Skip to contentSkip to conversation

Boot fails with 59faa4da7cd4 and 3accabda4da1

DISCUSSION Phil Auld 3 participants 7 messages Oct 10, 2025 – Oct 13, 2025

Subsystems (2)
lore
Share & tools
lore

Phil Auld

author
#0 lore raw

Hi,

After several days of failed boots I've gotten it down to these two commits.

59faa4da7cd4 maple_tree: use percpu sheaves for maple_node_cache 3accabda4da1 mm, vma: use percpu sheaves for vm_area_struct cache

The first is such an early failure it's silent. With just 3acca I get :

[    9.341152] BUG: kernel NULL pointer dereference, address: 0000000000000040
[    9.348115] #PF: supervisor read access in kernel mode
[    9.353264] #PF: error_code(0x0000) - not-present page
[    9.358413] PGD 0 P4D 0
[    9.360959] Oops: Oops: 0000 [#1] SMP NOPTI
[    9.365154] CPU: 21 UID: 0 PID: 818 Comm: kworker/u398:0 Not tainted 6.17.0-rc3.slab+ #5 PREEMPT(voluntary)
[    9.374982] Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS 1.26.0 07/30/2025
[    9.382641] RIP: 0010:__pcs_replace_empty_main+0x44/0x1d0
[    9.388048] Code: ec 08 48 8b 46 10 48 8b 76 08 48 85 c0 74 0b 8b 48 18 85 c9 0f 85 e5 00 00 00 65 48 63 05 e4 ee 50 02 49 8b 84 c6 e0 00 00 00 <4c> 8b 68 40 4c 89 ef e8 b0 81 ff ff 48 89 c5 48 85 c0 74 1d 48 89
[    9.406794] RSP: 0018:ffffd2d10950bdb0 EFLAGS: 00010246
[    9.412022] RAX: 0000000000000000 RBX: ffff8a775dab74b0 RCX: 00000000ffffffff
[    9.419156] RDX: 0000000000000cc0 RSI: ffff8a6800804000 RDI: ffff8a680004e300
[    9.426297] RBP: ffffd2d10950be40 R08: 0000000000000060 R09: ffffffffb9367388
[    9.433427] R10: 00000000000149e8 R11: ffff8a6f87a38000 R12: 0000000000000cc0
[    9.440562] R13: 0000000000000cc0 R14: ffff8a680004e300 R15: 00000000000000c0
[    9.447696] FS:  0000000000000000(0000) GS:ffff8a77a3541000(0000) knlGS:0000000000000000
[    9.455788] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    9.461535] CR2: 0000000000000040 CR3: 0000000e1aa24000 CR4: 00000000003506f0
[    9.468665] Call Trace:
[    9.471123]  <TASK>
[    9.473233]  ? srso_return_thunk+0x5/0x5f
[    9.477258]  ? vm_area_alloc+0x1e/0x60
[    9.481020]  kmem_cache_alloc_noprof+0x4ec/0x5b0
[    9.485647]  vm_area_alloc+0x1e/0x60
[    9.489235]  create_init_stack_vma+0x26/0x210
[    9.493605]  alloc_bprm+0x139/0x200
[    9.497104]  kernel_execve+0x4a/0x140
[    9.500779]  call_usermodehelper_exec_async+0xd0/0x190
[    9.505923]  ? __pfx_call_usermodehelper_exec_async+0x10/0x10
[    9.511670]  ret_from_fork+0xf0/0x110
[    9.515346]  ? __pfx_call_usermodehelper_exec_async+0x10/0x10
[    9.521095]  ret_from_fork_asm+0x1a/0x30
[    9.525035]  </TASK>
[    9.527225] Modules linked in:
[    9.530290] CR2: 0000000000000040
[    9.533617] ---[ end trace 0000000000000000 ]---
[    9.538245] RIP: 0010:__pcs_replace_empty_main+0x44/0x1d0
[    9.543653] Code: ec 08 48 8b 46 10 48 8b 76 08 48 85 c0 74 0b 8b 48 18 85 c9 0f 85 e5 00 00 00 65 48 63 05 e4 ee 50 02 49 8b 84 c6 e0 00 00 00 <4c> 8b 68 40 4c 89 ef e8 b0 81 ff ff 48 89 c5 48 85 c0 74 1d 48 89
[    9.562405] RSP: 0018:ffffd2d10950bdb0 EFLAGS: 00010246
[    9.567634] RAX: 0000000000000000 RBX: ffff8a775dab74b0 RCX: 00000000ffffffff
[    9.574774] RDX: 0000000000000cc0 RSI: ffff8a6800804000 RDI: ffff8a680004e300
[    9.581908] RBP: ffffd2d10950be40 R08: 0000000000000060 R09: ffffffffb9367388
[    9.589048] R10: 00000000000149e8 R11: ffff8a6f87a38000 R12: 0000000000000cc0
[    9.596178] R13: 0000000000000cc0 R14: ffff8a680004e300 R15: 00000000000000c0
[    9.603313] FS:  0000000000000000(0000) GS:ffff8a77a3541000(0000) knlGS:0000000000000000
[    9.611399] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    9.617145] CR2: 0000000000000040 CR3: 0000000e1aa24000 CR4: 00000000003506f0
[    9.624278] Kernel panic - not syncing: Fatal exception
[    9.631463] Kernel Offset: 0x36a00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[    9.642244] ---[ end Kernel panic - not syncing: Fatal exception ]---

Reverting both produces a working kernel.

I have not looked into what the percpu sheaves thing is actually doing but this is an AMD EPYC 7401 with 8 NUMA nodes configured such that memory is only on 2 of them.

