuf_info_msgzc and remove duplicated fields. This reduces the size from 48 bytes to just 16. Signed-off-by: Pavel Begunkov Acked-by: Paolo Abeni Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fd7dcb977fdf..920eb6413fee 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -533,25 +533,8 @@ enum { struct ubuf_info { void (*callback)(struct sk_buff *, struct ubuf_info *, bool zerocopy_success); - union { - struct { - unsigned long desc; - void *ctx; - }; - struct { - u32 id; - u16 len; - u16 zerocopy:1; - u32 bytelen; - }; - }; refcount_t refcnt; u8 flags; - - struct mmpin { - struct user_struct *user; - unsigned int num_pg; - } mmp; }; struct ubuf_info_msgzc { @@ -570,7 +553,10 @@ struct ubuf_info_msgzc { }; }; - struct mmpin mmp; + struct mmpin { + struct user_struct *user; + unsigned int num_pg; + } mmp; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) -- cgit v1.2.3 From b48b89f9c189d24eb5e2b4a0ac067da5a24ee86d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 27 Sep 2022 06:27:53 -0700 Subject: net: drop the weight argument from netif_napi_add We tell driver developers to always pass NAPI_POLL_WEIGHT as the weight to netif_napi_add(). This may be confusing to newcomers, drop the weight argument, those who really need to tweak the weight can use netif_napi_add_weight(). Acked-by: Marc Kleine-Budde # for CAN Link: https://lore.kernel.org/r/20220927132753.750069-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9f42fc871c3b..7a084a1c14e9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2553,16 +2553,15 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, * @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. */ static inline void netif_napi_add(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight) + int (*poll)(struct napi_struct *, int)) { - netif_napi_add_weight(dev, napi, poll, weight); + netif_napi_add_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } static inline void -- cgit v1.2.3 From 40b72108f9c609c5043903efb70c52d46b8aa871 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 27 Sep 2022 13:35:56 -0700 Subject: net/mlx5: Add the log_min_mkey_entity_size capability Add the capability that will allow the driver to determine the minimal MTT page size to be able to map the smallest possible pages in XSK. The older firmwares that don't have this capability default to 12 (i.e. 4096-byte pages). Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Reviewed-by: Saeed Mahameed Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3d963c0e47e4..1ad762e22d86 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1878,7 +1878,13 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 max_reformat_remove_size[0x8]; u8 max_reformat_remove_offset[0x8]; - u8 reserved_at_c0[0x160]; + u8 reserved_at_c0[0xe0]; + + u8 reserved_at_1a0[0xb]; + u8 log_min_mkey_entity_size[0x5]; + u8 reserved_at_1b0[0x10]; + + u8 reserved_at_1c0[0x60]; u8 reserved_at_220[0x1]; u8 sw_vhca_id_valid[0x1]; -- cgit v1.2.3 From 64696c40d03c01e0ea2e3e9aa1c490a7b6a1b6be Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 29 Sep 2022 00:04:03 -0700 Subject: bpf: Add __bpf_prog_{enter,exit}_struct_ops for struct_ops trampoline The struct_ops prog is to allow using bpf to implement the functions in a struct (eg. kernel module). The current usage is to implement the tcp_congestion. The kernel does not call the tcp-cc's ops (ie. the bpf prog) in a recursive way. The struct_ops is sharing the tracing-trampoline's enter/exit function which tracks prog->active to avoid recursion. It is needed for tracing prog. However, it turns out the struct_ops bpf prog will hit this prog->active and unnecessarily skipped running the struct_ops prog. eg. The '.ssthresh' may run in_task() and then interrupted by softirq that runs the same '.ssthresh'. Skip running the '.ssthresh' will end up returning random value to the caller. The patch adds __bpf_prog_{enter,exit}_struct_ops for the struct_ops trampoline. They do not track the prog->active to detect recursion. One exception is when the tcp_congestion's '.init' ops is doing bpf_setsockopt(TCP_CONGESTION) and then recurs to the same '.init' ops. This will be addressed in the following patches. Fixes: ca06f55b9002 ("bpf: Add per-program recursion prevention mechanism") Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20220929070407.965581-2-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0f3eaf3ed98c..9e7d46d16032 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -864,6 +864,10 @@ u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); +u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit_struct_ops(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); -- cgit v1.2.3 From 061ff040710e9f6f043d1fa80b1b362d2845b17a Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 29 Sep 2022 00:04:06 -0700 Subject: bpf: tcp: Stop bpf_setsockopt(TCP_CONGESTION) in init ops to recur itself When a bad bpf prog '.init' calls bpf_setsockopt(TCP_CONGESTION, "itself"), it will trigger this loop: .init => bpf_setsockopt(tcp_cc) => .init => bpf_setsockopt(tcp_cc) ... ... => .init => bpf_setsockopt(tcp_cc). It was prevented by the prog->active counter before but the prog->active detection cannot be used in struct_ops as explained in the earlier patch of the set. In this patch, the second bpf_setsockopt(tcp_cc) is not allowed in order to break the loop. This is done by using a bit of an existing 1 byte hole in tcp_sock to check if there is on-going bpf_setsockopt(TCP_CONGESTION) in this tcp_sock. Note that this essentially limits only the first '.init' can call bpf_setsockopt(TCP_CONGESTION) to pick a fallback cc (eg. peer does not support ECN) and the second '.init' cannot fallback to another cc. This applies even the second bpf_setsockopt(TCP_CONGESTION) will not cause a loop. Signed-off-by: Martin KaFai Lau Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220929070407.965581-5-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/tcp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index a9fbe22732c3..3bdf687e2fb3 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -388,6 +388,12 @@ struct tcp_sock { u8 bpf_sock_ops_cb_flags; /* Control calling BPF programs * values defined in uapi/linux/tcp.h */ + u8 bpf_chg_cc_inprogress:1; /* In the middle of + * bpf_setsockopt(TCP_CONGESTION), + * it is to avoid the bpf_tcp_cc->init() + * to recur itself by calling + * bpf_setsockopt(TCP_CONGESTION, "itself"). + */ #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_cb_flags & ARG) #else #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0 -- cgit v1.2.3 From dbae2b062824fc2d35ae2d5df2f500626c758e80 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 28 Sep 2022 10:43:09 +0200 Subject: net: skb: introduce and use a single page frag cache After commit 3226b158e67c ("net: avoid 32 x truesize under-estimation for tiny skbs") we are observing 10-20% regressions in performance tests with small packets. The perf trace points to high pressure on the slab allocator. This change tries to improve the allocation schema for small packets using an idea originally suggested by Eric: a new per CPU page frag is introduced and used in __napi_alloc_skb to cope with small allocation requests. To ensure that the above does not lead to excessive truesize underestimation, the frag size for small allocation is inflated to 1K and all the above is restricted to build with 4K page size. Note that we need to update accordingly the run-time check introduced with commit fd9ea57f4e95 ("net: add napi_get_frags_check() helper"). Alex suggested a smart page refcount schema to reduce the number of atomic operations and deal properly with pfmemalloc pages. Under small packet UDP flood, I measure a 15% peak tput increases. Suggested-by: Eric Dumazet Suggested-by: Alexander H Duyck Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Reviewed-by: Alexander Duyck Link: https://lore.kernel.org/r/6b6f65957c59f86a353fc09a5127e83a32ab5999.1664350652.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7a084a1c14e9..64c3a5864969 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3821,6 +3821,7 @@ void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); +void napi_get_frags_check(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); struct packet_offload *gro_find_receive_by_type(__be16 type); struct packet_offload *gro_find_complete_by_type(__be16 type); -- cgit v1.2.3 From aac4daa8941ea6566563ac001e9e5d4e54a674e2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 28 Sep 2022 12:51:57 +0300 Subject: net/sched: query offload capabilities through ndo_setup_tc() When adding optional new features to Qdisc offloads, existing drivers must reject the new configuration until they are coded up to act on it. Since modifying all drivers in lockstep with the changes in the Qdisc can create problems of its own, it would be nice if there existed an automatic opt-in mechanism for offloading optional features. Jakub proposes that we multiplex one more kind of call through ndo_setup_tc(): one where the driver populates a Qdisc-specific capability structure. First user will be taprio in further changes. Here we are introducing the definitions for the base functionality. Link: https://patchwork.kernel.org/project/netdevbpf/patch/20220923163310.3192733-3-vladimir.oltean@nxp.com/ Suggested-by: Jakub Kicinski Co-developed-by: Jakub Kicinski Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 64c3a5864969..eddf8ee270e7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -940,6 +940,7 @@ struct net_device_path_ctx { }; enum tc_setup_type { + TC_QUERY_CAPS, TC_SETUP_QDISC_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, -- cgit v1.2.3 From d427c8999b071af2003203b42a007c4a80156c18 Mon Sep 17 00:00:00 2001 From: Richard Gobert Date: Wed, 28 Sep 2022 14:55:31 +0200 Subject: net-next: skbuff: refactor pskb_pull pskb_may_pull already contains all of the checks performed by pskb_pull. Use pskb_may_pull for validation in pskb_pull, eliminating the duplication and making __pskb_pull obsolete. Replace __pskb_pull with pskb_pull where applicable. Signed-off-by: Richard Gobert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 23 +++++++++-------------- 1 file changed, 9 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 920eb6413fee..9fcf534f2d92 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2616,20 +2616,6 @@ void *skb_pull_data(struct sk_buff *skb, size_t len); void *__pskb_pull_tail(struct sk_buff *skb, int delta); -static inline void *__pskb_pull(struct sk_buff *skb, unsigned int len) -{ - if (len > skb_headlen(skb) && - !