FAILED: patch "[PATCH] acpi/apei/ghes: Use raw_spinlock_t for CXL CPER work locks" failed to apply to 6.12-stable tree

PATCH New [email protected] 2 participants 4 messages Sep 3 – Sep 8

Subsystems (4)

Stable branch ACPI CXL ACPI APEI

lore

Share & tools

lore

[email protected]

author maintainer

2026-09-03 14:05 UTC #0 lore raw

The patch below does not apply to the 6.12-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-6.12.y
git checkout FETCH_HEAD
git cherry-pick -x 6625ca499c3131ef63be3215f8f942d7a097ea3a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026090335-waking-roundworm-32ca@gregkh' --subject-prefix 'PATCH 6.12.y' 'HEAD^..'

Possible dependencies:

thanks,

greg k-h

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

From 6625ca499c3131ef63be3215f8f942d7a097ea3a Mon Sep 17 00:00:00 2001
From: Terry Bowman <[email protected]>
Date: Mon, 3 Aug 2026 17:17:59 -0500
Subject: [PATCH] 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 <[email protected]>

Signed-off-by Terry Bowman <[email protected]>

Fixes 5e4a264bf8b5 ("acpi/ghes: Process CXL Component Events")

Fixes 36f257e3b0ba ("acpi/ghes, cxl/pci: Process CXL CPER Protocol Errors")

Cc [email protected]

Reviewed-by Dave Jiang <[email protected]>

Reviewed-by Jonathan Cameron <[email protected]>

Reviewed-by Tony Luck <[email protected]>

Link https://patch.msgid.link/[email protected] open here

Signed-off-by Dave Jiang <[email protected]>

drivers/acpi/apei/ghes.c +33 ~~-17~~

index 3236a3ce79d6..ca7a138c1ff2 100644
@@ -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");

drivers/cxl/core/ras.c +0 -1

index 99fb00949c2f..bc74d4848132 100644
@@ -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)

drivers/cxl/pci.c +0 -1

index 267c679b0b3c..7c6faee7f85e 100644
@@ -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);
 }

Sasha Levin

maintainer

2026-09-08 01:21 UTC #1 lore raw

PATCH 1/3 efi/cper, cxl: Prefix protocol error struct and function names with cxl_

From: Smita Koralahalli <[email protected]>

[ Upstream commit 84973331442a57bac31b40eaef6f264496c6f3fd ]

Rename the protocol error struct from struct cper_sec_prot_err to struct cxl_cper_sec_prot_err and cper_print_prot_err() to cxl_cper_print_prot_err() to maintain naming consistency. No functional changes.

Signed-off-by Smita Koralahalli <[email protected]>

Reviewed-by Jonathan Cameron <[email protected]>

Reviewed-by Ira Weiny <[email protected]>

Reviewed-by Dave Jiang <[email protected]>

Reviewed-by Fan Ni <[email protected]>

Reviewed-by Gregory Price <[email protected]>

Reviewed-by Dan Williams <[email protected]>

Link https://patch.msgid.link/[email protected] open here

Signed-off-by Dave Jiang <[email protected]>

Stable-dep-of: 6625ca499c31 ("acpi/apei/ghes: Use raw_spinlock_t for CXL CPER work locks")

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

---
 drivers/firmware/efi/cper.c     | 4 ++--
 drivers/firmware/efi/cper_cxl.c | 3 ++-
 drivers/firmware/efi/cper_cxl.h | 5 +++--
 3 files changed, 7 insertions(+), 5 deletions(-)

drivers/firmware/efi/cper.c +2 -2

index 3587295cd0206..e0adbd6df9b53 100644
@@ -690,11 +690,11 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 		else
 			goto err_section_too_small;
 	} else if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR)) {
-		struct cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata);
+		struct cxl_cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata);
 
 		printk("%ssection_type: CXL Protocol Error\n", newpfx);
 		if (gdata->error_data_length >= sizeof(*prot_err))
-			cper_print_prot_err(newpfx, prot_err);
+			cxl_cper_print_prot_err(newpfx, prot_err);
 		else
 			goto err_section_too_small;
 	} else {

drivers/firmware/efi/cper_cxl.c +2 -1

index a55771b99a97a..cbaabcb7382d9 100644
@@ -55,7 +55,8 @@ enum {
 	USP,	/* CXL Upstream Switch Port */
 };
 
