FAILED: patch "[PATCH] mm: slub: avoid wake up kswapd in set_track_prepare" failed to apply to 6.6-stable tree

PATCH New [email protected] 2 participants 3 messages Sep 6, 2025 – Sep 7, 2025

Subsystems (3)

Stable branch Memory management Slab allocator

lore

Share & tools

lore

[email protected]

author maintainer

2025-09-06 18:41 UTC #0 lore raw

The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x 850470a8413a8a78e772c4f6bd9fe81ec6bd5b0f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2025090634-predator-composite-c799@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..

Possible dependencies:

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 850470a8413a8a78e772c4f6bd9fe81ec6bd5b0f Mon Sep 17 00:00:00 2001
From: yangshiguang <[email protected]>
Date: Sat, 30 Aug 2025 10:09:46 +0800
Subject: [PATCH] mm: slub: avoid wake up kswapd in set_track_prepare

set_track_prepare() can incur lock recursion.
The issue is that it is called from hrtimer_start_range_ns holding the per_cpu(hrtimer_bases)[n].lock, but when enabled CONFIG_DEBUG_OBJECTS_TIMERS, may wake up kswapd in set_track_prepare, and try to hold the per_cpu(hrtimer_bases)[n].lock.

Avoid deadlock caused by implicitly waking up kswapd by passing in allocation flags, which do not contain __GFP_KSWAPD_RECLAIM in the debug_objects_fill_pool() case. Inside stack depot they are processed by gfp_nested_mask().
Since ___slab_alloc() has preemption disabled, we mask out __GFP_DIRECT_RECLAIM from the flags there.

The oops looks something like:

BUG: spinlock recursion on CPU#3, swapper/3/0
 lock: 0xffffff8a4bf29c80, .magic: dead4ead, .owner: swapper/3/0, .owner_cpu: 3
Hardware name: Qualcomm Technologies, Inc. Popsicle based on SM8850 (DT)
Call trace:
spin_bug+0x0
_raw_spin_lock_irqsave+0x80
hrtimer_try_to_cancel+0x94
task_contending+0x10c
enqueue_dl_entity+0x2a4
dl_server_start+0x74
enqueue_task_fair+0x568
enqueue_task+0xac
do_activate_task+0x14c
ttwu_do_activate+0xcc
try_to_wake_up+0x6c8
default_wake_function+0x20
autoremove_wake_function+0x1c
__wake_up+0xac
wakeup_kswapd+0x19c
wake_all_kswapds+0x78
__alloc_pages_slowpath+0x1ac
__alloc_pages_noprof+0x298
stack_depot_save_flags+0x6b0
stack_depot_save+0x14
set_track_prepare+0x5c
___slab_alloc+0xccc
__kmalloc_cache_noprof+0x470
__set_page_owner+0x2bc
post_alloc_hook[jt]+0x1b8
prep_new_page+0x28
get_page_from_freelist+0x1edc
__alloc_pages_noprof+0x13c
alloc_slab_page+0x244
allocate_slab+0x7c
___slab_alloc+0x8e8
kmem_cache_alloc_noprof+0x450
debug_objects_fill_pool+0x22c
debug_object_activate+0x40
enqueue_hrtimer[jt]+0xdc
hrtimer_start_range_ns+0x5f8

...

Signed-off-by yangshiguang <[email protected]>

Fixes 5cf909c553e9 ("mm/slub: use stackdepot to save stack trace in objects")

Cc [email protected]

Signed-off-by Vlastimil Babka <[email protected]>

mm/slub.c +20 ~~-10~~

index 1787e4d51e48..d257141896c9 100644
@@ -962,19 +962,19 @@ static struct track *get_track(struct kmem_cache *s, void *object,
 }
 
 #ifdef CONFIG_STACKDEPOT
-static noinline depot_stack_handle_t set_track_prepare(void)
+static noinline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags)
 {
 	depot_stack_handle_t handle;
 	unsigned long entries[TRACK_ADDRS_COUNT];
 	unsigned int nr_entries;
 