# numactl --hardware
available: 8 nodes (0-7)
node 0 cpus: 0 8 16 24 32 40 48 56 64 72 80 88
node 0 size: 0 MB
node 0 free: 0 MB
node 1 cpus: 2 10 18 26 34 42 50 58 66 74 82 90
node 1 size: 31584 MB
node 1 free: 30397 MB
node 2 cpus: 4 12 20 28 36 44 52 60 68 76 84 92
node 2 size: 0 MB
node 2 free: 0 MB
node 3 cpus: 6 14 22 30 38 46 54 62 70 78 86 94
node 3 size: 0 MB
node 3 free: 0 MB
node 4 cpus: 1 9 17 25 33 41 49 57 65 73 81 89
node 4 size: 0 MB
node 4 free: 0 MB
node 5 cpus: 3 11 19 27 35 43 51 59 67 75 83 91
node 5 size: 32214 MB
node 5 free: 31625 MB
node 6 cpus: 5 13 21 29 37 45 53 61 69 77 85 93
node 6 size: 0 MB
node 6 free: 0 MB
node 7 cpus: 7 15 23 31 39 47 55 63 71 79 87 95
node 7 size: 0 MB
node 7 free: 0 MB
node distances:
node     0    1    2    3    4    5    6    7 
   0:   10   16   16   16   28   28   22   28 
   1:   16   10   16   16   28   28   28   22 
   2:   16   16   10   16   22   28   28   28 
   3:   16   16   16   10   28   22   28   28 
   4:   28   28   22   28   10   16   16   16 
   5:   28   28   28   22   16   10   16   16 
   6:   22   28   28   28   16   16   10   16 
   7:   28   22   28   28   16   16   16   10 

Let me know if I can provide any more information.

Thanks,
Phil

#1 lore raw
Quoted 10 lines · Phil Auld

After several days of failed boots I've gotten it down to these two commits.

59faa4da7cd4 maple_tree: use percpu sheaves for maple_node_cache 3accabda4da1 mm, vma: use percpu sheaves for vm_area_struct cache

The first is such an early failure it's silent. With just 3acca I get :

Quoted 9 lines
[    9.341152] BUG: kernel NULL pointer dereference, address: 0000000000000040
[    9.348115] #PF: supervisor read access in kernel mode
[    9.353264] #PF: error_code(0x0000) - not-present page
[    9.358413] PGD 0 P4D 0
[    9.360959] Oops: Oops: 0000 [#1] SMP NOPTI
[    9.365154] CPU: 21 UID: 0 PID: 818 Comm: kworker/u398:0 Not tainted 6.17.0-rc3.slab+ #5 PREEMPT(voluntary)
[    9.374982] Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS 1.26.0 07/30/2025
[    9.382641] RIP: 0010:__pcs_replace_empty_main+0x44/0x1d0
[    9.388048] Code: ec 08 48 8b 46 10 48 8b 76 08 48 85 c0 74 0b 8b 48 18 85 c9 0f 85 e5 00 00 00 65 48 63 05 e4 ee 50 02 49 8b 84 c6 e0 00 00 00 <4c> 8b 68 40 4c 89 ef e8 b0 81 ff ff 48 89 c5 48 85 c0 74 1d 48 89

That decodes to

   0:           mov    0x10(%rsi),%rax
   4:           mov    0x8(%rsi),%rsi
   8:           test   %rax,%rax
   b:           je     0x18
   d:           mov    0x18(%rax),%ecx
  10:           test   %ecx,%ecx
  12:           jne    0xfd
  18:           movslq %gs:0x250eee4(%rip),%rax
  20:           mov    0xe0(%r14,%rax,8),%rax
  28:*          mov    0x40(%rax),%r13          <-- trapping instruction
  2c:           mov    %r13,%rdi
  2f:           call   0xffffffffffff81e4
  34:           mov    %rax,%rbp
  37:           test   %rax,%rax
  3a:           je     0x59

which is the code around that barn_replace_empty_sheaf() call.

In particular, the trapping instruction is from get_barn(), it's the "->barn" in

        return get_node(s, numa_mem_id())->barn;

so it looks like 'get_node()' is returning NULL here:

        return s->node[node];

That 0x250eee4(%rip) is from "get_node()" becoming

18: movslq %gs:numa_node(%rip), %rax # node
20: mov 0xe0(%r14,%rax,8),%rax # ->node[node]

instruction, and then that ->barn dereference is the trapping instruction that tries to read node->barn:

28:* mov 0x40(%rax),%r13 # node->barn

but I did *not* look into why s->node[node] would be NULL.

Over to you Vlastimil,

Linus

#2 lore raw
Quoted 54 lines · Linus Torvalds
Quoted 10 lines · Phil Auld

After several days of failed boots I've gotten it down to these two commits.

59faa4da7cd4 maple_tree: use percpu sheaves for maple_node_cache 3accabda4da1 mm, vma: use percpu sheaves for vm_area_struct cache

The first is such an early failure it's silent. With just 3acca I get :

Quoted 9 lines
[    9.341152] BUG: kernel NULL pointer dereference, address: 0000000000000040
[    9.348115] #PF: supervisor read access in kernel mode
[    9.353264] #PF: error_code(0x0000) - not-present page
[    9.358413] PGD 0 P4D 0
[    9.360959] Oops: Oops: 0000 [#1] SMP NOPTI
[    9.365154] CPU: 21 UID: 0 PID: 818 Comm: kworker/u398:0 Not tainted 6.17.0-rc3.slab+ #5 PREEMPT(voluntary)
[    9.374982] Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS 1.26.0 07/30/2025
[    9.382641] RIP: 0010:__pcs_replace_empty_main+0x44/0x1d0
[    9.388048] Code: ec 08 48 8b 46 10 48 8b 76 08 48 85 c0 74 0b 8b 48 18 85 c9 0f 85 e5 00 00 00 65 48 63 05 e4 ee 50 02 49 8b 84 c6 e0 00 00 00 <4c> 8b 68 40 4c 89 ef e8 b0 81 ff ff 48 89 c5 48 85 c0 74 1d 48 89

That decodes to

   0:           mov    0x10(%rsi),%rax
   4:           mov    0x8(%rsi),%rsi
   8:           test   %rax,%rax
   b:           je     0x18
   d:           mov    0x18(%rax),%ecx
  10:           test   %ecx,%ecx
  12:           jne    0xfd
  18:           movslq %gs:0x250eee4(%rip),%rax
  20:           mov    0xe0(%r14,%rax,8),%rax
  28:*          mov    0x40(%rax),%r13          <-- trapping instruction
  2c:           mov    %r13,%rdi
  2f:           call   0xffffffffffff81e4
  34:           mov    %rax,%rbp
  37:           test   %rax,%rax
  3a:           je     0x59

which is the code around that barn_replace_empty_sheaf() call.

In particular, the trapping instruction is from get_barn(), it's the "->barn" in

        return get_node(s, numa_mem_id())->barn;

so it looks like 'get_node()' is returning NULL here:

        return s->node[node];

That 0x250eee4(%rip) is from "get_node()" becoming

18: movslq %gs:numa_node(%rip), %rax # node
20: mov 0xe0(%r14,%rax,8),%rax # ->node[node]

Quoted 8 lines

instruction, and then that ->barn dereference is the trapping instruction that tries to read node->barn:

28:* mov 0x40(%rax),%r13 # node->barn

but I did *not* look into why s->node[node] would be NULL.

