lib/ref_tracker.c | 6 ++++++ 1 file changed, 6 insertions(+)
stack_depot_save() cannot accept __GFP_NOFAIL flag because
__stack_depot_save() drops gfp flags which are not in
GFP_KERNEL | GFP_ATOMIC | __GFP_NOWARN. Also, changing
__stack_depot_save() to accept __GFP_NOFAIL is not possible
because rmqueue() does not want __GFP_NOFAIL flag for
order == DEPOT_POOL_ORDER allocation request.
Therefore, assume that stack_depot_save(GFP_KERNEL | __GFP_NOFAIL) from
ref_tracker_alloc() can silently fail, and emit "unreliable refcount
tracker." message.
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
---
lib/ref_tracker.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c
index dc7b14aa3431..ad48ff19adb2 100644
--- a/lib/ref_tracker.c
+++ b/lib/ref_tracker.c
@@ -84,12 +84,18 @@ int ref_tracker_alloc(struct ref_tracker_dir *dir,
gfp_mask |= __GFP_NOFAIL;
*trackerp = tracker = kzalloc(sizeof(*tracker), gfp_mask);
if (unlikely(!tracker)) {
+nomem:
pr_err_once("memory allocation failure, unreliable refcount tracker.\n");
refcount_inc(&dir->untracked);
return -ENOMEM;
}
nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
tracker->alloc_stack_handle = stack_depot_save(entries, nr_entries, gfp);
+ if (!tracker->alloc_stack_handle) {
+ *trackerp = NULL;
+ kfree(tracker);
+ goto nomem;
+ }
spin_lock_irqsave(&dir->lock, flags);
list_add(&tracker->head, &dir->list);
--
2.18.4On Sat, 27 May 2023 20:04:11 +0900 Tetsuo Handa wrote: > stack_depot_save() cannot accept __GFP_NOFAIL flag because > __stack_depot_save() drops gfp flags which are not in > GFP_KERNEL | GFP_ATOMIC | __GFP_NOWARN. Also, changing > __stack_depot_save() to accept __GFP_NOFAIL is not possible > because rmqueue() does not want __GFP_NOFAIL flag for > order == DEPOT_POOL_ORDER allocation request. > > Therefore, assume that stack_depot_save(GFP_KERNEL | __GFP_NOFAIL) from > ref_tracker_alloc() can silently fail, and emit "unreliable refcount > tracker." message. It's probably a good idea to CC netdev@vger. I'm not sure if anyone will pick this up from LKML. For the patch itself - I'm not sure it's needed, even if we don't record the stack we'll have a tracker object and still detect the leak. So printing the "unreliable refcount" message is not very precise. At least to me; Eric's opinion matters most.
On Tue, May 30, 2023 at 4:05 AM Jakub Kicinski <kuba@kernel.org> wrote:
>
> On Sat, 27 May 2023 20:04:11 +0900 Tetsuo Handa wrote:
> > stack_depot_save() cannot accept __GFP_NOFAIL flag because
> > __stack_depot_save() drops gfp flags which are not in
> > GFP_KERNEL | GFP_ATOMIC | __GFP_NOWARN. Also, changing
> > __stack_depot_save() to accept __GFP_NOFAIL is not possible
> > because rmqueue() does not want __GFP_NOFAIL flag for
> > order == DEPOT_POOL_ORDER allocation request.
> >
> > Therefore, assume that stack_depot_save(GFP_KERNEL | __GFP_NOFAIL) from
> > ref_tracker_alloc() can silently fail, and emit "unreliable refcount
> > tracker." message.
>
> It's probably a good idea to CC netdev@vger. I'm not sure if anyone
> will pick this up from LKML.
>
> For the patch itself - I'm not sure it's needed, even if we don't
> record the stack we'll have a tracker object and still detect the leak.
> So printing the "unreliable refcount" message is not very precise.
> At least to me; Eric's opinion matters most.
Thanks Jakub (I was on a 3-days week end, computer turned off)
This patch looks wrong to me, or at very least not complete ?
If we really want this, why not remove all the code dealing with
tracker->alloc_stack_handle
being potentially NULL ?