__pskb_pull_tail(skb, len - skb_headlen(skb))) - return NULL; - skb->len -= len; - return skb->data += len; -} - -static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) -{ - return unlikely(len > skb->len) ? NULL : __pskb_pull(skb, len); -} - static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { if (likely(len <= skb_headlen(skb))) @@ -2639,6 +2625,15 @@ static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) return __pskb_pull_tail(skb, len - skb_headlen(skb)) != NULL; } +static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) +{ + if (!pskb_may_pull(skb, len)) + return NULL; + + skb->len -= len; + return skb->data += len; +} + void skb_condense(struct sk_buff *skb); /** -- cgit v1.2.3 From f4ce91ce12a7c6ead19b128ffa8cff6e3ded2a14 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Wed, 28 Sep 2022 16:03:31 -0400 Subject: tcp: fix tcp_cwnd_validate() to not forget is_cwnd_limited This commit fixes a bug in the tracking of max_packets_out and is_cwnd_limited. This bug can cause the connection to fail to remember that is_cwnd_limited is true, causing the connection to fail to grow cwnd when it should, causing throughput to be lower than it should be. The following event sequence is an example that triggers the bug: (a) The connection is cwnd_limited, but packets_out is not at its peak due to TSO deferral deciding not to send another skb yet. In such cases the connection can advance max_packets_seq and set tp->is_cwnd_limited to true and max_packets_out to a small number. (b) Then later in the round trip the connection is pacing-limited (not cwnd-limited), and packets_out is larger. In such cases the connection would raise max_packets_out to a bigger number but (unexpectedly) flip tp->is_cwnd_limited from true to false. This commit fixes that bug. One straightforward fix would be to separately track (a) the next window after max_packets_out reaches a maximum, and (b) the next window after tp->is_cwnd_limited is set to true. But this would require consuming an extra u32 sequence number. Instead, to save space we track only the most important information. Specifically, we track the strongest available signal of the degree to which the cwnd is fully utilized: (1) If the connection is cwnd-limited then we remember that fact for the current window. (2) If the connection not cwnd-limited then we track the maximum number of outstanding packets in the current window. In particular, note that the new logic cannot trigger the buggy (a)/(b) sequence above because with the new logic a condition where tp->packets_out > tp->max_packets_out can only trigger an update of tp->is_cwnd_limited if tp->is_cwnd_limited is false. This first showed up in a testing of a BBRv2 dev branch, but this buggy behavior highlighted a general issue with the tcp_cwnd_validate() logic that can cause cwnd to fail to increase at the proper rate for any TCP congestion control, including Reno or CUBIC. Fixes: ca8a22634381 ("tcp: make cwnd-limited checks measurement-based, and gentler") Signed-off-by: Neal Cardwell Signed-off-by: Kevin(Yudong) Yang Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index a9fbe22732c3..4791fd801945 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -295,7 +295,7 @@ struct tcp_sock { u32 packets_out; /* Packets which are "in flight" */ u32 retrans_out; /* Retransmitted packets out */ u32 max_packets_out; /* max packets_out in last window */ - u32 max_packets_seq; /* right edge of max_packets_out flight */ + u32 cwnd_usage_seq; /* right edge of cwnd usage tracking flight */ u16 urg_data; /* Saved octet of OOB data and control flags */ u8 ecn_flags; /* ECN status bits. */ -- cgit v1.2.3 From e5a3cc83d54019a90119ce0cf17b5e21729b79bf Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 29 Sep 2022 00:21:42 -0700 Subject: net/mlx5e: Use runtime page_shift for striding RQ This commit allows striding RQ to determine MTT page size at runtime, instead of sticking to the compile-time PAGE_SIZE. This functionality will be used by a following commit that adjusts the MTT page size to the XSK frame size. Stick with PAGE_SIZE for XSK on legacy RQ, as frag_stride is not used in data path, it only helps calculate how pages are partitioned into fragments, and PAGE_SIZE will ensure each fragment starts at the beginning of a new allocation unit (XSK frame). Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/qp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index be640c749d5e..afac93f9552c 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -162,6 +162,8 @@ enum { MLX5_SEND_WQE_MAX_WQEBBS = 16, }; +#define MLX5_SEND_WQE_MAX_SIZE (MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQE_BB) + enum { MLX5_WQE_FMR_PERM_LOCAL_READ = 1 << 27, MLX5_WQE_FMR_PERM_LOCAL_WRITE = 1 << 28, -- cgit v1.2.3 From 6470d2e7e8ed8e9dd560d8dc3e09d1100a17ee26 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 29 Sep 2022 00:21:46 -0700 Subject: net/mlx5e: xsk: Use KSM for unaligned XSK UMR MTTs used in striding RQ have certain alignment requirements. While it's guaranteed to work when UMR pages are aligned to the UMR page size, in practice it works then UMR pages are aligned to 8 bytes. However, it's still not enough flexibility for the unaligned mode of XSK. This patch leverages KSM to map UMR pages without alignment requirements, when unaligned XSK is active. The downside is that KSM entries are twice as big as MTTs, which limits the maximum WQE size, so regular RQs and aligned XSK continue using MTTs. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/qp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index afac93f9552c..4657d5c54abe 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -478,6 +478,12 @@ struct mlx5_klm { __be64 va; }; +struct mlx5_ksm { + __be32 reserved; + __be32 key; + __be64 va; +}; + struct mlx5_stride_block_entry { __be16 stride; __be16 bcount; -- cgit v1.2.3 From fd580c9830316edad6f8b1d9f542563730658efe Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 30 Sep 2022 16:21:00 +0200 Subject: net: sfp: augment SFP parsing with phy_interface_t bitmap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We currently parse the SFP EEPROM to a bitmap of ethtool link modes, and then attempt to convert the link modes to a PHY interface mode. While this works at present, there are cases where this is sub-optimal. For example, where a module can operate with several different PHY interface modes. To start addressing this, arrange for the SFP EEPROM parsing to also provide a bitmap of the possible PHY interface modes. Signed-off-by: Russell King Signed-off-by: Marek Behún Signed-off-by: David S. Miller --- include/linux/sfp.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 302094b855fb..d1f343853b6c 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -535,7 +535,7 @@ int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support); bool sfp_may_have_phy(struct sfp_bus *bus, const struct sfp_eeprom_id *id); void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, - unsigned long *support); + unsigned long *support, unsigned long *interfaces); phy_interface_t sfp_select_interface(struct sfp_bus *bus, unsigned long *link_modes); @@ -568,7 +568,8 @@ static inline bool sfp_may_have_phy(struct sfp_bus *bus, static inline void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, - unsigned long *support) + unsigned long *support, + unsigned long *interfaces) { } -- cgit v1.2.3 From eca68a3c7d05b38b4e728cead0c49718f2bc1d5a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Fri, 30 Sep 2022 16:21:03 +0200 Subject: net: phylink: pass supported host PHY interface modes to phylib for SFP's PHYs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Pass the supported PHY interface types to phylib if the PHY we are connecting is inside a SFP, so that the PHY driver can select an appropriate host configuration mode for their interface according to the host capabilities. For example the Marvell 88X3310 PHY inside RollBall SFP modules defaults to 10gbase-r mode on host's side, and the marvell10g driver currently does not change this setting. But a host may not support 10gbase-r. For example Turris Omnia only supports sgmii, 1000base-x and 2500base-x modes. The PHY can be configured to use those modes, but in order for the PHY driver to do that, it needs to know which modes are supported. Signed-off-by: Marek Behún Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9c66f357f489..d65fc76fe0ae 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -571,6 +571,7 @@ struct macsec_ops; * @advertising: Currently advertised linkmodes * @adv_old: Saved advertised while power saving for WoL * @lp_advertising: Current link partner advertised linkmodes + * @host_interfaces: PHY interface modes supported by host * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited * @autoneg: Flag autoneg being used * @rate_matching: Current rate matching mode @@ -670,6 +671,9 @@ struct phy_device { /* used with phy_speed_down */ __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); + /* Host supported PHY interface types. Should be ignored if empty. */ + DECLARE_PHY_INTERFACE_MASK(host_interfaces); + /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; -- cgit v1.2.3 From e85b1347ace677c3822c12d9332dfaaffe594da6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Fri, 30 Sep 2022 16:21:08 +0200 Subject: net: sfp: create/destroy I2C mdiobus before PHY probe/after PHY release MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of configuring the I2C mdiobus when SFP driver is probed, create/destroy the mdiobus before the PHY is probed for/after it is released. This way we can tell the mdio-i2c code which protocol to use for each SFP transceiver. Move the code that determines MDIO I2C protocol from sfp_sm_probe_for_phy() to sfp_sm_mod_probe(), where most of the SFP ID parsing is done. Don't allocate I2C bus if no PHY is expected. Signed-off-by: Marek Behún Signed-off-by: David S. Miller --- include/linux/mdio/mdio-i2c.