Over to you Vlastimil,

Thanks, yeah will look ASAP. I suspect the "nodes with zero memory" is something that might not be handled well in general on x86. I know powerpc used to do these kind of setups first and they have some special handling, so numa_mem_id() would give you the closest node with memory in there and I suspect it's not happening here. CPU 21 is node 6 so it's one of those without memory. I'll see if I can simulate this with QEMU and what's the most sensible fix

Quoted 1 line

Linus

author
#3 lore raw
Quoted 64 lines · On Fri, Oct 10, 2025 at 08:27:30PM +0200 Vlastimil Babka wrote:
Quoted 54 lines · Linus Torvalds
Quoted 10 lines · Phil Auld

After several days of failed boots I've gotten it down to these two commits.

59faa4da7cd4 maple_tree: use percpu sheaves for maple_node_cache 3accabda4da1 mm, vma: use percpu sheaves for vm_area_struct cache

The first is such an early failure it's silent. With just 3acca I get :

Quoted 9 lines
[    9.341152] BUG: kernel NULL pointer dereference, address: 0000000000000040
[    9.348115] #PF: supervisor read access in kernel mode
[    9.353264] #PF: error_code(0x0000) - not-present page
[    9.358413] PGD 0 P4D 0
[    9.360959] Oops: Oops: 0000 [#1] SMP NOPTI
[    9.365154] CPU: 21 UID: 0 PID: 818 Comm: kworker/u398:0 Not tainted 6.17.0-rc3.slab+ #5 PREEMPT(voluntary)
[    9.374982] Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS 1.26.0 07/30/2025
[    9.382641] RIP: 0010:__pcs_replace_empty_main+0x44/0x1d0
[    9.388048] Code: ec 08 48 8b 46 10 48 8b 76 08 48 85 c0 74 0b 8b 48 18 85 c9 0f 85 e5 00 00 00 65 48 63 05 e4 ee 50 02 49 8b 84 c6 e0 00 00 00 <4c> 8b 68 40 4c 89 ef e8 b0 81 ff ff 48 89 c5 48 85 c0 74 1d 48 89

That decodes to

   0:           mov    0x10(%rsi),%rax
   4:           mov    0x8(%rsi),%rsi
   8:           test   %rax,%rax
   b:           je     0x18
   d:           mov    0x18(%rax),%ecx
  10:           test   %ecx,%ecx
  12:           jne    0xfd
  18:           movslq %gs:0x250eee4(%rip),%rax
  20:           mov    0xe0(%r14,%rax,8),%rax
  28:*          mov    0x40(%rax),%r13          <-- trapping instruction
  2c:           mov    %r13,%rdi
  2f:           call   0xffffffffffff81e4
  34:           mov    %rax,%rbp
  37:           test   %rax,%rax
  3a:           je     0x59

which is the code around that barn_replace_empty_sheaf() call.

In particular, the trapping instruction is from get_barn(), it's the "->barn" in

        return get_node(s, numa_mem_id())->barn;

so it looks like 'get_node()' is returning NULL here:

        return s->node[node];

That 0x250eee4(%rip) is from "get_node()" becoming

18: movslq %gs:numa_node(%rip), %rax # node
20: mov 0xe0(%r14,%rax,8),%rax # ->node[node]

Quoted 8 lines

instruction, and then that ->barn dereference is the trapping instruction that tries to read node->barn:

28:* mov 0x40(%rax),%r13 # node->barn

but I did *not* look into why s->node[node] would be NULL.

Over to you Vlastimil,

Quoted 8 lines

Thanks, yeah will look ASAP. I suspect the "nodes with zero memory" is something that might not be handled well in general on x86. I know powerpc used to do these kind of setups first and they have some special handling, so numa_mem_id() would give you the closest node with memory in there and I suspect it's not happening here. CPU 21 is node 6 so it's one of those without memory. I'll see if I can simulate this with QEMU and what's the most sensible fix

Thanks for taking a look. I thought the NPS4 thing might be playing a role.

I'm happy to take any test/fix code you have for a spin on this system.

Cheers,
Phil

Quoted 2 lines
Quoted 1 line

Linus

#4 lore raw
Quoted 74 lines · Phil Auld
Quoted 64 lines · On Fri, Oct 10, 2025 at 08:27:30PM +0200 Vlastimil Babka wrote:
Quoted 54 lines · Linus Torvalds
Quoted 10 lines · Phil Auld

After several days of failed boots I've gotten it down to these two commits.

59faa4da7cd4 maple_tree: use percpu sheaves for maple_node_cache 3accabda4da1 mm, vma: use percpu sheaves for vm_area_struct cache

The first is such an early failure it's silent. With just 3acca I get :

Quoted 9 lines
[    9.341152] BUG: kernel NULL pointer dereference, address: 0000000000000040
[    9.348115] #PF: supervisor read access in kernel mode
[    9.353264] #PF: error_code(0x0000) - not-present page
[    9.358413] PGD 0 P4D 0
[    9.360959] Oops: Oops: 0000 [#1] SMP NOPTI
[    9.365154] CPU: 21 UID: 0 PID: 818 Comm: kworker/u398:0 Not tainted 6.17.0-rc3.slab+ #5 PREEMPT(voluntary)
[    9.374982] Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS 1.26.0 07/30/2025
[    9.382641] RIP: 0010:__pcs_replace_empty_main+0x44/0x1d0
[    9.388048] Code: ec 08 48 8b 46 10 48 8b 76 08 48 85 c0 74 0b 8b 48 18 85 c9 0f 85 e5 00 00 00 65 48 63 05 e4 ee 50 02 49 8b 84 c6 e0 00 00 00 <4c> 8b 68 40 4c 89 ef e8 b0 81 ff ff 48 89 c5 48 85 c0 74 1d 48 89

That decodes to

   0:           mov    0x10(%rsi),%rax
   4:           mov    0x8(%rsi),%rsi
   8:           test   %rax,%rax
   b:           je     0x18
   d:           mov    0x18(%rax),%ecx
  10:           test   %ecx,%ecx
  12:           jne    0xfd
  18:           movslq %gs:0x250eee4(%rip),%rax
  20:           mov    0xe0(%r14,%rax,8),%rax
  28:*          mov    0x40(%rax),%r13          <-- trapping instruction
  2c:           mov    %r13,%rdi
  2f:           call   0xffffffffffff81e4
  34:           mov    %rax,%rbp
  37:           test   %rax,%rax
  3a:           je     0x59

which is the code around that barn_replace_empty_sheaf() call.

