From 9c03ee147193645be4c186d3688232fa438c57c7 Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Sat, 16 Jan 2016 00:31:23 +0530 Subject: sched: Fix crash in sched_init_numa() The following PowerPC commit: c118baf80256 ("arch/powerpc/mm/numa.c: do not allocate bootmem memory for non existing nodes") avoids allocating bootmem memory for non existent nodes. But when DEBUG_PER_CPU_MAPS=y is enabled, my powerNV system failed to boot because in sched_init_numa(), cpumask_or() operation was done on unallocated nodes. Fix that by making cpumask_or() operation only on existing nodes. [ Tested with and w/o DEBUG_PER_CPU_MAPS=y on x86 and PowerPC. ] Reported-by: Jan Stancek Tested-by: Jan Stancek Signed-off-by: Raghavendra K T Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Link: http://lkml.kernel.org/r/1452884483-11676-1-git-send-email-raghavendra.kt@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 44253adb3c36..474658b51fe6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6840,7 +6840,7 @@ static void sched_init_numa(void) sched_domains_numa_masks[i][j] = mask; - for (k = 0; k < nr_node_ids; k++) { + for_each_node(k) { if (node_distance(j, k) > sched_domains_numa_distance[i]) continue; -- cgit v1.2.3-59-g8ed1b From 1dff76b92f69051e579bdc131e01500da9fa2a91 Mon Sep 17 00:00:00 2001 From: Gavin Guo Date: Wed, 20 Jan 2016 12:36:58 +0800 Subject: sched/numa: Fix use-after-free bug in the task_numa_compare The following message can be observed on the Ubuntu v3.13.0-65 with KASan backported: ================================================================== BUG: KASan: use after free in task_numa_find_cpu+0x64c/0x890 at addr ffff880dd393ecd8 Read of size 8 by task qemu-system-x86/3998900 ============================================================================= BUG kmalloc-128 (Tainted: G B ): kasan: bad access detected ----------------------------------------------------------------------------- INFO: Allocated in task_numa_fault+0xc1b/0xed0 age=41980 cpu=18 pid=3998890 __slab_alloc+0x4f8/0x560 __kmalloc+0x1eb/0x280 task_numa_fault+0xc1b/0xed0 do_numa_page+0x192/0x200 handle_mm_fault+0x808/0x1160 __do_page_fault+0x218/0x750 do_page_fault+0x1a/0x70 page_fault+0x28/0x30 SyS_poll+0x66/0x1a0 system_call_fastpath+0x1a/0x1f INFO: Freed in task_numa_free+0x1d2/0x200 age=62 cpu=18 pid=0 __slab_free+0x2ab/0x3f0 kfree+0x161/0x170 task_numa_free+0x1d2/0x200 finish_task_switch+0x1d2/0x210 __schedule+0x5d4/0xc60 schedule_preempt_disabled+0x40/0xc0 cpu_startup_entry+0x2da/0x340 start_secondary+0x28f/0x360 Call Trace: [] dump_stack+0x45/0x56 [] print_trailer+0xfd/0x170 [] object_err+0x36/0x40 [] kasan_report_error+0x1e9/0x3a0 [] kasan_report+0x40/0x50 [] ? task_numa_find_cpu+0x64c/0x890 [] __asan_load8+0x69/0xa0 [] ? find_next_bit+0xd8/0x120 [] task_numa_find_cpu+0x64c/0x890 [] task_numa_migrate+0x4ac/0x7b0 [] numa_migrate_preferred+0xb3/0xc0 [] task_numa_fault+0xb88/0xed0 [] do_numa_page+0x192/0x200 [] handle_mm_fault+0x808/0x1160 [] ? sched_clock_cpu+0x10d/0x160 [] ? native_load_tls+0x82/0xa0 [] __do_page_fault+0x218/0x750 [] ? hrtimer_try_to_cancel+0x76/0x160 [] ? schedule_hrtimeout_range_clock.part.24+0xf7/0x1c0 [] do_page_fault+0x1a/0x70 [] page_fault+0x28/0x30 [] ? do_sys_poll+0x1c4/0x6d0 [] ? enqueue_task_fair+0x4b6/0xaa0 [] ? sched_clock+0x9/0x10 [] ? resched_task+0x7a/0xc0 [] ? check_preempt_curr+0xb3/0x130 [] ? poll_select_copy_remaining+0x170/0x170 [] ? wake_up_state+0x10/0x20 [] ? drop_futex_key_refs.isra.14+0x1f/0x90 [] ? futex_requeue+0x3de/0xba0 [] ? do_futex+0xbe/0x8f0 [] ? read_tsc+0x9/0x20 [] ? ktime_get_ts+0x12d/0x170 [] ? timespec_add_safe+0x59/0xe0 [] SyS_poll+0x66/0x1a0 [] system_call_fastpath+0x1a/0x1f As commit 1effd9f19324 ("sched/numa: Fix unsafe get_task_struct() in task_numa_assign()") points out, the rcu_read_lock() cannot protect the task_struct from being freed in the finish_task_switch(). And the