From f3854973f196baad5be6b62d8f5ea24b0346b63f Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 6 Dec 2016 11:17:12 -0200 Subject: [media] cec: fix report_current_latency In the (very) small print of the REPORT_CURRENT_LATENCY message there is a line that says that the last byte of the message (audio out delay) is only present if the 'audio out compensated' value is 3. I missed this, and so if this message was sent with a total length of 6 (i.e. without the audio out delay byte), then it was rejected by the framework since a minimum length of 7 was expected. Fix this minimum length check and update the wrappers in cec-funcs.h to do the right thing based on the message length. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/cec-funcs.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index 3cbc327801d6..c451eec42a83 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -1665,14 +1665,15 @@ static inline void cec_msg_report_current_latency(struct cec_msg *msg, __u8 audio_out_compensated, __u8 audio_out_delay) { - msg->len = 7; + msg->len = 6; msg->msg[0] |= 0xf; /* broadcast */ msg->msg[1] = CEC_MSG_REPORT_CURRENT_LATENCY; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; msg->msg[4] = video_latency; msg->msg[5] = (low_latency_mode << 2) | audio_out_compensated; - msg->msg[6] = audio_out_delay; + if (audio_out_compensated == 3) + msg->msg[msg->len++] = audio_out_delay; } static inline void cec_ops_report_current_latency(const struct cec_msg *msg, @@ -1686,7 +1687,10 @@ static inline void cec_ops_report_current_latency(const struct cec_msg *msg, *video_latency = msg->msg[4]; *low_latency_mode = (msg->msg[5] >> 2) & 1; *audio_out_compensated = msg->msg[5] & 3; - *audio_out_delay = msg->msg[6]; + if (*audio_out_compensated == 3 && msg->len >= 7) + *audio_out_delay = msg->msg[6]; + else + *audio_out_delay = 0; } static inline void cec_msg_request_current_latency(struct cec_msg *msg, -- cgit v1.2.3 From 3846fd9b86001bea171943cc3bb9222cb6da6b42 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 11 Jan 2017 10:01:17 +0100 Subject: drm/probe-helpers: Drop locking from poll_enable It was only needed to protect the connector_list walking, see commit 8c4ccc4ab6f64e859d4ff8d7c02c2ed2e956e07f Author: Daniel Vetter Date: Thu Jul 9 23:44:26 2015 +0200 drm/probe-helper: Grab mode_config.mutex in poll_init/enable Unfortunately the commit message of that patch fails to mention that the new locking check was for the connector_list. But that requirement disappeared in commit c36a3254f7857f1ad9badbe3578ccc92be541a8e Author: Daniel Vetter Date: Thu Dec 15 16:58:43 2016 +0100 drm: Convert all helpers to drm_connector_list_iter and so we can drop this again. This fixes a locking inversion on nouveau, where the rpm code needs to re-enable. But in other places the rpm_get() calls are nested within the big modeset locks. While at it, also improve the kerneldoc for these two functions a notch. v2: Update the kerneldoc even more to explain that these functions can't be called concurrently, or bad things happen (Chris). Cc: Dave Airlie Reviewed-by: Chris Wilson Cc: Chris Wilson Tested-by: Lyude Reviewed-by: Lyude Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20170111090117.5134-1-daniel.vetter@ffwll.ch --- include/drm/drm_crtc_helper.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h index 982c299e435a..d026f5017c33 100644 --- a/include/drm/drm_crtc_helper.h +++ b/include/drm/drm_crtc_helper.h @@ -73,6 +73,5 @@ extern void drm_kms_helper_hotplug_event(struct drm_device *dev); extern void drm_kms_helper_poll_disable(struct drm_device *dev); extern void drm_kms_helper_poll_enable(struct drm_device *dev); -extern void drm_kms_helper_poll_enable_locked(struct drm_device *dev); #endif -- cgit v1.2.3 From 488f94d7212b00a2ec72fb886b155f1b04c5aa98 Mon Sep 17 00:00:00 2001 From: Jintack Lim Date: Thu, 1 Dec 2016 14:32:05 -0500 Subject: KVM: arm64: Access CNTHCTL_EL2 bit fields correctly on VHE systems Current KVM world switch code is unintentionally setting wrong bits to CNTHCTL_EL2 when E2H == 1, which may allow guest OS to access physical timer. Bit positions of CNTHCTL_EL2 are changing depending on HCR_EL2.E2H bit. EL1PCEN and EL1PCTEN are 1st and 0th bits when E2H is not set, but they are 11th and 10th bits respectively when E2H is set. In fact, on VHE we only need to set those bits once, not for every world switch. This is because the host kernel runs in EL2 with HCR_EL2.TGE == 1, which makes those bits have no effect for the host kernel execution. So we just set those bits once for guests, and that's it. Signed-off-by: Jintack Lim Reviewed-by: Marc Zyngier Signed-off-by: Marc Zyngier --- include/kvm/arm_arch_timer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index b717ed9d2b75..5c970ce67949 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -76,4 +76,5 @@ void kvm_timer_unschedule(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu); +void kvm_timer_init_vhe(void); #endif -- cgit v1.2.3 From 52d7e48b86fc108e45a656d8e53e4237993c481d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 10 Jan 2017 02:28:26 -0800 Subject: rcu: Narrow early boot window of illegal synchronous grace periods The current preemptible RCU implementation goes through three phases during bootup. In the first phase, there is only one CPU that is running with preemption disabled, so that a no-op is a synchronous grace period. In the second mid-boot phase, the scheduler is running, but RCU has not yet gotten its kthreads spawned (and, for expedited grace periods, workqueues are not yet running. During