In particular, the trapping instruction is from get_barn(), it's the "->barn" in

        return get_node(s, numa_mem_id())->barn;

so it looks like 'get_node()' is returning NULL here:

        return s->node[node];

That 0x250eee4(%rip) is from "get_node()" becoming

18: movslq %gs:numa_node(%rip), %rax # node
20: mov 0xe0(%r14,%rax,8),%rax # ->node[node]

Quoted 8 lines

instruction, and then that ->barn dereference is the trapping instruction that tries to read node->barn:

28:* mov 0x40(%rax),%r13 # node->barn

but I did *not* look into why s->node[node] would be NULL.

Over to you Vlastimil,

Quoted 8 lines

Thanks, yeah will look ASAP. I suspect the "nodes with zero memory" is something that might not be handled well in general on x86. I know powerpc used to do these kind of setups first and they have some special handling, so numa_mem_id() would give you the closest node with memory in there and I suspect it's not happening here. CPU 21 is node 6 so it's one of those without memory. I'll see if I can simulate this with QEMU and what's the most sensible fix

Quoted 1 line

Thanks for taking a look. I thought the NPS4 thing might be playing a role.

From what I quickly found I understood that NPS4 is supposed to create extra numa nodes per socket (4 instead of 1) and interleave the memory between them. So it seems weird to me it would assign everything to one node and leave 3 others memoryless?

Quoted 1 line

I'm happy to take any test/fix code you have for a spin on this system.

Thanks. Here's a candidate fix in case you can test. I'll finalize it tomorrow. The slab performance won't be optimal on cpus on those memoryless nodes, that's why I'd like to figure out if it's a BIOS bug or not. If memoryless nodes are really intended we should look into initializing things so that numa_mem_id() works as expected and points to nearest populated node.

----8<----
From 097c6251882bf5537162d17b6726575288ba9715 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <[email protected]>
Date: Sat, 11 Oct 2025 00:13:20 +0200
Subject: [PATCH] slab: fix NULL pointer when trying to access barn

---
 mm/slub.c | 60 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 47 insertions(+), 13 deletions(-)
mm/slub.c +47 -13
index 135c408e0515..bd3c2821e6c3 100644
@@ -507,7 +507,12 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 /* Get the barn of the current cpu's memory node */
 static inline struct node_barn *get_barn(struct kmem_cache *s)
 {
-	return get_node(s, numa_mem_id())->barn;
+	struct kmem_cache_node *n = get_node(s, numa_mem_id());
+
+	if (!n)
+		return NULL;
+
+	return n->barn;
 }
 
 /*
@@ -4982,6 +4987,10 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	}
 
 	barn = get_barn(s);
+	if (!barn) {
+		local_unlock(&s->cpu_sheaves->lock);
+		return NULL;
+	}
 
 	full = barn_replace_empty_sheaf(barn, pcs->main);
 
@@ -5153,13 +5162,20 @@ unsigned int alloc_from_pcs_bulk(struct kmem_cache *s, size_t size, void **p)
 	if (unlikely(pcs->main->size == 0)) {
 
 		struct slab_sheaf *full;
+		struct node_barn *barn;
 
 		if (pcs->spare && pcs->spare->size > 0) {
 			swap(pcs->main, pcs->spare);
 			goto do_alloc;
 		}
 
-		full = barn_replace_empty_sheaf(get_barn(s), pcs->main);
+		barn = get_barn(s);
+		if (!barn) {
+			local_unlock(&s->cpu_sheaves->lock);
+			return allocated;
+		}
+
+		full = barn_replace_empty_sheaf(barn, pcs->main);
 
 		if (full) {
 			stat(s, BARN_GET);
@@ -5314,6 +5330,7 @@ kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size)
 {
 	struct slub_percpu_sheaves *pcs;
 	struct slab_sheaf *sheaf = NULL;
+	struct node_barn *barn;
 
 	if (unlikely(size > s->sheaf_capacity)) {
 
@@ -5355,8 +5372,11 @@ kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size)
 		pcs->spare = NULL;
 		stat(s, SHEAF_PREFILL_FAST);
 	} else {
+		barn = get_barn(s);
+
 		stat(s, SHEAF_PREFILL_SLOW);
-		sheaf = barn_get_full_or_empty_sheaf(get_barn(s));
+		if (barn)
+			sheaf = barn_get_full_or_empty_sheaf(barn);
 		if (sheaf && sheaf->size)
 			stat(s, BARN_GET);
 		else
@@ -5426,7 +5446,7 @@ void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp,
 	 * If the barn has too many full sheaves or we fail to refill the sheaf,
 	 * simply flush and free it.
 	 */
-	if (data_race(barn->nr_full) >= MAX_FULL_SHEAVES ||
+	if (!barn || data_race(barn->nr_full) >= MAX_FULL_SHEAVES ||
 	    refill_sheaf(s, sheaf, gfp)) {
 		sheaf_flush_unused(s, sheaf);
 		free_empty_sheaf(s, sheaf);
@@ -5943,10 +5963,9 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
  * put the full sheaf there.
  */
 static void __pcs_install_empty_sheaf(struct kmem_cache *s,
-		struct slub_percpu_sheaves *pcs, struct slab_sheaf *empty)
+		struct slub_percpu_sheaves *pcs, struct slab_sheaf *empty,
+		struct node_barn *barn)
 {
-	struct node_barn *barn;
-
 	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
 	/* This is what we expect to find if nobody interrupted us. */
@@ -5956,8 +5975,6 @@ static void __pcs_install_empty_sheaf(struct kmem_cache *s,
 		return;
 	}
 