Note: I never assumed stack_depot_save() would enforce/use NOFAIL.
diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c
index dc7b14aa3431e2bf7a97a7e78220f04da144563d..530c51ab31f227a64e1210d108e9780f0bad72f7
100644
--- a/lib/ref_tracker.c
+++ b/lib/ref_tracker.c
@@ -29,8 +29,7 @@ void ref_tracker_dir_exit(struct ref_tracker_dir *dir)
}
list_for_each_entry_safe(tracker, n, &dir->list, head) {
pr_err("leaked reference.\n");
- if (tracker->alloc_stack_handle)
- stack_depot_print(tracker->alloc_stack_handle);
+ stack_depot_print(tracker->alloc_stack_handle);
leak = true;
list_del(&tracker->head);
kfree(tracker);
@@ -53,8 +52,7 @@ void ref_tracker_dir_print(struct ref_tracker_dir *dir,
list_for_each_entry(tracker, &dir->list, head) {
if (i < display_limit) {
pr_err("leaked reference.\n");
- if (tracker->alloc_stack_handle)
- stack_depot_print(tracker->alloc_stack_handle);
+ stack_depot_print(tracker->alloc_stack_handle);
i++;
} else {
break;
@@ -124,10 +122,8 @@ int ref_tracker_free(struct ref_tracker_dir *dir,
spin_lock_irqsave(&dir->lock, flags);
if (tracker->dead) {
pr_err("reference already released.\n");
- if (tracker->alloc_stack_handle) {
- pr_err("allocated in:\n");
- stack_depot_print(tracker->alloc_stack_handle);
- }
+ pr_err("allocated in:\n");
+ stack_depot_print(tracker->alloc_stack_handle);
if (tracker->free_stack_handle) {
pr_err("freed in:\n");
stack_depot_print(tracker->free_stack_handle);
On 2023/05/30 16:22, Eric Dumazet wrote: >>> Therefore, assume that stack_depot_save(GFP_KERNEL | __GFP_NOFAIL) from >>> ref_tracker_alloc() can silently fail, and emit "unreliable refcount >>> tracker." message. > > Note: I never assumed stack_depot_save() would enforce/use NOFAIL. Hmm, I misread this function. if (gfp & __GFP_DIRECT_RECLAIM) gfp_mask |= __GFP_NOFAIL; // Or'ing to "gfp_mask" than "gfp". *trackerp = tracker = kzalloc(sizeof(*tracker), gfp_mask); // <= This is "gfp_mask". tracker->alloc_stack_handle = stack_depot_save(entries, nr_entries, gfp); // <= This is "gfp". So, stack_depot_save(GFP_KERNEL | __GFP_NOFAIL) is not happening. Then, question becomes whether we want tracker->alloc_stack_handle != NULL or not. If tracker->alloc_stack_handle == NULL is still useful, this patch will be useless...
On Tue, May 30, 2023 at 11:52 AM Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> wrote: > > On 2023/05/30 16:22, Eric Dumazet wrote: > >>> Therefore, assume that stack_depot_save(GFP_KERNEL | __GFP_NOFAIL) from > >>> ref_tracker_alloc() can silently fail, and emit "unreliable refcount > >>> tracker." message. > > > > Note: I never assumed stack_depot_save() would enforce/use NOFAIL. > > Hmm, I misread this function. > > if (gfp & __GFP_DIRECT_RECLAIM) > gfp_mask |= __GFP_NOFAIL; // Or'ing to "gfp_mask" than "gfp". > *trackerp = tracker = kzalloc(sizeof(*tracker), gfp_mask); // <= This is "gfp_mask". > tracker->alloc_stack_handle = stack_depot_save(entries, nr_entries, gfp); // <= This is "gfp". > > So, stack_depot_save(GFP_KERNEL | __GFP_NOFAIL) is not happening. Yes.1 > > Then, question becomes whether we want tracker->alloc_stack_handle != NULL or not. > If tracker->alloc_stack_handle == NULL is still useful, this patch will be useless... > I think it is useful to have the tracker (as Jakub hinted). It is better than nothing. We even might be able to allocate memory later for the free_stack_handle which could give us developers enough clues for bug hunting. Thanks.
© 2016 - 2026 Red Hat, Inc.