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdio/mdio-i2c.h b/include/linux/mdio/mdio-i2c.h index b1d27f7cd23f..3bde1a555a49 100644 --- a/include/linux/mdio/mdio-i2c.h +++ b/include/linux/mdio/mdio-i2c.h @@ -11,6 +11,12 @@ struct device; struct i2c_adapter; struct mii_bus; +enum mdio_i2c_proto { + MDIO_I2C_NONE, + MDIO_I2C_MARVELL_C22, + MDIO_I2C_C45, +}; + struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c); #endif -- cgit v1.2.3 From 09bbedac72d5a9267088c15d1a71c8c3a8fb47e7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Fri, 30 Sep 2022 16:21:09 +0200 Subject: net: phy: mdio-i2c: support I2C MDIO protocol for RollBall SFP modules MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some multigig SFPs from RollBall and Hilink do not expose functional MDIO access to the internal PHY of the SFP via I2C address 0x56 (although there seems to be read-only clause 22 access on this address). Instead these SFPs PHY can be accessed via I2C via the SFP Enhanced Digital Diagnostic Interface - I2C address 0x51. The SFP_PAGE has to be selected to 3 and the password must be filled with 0xff bytes for this PHY communication to work. This extends the mdio-i2c driver to support this protocol by adding a special parameter to mdio_i2c_alloc function via which this RollBall protocol can be selected. Signed-off-by: Marek Behún Cc: Andrew Lunn Cc: Russell King Signed-off-by: David S. Miller --- include/linux/mdio/mdio-i2c.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mdio/mdio-i2c.h b/include/linux/mdio/mdio-i2c.h index 3bde1a555a49..65b550a6fc32 100644 --- a/include/linux/mdio/mdio-i2c.h +++ b/include/linux/mdio/mdio-i2c.h @@ -15,8 +15,10 @@ enum mdio_i2c_proto { MDIO_I2C_NONE, MDIO_I2C_MARVELL_C22, MDIO_I2C_C45, + MDIO_I2C_ROLLBALL, }; -struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c); +struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c, + enum mdio_i2c_proto protocol); #endif -- cgit v1.2.3 From 62c07983bef9d3e78e71189441e1a470f0d1e653 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 1 Oct 2022 13:51:02 -0700 Subject: once: add DO_ONCE_SLOW() for sleepable contexts Christophe Leroy reported a ~80ms latency spike happening at first TCP connect() time. This is because __inet_hash_connect() uses get_random_once() to populate a perturbation table which became quite big after commit 4c2c8f03a5ab ("tcp: increase source port perturb table to 2^16") get_random_once() uses DO_ONCE(), which block hard irqs for the duration of the operation. This patch adds DO_ONCE_SLOW() which uses a mutex instead of a spinlock for operations where we prefer to stay in process context. Then __inet_hash_connect() can use get_random_slow_once() to populate its perturbation table. Fixes: 4c2c8f03a5ab ("tcp: increase source port perturb table to 2^16") Fixes: 190cc82489f4 ("tcp: change source port randomizarion at connect() time") Reported-by: Christophe Leroy Link: https://lore.kernel.org/netdev/CANn89iLAEYBaoYajy0Y9UmGFff5GPxDUoG-ErVB2jDdRNQ5Tug@mail.gmail.com/T/#t Signed-off-by: Eric Dumazet Cc: Willy Tarreau Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- include/linux/once.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/once.h b/include/linux/once.h index b14d8b309d52..176ab75b42df 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -5,10 +5,18 @@ #include #include +/* Helpers used from arbitrary contexts. + * Hard irqs are blocked, be cautious. + */ bool __do_once_start(bool *done, unsigned long *flags); void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags, struct module *mod); +/* Variant for process contexts only. */ +bool __do_once_slow_start(bool *done); +void __do_once_slow_done(bool *done, struct static_key_true *once_key, + struct module *mod); + /* Call a function exactly once. The idea of DO_ONCE() is to perform * a function call such as initialization of random seeds, etc, only * once, where DO_ONCE() can live in the fast-path. After @func has @@ -52,7 +60,27 @@ void __do_once_done(bool *done, struct static_key_true *once_key, ___ret; \ }) +/* Variant of DO_ONCE() for process/sleepable contexts. */ +#define DO_ONCE_SLOW(func, ...) \ + ({ \ + bool ___ret = false; \ + static bool __section(".data.once") ___done = false; \ + static DEFINE_STATIC_KEY_TRUE(___once_key); \ + if (static_branch_unlikely(&___once_key)) { \ + ___ret = __do_once_slow_start(&___done); \ + if (unlikely(___ret)) { \ + func(__VA_ARGS__); \ + __do_once_slow_done(&___done, &___once_key, \ + THIS_MODULE); \ + } \ + } \ + ___ret; \ + }) + #define get_random_once(buf, nbytes) \ DO_ONCE(get_random_bytes, (buf), (nbytes)) +#define get_random_slow_once(buf, nbytes) \ + DO_ONCE_SLOW(get_random_bytes, (buf), (nbytes)) + #endif /* _LINUX_ONCE_H */ -- cgit v1.2.3 From 168723c1f8d6e1e823d4c6ad3cf64478cf58330a Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Sat, 1 Oct 2022 21:56:22 -0700 Subject: net/mlx5e: xsk: Use umr_mode to calculate striding RQ parameters Instead of passing the unaligned flag, pass an enum that indicates the UMR mode. The next commit will add the third mode (KLM for certain configurations of XSK), which will be added to this enum instead of adding another bool flag everywhere. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/driver.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f8ecb33105d3..285f301a6390 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1288,4 +1288,8 @@ static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev) return mlx5_is_roce_on(dev); } +enum { + MLX5_OCTWORD = 16, +}; + #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3 From 16ab85e78439bab1201ff26ba430231d1574b4ae Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Sat, 1 Oct 2022 21:56:27 -0700 Subject: net/mlx5e: Expose rx_oversize_pkts_buffer counter Add the rx_oversize_pkts_buffer counter to ethtool statistics. This counter exposes the number of dropped received packets due to length which arrived to RQ and exceed software buffer size allocated by the device for incoming traffic. It might imply that the device MTU is larger than the software buffers size. Signed-off-by: Gal Pressman Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1ad762e22d86..06574d430ff5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1491,7 +1491,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_120[0xa]; u8 log_max_ra_req_dc[0x6]; - u8 reserved_at_130[0x9]; + u8 reserved_at_130[0x2]; + u8 eth_wqe_too_small[0x1]; + u8 reserved_at_133[0x6]; u8 vnic_env_cq_overrun[0x1]; u8 log_max_ra_res_dc[0x6]; @@ -3537,7 +3539,9 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits { u8 cq_overrun[0x20]; - u8 reserved_at_220[0xde0]; + u8 eth_wqe_too_small[0x20]; + + u8 reserved_at_220[0xdc0]; }; struct mlx5_ifc_traffic_counter_bits { -- cgit v1.2.3 From 9b98d395b85dd042fe83fb696b1ac02e6c93a520 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Sat, 1 Oct 2022 21:56:28 -0700 Subject: net/mlx5: Start health poll at earlier stage of driver load Start health poll at earlier stage, so if fw fatal issue occurred before or during initialization commands such as init_hca or set_hca_cap the poll health can detect and indicate that the driver is already in error state. Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 285f301a6390..a12929bc31b2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1017,6 +1017,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); +void mlx5_start_health_fw_log_up(struct mlx5_core_dev *dev); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, -- cgit v1.2.3 From 3114b075eb2531dea31a961944309485d6a53040 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 3 Oct 2022 08:51:57 +0200 Subject: net: add framework to support Ethernet PSE and PDs devices This framework was create with intention to provide support for Ethernet PSE (Power Sourcing Equipment) and PDs (Powered Device). At current step this patch implements generic PSE support for PoDL (Power over Data Lines 802.3bu) specification with reserving name space for PD devices as well. This framework can be extended to support 802.3af and 802.3at "Power via the Media Dependent Interface" (or PoE/Power over Ethernet) Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- include/linux/pse-pd/pse.h | 67 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) create mode 100644 include/linux/pse-pd/pse.h (limited to 'include/linux') diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h new file mode 100644 index 000000000000..3ba787a48b15 --- /dev/null +++ b/include/linux/pse-pd/pse.h @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +// Copyright (c) 2022 Pengutronix, Oleksij Rempel + */ +#ifndef _LINUX_PSE_CONTROLLER_H +#define _LINUX_PSE_CONTROLLER_H + +#include +#include +#include + +struct module; +struct device_node; +struct of_phandle_args; +struct pse_control; + +/** + * struct pse_controller_dev - PSE controller entity that might + * provide multiple PSE controls + * @ops: a pointer to device specific struct pse_controller_ops + * @owner: kernel module of the PSE controller driver + * @list: internal list of PSE controller devices + * @pse_control_head: head of internal list of requested PSE controls + * @dev: corresponding driver model device struct + * @of_pse_n_cells: number of cells in PSE line specifiers + * @of_xlate: translation function to translate from specifier as found in the + * device tree to id as given to the PSE control ops + * @nr_lines: number of PSE controls in this controller device + * @lock: Mutex for serialization access to the PSE controller + */ +struct pse_controller_dev { + const struct pse_controller_ops *ops; + struct module *owner; + struct list_head list; + struct list_head pse_control_head; + struct device *dev; + int of_pse_n_cells; + int (*of_xlate)(struct pse_controller_dev *pcdev, + const struct