[PATCH] cxl/hdm: fix a warning in devm_remove_action()
From: Sungwoo Kim
Date: Sun Mar 08 2026 - 20:11:01 EST
In the following race scenario, devm_remove_action() can be called
before devm_add_action(), triggering a warning because there is no
action to remove.
To fix this, extend a critical section to embrace both
__cxl_dpa_reserve() and devm_add_action().
task 1:
cxl_dpa_alloc()
__cxl_dpa_reserve() ...(1)
devm_add_action() ...(4)
task 2:
cxl_dpa_free()
guard()
if (!cxled->dpa_res) ...(2) pass, due to (1)
return 0;
devm_cxl_dpa_release()
devm_remove_action() ...(3) warning, no action is added yet
Warning log:
WARNING: ./include/linux/device/devres.h:160 at devm_remove_action include/linux/device/devres.h:160 [inline], CPU#0: syz.1.6464/25993
WARNING: ./include/linux/device/devres.h:160 at devm_cxl_dpa_release drivers/cxl/core/hdm.c:290 [inline], CPU#0: syz.1.6464/25993
WARNING: ./include/linux/device/devres.h:160 at cxl_dpa_free+0x2a4/0x320 drivers/cxl/core/hdm.c:572, CPU#0: syz.1.6464/25993
Modules linked in:
CPU: 0 UID: 0 PID: 25993 Comm: syz.1.6464 Not tainted 6.19.0-g15a37b05f387 #10 PREEMPT(lazy)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
RIP: 0010:devm_remove_action include/linux/device/devres.h:160 [inline]
RIP: 0010:devm_cxl_dpa_release drivers/cxl/core/hdm.c:290 [inline]
RIP: 0010:cxl_dpa_free+0x2a4/0x320 drivers/cxl/core/hdm.c:572
Code: 01 31 ff 41 89 c4 89 c6 e8 a9 91 1d fe 45 85 e4 0f 85 55 ff ff ff e8 4b 96 1d fe 90 0f 0b 90 e9 47 ff ff ff e8 3d 96 1d fe 90 <0f> 0b 90 e9 63 ff ff ff bb f0 ff ff ff e9 68 ff ff ff 48 c7 c7 f4
RSP: 0018:ffff888129f77bb8 EFLAGS: 00010282
RAX: 00000000000000f3 RBX: ffff888102f64000 RCX: ffffffff837301d3
RDX: 0000000000080000 RSI: ffffc90001c5a000 RDI: 0000000000000005
RBP: 00000000fffffffe R08: 0000000000000001 R09: ffff888123f98000
R10: 00000000fffffffe R11: 0000000000000000 R12: 0000000000000001
R13: ffff888102f64040 R14: dffffc0000000000 R15: ffff888102f64000
FS: 00007fae0488d6c0(0000) GS:ffff88827086d000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 000000012f7d6003 CR4: 0000000000770ef0
PKRU: 80000000
Call Trace:
<TASK>
dpa_size_store+0xfb/0x230 drivers/cxl/core/port.c:269
dev_attr_store+0x58/0x80 drivers/base/core.c:2437
sysfs_kf_write+0xf2/0x150 fs/sysfs/file.c:142
kernfs_fop_write_iter+0x3d6/0x5d0 fs/kernfs/file.c:352
new_sync_write fs/read_write.c:595 [inline]
vfs_write+0x68e/0x1050 fs/read_write.c:688
ksys_write+0x12a/0x250 fs/read_write.c:740
do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
do_syscall_64+0xfc/0x670 arch/x86/entry/syscall_64.c:94
entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fae0399c669
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fae0488d028 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007fae03c15fa0 RCX: 00007fae0399c669
RDX: 000000000000000a RSI: 00002000000001c0 RDI: 0000000000000009
RBP: 00007fae03a32c71 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007fae03c16038 R14: 00007fae03c15fa0 R15: 00007ffe53519fb8
</TASK>
irq event stamp: 1021
hardirqs last enabled at (1029): [<ffffffffb7d04c4b>] __up_console_sem+0x7b/0x90 kernel/printk/printk.c:347