bug happens in the process of calculation of imp which requires the access of p->numa_faults being freed in the following path: do_exit() current->flags |= PF_EXITING; release_task() ~~delayed_put_task_struct()~~ schedule() ... ... rq->curr = next; context_switch() finish_task_switch() put_task_struct() __put_task_struct() task_numa_free() The fix here to get_task_struct() early before end of dst_rq->lock to protect the calculation process and also put_task_struct() in the corresponding point if finally the dst_rq->curr somehow cannot be assigned. Additional credit to Liang Chen who helped fix the error logic and add the put_task_struct() to the place it missed. Signed-off-by: Gavin Guo Signed-off-by: Peter Zijlstra (Intel) Cc: Andrea Arcangeli Cc: Andrew Morton Cc: Hugh Dickins Cc: Linus Torvalds Cc: Mel Gorman Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: jay.vosburgh@canonical.com Cc: liang.chen@canonical.com Link: http://lkml.kernel.org/r/1453264618-17645-1-git-send-email-gavin.guo@canonical.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1926606ece80..56b7d4b83947 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1220,8 +1220,6 @@ static void task_numa_assign(struct task_numa_env *env, { if (env->best_task) put_task_struct(env->best_task); - if (p) - get_task_struct(p); env->best_task = p; env->best_imp = imp; @@ -1289,20 +1287,30 @@ static void task_numa_compare(struct task_numa_env *env, long imp = env->p->numa_group ? groupimp : taskimp; long moveimp = imp; int dist = env->dist; + bool assigned = false; rcu_read_lock(); raw_spin_lock_irq(&dst_rq->lock); cur = dst_rq->curr; /* - * No need to move the exiting task, and this ensures that ->curr - * wasn't reaped and thus get_task_struct() in task_numa_assign() - * is safe under RCU read lock. - * Note that rcu_read_lock() itself can't protect from the final - * put_task_struct() after the last schedule(). + * No need to move the exiting task or idle task. */ if ((cur->flags & PF_EXITING) || is_idle_task(cur)) cur = NULL; + else { + /* + * The task_struct must be protected here to protect the + * p->numa_faults access in the task_weight since the + * numa_faults could already be freed in the following path: + * finish_task_switch() + * --> put_task_struct() + * --> __put_task_struct() + * --> task_numa_free() + */ + get_task_struct(cur); + } + raw_spin_unlock_irq(&dst_rq->lock); /* @@ -1386,6 +1394,7 @@ balance: */ if (!load_too_imbalanced(src_load, dst_load, env)) { imp = moveimp - 1; + put_task_struct(cur); cur = NULL; goto assign; } @@ -1411,9 +1420,16 @@ balance: env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu); assign: + assigned = true; task_numa_assign(env, cur, imp); unlock: rcu_read_unlock(); + /* + * The dst_rq->curr isn't assigned. The protection for task_struct is + * finished. + */ + if (cur && !assigned) + put_task_struct(cur); } static void task_numa_find_cpu(struct task_numa_env *env, -- cgit v1.2.3-59-g8ed1b From 840d6fe7425ffb6a62d53b2759e01ae6daf90e4e Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Sat, 30 Jan 2016 10:04:17 +0800 Subject: pid: Fix spelling in comments Accidentally discovered this typo when I studied this module. Signed-off-by: Zhen Lei Cc: Hanjun Guo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tianhong Ding Cc: Xinwei Hu Cc: Zefan Li Link: http://lkml.kernel.org/r/1454119457-11272-1-git-send-email-thunder.leizhen@huawei.com Signed-off-by: Ingo Molnar --- kernel/pid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/pid.c b/kernel/pid.c index 78b3d9f80d44..e793d091f680 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -588,7 +588,7 @@ void __init pidhash_init(void) void __init pidmap_init(void) { - /* Veryify no one has done anything silly */ + /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING); /* bump default and minimum pid_max based on number of cpus */ -- cgit v1.2.3-59-g8ed1b