this time, any attempt to do a synchronous grace period will hang the system (or complain bitterly, depending). In the third and final phase, RCU is fully operational and everything works normally. This has been OK for some time, but there has recently been some synchronous grace periods showing up during the second mid-boot phase. This code worked "by accident" for awhile, but started failing as soon as expedited RCU grace periods switched over to workqueues in commit 8b355e3bc140 ("rcu: Drive expedited grace periods from workqueue"). Note that the code was buggy even before this commit, as it was subject to failure on real-time systems that forced all expedited grace periods to run as normal grace periods (for example, using the rcu_normal ksysfs parameter). The callchain from the failure case is as follows: early_amd_iommu_init() |-> acpi_put_table(ivrs_base); |-> acpi_tb_put_table(table_desc); |-> acpi_tb_invalidate_table(table_desc); |-> acpi_tb_release_table(...) |-> acpi_os_unmap_memory |-> acpi_os_unmap_iomem |-> acpi_os_map_cleanup |-> synchronize_rcu_expedited The kernel showing this callchain was built with CONFIG_PREEMPT_RCU=y, which caused the code to try using workqueues before they were initialized, which did not go well. This commit therefore reworks RCU to permit synchronous grace periods to proceed during this mid-boot phase. This commit is therefore a fix to a regression introduced in v4.9, and is therefore being put forward post-merge-window in v4.10. This commit sets a flag from the existing rcu_scheduler_starting() function which causes all synchronous grace periods to take the expedited path. The expedited path now checks this flag, using the requesting task to drive the expedited grace period forward during the mid-boot phase. Finally, this flag is updated by a core_initcall() function named rcu_exp_runtime_mode(), which causes the runtime codepaths to be used. Note that this arrangement assumes that tasks are not sent POSIX signals (or anything similar) from the time that the first task is spawned through core_initcall() time. Fixes: 8b355e3bc140 ("rcu: Drive expedited grace periods from workqueue") Reported-by: "Zheng, Lv" Reported-by: Borislav Petkov Signed-off-by: Paul E. McKenney Tested-by: Stan Kain Tested-by: Ivan Tested-by: Emanuel Castelo Tested-by: Bruno Pesavento Tested-by: Borislav Petkov Tested-by: Frederic Bezies Cc: # 4.9.0- --- include/linux/rcupdate.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 321f9ed552a9..01f71e1d2e94 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -444,6 +444,10 @@ bool __rcu_is_watching(void); #error "Unknown RCU implementation specified to kernel configuration" #endif +#define RCU_SCHEDULER_INACTIVE 0 +#define RCU_SCHEDULER_INIT 1 +#define RCU_SCHEDULER_RUNNING 2 + /* * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic * initialization and destruction of rcu_head on the stack. rcu_head structures -- cgit v1.2.3 From 4205e4786d0b9fc3b4fec7b1910cf645a0468307 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Jan 2017 14:01:05 +0100 Subject: cpu/hotplug: Provide dynamic range for prepare stage Mathieu reported that the LTTNG modules are broken as of 4.10-rc1 due to the removal of the cpu hotplug notifiers. Usually I don't care much about out of tree modules, but LTTNG is widely used in distros. There are two ways to solve that: 1) Reserve a hotplug state for LTTNG 2) Add a dynamic range for the prepare states. While #1 is the simplest solution, #2 is the proper one as we can convert in tree users, which do not care about ordering, to the dynamic range as well. Add a dynamic range which allows LTTNG to request states in the prepare stage. Reported-and-tested-by: Mathieu Desnoyers Signed-off-by: Thomas Gleixner Reviewed-by: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Sebastian Sewior Cc: Steven Rostedt Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1701101353010.3401@nanos Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 20bfefbe7594..d936a0021839 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -74,6 +74,8 @@ enum cpuhp_state { CPUHP_ZCOMP_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_MIPS_SOC_PREPARE, + CPUHP_BP_PREPARE_DYN, + CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, CPUHP_AP_OFFLINE, -- cgit v1.2.3 From d7f5762c5e532dfe8247ce1bc60d97af27ff8d00 Mon Sep 17 00:00:00 2001 From: Alexander Alemayhu Date: Wed, 4 Jan 2017 23:16:41 +0100 Subject: netfilter: nf_tables: fix spelling mistakes o s/numerice/numeric o s/opertaor/operator Signed-off-by: Alexander Alemayhu Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 881d49e94569..e3f27e09eb2b 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -235,7 +235,7 @@ enum nft_rule_compat_flags { /** * enum nft_rule_compat_attributes - nf_tables rule compat attributes * - * @NFTA_RULE_COMPAT_PROTO: numerice value of handled protocol (NLA_U32) + * @NFTA_RULE_COMPAT_PROTO: numeric value of handled protocol (NLA_U32) * @NFTA_RULE_COMPAT_FLAGS: bitmask of enum nft_rule_compat_flags (NLA_U32) */ enum nft_rule_compat_attributes { @@ -499,7 +499,7 @@ enum nft_bitwise_attributes { * enum nft_byteorder_ops - nf_tables byteorder operators * * @NFT_BYTEORDER_NTOH: network to host operator - * @NFT_BYTEORDER_HTON: host to network opertaor + * @NFT_BYTEORDER_HTON: host to network operator */ enum nft_byteorder_ops { NFT_BYTEORDER_NTOH, -- cgit v1.2.3 From 6443ebc3fdd6f3c766d9442c18be274b3d736050 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sat, 7 Jan 2017 20:49:18 +0800 Subject: netfilter: rpfilter: fix