aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorDavid Rientjes <rientjes@google.com>2012-10-16 17:31:23 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-10-16 18:00:50 -0700
commit32f8516a8c733d281faa9f6666b509035246505c (patch)
tree31e40b8d5c96dec8a3e6f8adfb3db992718fecc1 /fs
parentdd8e8c4a2c902d8350b702e7bc7c2799e5e7e331 (diff)
mm, mempolicy: fix printing stack contents in numa_maps
When reading /proc/pid/numa_maps, it's possible to return the contents of the stack where the mempolicy string should be printed if the policy gets freed from beneath us. This happens because mpol_to_str() may return an error the stack-allocated buffer is then printed without ever being stored. There are two possible error conditions in mpol_to_str(): - if the buffer allocated is insufficient for the string to be stored, and - if the mempolicy has an invalid mode. The first error condition is not triggered in any of the callers to mpol_to_str(): at least 50 bytes is always allocated on the stack and this is sufficient for the string to be written. A future patch should convert this into BUILD_BUG_ON() since we know the maximum strlen possible, but that's not -rc material. The second error condition is possible if a race occurs in dropping a reference to a task's mempolicy causing it to be freed during the read(). The slab poison value is then used for the mode and mpol_to_str() returns -EINVAL. This race is only possible because get_vma_policy() believes that mm->mmap_sem protects task->mempolicy, which isn't true. The exit path does not hold mm->mmap_sem when dropping the reference or setting task->mempolicy to NULL: it uses task_lock(task) instead. Thus, it's required for the caller of a task mempolicy to hold task_lock(task) while grabbing the mempolicy and reading it. Callers with a vma policy store their mempolicy earlier and can simply increment the reference count so it's guaranteed not to be freed. Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs')
-rw-r--r--fs/proc/task_mmu.c7
1 files changed, 5 insertions, 2 deletions
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 79827ce03e3..14df8806ff2 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1158,6 +1158,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
struct vm_area_struct *vma = v;
struct numa_maps *md = &numa_priv->md;
struct file *file = vma->vm_file;
+ struct task_struct *task = proc_priv->task;
struct mm_struct *mm = vma->vm_mm;
struct mm_walk walk = {};
struct mempolicy *pol;
@@ -1177,9 +1178,11 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
walk.private = md;
walk.mm = mm;
- pol = get_vma_policy(proc_priv->task, vma, vma->vm_start);
+ task_lock(task);
+ pol = get_vma_policy(task, vma, vma->vm_start);
mpol_to_str(buffer, sizeof(buffer), pol, 0);
mpol_cond_put(pol);
+ task_unlock(task);
seq_printf(m, "%08lx %s", vma->vm_start, buffer);
@@ -1189,7 +1192,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
seq_printf(m, " heap");
} else {
- pid_t tid = vm_is_stack(proc_priv->task, vma, is_pid);
+ pid_t tid = vm_is_stack(task, vma, is_pid);
if (tid != 0) {
/*
* Thread stack in /proc/PID/task/TID/maps or