 	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3);
-	handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT);
+	handle = stack_depot_save(entries, nr_entries, gfp_flags);
 
 	return handle;
 }
 #else
-static inline depot_stack_handle_t set_track_prepare(void)
+static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags)
 {
 	return 0;
 }

@@ -996,9 +996,9 @@ static void set_track_update(struct kmem_cache *s, void *object,
 }
 
 static __always_inline void set_track(struct kmem_cache *s, void *object,
-				      enum track_item alloc, unsigned long addr)
+				      enum track_item alloc, unsigned long addr, gfp_t gfp_flags)
 {
-	depot_stack_handle_t handle = set_track_prepare();
+	depot_stack_handle_t handle = set_track_prepare(gfp_flags);
 
 	set_track_update(s, object, alloc, addr, handle);
 }

@@ -1926,9 +1926,9 @@ static inline bool free_debug_processing(struct kmem_cache *s,
 static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {}
 static inline int check_object(struct kmem_cache *s, struct slab *slab,
 			void *object, u8 val) { return 1; }
-static inline depot_stack_handle_t set_track_prepare(void) { return 0; }
+static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; }
 static inline void set_track(struct kmem_cache *s, void *object,
-			     enum track_item alloc, unsigned long addr) {}
+			     enum track_item alloc, unsigned long addr, gfp_t gfp_flags) {}
 static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
 					struct slab *slab) {}
 static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,

@@ -3881,9 +3881,14 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 			 * For debug caches here we had to go through
 			 * alloc_single_from_partial() so just store the
 			 * tracking info and return the object.
+			 *
+			 * Due to disabled preemption we need to disallow
+			 * blocking. The flags are further adjusted by
+			 * gfp_nested_mask() in stack_depot itself.
 			 */
 			if (s->flags & SLAB_STORE_USER)
-				set_track(s, freelist, TRACK_ALLOC, addr);
+				set_track(s, freelist, TRACK_ALLOC, addr,
+					  gfpflags & ~(__GFP_DIRECT_RECLAIM));
 
 			return freelist;
 		}

@@ -3915,7 +3920,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 			goto new_objects;
 
 		if (s->flags & SLAB_STORE_USER)
-			set_track(s, freelist, TRACK_ALLOC, addr);
+			set_track(s, freelist, TRACK_ALLOC, addr,
+				  gfpflags & ~(__GFP_DIRECT_RECLAIM));
 
 		return freelist;
 	}

@@ -4426,8 +4432,12 @@ static noinline void free_to_partial_list(
 	unsigned long flags;
 	depot_stack_handle_t handle = 0;
 
+	/*
+	 * We cannot use GFP_NOWAIT as there are callsites where waking up
+	 * kswapd could deadlock
+	 */
 	if (s->flags & SLAB_STORE_USER)
-		handle = set_track_prepare();
+		handle = set_track_prepare(__GFP_NOWARN);
 
 	spin_lock_irqsave(&n->list_lock, flags);

Sasha Levin

maintainer

2025-09-07 14:56 UTC #1 lore raw

PATCH 1/2 slub: Reflow ___slab_alloc()

From: Chengming Zhou <[email protected]>

[ Upstream commit 24c6a097b5a270e05c6e99a99da66b91be81fd7d ]

The get_partial() interface used in ___slab_alloc() may return a single object in the "kmem_cache_debug(s)" case, in which we will just return the "freelist" object.

Move this handling up to prepare for later changes.

And the "pfmemalloc_match()" part is not needed for node partial slab, since we already check this in the get_partial_node().

