FAILED: patch "[PATCH] cxl: Fix CXL_HEADERLOG_SIZE to match RAS Capability size" failed to apply to 6.18-stable tree

FAILED: patch "[PATCH] cxl: Fix CXL_HEADERLOG_SIZE to match RAS Capability size" failed to apply to 6.18-stable tree

[gregkh]

The patch below does not apply to the 6.18-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 <stable@vger.kernel.org>.

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-6.18.y
git checkout FETCH_HEAD
git cherry-pick -x c268f949e219f9e179558e836f457f6c5fbec416
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2026072028-shaky-author-b5df@gregkh' --subject-prefix 'PATCH 6.18.y' 'HEAD^..'

Possible dependencies:



thanks,

greg k-h

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

From c268f949e219f9e179558e836f457f6c5fbec416 Mon Sep 17 00:00:00 2001
From: Terry Bowman <terry.bowman@amd.com>
Date: Fri, 5 Jun 2026 13:06:10 -0500
Subject: [PATCH] cxl: Fix CXL_HEADERLOG_SIZE to match RAS Capability size

The CXL r4.0 8.2.4.17.7 RAS Capability Structure has total length 0x58
bytes (CXL_RAS_CAPABILITY_LENGTH); the Header Log occupies the trailing
64 bytes at offset 0x18.  CXL_HEADERLOG_SIZE was defined as SZ_512,
eight times the actual on-device size.

header_log_copy() reads CXL_HEADERLOG_SIZE_U32 (128) dwords from the
RAS capability iomap, overrunning the 88-byte mapping by 448 bytes.
The cxl_aer_uncorrectable_error trace event memcpy()s CXL_HEADERLOG_SIZE
(512) bytes from its source.  For the CPER caller the source is
struct cxl_ras_capability_regs::header_log[16] (64 bytes) embedded in a
stack-local cxl_cper_prot_err_work_data, so the memcpy reads 448 bytes
of kernel stack into the trace event ring buffer where userspace can
read it via tracefs.

Set CXL_HEADERLOG_SIZE to 64 and derive CXL_HEADERLOG_SIZE_U32 from it,
bringing all iomap readers into agreement on 16 dwords.  Userspace tools
such as rasdaemon have grown a dependency on the buggy 512-byte (128 u32)
header_log layout in the cxl_aer_uncorrectable_error trace event.  Add
CXL_HEADERLOG_TRACE_SIZE_U32 = 128 and use it for the trace event
__array and its memcpy to preserve that ABI.  Both callers now pass a
zero-filled u32[CXL_HEADERLOG_TRACE_SIZE_U32] staging buffer with only
the first CXL_HEADERLOG_SIZE_U32 (16) entries populated from hardware;
the remaining 112 u32s are zero-padded, keeping the 512-byte trace ring
buffer layout intact.

[ dj: Replaced 64 with SZ_64 per RichardC ]

Fixes: 36f257e3b0ba ("acpi/ghes, cxl/pci: Process CXL CPER Protocol Errors")
Fixes: 2905cb5236cb ("cxl/pci: Add (hopeful) error handling support")
Cc: stable@vger.kernel.org
Reported-by: Sashiko
Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Ben Cheatham <benjamin.cheatham@amd.com>
Reviewed-by: Richard Cheng <icheng@nvidia.com>
Link: https://patch.msgid.link/20260605180610.2249458-1-terry.bowman@amd.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>

diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
index 006c6ffc2f56..99fb00949c2f 100644
--- a/drivers/cxl/core/ras.c
+++ b/drivers/cxl/core/ras.c
@@ -8,6 +8,10 @@
 #include <cxlpci.h>
 #include "trace.h"
 
+/* Check that UCE header definition is maintained to keep ABI intact  */
+static_assert(CXL_HEADERLOG_TRACE_SIZE_U32 == 128,
+	      "rasdaemon ABI requires exactly 128 u32s");
+
 static void cxl_cper_trace_corr_port_prot_err(struct pci_dev *pdev,
 					      struct cxl_ras_capability_regs ras_cap)
 {
@@ -19,6 +23,7 @@ static void cxl_cper_trace_corr_port_prot_err(struct pci_dev *pdev,
 static void cxl_cper_trace_uncorr_port_prot_err(struct pci_dev *pdev,
 						struct cxl_ras_capability_regs ras_cap)
 {
+	u32 hl[CXL_HEADERLOG_TRACE_SIZE_U32] = {};
 	u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask;
 	u32 fe;
 