-	barn = get_barn(s);
-
 	/*
 	 * Unlikely because if the main sheaf had space, we would have just
 	 * freed to it. Get rid of our empty sheaf.
@@ -6002,6 +6019,11 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs)
 	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
 	barn = get_barn(s);
+	if (!barn) {
+		local_unlock(&s->cpu_sheaves->lock);
+		return NULL;
+	}
+
 	put_fail = false;
 
 	if (!pcs->spare) {
@@ -6084,7 +6106,7 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs)
 	}
 
 	pcs = this_cpu_ptr(s->cpu_sheaves);
-	__pcs_install_empty_sheaf(s, pcs, empty);
+	__pcs_install_empty_sheaf(s, pcs, empty, barn);
 
 	return pcs;
 }
@@ -6121,8 +6143,9 @@ bool free_to_pcs(struct kmem_cache *s, void *object)
 
 static void rcu_free_sheaf(struct rcu_head *head)
 {
+	struct kmem_cache_node *n;
 	struct slab_sheaf *sheaf;
-	struct node_barn *barn;
+	struct node_barn *barn = NULL;
 	struct kmem_cache *s;
 
 	sheaf = container_of(head, struct slab_sheaf, rcu_head);
@@ -6139,7 +6162,11 @@ static void rcu_free_sheaf(struct rcu_head *head)
 	 */
 	__rcu_free_sheaf_prepare(s, sheaf);
 
-	barn = get_node(s, sheaf->node)->barn;
+	n = get_node(s, sheaf->node);
+	if (!n)
+		goto flush;
+
+	barn = n->barn;
 
 	/* due to slab_free_hook() */
 	if (unlikely(sheaf->size == 0))
@@ -6157,11 +6184,12 @@ static void rcu_free_sheaf(struct rcu_head *head)
 		return;
 	}
 
+flush:
 	stat(s, BARN_PUT_FAIL);
 	sheaf_flush_unused(s, sheaf);
 
 empty:
-	if (data_race(barn->nr_empty) < MAX_EMPTY_SHEAVES) {
+	if (barn && data_race(barn->nr_empty) < MAX_EMPTY_SHEAVES) {
 		barn_put_empty_sheaf(barn, sheaf);
 		return;
 	}
@@ -6191,6 +6219,10 @@ bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj)
 		}
 
 		barn = get_barn(s);
+		if (!barn) {
+			local_unlock(&s->cpu_sheaves->lock);
+			goto fail;
+		}
 
 		empty = barn_get_empty_sheaf(barn);
 
@@ -6304,6 +6336,8 @@ static void free_to_pcs_bulk(struct kmem_cache *s, size_t size, void **p)
 		goto do_free;
 
 	barn = get_barn(s);
+	if (!barn)
+		goto no_empty;
 
 	if (!pcs->spare) {
 		empty = barn_get_empty_sheaf(barn);
Signature · 1 line
2.51.0
author Tested-by
#5 lore raw

Hi Vlastimil,

Quoted 75 lines · On Sat, Oct 11, 2025 at 12:22:39AM +0200 Vlastimil Babka wrote:
Quoted 74 lines · Phil Auld
Quoted 72 lines · On Fri, Oct 10, 2025 at 08:27:30PM +0200 Vlastimil Babka wrote:
Quoted 54 lines · Linus Torvalds
Quoted 10 lines · Phil Auld

After several days of failed boots I've gotten it down to these two commits.

59faa4da7cd4 maple_tree: use percpu sheaves for maple_node_cache 3accabda4da1 mm, vma: use percpu sheaves for vm_area_struct cache

The first is such an early failure it's silent. With just 3acca I get :

Quoted 9 lines
[    9.341152] BUG: kernel NULL pointer dereference, address: 0000000000000040
[    9.348115] #PF: supervisor read access in kernel mode
[    9.353264] #PF: error_code(0x0000) - not-present page
[    9.358413] PGD 0 P4D 0
[    9.360959] Oops: Oops: 0000 [#1] SMP NOPTI
[    9.365154] CPU: 21 UID: 0 PID: 818 Comm: kworker/u398:0 Not tainted 6.17.0-rc3.slab+ #5 PREEMPT(voluntary)
[    9.374982] Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS 1.26.0 07/30/2025
[    9.382641] RIP: 0010:__pcs_replace_empty_main+0x44/0x1d0
[    9.388048] Code: ec 08 48 8b 46 10 48 8b 76 08 48 85 c0 74 0b 8b 48 18 85 c9 0f 85 e5 00 00 00 65 48 63 05 e4 ee 50 02 49 8b 84 c6 e0 00 00 00 <4c> 8b 68 40 4c 89 ef e8 b0 81 ff ff 48 89 c5 48 85 c0 74 1d 48 89

That decodes to

   0:           mov    0x10(%rsi),%rax
   4:           mov    0x8(%rsi),%rsi
   8:           test   %rax,%rax
   b:           je     0x18
   d:           mov    0x18(%rax),%ecx
  10:           test   %ecx,%ecx
  12:           jne    0xfd
  18:           movslq %gs:0x250eee4(%rip),%rax
  20:           mov    0xe0(%r14,%rax,8),%rax
  28:*          mov    0x40(%rax),%r13          <-- trapping instruction
  2c:           mov    %r13,%rdi
  2f:           call   0xffffffffffff81e4
  34:           mov    %rax,%rbp
  37:           test   %rax,%rax
  3a:           je     0x59

which is the code around that barn_replace_empty_sheaf() call.

In particular, the trapping instruction is from get_barn(), it's the "->barn" in

        return get_node(s, numa_mem_id())->barn;

so it looks like 'get_node()' is returning NULL here:

        return s->node[node];

That 0x250eee4(%rip) is from "get_node()" becoming

18: movslq %gs:numa_node(%rip), %rax # node
20: mov 0xe0(%r14,%rax,8),%rax # ->node[node]

Quoted 8 lines

instruction, and then that ->barn dereference is the trapping instruction that tries to read node->barn:

28:* mov 0x40(%rax),%r13 # node->barn

but I did *not* look into why s->node[node] would be NULL.

Over to you Vlastimil,

Thanks, yeah will look ASAP. I suspect the "nodes with zero memory" is something that might not be handled well in general on x86. I know powerpc used to do these kind of setups first and they have some special handling, so numa_mem_id() would give you the closest node with memory in there and I suspect it's not happening here. CPU 21 is node 6 so it's one of those without memory. I'll see if I can simulate this with QEMU and what's the most sensible fix

Quoted 7 lines
Quoted 1 line

Thanks for taking a look. I thought the NPS4 thing might be playing a role.

From what I quickly found I understood that NPS4 is supposed to create extra numa nodes per socket (4 instead of 1) and interleave the memory between them. So it seems weird to me it would assign everything to one node and leave 3 others memoryless?

That I don't know. Someone from AMD might be able to help there. This system has had its BIOS and other bits updated just a couple of months ago but this numa layout has been there since I've been using the system (several years now).