incorrect loopback packet judgment Currently, we check the existing rtable in PREROUTING hook, if RTCF_LOCAL is set, we assume that the packet is loopback. But this assumption is incorrect, for example, a packet encapsulated in ipsec transport mode was received and routed to local, after decapsulation, it would be delivered to local again, and the rtable was not dropped, so RTCF_LOCAL check would trigger. But actually, the packet was not loopback. So for these normal loopback packets, we can check whether the in device is IFF_LOOPBACK or not. For these locally generated broadcast/multicast, we can check whether the skb->pkt_type is PACKET_LOOPBACK or not. Finally, there's a subtle difference between nft fib expr and xtables rpfilter extension, user can add the following nft rule to do strict rpfilter check: # nft add rule x y meta iif eth0 fib saddr . iif oif != eth0 drop So when the packet is loopback, it's better to store the in device instead of the LOOPBACK_IFINDEX, otherwise, after adding the above nft rule, locally generated broad/multicast packets will be dropped incorrectly. Fixes: f83a7ea2075c ("netfilter: xt_rpfilter: skip locally generated broadcast/multicast, too") Fixes: f6d0cbcf09c5 ("netfilter: nf_tables: add fib expression") Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nft_fib.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index cbedda077db2..5ceb2205e4e3 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -9,6 +9,12 @@ struct nft_fib { extern const struct nla_policy nft_fib_policy[]; +static inline bool +nft_fib_is_loopback(const struct sk_buff *skb, const struct net_device *in) +{ + return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; +} + int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr); int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]); -- cgit v1.2.3 From 67d35e70af9cabb663c827e03bc5c1e89b43db72 Mon Sep 17 00:00:00 2001 From: Fam Zheng Date: Fri, 13 Jan 2017 11:40:01 +0800 Subject: scsi: libfc: Fix variable name in fc_set_wwpn The parameter name should be wwpn instead of wwnn. Signed-off-by: Fam Zheng Acked-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- include/scsi/libfc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h index 96dd0b3f70d7..da5033dd8cbc 100644 --- a/include/scsi/libfc.h +++ b/include/scsi/libfc.h @@ -809,11 +809,11 @@ static inline void fc_set_wwnn(struct fc_lport *lport, u64 wwnn) /** * fc_set_wwpn() - Set the World Wide Port Name of a local port * @lport: The local port whose WWPN is to be set - * @wwnn: The new WWPN + * @wwpn: The new WWPN */ -static inline void fc_set_wwpn(struct fc_lport *lport, u64 wwnn) +static inline void fc_set_wwpn(struct fc_lport *lport, u64 wwpn) { - lport->wwpn = wwnn; + lport->wwpn = wwpn; } /** -- cgit v1.2.3 From 7e9081c5aac73b8a0bc22e0b3e7a12c3e9cf5256 Mon Sep 17 00:00:00 2001 From: Gustavo Padovan Date: Fri, 13 Jan 2017 12:22:09 -0200 Subject: drm/fence: fix memory overwrite when setting out_fence fd Currently if the userspace declares a int variable to store the out_fence fd and pass it to OUT_FENCE_PTR the kernel will overwrite the 32 bits above the int variable on 64 bits systems. Fix this by making the internal storage of out_fence in the kernel a s32 pointer. Reported-by: Chad Versace Signed-off-by: Gustavo Padovan Fixes: beaf5af48034 ("drm/fence: add out-fences support") Cc: Daniel Vetter Cc: Rafael Antognolli Cc: Laurent Pinchart Acked-by: Laurent Pinchart Reviewed-and-Tested-by: Chad Versace Link: http://patchwork.freedesktop.org/patch/msgid/1484317329-9293-1-git-send-email-gustavo@padovan.org --- include/drm/drm_atomic.h | 2 +- include/drm/drm_mode_config.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index d6d241f63b9f..56814e8ae7ea 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -144,7 +144,7 @@ struct __drm_crtcs_state { struct drm_crtc *ptr; struct drm_crtc_state *state; struct drm_crtc_commit *commit; - s64 __user *out_fence_ptr; + s32 __user *out_fence_ptr; }; struct __drm_connnectors_state { diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index bf9991b20611..137432386310 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -488,7 +488,7 @@ struct drm_mode_config { /** * @prop_out_fence_ptr: Sync File fd pointer representing the * outgoing fences for a CRTC. Userspace should provide a pointer to a - * value of type s64, and then cast that pointer to u64. + * value of type s32, and then cast that pointer to u64. */ struct drm_property *prop_out_fence_ptr; /** -- cgit v1.2.3 From 5eb7c0d04f04a667c049fe090a95494a8de2955c Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Sun, 1 Jan 2017 20:25:25 -0600 Subject: taint/module: Fix problems when out-of-kernel driver defines true or false Commit 7fd8329ba502 ("taint/module: Clean up global and module taint flags handling") used the key words true and false as character members of a new struct. These names cause problems when out-of-kernel modules such as VirtualBox include their own definitions of true and false. Fixes: 7fd8329ba502 ("taint/module: Clean up global and module taint flags handling") Signed-off-by: Larry Finger Cc: Petr Mladek Cc: Jessica Yu Cc: Rusty Russell Reported-by: Valdis Kletnieks Reviewed-by: Petr Mladek Acked-by: Rusty Russell Signed-off-by: Jessica Yu --- include/linux/kernel.