@@ -28,8 +33,8 @@ static void cxl_cper_trace_uncorr_port_prot_err(struct pci_dev *pdev,
 	else
 		fe = status;
 
-	trace_cxl_port_aer_uncorrectable_error(&pdev->dev, status, fe,
-					       ras_cap.header_log);
+	memcpy(hl, ras_cap.header_log, CXL_HEADERLOG_SIZE);
+	trace_cxl_port_aer_uncorrectable_error(&pdev->dev, status, fe, hl);
 }
 
 static void cxl_cper_trace_corr_prot_err(struct cxl_memdev *cxlmd,
@@ -44,6 +49,7 @@ static void
 cxl_cper_trace_uncorr_prot_err(struct cxl_memdev *cxlmd,
 			       struct cxl_ras_capability_regs ras_cap)
 {
+	u32 hl[CXL_HEADERLOG_TRACE_SIZE_U32] = {};
 	u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask;
 	u32 fe;
 
@@ -53,8 +59,15 @@ cxl_cper_trace_uncorr_prot_err(struct cxl_memdev *cxlmd,
 	else
 		fe = status;
 
-	trace_cxl_aer_uncorrectable_error(cxlmd, status, fe,
-					  ras_cap.header_log);
+	/*
+	 * ras_cap.header_log[] holds CXL_HEADERLOG_SIZE_U32 (16) hardware
+	 * dwords.  Copy them into the front of a zero-filled
+	 * CXL_HEADERLOG_TRACE_SIZE_U32 (128) u32 staging buffer so the trace
+	 * event memcpy sees a full 512-byte source and the userspace ABI
+	 * (rasdaemon) is preserved.
+	 */
+	memcpy(hl, ras_cap.header_log, CXL_HEADERLOG_SIZE);
+	trace_cxl_aer_uncorrectable_error(cxlmd, status, fe, hl);
 }
 
 static int match_memdev_by_parent(struct device *dev, const void *uport)
@@ -204,12 +217,12 @@ static void header_log_copy(void __iomem *ras_base, u32 *log)
 {
 	void __iomem *addr;
 	u32 *log_addr;
-	int i, log_u32_size = CXL_HEADERLOG_SIZE / sizeof(u32);
+	int i;
 
 	addr = ras_base + CXL_RAS_HEADER_LOG_OFFSET;
 	log_addr = log;
 
