From ae1ff3d623905947158fd3394854c23026337810 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Mon, 13 Jul 2015 14:31:28 +0300 Subject: iommu: iova: Move iova cache management to the iova library This is necessary to separate intel-iommu from the iova library. Signed-off-by: Sakari Ailus Signed-off-by: David Woodhouse --- include/linux/iova.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 3920a19d8194..92f7177db2ce 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -68,8 +68,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) return iova >> iova_shift(iovad); } -int iommu_iova_cache_init(void); -void iommu_iova_cache_destroy(void); +int iova_cache_get(void); +void iova_cache_put(void); struct iova *alloc_iova_mem(void); void free_iova_mem(struct iova *iova); -- cgit v1.2.3 From 30035e45753b708e7d47a98398500ca005e02b86 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Wed, 29 Apr 2015 12:52:04 -0400 Subject: string: provide strscpy() The strscpy() API is intended to be used instead of strlcpy(), and instead of most uses of strncpy(). - Unlike strlcpy(), it doesn't read from memory beyond (src + size). - Unlike strlcpy() or strncpy(), the API provides an easy way to check for destination buffer overflow: an -E2BIG error return value. - The provided implementation is robust in the face of the source buffer being asynchronously changed during the copy, unlike the current implementation of strlcpy(). - Unlike strncpy(), the destination buffer will be NUL-terminated if the string in the source buffer is too long. - Also unlike strncpy(), the destination buffer will not be updated beyond the NUL termination, avoiding strncpy's behavior of zeroing the entire tail end of the destination buffer. (A memset() after the strscpy() can be used if this behavior is desired.) - The implementation should be reasonably performant on all platforms since it uses the asm/word-at-a-time.h API rather than simple byte copy. Kernel-to-kernel string copy is not considered to be performance critical in any case. Signed-off-by: Chris Metcalf --- include/linux/string.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index a8d90db9c4b0..9ef7795e65e4 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -25,6 +25,9 @@ extern char * strncpy(char *,const char *, __kernel_size_t); #ifndef __HAVE_ARCH_STRLCPY size_t strlcpy(char *, const char *, size_t); #endif +#ifndef __HAVE_ARCH_STRSCPY +ssize_t __must_check strscpy(char *, const char *, size_t); +#endif #ifndef __HAVE_ARCH_STRCAT extern char * strcat(char *, const char *); #endif -- cgit v1.2.3 From cd33dc9ac2977ebe30cecbf39d2992190fbac5b4 Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Tue, 8 Sep 2015 14:51:12 +0100 Subject: thermal: Fix thermal_zone_of_sensor_register to match documentation thermal_zone_of_sensor_register is documented as returning a pointer to either a valid thermal_zone_device on success, or a corresponding ERR_PTR() value. In contrast, the function returns NULL when THERMAL_OF is configured off. Fix this. Signed-off-by: Punit Agrawal Acked-by: Guenter Roeck Cc: Eduardo Valentin Cc: Zhang Rui Signed-off-by: Eduardo Valentin --- include/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 17292fee8686..0c5518e13584 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -360,7 +360,7 @@ static inline struct thermal_zone_device * thermal_zone_of_sensor_register(struct device *dev, int id, void *data, const struct thermal_zone_of_device_ops *ops) { - return NULL; + return ERR_PTR(-ENODEV); } static inline -- cgit v1.2.3 From c973c3bcec3752455c4d7545edd42935cd7942d9 Mon Sep 17 00:00:00 2001 From: Javi Merino Date: Mon, 14 Sep 2015 14:23:50 +0100 Subject: thermal: Add a function to get the minimum power The thermal core already has a function to get the maximum power of a cooling device: power_actor_get_max_power(). Add a function to get the minimum power of a cooling device. Cc: Zhang Rui Cc: Eduardo Valentin Reviewed-by: Daniel Kurtz Signed-off-by: Javi Merino Signed-off-by: Eduardo Valentin --- include/linux/thermal.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 0c5518e13584..157d366e761b 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -380,6 +380,8 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) int power_actor_get_max_power(struct thermal_cooling_device *, struct thermal_zone_device *tz, u32 *max_power); +int power_actor_get_min_power(struct thermal_cooling_device *, + struct thermal_zone_device *tz, u32 *min_power); int power_actor_set_power(struct thermal_cooling_device *, struct thermal_instance *, u32); struct thermal_zone_device *thermal_zone_device_register(const char *, int, int, @@ -415,6 +417,10 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) static inline int power_actor_get_max_power(struct thermal_cooling_device *cdev, struct thermal_zone_device *tz, u32 *max_power) { return 