Quoted 8 lines
Quoted 1 line

I'm happy to take any test/fix code you have for a spin on this system.

Thanks. Here's a candidate fix in case you can test. I'll finalize it tomorrow. The slab performance won't be optimal on cpus on those memoryless nodes, that's why I'd like to figure out if it's a BIOS bug or not. If memoryless nodes are really intended we should look into initializing things so that numa_mem_id() works as expected and points to nearest populated node.

The below does the trick. It boots and I ran a suite of stress-ng tests for sanity. Any performance it's getting now is better than it was when it wouldn't boot :)

Cheers,
Phil

Quoted 198 lines

----8<----
From 097c6251882bf5537162d17b6726575288ba9715 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <[email protected]>
Date: Sat, 11 Oct 2025 00:13:20 +0200
Subject: [PATCH] slab: fix NULL pointer when trying to access barn

---
 mm/slub.c | 60 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 47 insertions(+), 13 deletions(-)
mm/slub.c +47 -13
index 135c408e0515..bd3c2821e6c3 100644
@@ -507,7 +507,12 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 /* Get the barn of the current cpu's memory node */
 static inline struct node_barn *get_barn(struct kmem_cache *s)
 {
-	return get_node(s, numa_mem_id())->barn;
+	struct kmem_cache_node *n = get_node(s, numa_mem_id());
+
+	if (!n)
+		return NULL;
+
+	return n->barn;
 }
 
 /*
@@ -4982,6 +4987,10 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	}
 
 	barn = get_barn(s);
+	if (!barn) {
+		local_unlock(&s->cpu_sheaves->lock);
+		return NULL;
+	}
 
 	full = barn_replace_empty_sheaf(barn, pcs->main);
 
@@ -5153,13 +5162,20 @@ unsigned int alloc_from_pcs_bulk(struct kmem_cache *s, size_t size, void **p)
 	if (unlikely(pcs->main->size == 0)) {
 
 		struct slab_sheaf *full;
+		struct node_barn *barn;
 
 		if (pcs->spare && pcs->spare->size > 0) {
 			swap(pcs->main, pcs->spare);
 			goto do_alloc;
 		}
 
-		full = barn_replace_empty_sheaf(get_barn(s), pcs->main);
+		barn = get_barn(s);
+		if (!barn) {
+			local_unlock(&s->cpu_sheaves->lock);
+			return allocated;
+		}
+
+		full = barn_replace_empty_sheaf(barn, pcs->main);
 
 		if (full) {
 			stat(s, BARN_GET);
@@ -5314,6 +5330,7 @@ kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size)
 {
 	struct slub_percpu_sheaves *pcs;
 	struct slab_sheaf *sheaf = NULL;
+	struct node_barn *barn;
 
 	if (unlikely(size > s->sheaf_capacity)) {
 
@@ -5355,8 +5372,11 @@ kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size)
 		pcs->spare = NULL;
 		stat(s, SHEAF_PREFILL_FAST);
 	} else {
+		barn = get_barn(s);
+
 		stat(s, SHEAF_PREFILL_SLOW);
-		sheaf = barn_get_full_or_empty_sheaf(get_barn(s));
+		if (barn)
+			sheaf = barn_get_full_or_empty_sheaf(barn);
 		if (sheaf && sheaf->size)
 			stat(s, BARN_GET);
 		else
@@ -5426,7 +5446,7 @@ void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp,
 	 * If the barn has too many full sheaves or we fail to refill the sheaf,
 	 * simply flush and free it.
 	 */
-	if (data_race(barn->nr_full) >= MAX_FULL_SHEAVES ||
+	if (!barn || data_race(barn->nr_full) >= MAX_FULL_SHEAVES ||
 	    refill_sheaf(s, sheaf, gfp)) {
 		sheaf_flush_unused(s, sheaf);
 		free_empty_sheaf(s, sheaf);
@@ -5943,10 +5963,9 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
  * put the full sheaf there.
  */
 static void __pcs_install_empty_sheaf(struct kmem_cache *s,
-		struct slub_percpu_sheaves *pcs, struct slab_sheaf *empty)
+		struct slub_percpu_sheaves *pcs, struct slab_sheaf *empty,
+		struct node_barn *barn)
 {
-	struct node_barn *barn;
-
 	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
 	/* This is what we expect to find if nobody interrupted us. */
@@ -5956,8 +5975,6 @@ static void __pcs_install_empty_sheaf(struct kmem_cache *s,
 		return;
 	}
 
-	barn = get_barn(s);
-
 	/*
 	 * Unlikely because if the main sheaf had space, we would have just
 	 * freed to it. Get rid of our empty sheaf.
@@ -6002,6 +6019,11 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs)
 	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
 	barn = get_barn(s);
+	if (!barn) {
+		local_unlock(&s->cpu_sheaves->lock);
+		return NULL;
+	}
+
 	put_fail = false;
 
 	if (!pcs->spare) {
@@ -6084,7 +6106,7 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs)
 	}
 
 	pcs = this_cpu_ptr(s->cpu_sheaves);
-	__pcs_install_empty_sheaf(s, pcs, empty);
+	__pcs_install_empty_sheaf(s, pcs, empty, barn);
 
 	return pcs;
 }
@@ -6121,8 +6143,9 @@ bool free_to_pcs(struct kmem_cache *s, void *object)
 
 static void rcu_free_sheaf(struct rcu_head *head)
 {
+	struct kmem_cache_node *n;
 	struct slab_sheaf *sheaf;
-	struct node_barn *barn;
+	struct node_barn *barn = NULL;
 	struct kmem_cache *s;
 
 	sheaf = container_of(head, struct slab_sheaf, rcu_head);
@@ -6139,7 +6162,11 @@ static void rcu_free_sheaf(struct rcu_head *head)
 	 */
 	__rcu_free_sheaf_prepare(s, sheaf);
 
-	barn = get_node(s, sheaf->node)->barn;
+	n = get_node(s, sheaf->node);
+	if (!n)
+		goto flush;
+
+	barn = n->barn;
 
 	/* due to slab_free_hook() */
 	if (unlikely(sheaf->size == 0))
@@ -6157,11 +6184,12 @@ static void rcu_free_sheaf(struct rcu_head *head)
 		return;
 	}
 
