From 505970b96e3b7d22177c38e03435a68376628e7a Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Sat, 14 Jan 2006 13:21:06 -0800 Subject: [PATCH] cpuset oom lock fix The problem, reported in: http://bugzilla.kernel.org/show_bug.cgi?id=5859 and by various other email messages and lkml posts is that the cpuset hook in the oom (out of memory) code can try to take a cpuset semaphore while holding the tasklist_lock (a spinlock). One must not sleep while holding a spinlock. The fix seems easy enough - move the cpuset semaphore region outside the tasklist_lock region. This required a few lines of mechanism to implement. The oom code where the locking needs to be changed does not have access to the cpuset locks, which are internal to kernel/cpuset.c only. So I provided a couple more cpuset interface routines, available to the rest of the kernel, which simple take and drop the lock needed here (cpusets callback_sem). Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index d4b6bd7..fe2f71f 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2150,6 +2150,33 @@ int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) } /** + * cpuset_lock - lock out any changes to cpuset structures + * + * The out of memory (oom) code needs to lock down cpusets + * from being changed while it scans the tasklist looking for a + * task in an overlapping cpuset. Expose callback_sem via this + * cpuset_lock() routine, so the oom code can lock it, before + * locking the task list. The tasklist_lock is a spinlock, so + * must be taken inside callback_sem. + */ + +void cpuset_lock(void) +{ + down(&callback_sem); +} + +/** + * cpuset_unlock - release lock on cpuset changes + * + * Undo the lock taken in a previous cpuset_lock() call. + */ + +void cpuset_unlock(void) +{ + up(&callback_sem); +} + +/** * cpuset_excl_nodes_overlap - Do we overlap @p's mem_exclusive ancestors? * @p: pointer to task_struct of some other task. * @@ -2158,7 +2185,7 @@ int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) * determine if task @p's memory usage might impact the memory * available to the current task. * - * Acquires callback_sem - not suitable for calling from a fast path. + * Call while holding callback_sem. **/ int cpuset_excl_nodes_overlap(const struct task_struct *p) @@ -2166,8 +2193,6 @@ int cpuset_excl_nodes_overlap(const struct task_struct *p) const struct cpuset *cs1, *cs2; /* my and p's cpuset ancestors */ int overlap = 0; /* do cpusets overlap? */ - down(&callback_sem); - task_lock(current); if (current->flags & PF_EXITING) { task_unlock(current); @@ -2186,8 +2211,6 @@ int cpuset_excl_nodes_overlap(const struct task_struct *p) overlap = nodes_intersects(cs1->mems_allowed, cs2->mems_allowed); done: - up(&callback_sem); - return overlap; } -- cgit v1.1