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 56aec84237ad..cb09238f6d32 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -514,8 +514,8 @@ extern enum system_states { #define TAINT_FLAGS_COUNT 16 struct taint_flag { - char true; /* character printed when tainted */ - char false; /* character printed when not tainted */ + char c_true; /* character printed when tainted */ + char c_false; /* character printed when not tainted */ bool module; /* also show as a per-module taint flag */ }; -- cgit v1.2.3 From 9ed59592e3e379b2e9557dc1d9e9ec8fcbb33f16 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 17 Jan 2017 14:57:36 -0800 Subject: lwtunnel: fix autoload of lwt modules Trying to add an mpls encap route when the MPLS modules are not loaded hangs. For example: CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m $ ip route add 10.10.10.10/32 encap mpls 100 via inet 10.100.1.2 The ip command hangs: root 880 826 0 21:25 pts/0 00:00:00 ip route add 10.10.10.10/32 encap mpls 100 via inet 10.100.1.2 $ cat /proc/880/stack [] call_usermodehelper_exec+0xd6/0x134 [] __request_module+0x27b/0x30a [] lwtunnel_build_state+0xe4/0x178 [] fib_create_info+0x47f/0xdd4 [] fib_table_insert+0x90/0x41f [] inet_rtm_newroute+0x4b/0x52 ... modprobe is trying to load rtnl-lwt-MPLS: root 881 5 0 21:25 ? 00:00:00 /sbin/modprobe -q -- rtnl-lwt-MPLS and it hangs after loading mpls_router: $ cat /proc/881/stack [] rtnl_lock+0x12/0x14 [] register_netdevice_notifier+0x16/0x179 [] mpls_init+0x25/0x1000 [mpls_router] [] do_one_initcall+0x8e/0x13f [] do_init_module+0x5a/0x1e5 [] load_module+0x13bd/0x17d6 ... The problem is that lwtunnel_build_state is called with rtnl lock held preventing mpls_init from registering. Given the potential references held by the time lwtunnel_build_state it can not drop the rtnl lock to the load module. So, extract the module loading code from lwtunnel_build_state into a new function to validate the encap type. The new function is called while converting the user request into a fib_config which is well before any table, device or fib entries are examined. Fixes: 745041e2aaf1 ("lwtunnel: autoload of lwt modules") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/lwtunnel.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index d4c1c75b8862..0b585f1fd340 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -105,6 +105,8 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num); +int lwtunnel_valid_encap_type(u16 encap_type); +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len); int lwtunnel_build_state(struct net_device *dev, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, @@ -168,6 +170,15 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, return -EOPNOTSUPP; } +static inline int lwtunnel_valid_encap_type(u16 encap_type) +{ + return -EOPNOTSUPP; +} +static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len) +{ + return -EOPNOTSUPP; +} + static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, -- cgit v1.2.3 From d407bd25a204bd66b7346dde24bd3d37ef0e0b05 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 18 Jan 2017 15:14:17 +0100 Subject: bpf: don't trigger OOM killer under pressure with map alloc This patch adds two helpers, bpf_map_area_alloc() and bpf_map_area_free(), that are to be used for map allocations. Using kmalloc() for very large allocations can cause excessive work within the page allocator, so i) fall back earlier to vmalloc() when the attempt is considered costly anyway, and even more importantly ii) don't trigger OOM killer with any of the allocators. Since this is based on a user space request, for example, when creating maps with element pre-allocation, we really want such requests to fail instead of killing other user space processes. Also, don't spam the kernel log with warnings should any of the allocations fail under pressure. Given that, we can make backend selection in bpf_map_area_alloc() generic, and convert all maps over to use this API for spots with potentially large allocation requests. Note, replacing the one kmalloc_array() is fine as overflow checks happen earlier in htab_map_alloc(), since it must also protect the multiplication for vmalloc() should kmalloc_array() fail. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 05cf951df3fe..3ed1f3b1d594 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -247,6 +247,8 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); +void *bpf_map_area_alloc(size_t size); +void bpf_map_area_free(void *base); extern int sysctl_unprivileged_bpf_disabled; -- cgit v1.2.3 From 739e6f5945d88dcee01590913f6886132a10c215 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 11 Jan 2017 13:37:07 +0100 Subject: gpio: provide lockdep keys for nested/unnested irqchips The helper function for adding a GPIO chip compiles in a lockdep key for debugging, the same key is needed for nested chips as well. The macro construction is unreadable, replace this with two static inlines instead. The _gpiochip_irqchip_add prefixed function is not helpful, rename it with gpiochip_irqchip_add_key() that tell us what the function is actually doing. Fixes: d245b3f9bd36 ("gpio: simplify adding threaded interrupts") Cc: Roger Quadros Reported-by: Clemens Gruber Reported-by: Roger Quadros Reported-by: Grygorii Strashko Tested-by: Clemens Gruber Tested-by: Grygorii Strashko Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 70 ++++++++++++++++++++++++++++++++------------- 1 file changed, 50 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index c2748accea71..e973faba69dc 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -274,37 +274,67 @@ void gpiochip_set_nested_irqchip(struct gpio_chip *gpiochip, struct irq_chip *irqchip, int parent_irq); -int _gpiochip_irqchip_add(struct gpio_chip *gpiochip, +int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type, + bool