+flush:
 	stat(s, BARN_PUT_FAIL);
 	sheaf_flush_unused(s, sheaf);
 
 empty:
-	if (data_race(barn->nr_empty) < MAX_EMPTY_SHEAVES) {
+	if (barn && data_race(barn->nr_empty) < MAX_EMPTY_SHEAVES) {
 		barn_put_empty_sheaf(barn, sheaf);
 		return;
 	}
@@ -6191,6 +6219,10 @@ bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj)
 		}
 
 		barn = get_barn(s);
+		if (!barn) {
+			local_unlock(&s->cpu_sheaves->lock);
+			goto fail;
+		}
 
 		empty = barn_get_empty_sheaf(barn);
 
@@ -6304,6 +6336,8 @@ static void free_to_pcs_bulk(struct kmem_cache *s, size_t size, void **p)
 		goto do_free;
 
 	barn = get_barn(s);
+	if (!barn)
+		goto no_empty;
 
 	if (!pcs->spare) {
 		empty = barn_get_empty_sheaf(barn);
Signature · 1 line
2.51.0
author
#6 lore raw

Hi,

Quoted 86 lines · On Fri, Oct 10, 2025 at 08:29:07PM -0400 Phil Auld wrote:

Hi Vlastimil,

Quoted 75 lines · On Sat, Oct 11, 2025 at 12:22:39AM +0200 Vlastimil Babka wrote:
Quoted 74 lines · Phil Auld
Quoted 72 lines · On Fri, Oct 10, 2025 at 08:27:30PM +0200 Vlastimil Babka wrote:
Quoted 54 lines · Linus Torvalds
Quoted 10 lines · Phil Auld

After several days of failed boots I've gotten it down to these two commits.

59faa4da7cd4 maple_tree: use percpu sheaves for maple_node_cache 3accabda4da1 mm, vma: use percpu sheaves for vm_area_struct cache

The first is such an early failure it's silent. With just 3acca I get :

Quoted 9 lines
[    9.341152] BUG: kernel NULL pointer dereference, address: 0000000000000040
[    9.348115] #PF: supervisor read access in kernel mode
[    9.353264] #PF: error_code(0x0000) - not-present page
[    9.358413] PGD 0 P4D 0
[    9.360959] Oops: Oops: 0000 [#1] SMP NOPTI
[    9.365154] CPU: 21 UID: 0 PID: 818 Comm: kworker/u398:0 Not tainted 6.17.0-rc3.slab+ #5 PREEMPT(voluntary)
[    9.374982] Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS 1.26.0 07/30/2025
[    9.382641] RIP: 0010:__pcs_replace_empty_main+0x44/0x1d0
[    9.388048] Code: ec 08 48 8b 46 10 48 8b 76 08 48 85 c0 74 0b 8b 48 18 85 c9 0f 85 e5 00 00 00 65 48 63 05 e4 ee 50 02 49 8b 84 c6 e0 00 00 00 <4c> 8b 68 40 4c 89 ef e8 b0 81 ff ff 48 89 c5 48 85 c0 74 1d 48 89

That decodes to

   0:           mov    0x10(%rsi),%rax
   4:           mov    0x8(%rsi),%rsi
   8:           test   %rax,%rax
   b:           je     0x18
   d:           mov    0x18(%rax),%ecx
  10:           test   %ecx,%ecx
  12:           jne    0xfd
  18:           movslq %gs:0x250eee4(%rip),%rax
  20:           mov    0xe0(%r14,%rax,8),%rax
  28:*          mov    0x40(%rax),%r13          <-- trapping instruction
  2c:           mov    %r13,%rdi
  2f:           call   0xffffffffffff81e4
  34:           mov    %rax,%rbp
  37:           test   %rax,%rax
  3a:           je     0x59

which is the code around that barn_replace_empty_sheaf() call.

In particular, the trapping instruction is from get_barn(), it's the "->barn" in

        return get_node(s, numa_mem_id())->barn;

so it looks like 'get_node()' is returning NULL here:

        return s->node[node];

That 0x250eee4(%rip) is from "get_node()" becoming

18: movslq %gs:numa_node(%rip), %rax # node
20: mov 0xe0(%r14,%rax,8),%rax # ->node[node]

Quoted 8 lines

instruction, and then that ->barn dereference is the trapping instruction that tries to read node->barn:

28:* mov 0x40(%rax),%r13 # node->barn

but I did *not* look into why s->node[node] would be NULL.

Over to you Vlastimil,

Thanks, yeah will look ASAP. I suspect the "nodes with zero memory" is something that might not be handled well in general on x86. I know powerpc used to do these kind of setups first and they have some special handling, so numa_mem_id() would give you the closest node with memory in there and I suspect it's not happening here. CPU 21 is node 6 so it's one of those without memory. I'll see if I can simulate this with QEMU and what's the most sensible fix

Quoted 7 lines
Quoted 1 line

Thanks for taking a look. I thought the NPS4 thing might be playing a role.

From what I quickly found I understood that NPS4 is supposed to create extra numa nodes per socket (4 instead of 1) and interleave the memory between them. So it seems weird to me it would assign everything to one node and leave 3 others memoryless?

Quoted 5 lines

That I don't know. Someone from AMD might be able to help there. This system has had its BIOS and other bits updated just a couple of months ago but this numa layout has been there since I've been using the system (several years now).

Just to follow up here. I think the issue is just that this machine is somewhat underprovisioned in the memory department. It's got 32 slots, with only 4 actually populated. I suspect if it was fully populated there'd be memory in every node.

Thanks for the fix and getting it -rc1.

Cheers,
Phil

Quoted 219 lines
Quoted 8 lines
Quoted 1 line

I'm happy to take any test/fix code you have for a spin on this system.

Thanks. Here's a candidate fix in case you can test. I'll finalize it tomorrow. The slab performance won't be optimal on cpus on those memoryless nodes, that's why I'd like to figure out if it's a BIOS bug or not. If memoryless nodes are really intended we should look into initializing things so that numa_mem_id() works as expected and points to nearest populated node.