Signed-off-by Chengming Zhou <[email protected]>

Reviewed-by Vlastimil Babka <[email protected]>

Tested-by Hyeonggon Yoo <[email protected]>

Reviewed-by Hyeonggon Yoo <[email protected]>

Signed-off-by Vlastimil Babka <[email protected]>

Stable-dep-of: 850470a8413a ("mm: slub: avoid wake up kswapd in set_track_prepare")

Signed-off-by Sasha Levin <[email protected]>

---
 mm/slub.c | 31 +++++++++++++++----------------
 1 file changed, 15 insertions(+), 16 deletions(-)

mm/slub.c +15 ~~-16~~

index d2544c88a5c43..b7ee815d5d6cd 100644
@@ -3223,8 +3223,21 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	pc.slab = &slab;
 	pc.orig_size = orig_size;
 	freelist = get_partial(s, node, &pc);
-	if (freelist)
-		goto check_new_slab;
+	if (freelist) {
+		if (kmem_cache_debug(s)) {
+			/*
+			 * For debug caches here we had to go through
+			 * alloc_single_from_partial() so just store the
+			 * tracking info and return the object.
+			 */
+			if (s->flags & SLAB_STORE_USER)
+				set_track(s, freelist, TRACK_ALLOC, addr);
+
+			return freelist;
+		}
+
+		goto retry_load_slab;
+	}
 
 	slub_put_cpu_ptr(s->cpu_slab);
 	slab = new_slab(s, gfpflags, node);

@@ -3260,20 +3273,6 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 
 	inc_slabs_node(s, slab_nid(slab), slab->objects);
 
-check_new_slab:
-
-	if (kmem_cache_debug(s)) {
-		/*
-		 * For debug caches here we had to go through
-		 * alloc_single_from_partial() so just store the tracking info
-		 * and return the object
-		 */
-		if (s->flags & SLAB_STORE_USER)
-			set_track(s, freelist, TRACK_ALLOC, addr);
-
-		return freelist;
-	}
-
 	if (unlikely(!pfmemalloc_match(slab, gfpflags))) {
 		/*
 		 * For !pfmemalloc_match() case we don't load freelist so that

Signature · 1 line

2.51.0

Sasha Levin

maintainer

2025-09-07 14:56 UTC #2 lore raw

PATCH 2/2 mm: slub: avoid wake up kswapd in set_track_prepare

From: yangshiguang <[email protected]>

[ Upstream commit 850470a8413a8a78e772c4f6bd9fe81ec6bd5b0f ]

The oops looks something like:

BUG: spinlock recursion on CPU#3, swapper/3/0
 lock: 0xffffff8a4bf29c80, .magic: dead4ead, .owner: swapper/3/0, .owner_cpu: 3
Hardware name: Qualcomm Technologies, Inc. Popsicle based on SM8850 (DT)
Call trace:
spin_bug+0x0
_raw_spin_lock_irqsave+0x80
hrtimer_try_to_cancel+0x94
task_contending+0x10c
enqueue_dl_entity+0x2a4
dl_server_start+0x74
enqueue_task_fair+0x568
enqueue_task+0xac
do_activate_task+0x14c
ttwu_do_activate+0xcc
try_to_wake_up+0x6c8
default_wake_function+0x20
autoremove_wake_function+0x1c
__wake_up+0xac
wakeup_kswapd+0x19c
wake_all_kswapds+0x78
__alloc_pages_slowpath+0x1ac
__alloc_pages_noprof+0x298
stack_depot_save_flags+0x6b0
stack_depot_save+0x14
set_track_prepare+0x5c
___slab_alloc+0xccc
__kmalloc_cache_noprof+0x470
__set_page_owner+0x2bc
post_alloc_hook[jt]+0x1b8
prep_new_page+0x28
get_page_from_freelist+0x1edc
__alloc_pages_noprof+0x13c
alloc_slab_page+0x244
allocate_slab+0x7c
___slab_alloc+0x8e8
kmem_cache_alloc_noprof+0x450
debug_objects_fill_pool+0x22c
debug_object_activate+0x40
enqueue_hrtimer[jt]+0xdc
hrtimer_start_range_ns+0x5f8

...