hardirqs last disabled at (1038): [<ffffffffb7d04c30>] __up_console_sem+0x60/0x90 kernel/printk/printk.c:345
softirqs last enabled at (1016): [<ffffffffb7b73b93>] __do_softirq kernel/softirq.c:656 [inline]
softirqs last enabled at (1016): [<ffffffffb7b73b93>] invoke_softirq kernel/softirq.c:496 [inline]
softirqs last enabled at (1016): [<ffffffffb7b73b93>] __irq_exit_rcu+0xb3/0xe0 kernel/softirq.c:723
softirqs last disabled at (1005): [<ffffffffb7b73b93>] __do_softirq kernel/softirq.c:656 [inline]
softirqs last disabled at (1005): [<ffffffffb7b73b93>] invoke_softirq kernel/softirq.c:496 [inline]
softirqs last disabled at (1005): [<ffffffffb7b73b93>] __irq_exit_rcu+0xb3/0xe0 kernel/softirq.c:723
Fixes: cf880423b6a0 ("cxl/hdm: Add support for allocating DPA to an endpoint decoder")
Fixes: 9c57cde0dcbd ("cxl/hdm: Enumerate allocated DPA")
Signed-off-by: Sungwoo Kim <iam@xxxxxxxxxxxx>
---
drivers/cxl/core/hdm.c | 34 +++++++++++++++++++++++++++++-----
1 file changed, 29 insertions(+), 5 deletions(-)
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index e3f0c39e68124..86239b1790a31 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -509,13 +509,20 @@ int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
struct cxl_port *port = cxled_to_port(cxled);
int rc;
- scoped_guard(rwsem_write, &cxl_rwsem.dpa)
- rc = __cxl_dpa_reserve(cxled, base, len, skipped);
+ guard(rwsem_write)(&cxl_rwsem.dpa);
+ rc = __cxl_dpa_reserve(cxled, base, len, skipped);
if (rc)
return rc;
- return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled);
+ /* See comments in cxl_dpa_alloc()*/
+ rc = devm_add_action(&port->dev, cxl_dpa_release, cxled);
+ if (rc) {
+ __cxl_dpa_release(cxled);
+ return rc;
+ }
+
+ return 0;
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_dpa_reserve, "CXL");
@@ -613,7 +620,7 @@ static int __cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, u64 size)
struct resource *p, *last;
int part;
- guard(rwsem_write)(&cxl_rwsem.dpa);
+ lockdep_assert_held_write(&cxl_rwsem.dpa);
if (cxled->cxld.region) {
dev_dbg(dev, "decoder attached to %s\n",
dev_name(&cxled->cxld.region->dev));
@@ -679,11 +686,28 @@ int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, u64 size)
struct cxl_port *port = cxled_to_port(cxled);
int rc;
+ guard(rwsem_write)(&cxl_rwsem.dpa);
rc = __cxl_dpa_alloc(cxled, size);
if (rc)
return rc;
- return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled);
+ /*
+ * Add the devres action while still holding cxl_rwsem.dpa to prevent
+ * a race with cxl_dpa_free(). Without this, a concurrent cxl_dpa_free()
+ * can observe dpa_res set (by __cxl_dpa_reserve()) and attempt
+ * devm_remove_action() before devm_add_action() has been called,
+ * triggering a WARN_ON in devm_remove_action().
+ * Also, devm_add_action_or_reset() cannot be used here because
+ * cxl_dpa_release() tries to hold the dpa lock that is already held,
+ * causing a self deadlock.
+ */
+ rc = devm_add_action(&port->dev, cxl_dpa_release, cxled);
+ if (rc) {
+ __cxl_dpa_release(cxled);
+ return rc;
+ }
+
+ return 0;
}
static void cxld_set_interleave(struct cxl_decoder *cxld, u32 *ctrl)
--
2.47.3