The below does the trick. It boots and I ran a suite of stress-ng tests for sanity. Any performance it's getting now is better than it was when it wouldn't boot :)

Cheers,
Phil

Quoted 198 lines

----8<----
From 097c6251882bf5537162d17b6726575288ba9715 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <[email protected]>
Date: Sat, 11 Oct 2025 00:13:20 +0200
Subject: [PATCH] slab: fix NULL pointer when trying to access barn

---
 mm/slub.c | 60 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 47 insertions(+), 13 deletions(-)
mm/slub.c +47 -13
index 135c408e0515..bd3c2821e6c3 100644
@@ -507,7 +507,12 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 /* Get the barn of the current cpu's memory node */
 static inline struct node_barn *get_barn(struct kmem_cache *s)
 {
-	return get_node(s, numa_mem_id())->barn;
+	struct kmem_cache_node *n = get_node(s, numa_mem_id());
+
+	if (!n)
+		return NULL;
+
+	return n->barn;
 }
 
 /*
@@ -4982,6 +4987,10 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	}
 
 	barn = get_barn(s);
+	if (!barn) {
+		local_unlock(&s->cpu_sheaves->lock);
+		return NULL;
+	}
 
 	full = barn_replace_empty_sheaf(barn, pcs->main);
 
@@ -5153,13 +5162,20 @@ unsigned int alloc_from_pcs_bulk(struct kmem_cache *s, size_t size, void **p)
 	if (unlikely(pcs->main->size == 0)) {
 
 		struct slab_sheaf *full;
+		struct node_barn *barn;
 
 		if (pcs->spare && pcs->spare->size > 0) {
 			swap(pcs->main, pcs->spare);
 			goto do_alloc;
 		}
 
-		full = barn_replace_empty_sheaf(get_barn(s), pcs->main);
+		barn = get_barn(s);
+		if (!barn) {
+			local_unlock(&s->cpu_sheaves->lock);
+			return allocated;
+		}
+
+		full = barn_replace_empty_sheaf(barn, pcs->main);
 
 		if (full) {
 			stat(s, BARN_GET);
@@ -5314,6 +5330,7 @@ kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size)
 {
 	struct slub_percpu_sheaves *pcs;
 	struct slab_sheaf *sheaf = NULL;
+	struct node_barn *barn;
 
 	if (unlikely(size > s->sheaf_capacity)) {
 
@@ -5355,8 +5372,11 @@ kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size)
 		pcs->spare = NULL;
 		stat(s, SHEAF_PREFILL_FAST);
 	} else {
+		barn = get_barn(s);
+
 		stat(s, SHEAF_PREFILL_SLOW);
-		sheaf = barn_get_full_or_empty_sheaf(get_barn(s));
+		if (barn)
+			sheaf = barn_get_full_or_empty_sheaf(barn);
 		if (sheaf && sheaf->size)
 			stat(s, BARN_GET);
 		else
@@ -5426,7 +5446,7 @@ void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp,
 	 * If the barn has too many full sheaves or we fail to refill the sheaf,
 	 * simply flush and free it.
 	 */
-	if (data_race(barn->nr_full) >= MAX_FULL_SHEAVES ||
+	if (!barn || data_race(barn->nr_full) >= MAX_FULL_SHEAVES ||
 	    refill_sheaf(s, sheaf, gfp)) {
 		sheaf_flush_unused(s, sheaf);
 		free_empty_sheaf(s, sheaf);
@@ -5943,10 +5963,9 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
  * put the full sheaf there.
  */
 static void __pcs_install_empty_sheaf(struct kmem_cache *s,
-		struct slub_percpu_sheaves *pcs, struct slab_sheaf *empty)
+		struct slub_percpu_sheaves *pcs, struct slab_sheaf *empty,
+		struct node_barn *barn)
 {
-	struct node_barn *barn;
-
 	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
 	/* This is what we expect to find if nobody interrupted us. */
@@ -5956,8 +5975,6 @@ static void __pcs_install_empty_sheaf(struct kmem_cache *s,
 		return;
 	}
 
-	barn = get_barn(s);
-
 	/*
 	 * Unlikely because if the main sheaf had space, we would have just
 	 * freed to it. Get rid of our empty sheaf.
@@ -6002,6 +6019,11 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs)
 	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
 	barn = get_barn(s);
+	if (!barn) {
+		local_unlock(&s->cpu_sheaves->lock);
+		return NULL;
+	}
+
 	put_fail = false;
 
 	if (!pcs->spare) {
@@ -6084,7 +6106,7 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs)
 	}
 
 	pcs = this_cpu_ptr(s->cpu_sheaves);
-	__pcs_install_empty_sheaf(s, pcs, empty);
+	__pcs_install_empty_sheaf(s, pcs, empty, barn);
 
 	return pcs;
 }
@@ -6121,8 +6143,9 @@ bool free_to_pcs(struct kmem_cache *s, void *object)
 
 static void rcu_free_sheaf(struct rcu_head *head)
 {
+	struct kmem_cache_node *n;
 	struct slab_sheaf *sheaf;
-	struct node_barn *barn;
+	struct node_barn *barn = NULL;
 	struct kmem_cache *s;
 
 	sheaf = container_of(head, struct slab_sheaf, rcu_head);
@@ -6139,7 +6162,11 @@ static void rcu_free_sheaf(struct rcu_head *head)
 	 */
 	__rcu_free_sheaf_prepare(s, sheaf);
 
-	barn = get_node(s, sheaf->node)->barn;
+	n = get_node(s, sheaf->node);
+	if (!n)
+		goto flush;
+
+	barn = n->barn;
 
 	/* due to slab_free_hook() */
 	if (unlikely(sheaf->size == 0))
@@ -6157,11 +6184,12 @@ static void rcu_free_sheaf(struct rcu_head *head)
 		return;
 	}
 
+flush:
 	stat(s, BARN_PUT_FAIL);
 	sheaf_flush_unused(s, sheaf);
 
 empty:
-	if (data_race(barn->nr_empty) < MAX_EMPTY_SHEAVES) {
+	if (barn && data_race(barn->nr_empty) < MAX_EMPTY_SHEAVES) {
 		barn_put_empty_sheaf(barn, sheaf);
 		return;
 	}
@@ -6191,6 +6219,10 @@ bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj)
 		}
 
 		barn = get_barn(s);
+		if (!barn) {
+			local_unlock(&s->cpu_sheaves->lock);
+			goto fail;
+		}
 
 		empty = barn_get_empty_sheaf(barn);
 
@@ -6304,6 +6336,8 @@ static void free_to_pcs_bulk(struct kmem_cache *s, size_t size, void **p)
 		goto do_free;
 
 	barn = get_barn(s);
+	if (!barn)
+		goto no_empty;
 
 	if (!pcs->spare) {
 		empty = barn_get_empty_sheaf(barn);
Signature · 1 line
2.51.0