of_phandle_args *pse_spec); + unsigned int nr_lines; + struct mutex lock; +}; + +#if IS_ENABLED(CONFIG_PSE_CONTROLLER) +int pse_controller_register(struct pse_controller_dev *pcdev); +void pse_controller_unregister(struct pse_controller_dev *pcdev); +struct device; +int devm_pse_controller_register(struct device *dev, + struct pse_controller_dev *pcdev); + +struct pse_control *of_pse_control_get(struct device_node *node); +void pse_control_put(struct pse_control *psec); + +#else + +static inline struct pse_control *of_pse_control_get(struct device_node *node) +{ + return ERR_PTR(-ENOENT); +} + +static inline void pse_control_put(struct pse_control *psec) +{ +} + +#endif + +#endif -- cgit v1.2.3 From 5e82147de1cbd758bb280908daa39d95ed467538 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 3 Oct 2022 08:51:59 +0200 Subject: net: mdiobus: search for PSE nodes by parsing PHY nodes. Some PHYs can be linked with PSE (Power Sourcing Equipment), so search for related nodes and attach it to the phydev. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index d65fc76fe0ae..ddf66198f751 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -597,6 +597,7 @@ struct macsec_ops; * @master_slave_get: Current master/slave advertisement * @master_slave_state: Current master/slave configuration * @mii_ts: Pointer to time stamper callbacks + * @psec: Pointer to Power Sourcing Equipment control struct * @lock: Mutex for serialization access to PHY * @state_queue: Work queue for state machine * @shared: Pointer to private data shared by phys in one package @@ -715,6 +716,7 @@ struct phy_device { struct phylink *phylink; struct net_device *attached_dev; struct mii_timestamper *mii_ts; + struct pse_control *psec; u8 mdix; u8 mdix_ctrl; -- cgit v1.2.3 From 18ff0bcda6d1dd3d53b4ce3f03e61bf1a648f960 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 3 Oct 2022 08:52:00 +0200 Subject: ethtool: add interface to interact with Ethernet Power Equipment Add interface to support Power Sourcing Equipment. At current step it provides generic way to address all variants of PSE devices as defined in IEEE 802.3-2018 but support only objects specified for IEEE 802.3-2018 104.4 PoDL Power Sourcing Equipment (PSE). Currently supported and mandatory objects are: IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState IEEE 802.3-2018 30.15.1.2.1 acPoDLPSEAdminControl This is minimal interface needed to control PSE on each separate ethernet port but it provides not all mandatory objects specified in IEEE 802.3-2018. Since "PoDL PSE" and "PSE" have similar names, but some different values I decide to not merge them and keep separate naming schema. This should allow as to be as close to IEEE 802.3 spec as possible and avoid name conflicts in the future. This implementation is connected to PHYs instead of MACs because PSE auto classification can potentially interfere with PHY auto negotiation. So, may be some extra PHY related initialization will be needed. With WIP version of ethtools interaction with PSE capable link looks as following: $ ip l ... 5: t1l1@eth0: .. ... $ ethtool --show-pse t1l1 PSE attributs for t1l1: PoDL PSE Admin State: disabled PoDL PSE Power Detection Status: disabled $ ethtool --set-pse t1l1 podl-pse-admin-control enable $ ethtool --show-pse t1l1 PSE attributs for t1l1: PoDL PSE Admin State: enabled PoDL PSE Power Detection Status: delivering power Signed-off-by: kernel test robot Signed-off-by: Oleksij Rempel Reviewed-by: Bagas Sanjaya Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- include/linux/pse-pd/pse.h | 62 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index 3ba787a48b15..fd1a916eeeba 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -9,6 +9,47 @@ #include #include +struct phy_device; +struct pse_controller_dev; + +/** + * struct pse_control_config - PSE control/channel configuration. + * + * @admin_cotrol: set PoDL PSE admin control as described in + * IEEE 802.3-2018 30.15.1.2.1 acPoDLPSEAdminControl + */ +struct pse_control_config { + enum ethtool_podl_pse_admin_state admin_cotrol; +}; + +/** + * struct pse_control_status - PSE control/channel status. + * + * @podl_admin_state: operational state of the PoDL PSE + * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState + * @podl_pw_status: power detection status of the PoDL PSE. + * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus: + */ +struct pse_control_status { + enum ethtool_podl_pse_admin_state podl_admin_state; + enum ethtool_podl_pse_pw_d_status podl_pw_status; +}; + +/** + * struct pse_controller_ops - PSE controller driver callbacks + * + * @ethtool_get_status: get PSE control status for ethtool interface + * @ethtool_set_config: set PSE control configuration over ethtool interface + */ +struct pse_controller_ops { + int (*ethtool_get_status)(struct pse_controller_dev *pcdev, + unsigned long id, struct netlink_ext_ack *extack, + struct pse_control_status *status); + int (*ethtool_set_config)(struct pse_controller_dev *pcdev, + unsigned long id, struct netlink_ext_ack *extack, + const struct