mirror of
https://github.com/torvalds/linux.git
synced 2026-09-23 13:14:02 +02:00
acpi/apei/ghes: Use raw_spinlock_t for CXL CPER work locks
The CXL CPER work registration and unregistration helpers acquire cxl_cper_work_lock and cxl_cper_prot_err_work_lock with a spinlock guard(), which leaves local interrupts enabled. The corresponding post paths (cxl_cper_post_event(), cxl_cper_post_prot_err()) execute in hard IRQ context (they are called from the GHES error notification path) and acquire the same locks with an irqsave guard(). If a CPU is holding one of these locks via a spinlock guard() when a GHES interrupt arrives on the same CPU, the IRQ handler spins on the held lock waiting for it to release, while the lock holder is preempted by the IRQ. The result is a deadlock. Convert both locks from spinlock_t to raw_spinlock_t and use guard() at all call sites. On PREEMPT_RT kernels spinlock_t is backed by rt_mutex and sleeping from hard IRQ context is not permitted; raw_spinlock_t is safe in both contexts. Add WARN_ONCE to both register functions to surface double-registration bugs at runtime. Restructure both unregister functions to clear the global work pointer under the lock before calling cancel_work_sync(), closing the window where a CPER interrupt could schedule work on a pointer about to be freed. Add kfifo_reset() after cancel_work_sync() so stale entries are not replayed on next module load. Both kfifos are single-consumer: only one work_struct is registered at a time, enforced by the WARN_ONCE guard in the register functions. kfifo_reset() is safe outside the lock because cancel_work_sync() has already quiesced the consumer, and no new consumer can register until the current module exit completes and a fresh module init runs. Remove the redundant cancel_work_sync() call from cxl_ras_exit() and cxl_pci_driver_exit(). The CPER unregister functions now quiesce the work internally. Reported-by: Sashiko <sashiko@linuxfoundation.org> Signed-off-by: Terry Bowman <terry.bowman@amd.com> Fixes:5e4a264bf8("acpi/ghes: Process CXL Component Events") Fixes:36f257e3b0("acpi/ghes, cxl/pci: Process CXL CPER Protocol Errors") Cc: stable@vger.kernel.org Reviewed-by: Dave Jiang <dave.jiang@intel.com> Reviewed-by: Jonathan Cameron <jonathan.cameron@oss.qualcomm.com> Reviewed-by: Tony Luck <tony.luck@intel.com> Link: https://patch.msgid.link/20260803221810.3685703-4-terry.bowman@amd.com Signed-off-by: Dave Jiang <dave.jiang@intel.com>
This commit is contained in:
parent
9d39952612
commit
6625ca499c
|
|
@ -749,7 +749,7 @@ static DEFINE_KFIFO(cxl_cper_prot_err_fifo, struct cxl_cper_prot_err_work_data,
|
|||
CXL_CPER_PROT_ERR_FIFO_DEPTH);
|
||||
|
||||
/* Synchronize schedule_work() with cxl_cper_prot_err_work changes */
|
||||
static DEFINE_SPINLOCK(cxl_cper_prot_err_work_lock);
|
||||
static DEFINE_RAW_SPINLOCK(cxl_cper_prot_err_work_lock);
|
||||
struct work_struct *cxl_cper_prot_err_work;
|
||||
|
||||
static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
|
||||
|
|
@ -761,7 +761,7 @@ static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
|
|||
if (cxl_cper_sec_prot_err_valid(prot_err))
|
||||
return;
|
||||
|
||||
guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
|
||||
guard(raw_spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
|
||||
|
||||
if (!cxl_cper_prot_err_work)
|
||||
return;
|
||||
|
|
@ -780,10 +780,11 @@ static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
|
|||
|
||||
int cxl_cper_register_prot_err_work(struct work_struct *work)
|
||||
{
|
||||
if (cxl_cper_prot_err_work)
|
||||
return -EINVAL;
|
||||
guard(raw_spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
|
||||
|
||||
guard(spinlock)(&cxl_cper_prot_err_work_lock);
|
||||
