From a91dbff551a6f1865b68fa82b654591490b59901 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 3 Aug 2017 16:29:43 -0400 Subject: sock: ulimit on MSG_ZEROCOPY pages Bound the number of pages that a user may pin. Follow the lead of perf tools to maintain a per-user bound on memory locked pages commit 789f90fcf6b0 ("perf_counter: per user mlock gift") Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/sched/user.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 5d5415e129d4..3c07e4135127 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -36,7 +36,8 @@ struct user_struct { struct hlist_node uidhash_node; kuid_t uid; -#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) +#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ + defined(CONFIG_NET) atomic_long_t locked_vm; #endif }; -- cgit v1.2.3 From 18f08dae19990f5fffde92e3a63e0d90cda0f1a8 Mon Sep 17 00:00:00 2001 From: Cheng Jian Date: Fri, 4 Aug 2017 17:19:37 +0800 Subject: sched/core: Remove unnecessary initialization init_idle_bootup_task() init_idle_bootup_task( ) is called in rest_init( ) to switch the scheduling class of the boot thread to the idle class. the function only sets: idle->sched_class = &idle_sched_class; which has been set in init_idle() called by sched_init(): /* * The idle tasks have their own, simple scheduling class: */ idle->sched_class = &idle_sched_class; We've already set the boot thread to idle class in start_kernel()->sched_init()->init_idle() so it's unnecessary to set it again in start_kernel()->rest_init()->init_idle_bootup_task() Signed-off-by: Cheng Jian Signed-off-by: Xie XiuQi Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1501838377-109720-1-git-send-email-cj.chengjian@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched/task.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index c97e5f096927..79a2a744648d 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -30,7 +30,6 @@ extern int lockdep_tasklist_lock_is_held(void); extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); -extern void init_idle_bootup_task(struct task_struct *idle); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); extern void sched_dead(struct task_struct *p); -- cgit v1.2.3 From 74dc3384fc7983b78cc46ebb1824968a3db85eb1 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sun, 6 Aug 2017 14:41:41 +1000 Subject: sched/debug: Use task_pid_nr_ns in /proc/$pid/sched It appears as though the addition of the PID namespace did not update the output code for /proc/*/sched, which resulted in it providing PIDs that were not self-consistent with the /proc mount. This additionally made it trivial to detect whether a process was inside &init_pid_ns from userspace, making container detection trivial: https://github.com/jessfraz/amicontained This leads to situations such as: % unshare -pmf % mount -t proc proc /proc % head -n1 /proc/1/sched head (10047, #threads: 1) Fix this by just using task_pid_nr_ns for the output of /proc/*/sched. All of the other uses of task_pid_nr in kernel/sched/debug.c are from a sysctl context and thus don't need to be namespaced. Signed-off-by: Aleksa Sarai Signed-off-by: Peter Zijlstra (Intel) Acked-by: Eric W. Biederman Cc: Jess Frazelle Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: cyphar@cyphar.com Link: http://lkml.kernel.org/r/20170806044141.5093-1-asarai@suse.com Signed-off-by: Ingo Molnar --- include/linux/sched/debug.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index e0eaee54c5a4..5d58d49e9f87 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -6,6 +6,7 @@ */ struct task_struct; +struct pid_namespace; extern void dump_cpu_task(int cpu); @@ -34,7 +35,8 @@ extern void sched_show_task(struct task_struct *p); #ifdef CONFIG_SCHED_DEBUG struct seq_file; -extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); +extern void proc_sched_show_task(struct task_struct *p, + struct pid_namespace *ns, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); #endif -- cgit v1.2.3 From d92a8cfcb37ecd1315269dab741f073b63b3a8b6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 3 Mar 2017 10:13:38 +0100 Subject: locking/lockdep: Rework FS_RECLAIM annotation A while ago someone, and I cannot find the email just now, asked if we could not implement the RECLAIM_FS inversion stuff with a 'fake' lock like we use for other things like workqueues etc. I think this should be possible which allows reducing the 'irq' states and will reduce the amount of __bfs() lookups we do. Removing the 1 IRQ state results in 4 less __bfs() walks per dependency, improving lockdep performance. And by moving this annotation out of the lockdep code it becomes easier for the mm people to extend. Signed-off-by: Peter Zijlstra (Intel) Cc: Byungchul Park Cc: Linus Torvalds Cc: Mel Gorman Cc: Michal Hocko Cc: Nikolay Borisov Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: boqun.feng@gmail.com Cc: iamjoonsoo.kim@lge.com Cc: kernel-team@lge.com Cc: kirill@shutemov.name Cc: npiggin@gmail.com Cc: walken@google.com Signed-off-by: Ingo Molnar --- include/linux/sched/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/sched') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2b24a6974847..2b0a281f9d26 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -167,6 +167,14 @@ static inline gfp_t current_gfp_context(gfp_t flags) return flags; } +#ifdef CONFIG_LOCKDEP +extern void fs_reclaim_acquire(gfp_t gfp_mask); +extern void fs_reclaim_release(gfp_t gfp_mask); +#else +static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } +static inline void fs_reclaim_release(gfp_t gfp_mask) { } +#endif + static inline unsigned int memalloc_noio_save(void) { unsigned int flags = current->flags & PF_MEMALLOC_NOIO; -- cgit v1.2.3 From 90001d67be2fa2acbe3510d1f64fa6533efa30ef Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 31 Jul 2017 17:50:05 +0200 Subject: sched/fair: Fix wake_affine() for !NUMA_BALANCING In commit: 3fed382b46ba ("sched/numa: Implement NUMA node level wake_affine()") Rik changed wake_affine to consider NUMA information when balancing between LLC domains. There are a number of problems here which this patch tries to address: - LLC < NODE; in this case we'd use the wrong information to balance - !NUMA_BALANCING: in this case, the new code doesn't do any balancing at all - re-computes the NUMA data for every wakeup, this can mean iterating up to 64 CPUs for every wakeup. - default affine wakeups inside a cache We address these by saving the load/capacity values for each sched_domain during regular load-balance and using these values in wake_affine_llc(). The obvious down-side to using cached values is that they can be too old and poorly reflect reality. But this way we can use LLC wide information and thus not rely on assuming LLC matches NODE. We also don't rely on NUMA_BALANCING nor do we have to aggegate two nodes (or even cache domains) worth of CPUs for each wakeup. Signed-off-by: Peter Zijlstra (Intel) Cc: Josef Bacik Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Fixes: 3fed382b46ba ("sched/numa: Implement NUMA node level wake_affine()") [ Minor readability improvements. ] Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/sched') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7d065abc7a47..d7b6dab956ec 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -71,6 +71,14 @@ struct sched_domain_shared { atomic_t ref; atomic_t nr_busy_cpus; int has_idle_cores; + + /* + * Some variables from the most recent sd_lb_stats for this domain, + * used by wake_affine(). + */ + unsigned long nr_running; + unsigned long load; + unsigned long capacity; }; struct sched_domain { -- cgit v1.2.3 From 212925802454672e6cd2949a727f5e2c1377bf06 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 6 Sep 2017 16:25:00 -0700 Subject: mm: oom: let oom_reap_task and exit_mmap run concurrently This is purely required because exit_aio() may block and exit_mmap() may never start, if the oom_reap_task cannot start running on a mm with mm_users == 0. At the same time if the OOM reaper doesn't wait at all for the memory of the current OOM candidate to be freed by exit_mmap->unmap_vmas, it would generate a spurious OOM kill. If it wasn't because of the exit_aio or similar blocking functions in the last mmput, it would be enough to change the oom_reap_task() in the case it finds mm_users == 0, to wait for a timeout or to wait for __mmput to set MMF_OOM_SKIP itself, but it's not just exit_mmap the problem here so the concurrency of exit_mmap and oom_reap_task is apparently warranted. It's a non standard runtime, exit_mmap() runs without mmap_sem, and oom_reap_task runs with the mmap_sem for reading as usual (kind of MADV_DONTNEED). The race between the two is solved with a combination of tsk_is_oom_victim() (serialized by task_lock) and MMF_OOM_SKIP (serialized by a dummy down_write/up_write cycle on the same lines of the ksm_exit method). If the oom_reap_task() may be running concurrently during exit_mmap, exit_mmap will wait it to finish in down_write (before taking down mm structures that would make the oom_reap_task fail with use after free). If exit_mmap comes first, oom_reap_task() will skip the mm if MMF_OOM_SKIP is already set and in turn all memory is already freed and furthermore the mm data structures may already have been taken down by free_pgtables. [aarcange@redhat.com: incremental one liner] Link: http://lkml.kernel.org/r/20170726164319.GC29716@redhat.com [rientjes@google.com: remove unused mmput_async] Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1708141733130.50317@chino.kir.corp.google.com [aarcange@redhat.com: microoptimization] Link: http://lkml.kernel.org/r/20170817171240.GB5066@redhat.com Link: http://lkml.kernel.org/r/20170726162912.GA29716@redhat.com Fixes: 26db62f179d1 ("oom: keep mm of the killed task available") Signed-off-by: Andrea Arcangeli Signed-off-by: David Rientjes Reported-by: David Rientjes Tested-by: David Rientjes Reviewed-by: Michal Hocko Cc: Tetsuo Handa Cc: Oleg Nesterov Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2b0a281f9d26..3a19c253bdb1 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -84,12 +84,6 @@ static inline bool mmget_not_zero(struct mm_struct *mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); -#ifdef CONFIG_MMU -/* same as above but performs the slow path from the async context. Can - * be called from the atomic context as well - */ -extern void mmput_async(struct mm_struct *); -#endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); -- cgit v1.2.3