nested, + struct lock_class_key *lock_key); + +#ifdef CONFIG_LOCKDEP + +/* + * Lockdep requires that each irqchip instance be created with a + * unique key so as to avoid unnecessary warnings. This upfront + * boilerplate static inlines provides such a key for each + * unique instance. + */ +static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type) +{ + static struct lock_class_key key; + + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, false, &key); +} + +static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, struct irq_chip *irqchip, unsigned int first_irq, irq_flow_handler_t handler, - unsigned int type, - bool nested, - struct lock_class_key *lock_key); + unsigned int type) +{ + + static struct lock_class_key key; + + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, true, &key); +} +#else +static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip, + struct irq_chip *irqchip, + unsigned int first_irq, + irq_flow_handler_t handler, + unsigned int type) +{ + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, false, NULL); +} -/* FIXME: I assume threaded IRQchips do not have the lockdep problem */ static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, struct irq_chip *irqchip, unsigned int first_irq, irq_flow_handler_t handler, unsigned int type) { - return _gpiochip_irqchip_add(gpiochip, irqchip, first_irq, - handler, type, true, NULL); + return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, + handler, type, true, NULL); } - -#ifdef CONFIG_LOCKDEP -#define gpiochip_irqchip_add(...) \ -( \ - ({ \ - static struct lock_class_key _key; \ - _gpiochip_irqchip_add(__VA_ARGS__, false, &_key); \ - }) \ -) -#else -#define gpiochip_irqchip_add(...) \ - _gpiochip_irqchip_add(__VA_ARGS__, false, NULL) -#endif +#endif /* CONFIG_LOCKDEP */ #endif /* CONFIG_GPIOLIB_IRQCHIP */ -- cgit v1.2.3 From e326ce013a8e851193eb337aafb1aa396c533a61 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 20 Jan 2017 03:25:34 +0100 Subject: Revert "PM / sleep / ACPI: Use the ACPI_FADT_LOW_POWER_S0 flag" Revert commit 08b98d329165 (PM / sleep / ACPI: Use the ACPI_FADT_LOW_POWER_S0 flag) as it caused system suspend (in the default configuration) to fail on Dell XPS13 (9360) with the Kaby Lake processor. Fixes: 08b98d329165 (PM / sleep / ACPI: Use the ACPI_FADT_LOW_POWER_S0 flag) Reported-by: Paul Menzel Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 0c729c3c8549..d9718378a8be 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -194,8 +194,6 @@ struct platform_freeze_ops { }; #ifdef CONFIG_SUSPEND -extern suspend_state_t mem_sleep_default; - /** * suspend_set_ops - set platform dependent suspend operations * @ops: The new suspend operations to set. -- cgit v1.2.3 From 6391a4481ba0796805d6581e42f9f0418c099e34 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 20 Jan 2017 14:32:42 +0800 Subject: virtio-net: restore VIRTIO_HDR_F_DATA_VALID on receiving Commit 501db511397f ("virtio: don't set VIRTIO_NET_HDR_F_DATA_VALID on xmit") in fact disables VIRTIO_HDR_F_DATA_VALID on receiving path too, fixing this by adding a hint (has_data_valid) and set it only on the receiving path. Cc: Rolf Neugebauer Signed-off-by: Jason Wang Acked-by: Rolf Neugebauer Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 56436472ccc7..5209b5ed2a64 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -56,7 +56,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, - bool little_endian) + bool little_endian, + bool has_data_valid) { memset(hdr, 0, sizeof(*hdr)); /* no info leak */ @@ -91,6 +92,9 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, skb_checksum_start_offset(skb)); hdr->csum_offset = __cpu_to_virtio16(little_endian, skb->csum_offset); + } else if (has_data_valid && + skb->ip_summed == CHECKSUM_UNNECESSARY) { + hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ return 0; -- cgit v1.2.3 From b1a27eac7fefff33ccf6acc919fc0725bf9815fb Mon Sep 17 00:00:00 2001 From: Nicolas Iooss Date: Sun, 22 Jan 2017 14:41:22 +0100 Subject: IB/cxgb3: fix misspelling in header guard Use CXGB3_... instead of CXBG3_... Fixes: a85fb3383340 ("IB/cxgb3: Move user vendor structures") Cc: stable@vger.kernel.org # 4.9 Signed-off-by: Nicolas Iooss Reviewed-by: Leon Romanovsky Acked-by: Steve Wise Signed-off-by: Doug Ledford --- include/uapi/rdma/cxgb3-abi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/rdma/cxgb3-abi.h b/include/uapi/rdma/cxgb3-abi.h index 48a19bda071b..d24eee12128f 100644 --- a/include/uapi/rdma/cxgb3-abi.h +++ b/include/uapi/rdma/cxgb3-abi.h @@ -30,7 +30,7 @@ * SOFTWARE. */ #ifndef CXGB3_ABI_USER_H -#define CXBG3_ABI_USER_H +#define CXGB3_ABI_USER_H #include -- cgit v1.2.3 From d3f4aadd614c4627244452ad64eaf351179f2c31 Mon Sep 17 00:00:00 2001 From: "Amrani, Ram" Date: Mon, 26 Dec 2016 08:40:57 +0200 Subject: RDMA/core: Add the function ib_mtu_int_to_enum As the functionality to convert the MTU from a number to enum_ib_mtu is ubiquitous, define a dedicated function and remove the duplicated code. Signed-off-by: Ram Amrani Reviewed-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 958a24d8fae7..b567e4452a47 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -352,6 +352,20 @@ static inline int ib_mtu_enum_to_int(enum ib_mtu mtu) } } +static inline enum ib_mtu ib_mtu_int_to_enum(int mtu) +{ + if (mtu >= 4096) + return IB_MTU_4096; + else if (mtu >= 2048) + return IB_MTU_2048; + else if (mtu >= 1024) + return IB_MTU_1024; + else if (mtu >= 512) + return IB_MTU_512; + else + return IB_MTU_256; +} + enum ib_port_state { IB_PORT_NOP = 0, IB_PORT_DOWN = 