stackdepot: fix stack_depot_save_flags() in NMI context

Per documentation, stack_depot_save_flags() was meant to be usable from
NMI context if STACK_DEPOT_FLAG_CAN_ALLOC is unset.  However, it still
would try to take the pool_lock in an attempt to save a stack trace in the
current pool (if space is available).

This could result in deadlock if an NMI is handled while pool_lock is
already held.  To avoid deadlock, only try to take the lock in NMI context
and give up if unsuccessful.

The documentation is fixed to clearly convey this.

Link: https://lkml.kernel.org/r/Z0CcyfbPqmxJ9uJH@elver.google.com
Link: https://lkml.kernel.org/r/20241122154051.3914732-1-elver@google.com
Fixes: 4434a56ec209 ("stackdepot: make fast paths lock-less again")
Signed-off-by: Marco Elver <elver@google.com>
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index e9ec32fb97d4a729e06aaabc7cd5627bb384d72f..2cc21ffcdaf9e435445c47b4638f3107657c45d1 100644 (file)
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -147,7 +147,7 @@ static inline int stack_depot_early_init(void)      { return 0; }
  * If the provided stack trace comes from the interrupt context, only the part
  * up to the interrupt entry is saved.
  *
- * Context: Any context, but setting STACK_DEPOT_FLAG_CAN_ALLOC is required if
+ * Context: Any context, but unsetting STACK_DEPOT_FLAG_CAN_ALLOC is required if
  *          alloc_pages() cannot be used from the current context. Currently
  *          this is the case for contexts where neither %GFP_ATOMIC nor
  *          %GFP_NOWAIT can be used (NMI, raw_spin_lock).
@@ -156,7 +156,7 @@ static inline int stack_depot_early_init(void)      { return 0; }
  */
 depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
                                            unsigned int nr_entries,
-                                           gfp_t gfp_flags,
+                                           gfp_t alloc_flags,
                                            depot_flags_t depot_flags);
 
 /**
@@ -175,7 +175,7 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
  * Return: Handle of the stack trace stored in depot, 0 on failure
  */
 depot_stack_handle_t stack_depot_save(unsigned long *entries,
-                                     unsigned int nr_entries, gfp_t gfp_flags);
+                                     unsigned int nr_entries, gfp_t alloc_flags);
 
 /**
  * __stack_depot_get_stack_record - Get a pointer to a stack_record struct

diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 5ed34cc963fc382c09f8cae7ed124a67594259dd..245d5b4166999521ae391e5b43b6ea48951efb57 100644 (file)
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -630,7 +630,15 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
                        prealloc = page_address(page);
        }
 
-       raw_spin_lock_irqsave(&pool_lock, flags);
+       if (in_nmi()) {
+               /* We can never allocate in NMI context. */
+               WARN_ON_ONCE(can_alloc);
+               /* Best effort; bail if we fail to take the lock. */
+               if (!raw_spin_trylock_irqsave(&pool_lock, flags))
+                       goto exit;
+       } else {
+               raw_spin_lock_irqsave(&pool_lock, flags);
+       }
        printk_deferred_enter();
 
        /* Try to find again, to avoid concurrently inserting duplicates. */