0; } +static inline int power_actor_get_min_power(struct thermal_cooling_device *cdev, + struct thermal_zone_device *tz, + u32 *min_power) +{ return -ENODEV; } static inline int power_actor_set_power(struct thermal_cooling_device *cdev, struct thermal_instance *tz, u32 power) { return 0; } -- cgit v1.2.3 From 63cdbc06b357dcb3a7104a421ee4a4550d7fadfd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 14 Sep 2015 17:06:27 +0200 Subject: netfilter: bridge: fix routing of bridge frames with call-iptables=1 We can't re-use the physoutdev storage area. 1. When using NFQUEUE in PREROUTING, we attempt to bump a bogus refcnt since nf_bridge->physoutdev is garbage (ipv4/ipv6 address) 2. for same reason, we crash in physdev match in FORWARD or later if skb is routed instead of bridged. This increases nf_bridge_info to 40 bytes, but we have no other choice. Fixes: 72b1e5e4cac7 ("netfilter: bridge: reduce nf_bridge_info to 32 bytes again") Reported-by: Sander Eikelenboom Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2738d355cdf9..9987af080fa0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -179,6 +179,9 @@ struct nf_bridge_info { u8 bridged_dnat:1; __u16 frag_max_size; struct net_device *physindev; + + /* always valid & non-NULL from FORWARD on, for physdev match */ + struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; @@ -189,9 +192,6 @@ struct nf_bridge_info { * skb is out in neigh layer. */ char neigh_header[8]; - - /* always valid & non-NULL from FORWARD on, for physdev match */ - struct net_device *physoutdev; }; }; #endif -- cgit v1.2.3 From 0c986253b939cc14c69d4adbe2b4121bdf4aa220 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 16 Sep 2015 11:51:12 -0400 Subject: Revert "sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem" This reverts commit d59cfc09c32a2ae31f1c3bc2983a0cd79afb3f14. d59cfc09c32a ("sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem") and b5ba75b5fc0e ("cgroup: simplify threadgroup locking") changed how cgroup synchronizes against task fork and exits so that it uses global percpu_rwsem instead of per-process rwsem; unfortunately, the write [un]lock paths of percpu_rwsem always involve synchronize_rcu_expedited() which turned out to be too expensive. Improvements for percpu_rwsem are scheduled to be merged in the coming v4.4-rc1 merge window which alleviates this issue. For now, revert the two commits to restore per-process rwsem. They will be re-applied for the v4.4-rc1 merge window. Signed-off-by: Tejun Heo Link: http://lkml.kernel.org/g/55F8097A.7000206@de.ibm.com Reported-by: Christian Borntraeger Cc: Oleg Nesterov Cc: "Paul E. McKenney" Cc: Peter Zijlstra Cc: Paolo Bonzini Cc: stable@vger.kernel.org # v4.2+ --- include/linux/cgroup-defs.h | 27 ++------------------------- include/linux/init_task.h | 8 ++++++++ include/linux/sched.h | 12 ++++++++++++ 3 files changed, 22 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4d8fcf2187dc..8492721b39be 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -473,31 +473,8 @@ struct cgroup_subsys { unsigned int depends_on; }; -extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; - -/** - * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups - * @tsk: target task - * - * Called from threadgroup_change_begin() and allows cgroup operations to - * synchronize against threadgroup changes using a percpu_rw_semaphore. - */ -static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) -{ - percpu_down_read(&cgroup_threadgroup_rwsem); -} - -/** - * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups - * @tsk: target task - * - * Called from threadgroup_change_end(). Counterpart of - * cgroup_threadcgroup_change_begin(). - */ -static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) -{ - percpu_up_read(&cgroup_threadgroup_rwsem); -} +void cgroup_threadgroup_change_begin(struct task_struct *tsk); +void cgroup_threadgroup_change_end(struct task_struct *tsk); #else /* CONFIG_CGROUPS */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index d0b380ee7d67..e38681f4912d 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -25,6 +25,13 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; +#ifdef CONFIG_CGROUPS +#define INIT_GROUP_RWSEM(sig) \ + .group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem), +#else +#define INIT_GROUP_RWSEM(sig) +#endif + #ifdef CONFIG_CPUSETS #define INIT_CPUSET_SEQ(tsk) \ .mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq), @@ -57,6 +64,7 @@ extern struct fs_struct init_fs; INIT_PREV_CPUTIME(sig) \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ + INIT_GROUP_RWSEM(sig) \ } extern struct nsproxy init_nsproxy; diff --git a/include/linux/sched.h b/include/linux/sched.h index a4ab9daa387c..b7b9501b41af 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -762,6 +762,18 @@ struct signal_struct { unsigned audit_tty_log_passwd; struct tty_audit_buf *tty_audit_buf; #endif +#ifdef CONFIG_CGROUPS + /* + * group_rwsem prevents new tasks from entering the threadgroup and + * member tasks from exiting,a more specifically, setting of + * PF_EXITING. fork and exit paths are protected with this rwsem + * using threadgroup_change_begin/end(). Users which require + * threadgroup to remain stable should use threadgroup_[un]lock() + * which also takes care of exec path. Currently, cgroup is the + * only user. + */ + struct rw_semaphore group_rwsem; +#endif oom_flags_t oom_flags; short oom_score_adj; /* OOM kill score adjustment */ -- cgit v1.2.3 From 0243ed44ad4a25dbd2e92ad97e5e12a1a6c72d6c Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Tue, 15 Sep 2015 04:59:21 -0700 Subject: spi: fix kernel-doc warnings in spi.h Fix the following 'make htmldocs' warnings: .//include/linux/spi/spi.h:71: warning: No description found for parameter 'lock' .//include/linux/spi/spi.h:71: warning: Excess struct/union/enum/typedef member 'clock' description in 'spi_statistics' Signed-off-by: Geliang Tang Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 269e8afd3e2a..6b00f18f5e6b 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -34,7 +34,7 @@ extern struct bus_type spi_bus_type; /** * struct spi_statistics - statistics for spi transfers - * @clock: lock protecting this structure + * @lock: lock protecting this structure * * @messages: number of spi-messages handled * @transfers: number of spi_transfers handled -- cgit v1.2.3 From 0fdea1e8a2853f79d39b8555cc9de16a7e0ab26f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 16 Sep 2015 23:43:17 -0400 Subject: SUNRPC: Ensure that we wait for connections to complete before retrying Commit 718ba5b87343, moved the responsibility for unlocking the socket to xs_tcp_setup_socket, meaning that the socket will be unlocked before we know that it has finished trying to connect. The following patch is based on an initial patch by Russell King to ensure that we delay clearing the XPRT_CONNECTING flag until we either know that we failed to initiate a connection attempt, or the connection attempt itself failed. Fixes: 718ba5b87343 ("SUNRPC: Add helpers to prevent socket create from racing") Reported-by: Russell King Reported-by: Russell King Tested-by: Russell King Tested-by: Benjamin Coddington Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 7591788e9fbf..357e44c1a46b 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -42,6 +42,7 @@ struct sock_xprt { /* * Connection of transports */ + unsigned long sock_state; struct delayed_work connect_worker; struct sockaddr_storage srcaddr; unsigned short srcport; @@ -76,6 +77,8 @@ struct sock_xprt { */ #define TCP_RPC_REPLY (1UL << 6) +#define XPRT_SOCK_CONNECTING 1U + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ -- cgit v1.2.3 From b7f76ea2ef6739ee484a165ffbac98deb855d3d3 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 18 Sep 2015 23:41:23 +0200 Subject: security: fix typo in security_task_prctl Signed-off-by: Jann Horn Reviewed-by: Andy Lutomirski Signed-off-by: Linus Torvalds --- include/linux/security.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 79d85ddf8093..2f4c1f7aa7db 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -946,7 +946,7 @@ static inline int security_task_prctl(int option, unsigned long arg2, unsigned long arg4, unsigned long arg5) { - return cap_task_prctl(option, arg2, arg3, arg3, arg5); + return cap_task_prctl(option, arg2, arg3, arg4, arg5); } static inline void security_task_to_inode(struct task_struct *p, struct inode *inode) -- cgit v1.2.3 From 66e8c57da6bf6b847a48a5a6fda59512f733ed78 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 25 Aug 2015 20:45:18 +0200 Subject: rcu: Change _wait_rcu_gp() to work around GCC bug 67055 Code like this in inline functions confuses some recent versions of gcc: const int n = const-expr; whatever_t array[n]; For more details, see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67055#c13 This compiler bug results in the following failure after 114b7fd4b (rcu: Create rcu_sync infrastructure): In file included from include/linux/rcupdate.h:429:0, from include/linux/rcu_sync.h:5, from kernel/rcu/sync.c:1: include/linux/rcutiny.h: In function 'rcu_barrier_sched': include/linux/rcutiny.h:55:20: internal compiler error: Segmentation fault static inline void rcu_barrier_sched(void) This commit therefore eliminates the constant local variable in favor of direct use of the expression. Reported-and-tested-by: Mark Salter Reported-by: Guenter Roeck Signed-off-by: Oleg Nesterov Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index ff476515f716..581abf848566 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -230,12 +230,11 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, struct rcu_synchronize *rs_array); #define _wait_rcu_gp(checktiny, ...) \ -do { \ - call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ - const int __n = ARRAY_SIZE(__crcu_array); \ - struct rcu_synchronize __rs_array[__n]; \ - \ - __wait_rcu_gp(checktiny, __n, __crcu_array, __rs_array); \ +do { \ + call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ + struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ + __wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array), \ + __crcu_array, __rs_array); \ } while (0) #define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) -- cgit v1.2.3 From ac5be6b47e8bd25b62bed2c82cda7398999f59e9 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Tue, 22 Sep 2015 14:58:49 -0700 Subject: userfaultfd: revert "userfaultfd: waitqueue: add nr wake parameter to __wake_up_locked_key" This reverts commit 51360155eccb907ff8635bd10fc7de876408c2e0 and adapts fs/userfaultfd.c to use the old version of that function. It didn't look robust to call __wake_up_common with "nr == 1" when we absolutely require wakeall semantics, but we've full control of what we insert in the two waitqueue heads of the blocked userfaults. No exclusive waitqueue risks to be inserted into those two waitqueue heads so we can as well stick to "nr == 1" of the old code and we can rely purely on the fact no waitqueue inserted in one of the two waitqueue heads we must enforce as wakeall, has wait->flags WQ_FLAG_EXCLUSIVE set. Signed-off-by: Andrea Arcangeli Cc: Dr. David Alan Gilbert Cc: Michael Ellerman Cc: Shuah Khan Cc: Thierry Reding Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index d3d077228d4c..1e1bf9f963a9 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -147,8 +147,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) typedef int wait_bit_action_f(struct wait_bit_key *); void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr, - void *key); +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); @@ -180,7 +179,7 @@ wait_queue_head_t *bit_waitqueue(void *, int); #define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, (void *) (m)) #define wake_up_locked_poll(x, m) \ - __wake_up_locked_key((x), TASK_NORMAL, 1, (void *) (m)) + __wake_up_locked_key((x), TASK_NORMAL, (void *) (m)) #define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m)) #define wake_up_interruptible_sync_poll(x, m) \ -- cgit v1.2.3 From 2d8bff12699abc3a9bf886bb0b79f44d94d81496 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Wed, 23 Sep 2015 14:57:58 -0400 Subject: netpoll: Close race condition between poll_one_napi and napi_disable Drivers might call napi_disable while not holding the napi instance poll_lock. In those instances, its possible for a race condition to exist between poll_one_napi and napi_disable. That is to say, poll_one_napi only tests the NAPI_STATE_SCHED bit to see if there is work to do during a poll, and as such the following may happen: CPU0 CPU1 ndo_tx_timeout napi_poll_dev napi_disable poll_one_napi test_and_set_bit (ret 0) test_bit (ret 1) reset adapter napi_poll_routine If the adapter gets a tx timeout without a napi instance scheduled, its possible for the adapter to think it has exclusive access to the hardware (as the napi instance is now scheduled via the napi_disable call), while the netpoll code thinks there is simply work to do. The result is parallel hardware access leading to corrupt data structures in the driver, and a crash. Additionaly, there is another, more critical race between netpoll and napi_disable. The disabled napi state is actually identical to the scheduled state for a given napi instance. The implication being that, if a napi instance is disabled, a netconsole instance would see the napi state of the device as having been scheduled, and poll it, likely while the driver was dong something requiring exclusive access. In the case above, its fairly clear that not having the rings in a state ready to be polled will cause any number of crashes. The fix should be pretty easy. netpoll uses its own bit to indicate that that the napi instance is in a state of being serviced by netpoll (NAPI_STATE_NPSVC). We can just gate disabling on that bit as well as the sched bit. That should prevent netpoll from conducting a napi poll if we convert its set bit to a test_and_set_bit operation to provide mutual exclusion Change notes: V2) Remove a trailing whtiespace Resubmit with proper subject prefix V3) Clean up spacing nits Signed-off-by: Neil Horman CC: "David S. Miller" CC: jmaxwell@redhat.com Tested-by: jmaxwell@redhat.com Signed-off-by: David S. Miller --- 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 88a00694eda5..2d15e3831440 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -507,6 +507,7 @@ static inline void napi_enable(struct napi_struct *n) BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); smp_mb__before_atomic(); clear_bit(NAPI_STATE_SCHED, &n->state); + clear_bit(NAPI_STATE_NPSVC, &n->state); } #ifdef