Signed-off-by yangshiguang <[email protected]>

Fixes 5cf909c553e9 ("mm/slub: use stackdepot to save stack trace in objects")

Cc [email protected]

Signed-off-by Vlastimil Babka <[email protected]>

Signed-off-by Sasha Levin <[email protected]>

---
 mm/slub.c | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

mm/slub.c +20 ~~-10~~

index b7ee815d5d6cd..305b0eca6146c 100644
@@ -771,19 +771,19 @@ static struct track *get_track(struct kmem_cache *s, void *object,
 }
 
 #ifdef CONFIG_STACKDEPOT
-static noinline depot_stack_handle_t set_track_prepare(void)
+static noinline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags)
 {
 	depot_stack_handle_t handle;
 	unsigned long entries[TRACK_ADDRS_COUNT];
 	unsigned int nr_entries;
 
 	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3);
-	handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT);
+	handle = stack_depot_save(entries, nr_entries, gfp_flags);
 
 	return handle;
 }
 #else
-static inline depot_stack_handle_t set_track_prepare(void)
+static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags)
 {
 	return 0;
 }

@@ -805,9 +805,9 @@ static void set_track_update(struct kmem_cache *s, void *object,
 }
 
 static __always_inline void set_track(struct kmem_cache *s, void *object,
-				      enum track_item alloc, unsigned long addr)
+				      enum track_item alloc, unsigned long addr, gfp_t gfp_flags)
 {
-	depot_stack_handle_t handle = set_track_prepare();
+	depot_stack_handle_t handle = set_track_prepare(gfp_flags);
 
 	set_track_update(s, object, alloc, addr, handle);
 }

@@ -1733,9 +1733,9 @@ static inline bool free_debug_processing(struct kmem_cache *s,
 static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {}
 static inline int check_object(struct kmem_cache *s, struct slab *slab,
 			void *object, u8 val) { return 1; }
-static inline depot_stack_handle_t set_track_prepare(void) { return 0; }
+static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; }
 static inline void set_track(struct kmem_cache *s, void *object,
-			     enum track_item alloc, unsigned long addr) {}
+			     enum track_item alloc, unsigned long addr, gfp_t gfp_flags) {}
 static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
 					struct slab *slab) {}
 static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,

@@ -3229,9 +3229,14 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 			 * For debug caches here we had to go through
 			 * alloc_single_from_partial() so just store the
 			 * tracking info and return the object.
+			 *
+			 * Due to disabled preemption we need to disallow
+			 * blocking. The flags are further adjusted by
+			 * gfp_nested_mask() in stack_depot itself.
 			 */
 			if (s->flags & SLAB_STORE_USER)
-				set_track(s, freelist, TRACK_ALLOC, addr);
+				set_track(s, freelist, TRACK_ALLOC, addr,
+					  gfpflags & ~(__GFP_DIRECT_RECLAIM));
 
 			return freelist;
 		}

@@ -3257,7 +3262,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 			goto new_objects;
 
 		if (s->flags & SLAB_STORE_USER)
-			set_track(s, freelist, TRACK_ALLOC, addr);
+			set_track(s, freelist, TRACK_ALLOC, addr,
+				  gfpflags & ~(__GFP_DIRECT_RECLAIM));
 
 		return freelist;
 	}

@@ -3545,8 +3551,12 @@ static noinline void free_to_partial_list(
 	unsigned long flags;
 	depot_stack_handle_t handle = 0;
 
+	/*
+	 * We cannot use GFP_NOWAIT as there are callsites where waking up
+	 * kswapd could deadlock
+	 */
 	if (s->flags & SLAB_STORE_USER)
-		handle = set_track_prepare();
+		handle = set_track_prepare(__GFP_NOWARN);
 
 	spin_lock_irqsave(&n->list_lock, flags);

Signature · 1 line

2.51.0