From aa00d89c2780d72d082a015e8cbb751e65fb30ee Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:33 -0800 Subject: sched: do not use cpu_to_node() to find an offlined cpu's node. If a cpu is offline, its nid will be set to -1, and cpu_to_node(cpu) will return -1. As a result, cpumask_of_node(nid) will return NULL. In this case, find_next_bit() in for_each_cpu will get a NULL pointer and cause panic. Here is a call trace: Call Trace: select_fallback_rq+0x71/0x190 try_to_wake_up+0x2cb/0x2f0 wake_up_process+0x15/0x20 hrtimer_wakeup+0x22/0x30 __run_hrtimer+0x83/0x320 hrtimer_interrupt+0x106/0x280 smp_apic_timer_interrupt+0x69/0x99 apic_timer_interrupt+0x6f/0x80 There is a hrtimer process sleeping, whose cpu has already been offlined. When it is waken up, it tries to find another cpu to run, and get a -1 nid. As a result, cpumask_of_node(-1) returns NULL, and causes ernel panic. This patch fixes this problem by judging if the nid is -1. If nid is not -1, a cpu on the same node will be picked. Else, a online cpu on another node will be picked. Signed-off-by: Tang Chen Signed-off-by: Wen Congyang Cc: Yasuaki Ishimatsu Cc: David Rientjes Cc: Jiang Liu Cc: Minchan Kim Cc: KOSAKI Motohiro Cc: Mel Gorman Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched/core.c | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3a673a3b0c6..053dfd7692d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1132,18 +1132,28 @@ EXPORT_SYMBOL_GPL(kick_process); */ static int select_fallback_rq(int cpu, struct task_struct *p) { - const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu)); + int nid = cpu_to_node(cpu); + const struct cpumask *nodemask = NULL; enum { cpuset, possible, fail } state = cpuset; int dest_cpu; - /* Look for allowed, online CPU in same node. */ - for_each_cpu(dest_cpu, nodemask) { - if (!cpu_online(dest_cpu)) - continue; - if (!cpu_active(dest_cpu)) - continue; - if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) - return dest_cpu; + /* + * If the node that the cpu is on has been offlined, cpu_to_node() + * will return -1. There is no cpu on the node, and we should + * select the cpu on the other node. + */ + if (nid != -1) { + nodemask = cpumask_of_node(nid); + + /* Look for allowed, online CPU in same node. */ + for_each_cpu(dest_cpu, nodemask) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; + if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) + return dest_cpu; + } } for (;;) { -- cgit v1.2.3-70-g09d2 From 75f7ad8e043d9383337d917584297f7737154bbf Mon Sep 17 00:00:00 2001 From: Paul Szabo Date: Fri, 22 Feb 2013 16:34:42 -0800 Subject: page-writeback.c: subtract min_free_kbytes from dirtyable memory When calculating amount of dirtyable memory, min_free_kbytes should be subtracted because it is not intended for dirty pages. Addresses http://bugs.debian.org/695182 [akpm@linux-foundation.org: fix up min_free_kbytes extern declarations] [akpm@linux-foundation.org: fix min() warning] Signed-off-by: Paul Szabo Acked-by: Rik van Riel Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ kernel/sysctl.c | 1 - mm/huge_memory.c | 1 - mm/page-writeback.c | 3 +++ 4 files changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1d4122bf6f2..437da0ce78c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1393,6 +1393,9 @@ extern void setup_per_cpu_pageset(void); extern void zone_pcp_update(struct zone *zone); extern void zone_pcp_reset(struct zone *zone); +/* page_alloc.c */ +extern int min_free_kbytes; + /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 467d8b923fc..95e9e55602a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -105,7 +105,6 @@ extern char core_pattern[]; extern unsigned int core_pipe_limit; #endif extern int pid_max; -extern int min_free_kbytes; extern int pid_max_min, pid_max_max; extern int sysctl_drop_caches; extern int percpu_pagelist_fraction; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b1cc6591ed8..c63a21d0e99 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -105,7 +105,6 @@ static int set_recommended_min_free_kbytes(void) struct zone *zone; int nr_zones = 0; unsigned long recommended_min; - extern int min_free_kbytes; if (!khugepaged_enabled()) return 0; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7300c9d5e1d..cdc377c456c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -241,6 +241,9 @@ static unsigned long global_dirtyable_memory(void) if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); + /* Subtract min_free_kbytes */ + x -= min_t(unsigned long, x, min_free_kbytes >> (PAGE_SHIFT - 10)); + return x + 1; /* Ensure that we never return 0 */ } -- cgit v1.2.3-70-g09d2