if (WARN_ONCE(cxl_cper_prot_err_work,
|
||||
"CPER-CXL kfifo consumer already registered\n"))
|
||||
return -EINVAL;
|
||||
cxl_cper_prot_err_work = work;
|
||||
return 0;
|
||||
}
|
||||
|
|
@ -791,11 +792,18 @@ EXPORT_SYMBOL_NS_GPL(cxl_cper_register_prot_err_work, "CXL");
|
|||
|
||||
int cxl_cper_unregister_prot_err_work(struct work_struct *work)
|
||||
{
|
||||
if (cxl_cper_prot_err_work != work)
|
||||
return -EINVAL;
|
||||
scoped_guard(raw_spinlock_irqsave, &cxl_cper_prot_err_work_lock) {
|
||||
if (WARN_ONCE(cxl_cper_prot_err_work != work,
|
||||
"CPER-CXL kfifo consumer mismatch on unregister\n"))
|
||||
return -EINVAL;
|
||||
cxl_cper_prot_err_work = NULL;
|
||||
}
|
||||
|
||||
cancel_work_sync(work);
|
||||
|
||||
/* Discard stale entries so they are not replayed on next module load */
|
||||
kfifo_reset(&cxl_cper_prot_err_fifo);
|
||||
|
||||
guard(spinlock)(&cxl_cper_prot_err_work_lock);
|
||||
cxl_cper_prot_err_work = NULL;
|
||||
return 0;
|
||||
}
|
||||
EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_prot_err_work, "CXL");
|
||||
|
|
@ -811,7 +819,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_cper_prot_err_kfifo_get, "CXL");
|
|||
DEFINE_KFIFO(cxl_cper_fifo, struct cxl_cper_work_data, CXL_CPER_FIFO_DEPTH);
|
||||
|
||||
/* Synchronize schedule_work() with cxl_cper_work changes */
|
||||
static DEFINE_SPINLOCK(cxl_cper_work_lock);
|
||||
static DEFINE_RAW_SPINLOCK(cxl_cper_work_lock);
|
||||
struct work_struct *cxl_cper_work;
|
||||
|
||||
static void cxl_cper_post_event(enum cxl_event_type event_type,
|
||||
|
|
@ -831,7 +839,7 @@ static void cxl_cper_post_event(enum cxl_event_type event_type,
|
|||
return;
|
||||
}
|
||||
|
||||
guard(spinlock_irqsave)(&cxl_cper_work_lock);
|
||||
guard(raw_spinlock_irqsave)(&cxl_cper_work_lock);
|
||||
|
||||
if (!cxl_cper_work)
|
||||
return;
|
||||
|
|
@ -849,10 +857,11 @@ static void cxl_cper_post_event(enum cxl_event_type event_type,
|
|||
|
||||
int cxl_cper_register_work(struct work_struct *work)
|
||||
{
|
||||
if (cxl_cper_work)
|
||||
guard(raw_spinlock_irqsave)(&cxl_cper_work_lock);
|
||||
if (WARN_ONCE(cxl_cper_work,
|
||||
"CXL CPER kfifo consumer already registered\n"))
|
||||
return -EINVAL;
|
||||
|
||||
guard(spinlock)(&cxl_cper_work_lock);
|
||||
cxl_cper_work = work;
|
||||
return 0;
|
||||
}
|
||||
|
|
@ -860,11 +869,18 @@ EXPORT_SYMBOL_NS_GPL(cxl_cper_register_work, "CXL");
|
|||
|
||||
int cxl_cper_unregister_work(struct work_struct *work)
|
||||
{
|
||||
if (cxl_cper_work != work)
|
||||
return -EINVAL;
|
||||
scoped_guard(raw_spinlock_irqsave, &cxl_cper_work_lock) {
|
||||
if (WARN_ONCE(cxl_cper_work != work,
|
||||
"CXL CPER kfifo consumer mismatch on unregister\n"))
|
||||
return -EINVAL;
|
||||
cxl_cper_work = NULL;
|
||||
}
|
||||
|
||||
cancel_work_sync(work);
|
||||
|
||||
/* Discard stale entries so they are not replayed on next module load */
|
||||
kfifo_reset(&cxl_cper_fifo);
|
||||
|
||||
guard(spinlock)(&cxl_cper_work_lock);
|
||||
cxl_cper_work = NULL;
|
||||
return 0;
|
||||
}
|
||||
EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_work, "CXL");
|
||||
|
|
|
|||
|
|
@ -137,7 +137,6 @@ int cxl_ras_init(void)
|
|||
void cxl_ras_exit(void)
|
||||
{
|
||||
cxl_cper_unregister_prot_err_work(&cxl_cper_prot_err_work);
|
||||
cancel_work_sync(&cxl_cper_prot_err_work);
|
||||
}
|
||||
|
||||
static void cxl_dport_map_ras(struct cxl_dport *dport)
|
||||
|
|
|
|||
|
|
@ -1083,7 +1083,6 @@ static int __init cxl_pci_driver_init(void)
|
|||
static void __exit cxl_pci_driver_exit(void)
|
||||
{
|
||||
cxl_cper_unregister_work(&cxl_cper_work);
|
||||
cancel_work_sync(&cxl_cper_work);
|
||||
pci_unregister_driver(&cxl_pci_driver);
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user