CONFIG_SMP -- cgit v1.2.3 From 9badce000e2ce68ba74838a3cd356dde58221c2f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 23 Sep 2015 17:07:29 -0400 Subject: cgroup, writeback: don't enable cgroup writeback on traditional hierarchies inode_cgwb_enabled() gates cgroup writeback support. If it returns true, each inode is attached to the corresponding memory domain which gets mapped to io domain. It currently only tests whether the filesystem and bdi support cgroup writeback; however, cgroup writeback support doesn't work on traditional hierarchies and thus it should also test whether memcg and iocg are on the default hierarchy. This caused traditional hierarchy setups to hit the cgroup writeback path inadvertently and ended up creating separate writeback domains for each memcg and mapping them all to the root iocg uncovering a couple issues in the cgroup writeback path. cgroup writeback was never meant to be enabled on traditional hierarchies. Make inode_cgwb_enabled() test whether both memcg and iocg are on the default hierarchy. Signed-off-by: Tejun Heo Reported-by: Artem Bityutskiy Reported-by: Dexuan Cui Link: http://lkml.kernel.org/g/1443012552.19983.209.camel@gmail.com Link: http://lkml.kernel.org/g/f30d4a6aa8a546ff88f73021d026a453@SIXPR30MB031.064d.mgd.msft.net --- include/linux/backing-dev.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 5a5d79ee256f..d5eb4ad1c534 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -252,13 +253,19 @@ int inode_congested(struct inode *inode, int cong_bits); * @inode: inode of interest * * cgroup writeback requires support from both the bdi and filesystem. - * Test whether @inode has both. + * Also, both memcg and iocg have to be on the default hierarchy. Test + * whether all conditions are met. + * + * Note that the test result may change dynamically on the same inode + * depending on how memcg and iocg are configured. */ static inline bool inode_cgwb_enabled(struct inode *inode) { struct backing_dev_info *bdi = inode_to_bdi(inode); - return bdi_cap_account_dirty(bdi) && + return cgroup_on_dfl(mem_cgroup_root_css->cgroup) && + cgroup_on_dfl(blkcg_root_css->cgroup) && + bdi_cap_account_dirty(bdi) && (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } -- cgit v1.2.3 From 6ae459bdaaeebc632b16e54dcbabb490c6931d61 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Tue, 22 Sep 2015 12:57:53 -0700 Subject: skbuff: Fix skb checksum flag on skb pull VXLAN device can receive skb with checksum partial. But the checksum offset could be in outer header which is pulled on receive. This results in negative checksum offset for the skb. Such skb can cause the assert failure in skb_checksum_help(). Following patch fixes the bug by setting checksum-none while pulling outer header. Following is the kernel panic msg from old kernel hitting the bug. ------------[ cut here ]------------ kernel BUG at net/core/dev.c:1906! RIP: 0010:[] skb_checksum_help+0x144/0x150 Call Trace: [] queue_userspace_packet+0x408/0x470 [openvswitch] [] ovs_dp_upcall+0x5d/0x60 [openvswitch] [] ovs_dp_process_packet_with_key+0xe6/0x100 [openvswitch] [] ovs_dp_process_received_packet+0x4b/0x80 [openvswitch] [] ovs_vport_receive+0x2a/0x30 [openvswitch] [] vxlan_rcv+0x53/0x60 [openvswitch] [] vxlan_udp_encap_recv+0x8b/0xf0 [openvswitch] [] udp_queue_rcv_skb+0x2dc/0x3b0 [] __udp4_lib_rcv+0x1cf/0x6c0 [] udp_rcv+0x1a/0x20 [] ip_local_deliver_finish+0xdd/0x280 [] ip_local_deliver+0x88/0x90 [] ip_rcv_finish+0x10d/0x370 [] ip_rcv+0x235/0x300 [] __netif_receive_skb+0x55d/0x620 [] netif_receive_skb+0x80/0x90 [] virtnet_poll+0x555/0x6f0 [] net_rx_action+0x134/0x290 [] __do_softirq+0xa8/0x210 [] call_softirq+0x1c/0x30 [] do_softirq+0x65/0xa0 [] irq_exit+0x8e/0xb0 [] do_IRQ+0x63/0xe0 [] common_interrupt+0x6e/0x6e Reported-by: Anupam Chanda Signed-off-by: Pravin B Shelar Acked-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9987af080fa0..2b0a30a6e31c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2707,6 +2707,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) <= len) + skb->ip_summed = CHECKSUM_NONE; } unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); -- cgit v1.2.3 From 3e3aaf649416988ca8be4ad2c52dc24d8be7b46e Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 24 Sep 2015 20:36:02 +0100 Subject: phy: fix mdiobus module safety Re-implement the mdiobus module refcounting to ensure that we actually ensure that the mdiobus module code does not go away while we might call into it. The old scheme using bus->dev.driver was buggy, because bus->dev is a class device which never has a struct device_driver associated with it, and hence the associated code trying to obtain a refcount did nothing useful. Instead, take the approach that other subsystems do: pass the module when calling mdiobus_register(), and record that in the mii_bus struct. When we need to increment the module use count in the phy code, use this stored pointer. When the phy is deteched, drop the module refcount, remembering that the phy device might go away at that point. This doesn't stop the mii_bus going away while there are in-use phys - it merely stops the underlying code vanishing. Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 962387a192f1..11bce44f6d65 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -153,6 +154,7 @@ struct sk_buff; * PHYs should register using this structure */ struct mii_bus { + struct module *owner; const char *name; char id[MII_BUS_ID_SIZE]; void *priv; @@ -198,7 +200,8 @@ static inline struct mii_bus *mdiobus_alloc(void) return mdiobus_alloc_size(0); } -int mdiobus_register(struct mii_bus *bus); +int __mdiobus_register(struct mii_bus *bus, struct module *owner); +#define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); -- cgit v1.2.3 From 38737e490d4ea91660d3cec83ef88c4e6d360ae4 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 24 Sep 2015 20:36:28 +0100 Subject: phy: add phy_device_remove() Add a phy_device_remove() function to complement phy_device_register(), which undoes the effects of phy_device_register() by removing the phy device from visibility, but not freeing it. This allows these details to be moved out of the mdio bus code into the phy code where this action belongs. Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 11bce44f6d65..4a4e3a092337 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -745,6 +745,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, struct phy_c45_device_ids *c45_ids); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); +void phy_device_remove(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); -- cgit v1.2.3 From c6790aa9f4fdc26b1246ba36da2fd749663beb65 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 24 Sep 2015 10:34:23 +0300 Subject: IB/mlx5: Remove support for IB_DEVICE_LOCAL_DMA_LKEY Commit 96249d70dd70 ("IB/core: Guarantee that a local_dma_lkey is available") allows ULPs that make use of the local dma key to keep working as before by allocating a DMA MR with local permissions and converted these consumers to use the MR associated with the PD rather then device->local_dma_lkey. ConnectIB has some known issues with memory registration using the local_dma_lkey (SEND, RDMA, RECV seems to work ok). Thus don't expose support for it (remove device->local_dma_lkey setting), and take advantage of the above commit such that no regression is introduced to working systems. The local_dma_lkey support will be restored in CX4 depending on FW capability query. Signed-off-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/linux/mlx5/device.h | 11 ----------- include/linux/mlx5/driver.h | 1 - 2 files changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8eb3b19af2a4..250b1ff8b48d 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -402,17 +402,6 @@ struct mlx5_cmd_teardown_hca_mbox_out { u8 rsvd[8]; }; -struct mlx5_cmd_query_special_contexts_mbox_in { - struct mlx5_inbox_hdr hdr; - u8 rsvd[8]; -}; - -struct mlx5_cmd_query_special_contexts_mbox_out { - struct mlx5_outbox_hdr hdr; - __be32 dump_fill_mkey; - __be32 resd_lkey; -}; - struct mlx5_cmd_layout { u8 type; u8 rsvd0[3]; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 27b53f9a24ad..8b6d6f2154a4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -845,7 +845,6 @@ void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol); int mlx5_register_interface(struct mlx5_interface *intf); void mlx5_unregister_interface(struct mlx5_interface *intf); int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id); -int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey); struct mlx5_profile { u64 mask; -- cgit v1.2.3 From 5ebc76035303016ec41bb752bec156ea9fde7c34 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Thu, 17 Sep 2015 14:02:45 +0800 Subject: ACPI, PCI, irq: Do not share PCI IRQ with ISA IRQ Avoid IRQs occupied by ISA IRQs when allocating IRQs for PCI link devices, otherwise it may cause interrupt storm due to incompatible pin attributes. This issue was triggered on a KVM virtual machine, which 1) uses IRQ9 for SCI in high level mode. 2) defines an PCI interrupt link device (LNKS) with IRQ9 as the only possible irq. 3) has an PCI device referring to link device LNKS. So it causes interrupt storm when enabling the PCI device because PCI IRQ works in low level mode. Signed-off-by: Jiang Liu Acked-by: Bjorn Helgaas Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 7235c4851460..43856d19cf4d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -217,6 +217,7 @@ struct pci_dev; int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); +bool acpi_isa_irq_available(int irq); void acpi_penalize_sci_irq(int irq, int trigger, int polarity); void acpi_pci_irq_disable (struct pci_dev *dev); -- cgit v1.2.3 