pse_control_config *config); +}; + struct module; struct device_node; struct of_phandle_args; @@ -51,6 +92,13 @@ int devm_pse_controller_register(struct device *dev, struct pse_control *of_pse_control_get(struct device_node *node); void pse_control_put(struct pse_control *psec); +int pse_ethtool_get_status(struct pse_control *psec, + struct netlink_ext_ack *extack, + struct pse_control_status *status); +int pse_ethtool_set_config(struct pse_control *psec, + struct netlink_ext_ack *extack, + const struct pse_control_config *config); + #else static inline struct pse_control *of_pse_control_get(struct device_node *node) @@ -62,6 +110,20 @@ static inline void pse_control_put(struct pse_control *psec) { } +int pse_ethtool_get_status(struct pse_control *psec, + struct netlink_ext_ack *extack, + struct pse_control_status *status) +{ + return -ENOTSUPP; +} + +int pse_ethtool_set_config(struct pse_control *psec, + struct netlink_ext_ack *extack, + const struct pse_control_config *config) +{ + return -ENOTSUPP; +} + #endif #endif -- cgit v1.2.3 From 2a4187f4406ec3236f8b9d0d5150d2bf8d021b68 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Mon, 3 Oct 2022 20:14:13 +0200 Subject: once: rename _SLOW to _SLEEPABLE The _SLOW designation wasn't really descriptive of anything. This is meant to be called from process context when it's possible to sleep. So name this more aptly _SLEEPABLE, which better fits its intended use. Fixes: 62c07983bef9 ("once: add DO_ONCE_SLOW() for sleepable contexts") Cc: Christophe Leroy Signed-off-by: Jason A. Donenfeld Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20221003181413.1221968-1-Jason@zx2c4.com Signed-off-by: Jakub Kicinski --- include/linux/once.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/once.h b/include/linux/once.h index 176ab75b42df..bc714d414448 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -13,9 +13,9 @@ void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags, struct module *mod); /* Variant for process contexts only. */ -bool __do_once_slow_start(bool *done); -void __do_once_slow_done(bool *done, struct static_key_true *once_key, - struct module *mod); +bool __do_once_sleepable_start(bool *done); +void __do_once_sleepable_done(bool *done, struct static_key_true *once_key, + struct module *mod); /* Call a function exactly once. The idea of DO_ONCE() is to perform * a function call such as initialization of random seeds, etc, only @@ -61,26 +61,26 @@ void __do_once_slow_done(bool *done, struct static_key_true *once_key, }) /* Variant of DO_ONCE() for process/sleepable contexts. */ -#define DO_ONCE_SLOW(func, ...) \ - ({ \ - bool ___ret = false; \ - static bool __section(".data.once") ___done = false; \ - static DEFINE_STATIC_KEY_TRUE(___once_key); \ - if (static_branch_unlikely(&___once_key)) { \ - ___ret = __do_once_slow_start(&___done); \ - if (unlikely(___ret)) { \ - func(__VA_ARGS__); \ - __do_once_slow_done(&___done, &___once_key, \ - THIS_MODULE); \ - } \ - } \ - ___ret; \ +#define DO_ONCE_SLEEPABLE(func, ...) \ + ({ \ + bool ___ret = false; \ + static bool __section(".data.once") ___done = false; \ + static DEFINE_STATIC_KEY_TRUE(___once_key); \ + if (static_branch_unlikely(&___once_key)) { \ + ___ret = __do_once_sleepable_start(&___done); \ + if (unlikely(___ret)) { \ + func(__VA_ARGS__); \ + __do_once_sleepable_done(&___done, &___once_key,\ + THIS_MODULE); \ + } \ + } \ + ___ret; \ }) #define get_random_once(buf, nbytes) \ DO_ONCE(get_random_bytes, (buf), (nbytes)) -#define get_random_slow_once(buf, nbytes) \ - DO_ONCE_SLOW(get_random_bytes, (buf), (nbytes)) +#define get_random_sleepable_once(buf, nbytes) \ + DO_ONCE_SLEEPABLE(get_random_bytes, (buf), (nbytes)) #endif /* _LINUX_ONCE_H */ -- cgit v1.2.3 From 681bf011b9b5989c6e9db6beb64494918aab9a43 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 3 Oct 2022 21:03:27 -0700 Subject: eth: pse: add missing static inlines build bot reports missing 'static inline' qualifiers in the header. Reported-by: kernel test robot Fixes: 18ff0bcda6d1 ("ethtool: add interface to interact with Ethernet Power Equipment") Reviewed-by: Oleksij Rempel Link: https://lore.kernel.org/r/20221004040327.2034878-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/pse-pd/pse.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index fd1a916eeeba..fb724c65c77b 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -110,16 +110,16 @@ static inline void pse_control_put(struct pse_control *psec) { } -int pse_ethtool_get_status(struct pse_control *psec, - struct netlink_ext_ack *extack, - struct pse_control_status *status) +static inline int pse_ethtool_get_status(struct pse_control *psec, + struct netlink_ext_ack *extack, + struct pse_control_status *status) { return -ENOTSUPP; } -int pse_ethtool_set_config(struct pse_control *psec, - struct netlink_ext_ack *extack, - const struct pse_control_config *config) +static inline int pse_ethtool_set_config(struct pse_control *psec, + struct netlink_ext_ack *extack, + const struct pse_control_config *config) { return -ENOTSUPP; } -- cgit v1.2.3