1, -- cgit v1.2.3 From 20f5e10ef8bcf29a915642245b66e5a132e38fc4 Mon Sep 17 00:00:00 2001 From: "Amrani, Ram" Date: Tue, 24 Jan 2017 12:01:31 +0200 Subject: RDMA/qedr: Add uapi header qedr-abi.h Signed-off-by: Ram Amrani Signed-off-by: Doug Ledford --- include/uapi/rdma/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/rdma/Kbuild b/include/uapi/rdma/Kbuild index 82bdf5626859..bb68cb1b04ed 100644 --- a/include/uapi/rdma/Kbuild +++ b/include/uapi/rdma/Kbuild @@ -16,3 +16,4 @@ header-y += nes-abi.h header-y += ocrdma-abi.h header-y += hns-abi.h header-y += vmw_pvrdma-abi.h +header-y += qedr-abi.h -- cgit v1.2.3 From 5ce6b04ce96896e8a79e6f60740ced911eaac7a4 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sun, 22 Jan 2017 22:10:32 +0800 Subject: netfilter: nft_log: restrict the log prefix length to 127 First, log prefix will be truncated to NF_LOG_PREFIXLEN-1, i.e. 127, at nf_log_packet(), so the extra part is useless. Second, after adding a log rule with a very very long prefix, we will fail to dump the nft rules after this _special_ one, but acctually, they do exist. For example: # name_65000=$(printf "%0.sQ" {1..65000}) # nft add rule filter output log prefix "$name_65000" # nft add rule filter output counter # nft add rule filter output counter # nft list chain filter output table ip filter { chain output { type filter hook output priority 0; policy accept; } } So now, restrict the log prefix length to NF_LOG_PREFIXLEN-1. Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_log.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_log.h b/include/uapi/linux/netfilter/nf_log.h index 8be21e02387d..d0b5fa91ff54 100644 --- a/include/uapi/linux/netfilter/nf_log.h +++ b/include/uapi/linux/netfilter/nf_log.h @@ -9,4 +9,6 @@ #define NF_LOG_MACDECODE 0x20 /* Decode MAC header */ #define NF_LOG_MASK 0x2f +#define NF_LOG_PREFIXLEN 128 + #endif /* _NETFILTER_NF_LOG_H */ -- cgit v1.2.3 From de70185de0333783154863278ac87bfbbc54e384 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 24 Jan 2017 00:51:41 +0100 Subject: netfilter: nf_tables: deconstify walk callback function The flush operation needs to modify set and element objects, so let's deconstify this. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 924325c46aab..7dfdb517f0be 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -207,9 +207,9 @@ struct nft_set_iter { unsigned int skip; int err; int (*fn)(const struct nft_ctx *ctx, - const struct nft_set *set, + struct nft_set *set, const struct nft_set_iter *iter, - const struct nft_set_elem *elem); + struct nft_set_elem *elem); }; /** @@ -301,7 +301,7 @@ struct nft_set_ops { void (*remove)(const struct nft_set *set, const struct nft_set_elem *elem); void (*walk)(const struct nft_ctx *ctx, - const struct nft_set *set, + struct nft_set *set, struct nft_set_iter *iter); unsigned int (*privsize)(const struct nlattr * const nla[]); -- cgit v1.2.3 From 88ff7334f25909802140e690c0e16433e485b0a0 Mon Sep 17 00:00:00 2001 From: Robert Shearman Date: Tue, 24 Jan 2017 16:26:47 +0000 Subject: net: Specify the owning module for lwtunnel ops Modules implementing lwtunnel ops should not be allowed to unload while there is state alive using those ops, so specify the owning module for all lwtunnel ops. Signed-off-by: Robert Shearman Signed-off-by: David S. Miller --- include/net/lwtunnel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 0b585f1fd340..73dd87647460 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -44,6 +44,8 @@ struct lwtunnel_encap_ops { int (*get_encap_size)(struct lwtunnel_state *lwtstate); int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b); int (*xmit)(struct sk_buff *skb); + + struct module *owner; }; #ifdef CONFIG_LWTUNNEL -- cgit v1.2.3 From 8a1f780e7f28c7c1d640118242cf68d528c456cd Mon Sep 17 00:00:00 2001 From: Yasuaki Ishimatsu Date: Tue, 24 Jan 2017 15:17:45 -0800 Subject: memory_hotplug: make zone_can_shift() return a boolean value online_{kernel|movable} is used to change the memory zone to ZONE_{NORMAL|MOVABLE} and online the memory. To check that memory zone can be changed, zone_can_shift() is used. Currently the function returns minus integer value, plus integer value and 0. When the function returns minus or plus integer value, it means that the memory zone can be changed to ZONE_{NORNAL|MOVABLE}. But when the function returns 0, there are two meanings. One of the meanings is that the memory zone does not need to be changed. For example, when memory is in ZONE_NORMAL and onlined by online_kernel the memory zone does not need to be changed. Another meaning is that the memory zone cannot be changed. When memory is in ZONE_NORMAL and onlined by online_movable, the memory zone may not be changed to ZONE_MOVALBE due to memory online limitation(see Documentation/memory-hotplug.txt). In this case, memory must not be onlined. The patch changes the return type of zone_can_shift() so that memory online operation fails when memory zone cannot be changed as follows: Before applying patch: # grep -A 35 "Node 2" /proc/zoneinfo Node 2, zone Normal node_scanned 0 spanned 8388608 present 7864320 managed 7864320 # echo online_movable > memory4097/state # grep -A 35 "Node 2" /proc/zoneinfo Node 2, zone Normal node_scanned 0 spanned 8388608 present 8388608 managed 8388608 online_movable operation succeeded. But memory is onlined as ZONE_NORMAL, not ZONE_MOVABLE. After applying patch: # grep -A 35 "Node 2" /proc/zoneinfo Node 2, zone Normal node_scanned 0 spanned 8388608 present 7864320 managed 7864320 # echo online_movable > memory4097/state bash: echo: write error: Invalid argument # grep -A 35 "Node 2" /proc/zoneinfo Node 2, zone Normal node_scanned 0 spanned 8388608 present 7864320 managed 7864320 online_movable operation failed because of failure of changing the memory zone from ZONE_NORMAL to ZONE_MOVABLE Fixes: df429ac03936 ("memory-hotplug: more general validation of zone during online") Link: http://lkml.kernel.org/r/2f9c3837-33d7-b6e5-59c0-6ca4372b2d84@gmail.com Signed-off-by: Yasuaki Ishimatsu Reviewed-by: Reza Arbab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 01033fadea47..c1784c0b4f35 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -284,7 +284,7 @@ extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, unsigned long map_offset); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); -extern int zone_can_shift(unsigned long pfn, unsigned long nr_pages, - enum zone_type target); +extern bool zone_can_shift(unsigned long pfn, unsigned long nr_pages, + enum zone_type target, int *zone_shift); #endif /* __LINUX_MEMORY_HOTPLUG_H */ -- cgit v1.2.3 From b94f51183b0617e7b9b4fb4137d4cf1cab7547c2 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Tue, 24 Jan 2017 15:17:53 -0800 Subject: kernel/watchdog: prevent false hardlockup on overloaded system On an overloaded system, it is possible that a change in the watchdog threshold can be delayed long enough to trigger a false positive. This can easily be achieved by having a cpu spinning indefinitely on a task, while another cpu updates watchdog threshold. What happens is while trying to park the watchdog threads, the hrtimers on the other cpus trigger and reprogram themselves with the new slower watchdog threshold. Meanwhile, the nmi watchdog is still programmed with the old faster threshold. Because the one cpu is blocked, it prevents the thread parking on the other cpus from completing, which is needed to shutdown the nmi watchdog and reprogram it correctly. As a result, a false positive from the nmi watchdog is reported. Fix this by setting a park_in_progress flag to block all lockups until the parking is complete. Fix provided by Ulrich Obergfell. [akpm@linux-foundation.org: s/park_in_progress/watchdog_park_in_progress/] Link: http://lkml.kernel.org/r/1481041033-192236-1-git-send-email-dzickus@redhat.com Signed-off-by: Don Zickus Reviewed-by: Aaron Tomlin Cc: Ulrich Obergfell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nmi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index aacca824a6ae..0a3fadc32693 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -110,6 +110,7 @@ extern int watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; extern unsigned long *watchdog_cpumask_bits; +extern atomic_t watchdog_park_in_progress; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; -- cgit v1.2.3 From ea57485af8f4221312a5a95d63c382b45e7840dc Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 24 Jan 2017 15:18:32 -0800 Subject: mm, page_alloc: fix check for NULL preferred_zone Patch series "fix premature OOM regression in 4.7+ due to cpuset races". This is v2 of my attempt to fix the recent report based on LTP cpuset stress test [1]. The intention is to go to stable 4.9 LTSS with this, as triggering repeated OOMs is not nice. That's why the patches try to be not too intrusive. Unfortunately why investigating I found that modifying the testcase to use per-VMA policies instead of per-task policies will bring the OOM's back, but that seems to be much older and harder to fix problem. I have posted a RFC [2] but I believe that fixing the recent regressions has a higher priority. Longer-term we might try to think how to fix the cpuset mess in a better and less error prone way. I was for example very surprised to learn, that cpuset updates change not only task->mems_allowed, but also nodemask of mempolicies. Until now I expected the parameter to alloc_pages_nodemask() to be stable. I wonder why do we then treat cpusets specially in get_page_from_freelist() and distinguish HARDWALL etc, when there's unconditional intersection between mempolicy and cpuset. I would expect the nodemask adjustment for saving overhead in g_p_f(), but that clearly doesn't happen in the current form. So we have both crazy complexity and overhead, AFAICS. [1] https://lkml.kernel.org/r/CAFpQJXUq-JuEP=QPidy4p_=FN0rkH5Z-kfB4qBvsf6jMS87Edg@mail.gmail.com [2] https://lkml.kernel.org/r/7c459f26-13a6-a817-e508-b65b903a8378@suse.cz This patch (of 4): Since commit c33d6c06f60f ("mm, page_alloc: avoid looking up the first zone in a zonelist twice") we have a wrong check for NULL preferred_zone, which can theoretically happen due to concurrent cpuset modification. We check the zoneref pointer which is never NULL and we should check the zone pointer. Also document this in first_zones_zonelist() comment per Michal Hocko. Fixes: c33d6c06f60f ("mm, page_alloc: avoid looking up the first zone in a zonelist twice") Link: http://lkml.kernel.org/r/20170120103843.24587-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Hillf Danton Cc: Ganapatrao Kulkarni Cc: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 36d9896fbc1e..f4aac87adcc3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -972,12 +972,16 @@ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, * @zonelist - The zonelist to search for a suitable zone * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with - * @zone - The first suitable zone found is returned via this parameter + * @return - Zoneref pointer for the first suitable zone found (see below) * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. + * + * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is + * never NULL). This may happen either genuinely, or due to concurrent nodemask + * update due to cpuset modification. */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, -- cgit v1.2.3 From d6f8cfa3dea294eabf8f302e90176dd6381fb66e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 25 Jan 2017 11:39:49 +0100 Subject: net: phy: leds: Break dependency of phy.h on phy_led_triggers.h includes , which is not really needed. Drop the include from , and add it to all users that didn't include it explicitly. Suggested-by: Andrew Lunn Signed-off-by: Geert Uytterhoeven Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index f7d95f644eed..7fc1105605bf 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -25,7 +25,6 @@ #include #include #include -#include #include -- cgit v1.2.3 From 3c880eb0205222bb062970085ebedc73ec8dfd14 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 25 Jan 2017 11:39:50 +0100 Subject: net: phy: leds: Fix truncated LED trigger names Commit 4567d686f5c6d955 ("phy: increase size of MII_BUS_ID_SIZE and bus_id") increased the size of MII bus IDs, but forgot to update the private definition in . This may cause: 1. Truncation of LED trigger names, 2. Duplicate LED trigger names, 3. Failures registering LED triggers, 4. Crashes due to bad error handling in the LED trigger failure path. To fix this, and prevent the definitions going out of sync again in the future, let the PHY LED trigger code use the existing MII_BUS_ID_SIZE definition. Example: - Before I had triggers "ee700000.etherne:01:100Mbps" and "ee700000.etherne:01:10Mbps", - After the increase of MII_BUS_ID_SIZE, both became "ee700000.ethernet-ffffffff:01:" => FAIL, - Now, the triggers are "ee700000.ethernet-ffffffff:01:100Mbps" and "ee700000.ethernet-ffffffff:01:10Mbps", which are unique again. Fixes: 4567d686f5c6d955 ("phy: increase size of MII_BUS_ID_SIZE and bus_id") Fixes: 2e0bc452f4721520 ("net: phy: leds: add support for led triggers on phy link state change") Signed-off-by: Geert Uytterhoeven Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy_led_triggers.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h index a2daea0a37d2..b37b05bfd1a6 100644 --- a/include/linux/phy_led_triggers.h +++ b/include/linux/phy_led_triggers.h @@ -18,11 +18,11 @@ struct phy_device; #ifdef CONFIG_LED_TRIGGER_PHY #include +#include #define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 10 -#define PHY_MII_BUS_ID_SIZE (20 - 3) -#define PHY_LINK_LED_TRIGGER_NAME_SIZE (PHY_MII_BUS_ID_SIZE + \ +#define PHY_LINK_LED_TRIGGER_NAME_SIZE (MII_BUS_ID_SIZE + \ FIELD_SIZEOF(struct mdio_device, addr)+\ PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE) -- cgit v1.2.3 From 54a07c7bb0da0343734c78212bbe9f3735394962 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 26 Jan 2017 06:44:03 +1000 Subject: Revert "drm/probe-helpers: Drop locking from poll_enable" This reverts commit 3846fd9b86001bea171943cc3bb9222cb6da6b42. There were some precursor commits missing for this around connector locking, we should probably merge Lyude's nouveau avoid the problem patch. --- include/drm/drm_crtc_helper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h index d026f5017c33..982c299e435a 100644 --- a/include/drm/drm_crtc_helper.h +++ b/include/drm/drm_crtc_helper.h @@ -73,5 +73,6 @@ extern void drm_kms_helper_hotplug_event(struct drm_device *dev); extern void drm_kms_helper_poll_disable(struct drm_device *dev); extern void drm_kms_helper_poll_enable(struct drm_device *dev); +extern void drm_kms_helper_poll_enable_locked(struct drm_device *dev); #endif -- cgit v1.2.3 From 92e55f412cffd016cc245a74278cb4d7b89bb3bc Mon Sep 17 00:00:00 2001 From: Pablo Neira Date: Thu, 26 Jan 2017 22:56:21 +0100 Subject: tcp: don't annotate mark on control socket from tcp_v6_send_response() Unlike ipv4, this control socket is shared by all cpus so we cannot use it as scratchpad area to annotate the mark that we pass to ip6_xmit(). Add a new parameter to ip6_xmit() to indicate the mark. The SCTP socket family caches the flowi6 structure in the sctp_transport structure, so we cannot use to carry the mark unless we later on reset it back, which I discarded since it looks ugly to me. Fixes: bf99b4ded5f8 ("tcp: fix mark propagation with fwmark_reflect enabled") Suggested-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 487e57391664..7afe991e900e 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -871,7 +871,7 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); * upper-layer output functions */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, - struct ipv6_txoptions *opt, int tclass); + __u32 mark, struct ipv6_txoptions *opt, int tclass); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); -- cgit v1.2.3 From 9d162ed69f51cbd9ee5a0c7e82aba7acc96362ff Mon Sep 17 00:00:00 2001 From: Sean Nyekjaer Date: Fri, 27 Jan 2017 08:46:23 +0100 Subject: net: phy: micrel: add support for KSZ8795 This is adds support for the PHYs in the KSZ8795 5port managed switch. It will allow to detect the link between the switch and the soc and uses the same read_status functions as the KSZ8873MLL switch. Signed-off-by: Sean Nyekjaer Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 257173e0095e..f541da68d1e7 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -35,6 +35,8 @@ #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 +#define PHY_ID_KSZ8795 0x00221550 + /* struct phy_device dev_flags definitions */ #define MICREL_PHY_50MHZ_CLK 0x00000001 #define MICREL_PHY_FXEN 0x00000002 -- cgit v1.2.3