From 4593fdbe7a2f44d5e64c627c715dd0bcec9bdf14 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Sun, 27 Sep 2015 02:09:20 +0900 Subject: blk-mq: fix sysfs registration/unregistration race There is a race between cpu hotplug handling and adding/deleting gendisk for blk-mq, where both are trying to register and unregister the same sysfs entries. null_add_dev --> blk_mq_init_queue --> blk_mq_init_allocated_queue --> add to 'all_q_list' (*) --> add_disk --> blk_register_queue --> blk_mq_register_disk (++) null_del_dev --> del_gendisk --> blk_unregister_queue --> blk_mq_unregister_disk (--) --> blk_cleanup_queue --> blk_mq_free_queue --> del from 'all_q_list' (*) blk_mq_queue_reinit --> blk_mq_sysfs_unregister (-) --> blk_mq_sysfs_register (+) While the request queue is added to 'all_q_list' (*), blk_mq_queue_reinit() can be called for the queue anytime by CPU hotplug callback. But blk_mq_sysfs_unregister (-) and blk_mq_sysfs_register (+) in blk_mq_queue_reinit must not be called before blk_mq_register_disk (++) and after blk_mq_unregister_disk (--) is finished. Because '/sys/block/*/mq/' is not exists. There has already been BLK_MQ_F_SYSFS_UP flag in hctx->flags which can be used to track these sysfs stuff, but it is only fixing this issue partially. In order to fix it completely, we just need per-queue flag instead of per-hctx flag with appropriate locking. So this introduces q->mq_sysfs_init_done which is properly protected with all_q_mutex. Also, we need to ensure that blk_mq_map_swqueue() is called with all_q_mutex is held. Since hctx->nr_ctx is reset temporarily and updated in blk_mq_map_swqueue(), so we should avoid blk_mq_register_hctx() seeing the temporary hctx->nr_ctx value in CPU hotplug handling or adding/deleting gendisk . Signed-off-by: Akinobu Mita Reviewed-by: Ming Lei Cc: Ming Lei Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 - include/linux/blkdev.h | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 37d1602c4f7a..b80ba4572a31 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -145,7 +145,6 @@ enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_SHARED = 1 << 1, BLK_MQ_F_SG_MERGE = 1 << 2, - BLK_MQ_F_SYSFS_UP = 1 << 3, BLK_MQ_F_DEFER_ISSUE = 1 << 4, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, BLK_MQ_F_ALLOC_POLICY_BITS = 1, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 99da9ebc7377..19c2e947d4d1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -456,6 +456,8 @@ struct request_queue { struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; struct bio_set *bio_split; + + bool mq_sysfs_init_done; }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ -- cgit v1.2.3 From 31b33dfb0a144469dd805514c9e63f4993729a48 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Mon, 28 Sep 2015 17:24:25 -0700 Subject: skbuff: Fix skb checksum partial check. Earlier patch 6ae459bda tried to detect void ckecksum partial skb by comparing pull length to checksum offset. But it does not work for all cases since checksum-offset depends on updates to skb->data. Following patch fixes it by validating checksum start offset after skb-data pointer is updated. Negative value of checksum offset start means there is no need to checksum. Fixes: 6ae459bda ("skbuff: Fix skb checksum flag on skb pull") Reported-by: Andrew Vagin Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2b0a30a6e31c..4398411236f1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2708,7 +2708,7 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); else if (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_start_offset(skb) <= len) + skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } -- cgit v1.2.3 From f4829a9b7a61e159367350008a608b062c4f6840 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 27 Sep 2015 21:01:50 +0200 Subject: blk-mq: fix racy updates of rq->errors blk_mq_complete_request may be a no-op if the request has already been completed by others means (e.g. a timeout or cancellation), but currently drivers have to set rq->errors before calling blk_mq_complete_request, which might leave us with the wrong error value. Add an error parameter to blk_mq_complete_request so that we can defer setting rq->errors until we known we won the race to complete the request. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index b80ba4572a31..c1b5c867ff07 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -214,7 +214,7 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head); void blk_mq_cancel_requeue_work(struct request_queue *q); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_abort_requeue_list(struct request_queue *q); -void blk_mq_complete_request(struct request *rq); +void blk_mq_complete_request(struct request *rq, int error); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); -- cgit v1.2.3 From 0bf6cd5b9531bcc29c0a5e504b6ce2984c6fd8d8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 27 Sep 2015 21:01:51 +0200 Subject: blk-mq: factor out a helper to iterate all tags for a request_queue And replace the blk_mq_tag_busy_iter with it - the driver use has been replaced with a new helper a while ago, and internal to the block we only need the new version. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index c1b5c867ff07..5e7d43ab61c0 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -223,8 +223,6 @@ void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); -void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn, - void *priv); void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv); void blk_mq_freeze_queue(struct request_queue *q); -- cgit v1.2.3 From 0610c25daa3e76e38ad5a8fae683a89ff9f71798 Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Thu, 1 Oct 2015 15:37:02 -0700 Subject: memcg: fix dirty page migration The problem starts with a file backed dirty page which is charged to a memcg. Then page migration is used to move oldpage to newpage. Migration: - copies the oldpage's data to newpage - clears oldpage.PG_dirty - sets newpage.PG_dirty - uncharges oldpage from memcg - charges newpage to memcg Clearing oldpage.PG_dirty decrements the charged memcg's dirty page count. However, because newpage is not yet charged, setting newpage.PG_dirty does not increment the memcg's dirty page count. After migration completes newpage.PG_dirty is eventually cleared, often in account_page_cleaned(). At this time newpage is charged to a memcg so the memcg's dirty page count is decremented which causes underflow because the count was not previously incremented by migration. This underflow causes balance_dirty_pages() to see a very large unsigned number of dirty memcg pages which leads to aggressive throttling of buffered writes by processes in non root memcg. This issue: - can harm performance of non root memcg buffered writes. - can report too small (even negative) values in memory.stat[(total_)dirty] counters of all memcg, including the root. To avoid polluting migrate.c with #ifdef CONFIG_MEMCG checks, introduce page_memcg() and set_page_memcg() helpers. Test: 0) setup and enter limited memcg mkdir /sys/fs/cgroup/test echo 1G > /sys/fs/cgroup/test/memory.limit_in_bytes echo $$ > /sys/fs/cgroup/test/cgroup.procs 1) buffered writes baseline dd if=/dev/zero of=/data/tmp/foo bs=1M count=1k sync grep ^dirty /sys/fs/cgroup/test/memory.stat 2) buffered writes with compaction antagonist to induce migration yes 1 > /proc/sys/vm/compact_memory & rm -rf /data/tmp/foo dd if=/dev/zero of=/data/tmp/foo bs=1M count=1k kill % sync grep ^dirty /sys/fs/cgroup/test/memory.stat 3) buffered writes without antagonist, should match baseline rm -rf /data/tmp/foo dd if=/dev/zero of=/data/tmp/foo bs=1M count=1k sync grep ^dirty /sys/fs/cgroup/test/memory.stat (speed, dirty residue) unpatched patched 1) 841 MB/s 0 dirty pages 886 MB/s 0 dirty pages 2) 611 MB/s -33427456 dirty pages 793 MB/s 0 dirty pages 3) 114 MB/s -33427456 dirty pages 891 MB/s 0 dirty pages Notice that unpatched baseline performance (1) fell after migration (3): 841 -> 114 MB/s. In the patched kernel, post migration performance matches baseline. Fixes: c4843a7593a9 ("memcg: add per cgroup dirty page accounting") Signed-off-by: Greg Thelen Reported-by: Dave Hansen Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: [4.2+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 91c08f6f0dc9..80001de019ba 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -905,6 +905,27 @@ static inline void set_page_links(struct page *page, enum zone_type zone, #endif } +#ifdef CONFIG_MEMCG +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return page->mem_cgroup; +} + +static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) +{ + page->mem_cgroup = memcg; +} +#else +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return NULL; +} + +static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) +{ +} +#endif + /* * Some inline functions in vmstat.h depend on page_zone() */ -- cgit v1.2.3 From ef510194cefe0cd369ef73419cd65b0a5bb4fb5b Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Thu, 1 Oct 2015 15:37:13 -0700 Subject: memcg: remove pcp_counter_lock Commit 733a572e66d2 ("memcg: make mem_cgroup_read_{stat|event}() iterate possible cpus instead of online") removed the last use of the per memcg pcp_counter_lock but forgot to remove the variable. Kill the vestigial variable. Signed-off-by: Greg Thelen Acked-by: Michal Hocko Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ad800e62cb7a..6452ff4c463f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -242,7 +242,6 @@ struct mem_cgroup { * percpu counter. */ struct mem_cgroup_stat_cpu __percpu *stat; - spinlock_t pcp_counter_lock; #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) struct cg_proto tcp_mem; -- cgit v1.2.3