-void cper_print_prot_err(const char *pfx, const struct cper_sec_prot_err *prot_err)
+void cxl_cper_print_prot_err(const char *pfx,
+			     const struct cxl_cper_sec_prot_err *prot_err)
 {
 	if (prot_err->valid_bits & PROT_ERR_VALID_AGENT_TYPE)
 		pr_info("%s agent_type: %d, %s\n", pfx, prot_err->agent_type,

drivers/firmware/efi/cper_cxl.h +3 -2

index 86bfcf7909eca..0e3ab0ba17c36 100644
@@ -18,7 +18,7 @@
 #pragma pack(1)
 
 /* Compute Express Link Protocol Error Section, UEFI v2.10 sec N.2.13 */
-struct cper_sec_prot_err {
+struct cxl_cper_sec_prot_err {
 	u64 valid_bits;
 	u8 agent_type;
 	u8 reserved[7];

@@ -61,6 +61,7 @@ struct cper_sec_prot_err {
 
 #pragma pack()
 
-void cper_print_prot_err(const char *pfx, const struct cper_sec_prot_err *prot_err);
+void cxl_cper_print_prot_err(const char *pfx,
+			     const struct cxl_cper_sec_prot_err *prot_err);
 
 #endif //__CPER_CXL_

Signature · 1 line

2.53.0

Sasha Levin

maintainer

2026-09-08 01:21 UTC #2 lore raw

PATCH 2/3 efi/cper, cxl: Make definitions and structures global

From: Smita Koralahalli <[email protected]>

[ Upstream commit 958c3a6706863f9f77b21c90d2428473441cd8a1 ]

In preparation to add tracepoint support, move protocol error UUID definition to a common location, Also, make struct CXL RAS capability, cxl_cper_sec_prot_err and CPER validation flags global for use across different modules.

Signed-off-by Smita Koralahalli <[email protected]>

Reviewed-by Jonathan Cameron <[email protected]>

Reviewed-by Ira Weiny <[email protected]>

Reviewed-by Dave Jiang <[email protected]>

Reviewed-by Fan Ni <[email protected]>

Reviewed-by Gregory Price <[email protected]>

Reviewed-by Dan Williams <[email protected]>

Link https://patch.msgid.link/[email protected] open here

Signed-off-by Dave Jiang <[email protected]>

Stable-dep-of: 6625ca499c31 ("acpi/apei/ghes: Use raw_spinlock_t for CXL CPER work locks")

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

---
 drivers/firmware/efi/cper.c     |  1 +
 drivers/firmware/efi/cper_cxl.c | 35 +--------------
 drivers/firmware/efi/cper_cxl.h | 51 ---------------------
 include/cxl/event.h             | 80 +++++++++++++++++++++++++++++++++
 include/linux/cper.h            |  4 ++
 5 files changed, 86 insertions(+), 85 deletions(-)

drivers/firmware/efi/cper.c +1 -0

index e0adbd6df9b53..7fe10a06e68c3 100644
@@ -25,6 +25,7 @@
 #include <linux/bcd.h>
 #include <acpi/ghes.h>
 #include <ras/ras_event.h>
+#include <cxl/event.h>
 #include "cper_cxl.h"
 
 /*

drivers/firmware/efi/cper_cxl.c +1 ~~-34~~

index cbaabcb7382d9..64c0dd27be6ed 100644
@@ -8,27 +8,9 @@
  */
 
 #include <linux/cper.h>
+#include <cxl/event.h>
 #include "cper_cxl.h"
 
-#define PROT_ERR_VALID_AGENT_TYPE		BIT_ULL(0)
-#define PROT_ERR_VALID_AGENT_ADDRESS		BIT_ULL(1)
-#define PROT_ERR_VALID_DEVICE_ID		BIT_ULL(2)
-#define PROT_ERR_VALID_SERIAL_NUMBER		BIT_ULL(3)
-#define PROT_ERR_VALID_CAPABILITY		BIT_ULL(4)
-#define PROT_ERR_VALID_DVSEC			BIT_ULL(5)
-#define PROT_ERR_VALID_ERROR_LOG		BIT_ULL(6)
-
-/* CXL RAS Capability Structure, CXL v3.0 sec 8.2.4.16 */
-struct cxl_ras_capability_regs {
-	u32 uncor_status;
-	u32 uncor_mask;
-	u32 uncor_severity;
-	u32 cor_status;
-	u32 cor_mask;
-	u32 cap_control;
-	u32 header_log[16];
-};
-
 static const char * const prot_err_agent_type_strs[] = {
 	"Restricted CXL Device",
 	"Restricted CXL Host Downstream Port",

@@ -40,21 +22,6 @@ static const char * const prot_err_agent_type_strs[] = {
 	"CXL Upstream Switch Port",
 };
 
-/*
- * The layout of the enumeration and the values matches CXL Agent Type
- * field in the UEFI 2.10 Section N.2.13,
- */
-enum {
-	RCD,	/* Restricted CXL Device */
-	RCH_DP,	/* Restricted CXL Host Downstream Port */
-	DEVICE,	/* CXL Device */
-	LD,	/* CXL Logical Device */
-	FMLD,	/* CXL Fabric Manager managed Logical Device */
-	RP,	/* CXL Root Port */
-	DSP,	/* CXL Downstream Switch Port */
-	USP,	/* CXL Upstream Switch Port */
-};
-
 void cxl_cper_print_prot_err(const char *pfx,
 			     const struct cxl_cper_sec_prot_err *prot_err)
 {

drivers/firmware/efi/cper_cxl.h +0 ~~-51~~

57 lines not on this page · raw message

include/cxl/event.h +80 -0

86 lines not on this page · raw message

include/linux/cper.h +4 -0

index 951291fa50d4f..e9c0331fe204a 100644
@@ -89,6 +89,10 @@ enum {
 #define CPER_NOTIFY_DMAR						\
 	GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E,	\
 		  0x72, 0x2D, 0xEB, 0x41)
+/* CXL Protocol Error Section */
+#define CPER_SEC_CXL_PROT_ERR						\
+	GUID_INIT(0x80B9EFB4, 0x52B5, 0x4DE3, 0xA7, 0x77, 0x68, 0x78,	\
+		  0x4B, 0x77, 0x10, 0x48)
 
 /* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
 /*

Signature · 1 line

2.53.0

Sasha Levin

maintainer

2026-09-08 01:21 UTC #3 lore raw

PATCH 3/3 acpi/apei/ghes: Use raw_spinlock_t for CXL CPER work locks

In reply to Sasha Levin

From: Terry Bowman <[email protected]>

[ Upstream commit 6625ca499c3131ef63be3215f8f942d7a097ea3a ]

Add WARN_ONCE to both register functions to surface double-registration bugs at runtime.

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 <[email protected]>

Signed-off-by Terry Bowman <[email protected]>

Fixes 5e4a264bf8b5 ("acpi/ghes: Process CXL Component Events")

Fixes 36f257e3b0ba ("acpi/ghes, cxl/pci: Process CXL CPER Protocol Errors")

Cc [email protected]

Reviewed-by Dave Jiang <[email protected]>

Reviewed-by Jonathan Cameron <[email protected]>

Reviewed-by Tony Luck <[email protected]>

Link https://patch.msgid.link/[email protected] open here

Signed-off-by Dave Jiang <[email protected]>

[ omitted protocol-error changes because the corresponding consumer infrastructure is absent in 6.12 ]

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

---
 drivers/acpi/apei/ghes.c | 24 ++++++++++++++++--------
 drivers/cxl/pci.c        |  1 -
 2 files changed, 16 insertions(+), 9 deletions(-)

drivers/acpi/apei/ghes.c +16 -8

index 25163eb9b8053..e1cbc35919cbf 100644
@@ -710,7 +710,7 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 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,

@@ -730,7 +730,7 @@ 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;

@@ -748,10 +748,11 @@ 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;
 }

@@ -759,11 +760,18 @@ 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);

drivers/cxl/pci.c +0 -1

index 09a2bc817d645..4c307ee6cd28e 100644
@@ -1087,7 +1087,6 @@ 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);
 }

Signature · 1 line

2.53.0