-	for (i = 0; i < log_u32_size; i++) {
+	for (i = 0; i < CXL_HEADERLOG_SIZE_U32; i++) {
 		*log_addr = readl(addr);
 		log_addr++;
 		addr += sizeof(u32);
@@ -222,7 +235,7 @@ static void header_log_copy(void __iomem *ras_base, u32 *log)
  */
 bool cxl_handle_ras(struct device *dev, void __iomem *ras_base)
 {
-	u32 hl[CXL_HEADERLOG_SIZE_U32];
+	u32 hl[CXL_HEADERLOG_TRACE_SIZE_U32] = {};
 	void __iomem *addr;
 	u32 status;
 	u32 fe;
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index a972e4ef1936..d37876096dd7 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -56,7 +56,7 @@ TRACE_EVENT(cxl_port_aer_uncorrectable_error,
 		__string(host, dev_name(dev->parent))
 		__field(u32, status)
 		__field(u32, first_error)
-		__array(u32, header_log, CXL_HEADERLOG_SIZE_U32)
+		__array(u32, header_log, CXL_HEADERLOG_TRACE_SIZE_U32)
 	),
 	TP_fast_assign(
 		__assign_str(device);
@@ -64,10 +64,14 @@ TRACE_EVENT(cxl_port_aer_uncorrectable_error,
 		__entry->status = status;
 		__entry->first_error = fe;
 		/*
-		 * Embed the 512B headerlog data for user app retrieval and
-		 * parsing, but no need to print this in the trace buffer.
+		 * Embed headerlog data for user app retrieval and parsing,
+		 * but no need to print in the trace buffer. Only
+		 * CXL_HEADERLOG_SIZE_U32 (16) dwords are hardware data;
+		 * the remaining entries preserve the 512-byte ABI layout
+		 * rasdaemon depends on and are zero-filled by the caller.
 		 */
-		memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE);
+		memcpy(__entry->header_log, hl,
+			CXL_HEADERLOG_TRACE_SIZE_U32 * sizeof(u32));
 	),
 	TP_printk("device=%s host=%s status: '%s' first_error: '%s'",
 		  __get_str(device), __get_str(host),
@@ -85,7 +89,7 @@ TRACE_EVENT(cxl_aer_uncorrectable_error,
 		__field(u64, serial)
 		__field(u32, status)
 		__field(u32, first_error)
-		__array(u32, header_log, CXL_HEADERLOG_SIZE_U32)
+		__array(u32, header_log, CXL_HEADERLOG_TRACE_SIZE_U32)
 	),
 	TP_fast_assign(
 		__assign_str(memdev);
@@ -94,10 +98,14 @@ TRACE_EVENT(cxl_aer_uncorrectable_error,
 		__entry->status = status;
 		__entry->first_error = fe;
 		/*
-		 * Embed the 512B headerlog data for user app retrieval and
-		 * parsing, but no need to print this in the trace buffer.
+		 * Embed headerlog data for user app retrieval and parsing,
+		 * but no need to print in the trace buffer. Only
+		 * CXL_HEADERLOG_SIZE_U32 (16) dwords are hardware data;
+		 * the remaining entries preserve the 512-byte ABI layout
+		 * rasdaemon depends on and are zero-filled by the caller.
 		 */
-		memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE);
+		memcpy(__entry->header_log, hl,
+			CXL_HEADERLOG_TRACE_SIZE_U32 * sizeof(u32));
 	),
 	TP_printk("memdev=%s host=%s serial=%lld: status: '%s' first_error: '%s'",
 		  __get_str(memdev), __get_str(host), __entry->serial,
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 1297594beaec..21fc89d3aeea 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -158,8 +158,18 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
 #define CXL_RAS_CAP_CONTROL_FE_MASK GENMASK(5, 0)
 #define CXL_RAS_HEADER_LOG_OFFSET 0x18
 #define CXL_RAS_CAPABILITY_LENGTH 0x58
-#define CXL_HEADERLOG_SIZE SZ_512
-#define CXL_HEADERLOG_SIZE_U32 SZ_512 / sizeof(u32)
+#define CXL_HEADERLOG_SIZE SZ_64
+#define CXL_HEADERLOG_SIZE_U32 (CXL_HEADERLOG_SIZE / sizeof(u32))
+
+/*
+ * The RAS UCE trace event header array was originally sized at SZ_512/sizeof(u32)
+ * = 128 u32s due to a bug. Userspace tools (rasdaemon) have grown a dependency
+ * on that 512-byte layout. Keep the trace array at 128 u32s to preserve the
+ * ABI; only CXL_HEADERLOG_SIZE_U32 (16) dwords are valid hardware data, the
+ * remainder are zero-filled.
+ */
+#define CXL_HEADERLOG_TRACE_SIZE SZ_512
+#define CXL_HEADERLOG_TRACE_SIZE_U32 (CXL_HEADERLOG_TRACE_SIZE / sizeof(u32))
 
 /* CXL 2.0 8.2.8.1 Device Capabilities Array Register */
 #define CXLDEV_CAP_ARRAY_OFFSET 0x0

[PATCH 6.18.y 1/4] cxl/pci: Remove unnecessary CXL Endpoint handling helper functions

[Sasha Levin]

From: Terry Bowman <terry.bowman@amd.com>

[ Upstream commit ca3d1a53e62093d17436abd447463da9c0f4e56b ]

The CXL driver's cxl_handle_endpoint_cor_ras()/cxl_handle_endpoint_ras()
are unnecessary helper functions used only for Endpoints. Remove these
functions as they are not common for all CXL devices and do not provide
value for EP handling.

Rename __cxl_handle_ras to cxl_handle_ras() and __cxl_handle_cor_ras()
to cxl_handle_cor_ras().

Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Tested-by: Joshua Hahn <joshua.hahnjy@gmail.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260114182055.46029-5-terry.bowman@amd.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Stable-dep-of: c268f949e219 ("cxl: Fix CXL_HEADERLOG_SIZE to match RAS Capability size")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/cxl/core/pci.c | 26 ++++++++------------------
 1 file changed, 8 insertions(+), 18 deletions(-)

diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 18825e1505d6ad..078e9e5651e1bc 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -711,8 +711,8 @@ void read_cdat_data(struct cxl_port *port)
 }
 EXPORT_SYMBOL_NS_GPL(read_cdat_data, "CXL");
 
-static void __cxl_handle_cor_ras(struct cxl_dev_state *cxlds,
-				 void __iomem *ras_base)
+static void cxl_handle_cor_ras(struct cxl_dev_state *cxlds,
+			       void __iomem *ras_base)
 {
 	void __iomem *addr;
 	u32 status;
@@ -728,11 +728,6 @@ static void __cxl_handle_cor_ras(struct cxl_dev_state *cxlds,
 	}
 }
 
-static void cxl_handle_endpoint_cor_ras(struct cxl_dev_state *cxlds)
-{
-	return __cxl_handle_cor_ras(cxlds, cxlds->regs.ras);
-}
-
 /* CXL spec rev3.0 8.2.4.16.1 */
 static void header_log_copy(void __iomem *ras_base, u32 *log)
 {
@@ -754,8 +749,8 @@ static void header_log_copy(void __iomem *ras_base, u32 *log)
  * Log the state of the RAS status registers and prepare them to log the
  * next error status. Return 1 if reset needed.
  */
-static bool __cxl_handle_ras(struct cxl_dev_state *cxlds,
-				  void __iomem *ras_base)
+static bool cxl_handle_ras(struct cxl_dev_state *cxlds,
+			   void __iomem *ras_base)
 {
 	u32 hl[CXL_HEADERLOG_SIZE_U32];
 	void __iomem *addr;
@@ -788,11 +783,6 @@ static bool __cxl_handle_ras(struct cxl_dev_state *cxlds,
 	return true;
 }
 
-static bool cxl_handle_endpoint_ras(struct cxl_dev_state *cxlds)
-{
-	return __cxl_handle_ras(cxlds, cxlds->regs.ras);
-}
-
 #ifdef CONFIG_PCIEAER_CXL
 
 static void cxl_dport_map_rch_aer(struct cxl_dport *dport)
@@ -871,13 +861,13 @@ EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
 static void cxl_handle_rdport_cor_ras(struct cxl_dev_state *cxlds,
 					  struct cxl_dport *dport)
 {
-	return __cxl_handle_cor_ras(cxlds, dport->regs.ras);
+	return cxl_handle_cor_ras(cxlds, dport->regs.ras);
 }
 
 static bool cxl_handle_rdport_ras(struct cxl_dev_state *cxlds,
 				       struct cxl_dport *dport)
 {
-	return __cxl_handle_ras(cxlds, dport->regs.ras);
+	return cxl_handle_ras(cxlds, dport->regs.ras);
 }
 
 /*
@@ -974,7 +964,7 @@ void cxl_cor_error_detected(struct pci_dev *pdev)
 		if (cxlds->rcd)
 			cxl_handle_rdport_errors(cxlds);
 
-		cxl_handle_endpoint_cor_ras(cxlds);
+		cxl_handle_cor_ras(cxlds, cxlds->regs.ras);
 	}
 }
 EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, "CXL");
@@ -1003,7 +993,7 @@ pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
 		 * chance the situation is recoverable dump the status of the RAS
 		 * capability registers and bounce the active state of the memdev.
 		 */
-		ue = cxl_handle_endpoint_ras(cxlds);
+		ue = cxl_handle_ras(cxlds, cxlds->regs.ras);
 	}
 
 
-- 
2.53.0

[PATCH 6.18.y 2/4] cxl/pci: Remove unnecessary CXL RCH handling helper functions

[Sasha Levin]

From: Terry Bowman <terry.bowman@amd.com>

[ Upstream commit eb78ef4d6f0e51243c1ee117f801dbc503e886ab ]

cxl_handle_rdport_cor_ras() and cxl_handle_rdport_ras() are specific
to Restricted CXL Host (RCH) handling. Improve readability and
maintainability by replacing these and instead using the common
cxl_handle_cor_ras() and cxl_handle_ras() functions.

Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Reviewed-by: Alejandro Lucero <alucerop@amd.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260114182055.46029-6-terry.bowman@amd.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Stable-dep-of: c268f949e219 ("cxl: Fix CXL_HEADERLOG_SIZE to match RAS Capability size")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/cxl/core/pci.c | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 078e9e5651e1bc..3fb9462954da20 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -858,18 +858,6 @@ void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
 
-static void cxl_handle_rdport_cor_ras(struct cxl_dev_state *cxlds,
-					  struct cxl_dport *dport)
-{
-	return cxl_handle_cor_ras(cxlds, dport->regs.ras);
-}
-
-static bool cxl_handle_rdport_ras(struct cxl_dev_state *cxlds,
-				       struct cxl_dport *dport)
-{
-	return cxl_handle_ras(cxlds, dport->regs.ras);
-}
-
 /*
  * Copy the AER capability registers using 32 bit read accesses.
  * This is necessary because RCRB AER capability is MMIO mapped. Clear the
@@ -939,9 +927,9 @@ static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds)
 	pci_print_aer(pdev, severity, &aer_regs);
 
 	if (severity == AER_CORRECTABLE)
-		cxl_handle_rdport_cor_ras(cxlds, dport);
+		cxl_handle_cor_ras(cxlds, dport->regs.ras);
 	else
-		cxl_handle_rdport_ras(cxlds, dport);
+		cxl_handle_ras(cxlds, dport->regs.ras);
 }
 
 #else
-- 
2.53.0

[PATCH 6.18.y 3/4] cxl/pci: Remove CXL VH handling in CONFIG_PCIEAER_CXL conditional blocks from core/pci.c

[Sasha Levin]

From: Dave Jiang <dave.jiang@intel.com>

[ Upstream commit 7ff8b1d60881c5f97b5ae426e14d2822917d3b69 ]

Create new config CONFIG_CXL_RAS and put all CXL RAS items behind the
config. The config will depend on CPER and PCIE AER to build. Move the
related VH RAS code from core/pci.c to core/ras.c.

Restricted CXL host (RCH) RAS functions will be moved in a future patch.

Cc: Robert Richter <rrichter@amd.com>
Reviewed-by: Joshua Hahn <joshua.hahnjy@gmail.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Co-developed-by: Terry Bowman <terry.bowman@amd.com>
Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260114182055.46029-8-terry.bowman@amd.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Stable-dep-of: c268f949e219 ("cxl: Fix CXL_HEADERLOG_SIZE to match RAS Capability size")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/cxl/Kconfig       |   4 +
 drivers/cxl/core/Makefile |   2 +-
 drivers/cxl/core/core.h   |  31 +++++++
 drivers/cxl/core/pci.c    | 189 +-------------------------------------
 drivers/cxl/core/ras.c    | 176 +++++++++++++++++++++++++++++++++++
 drivers/cxl/cxl.h         |   8 --
 drivers/cxl/cxlpci.h      |  16 ++++
 tools/testing/cxl/Kbuild  |   2 +-
 8 files changed, 233 insertions(+), 195 deletions(-)

diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig
index 599e126a18eb72..4bdec46b2a6bbe 100644
--- a/drivers/cxl/Kconfig
+++ b/drivers/cxl/Kconfig
@@ -234,4 +234,8 @@ config CXL_MCE
 	def_bool y
 	depends on X86_MCE && MEMORY_FAILURE
 
+config CXL_RAS
+	def_bool y
+	depends on ACPI_APEI_GHES && PCIEAER && CXL_PCI
+
 endif
diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile
index 5ad8fef210b5c8..b2930cc54f8ba2 100644
--- a/drivers/cxl/core/Makefile
+++ b/drivers/cxl/core/Makefile
@@ -14,9 +14,9 @@ cxl_core-y += pci.o
 cxl_core-y += hdm.o
 cxl_core-y += pmu.o
 cxl_core-y += cdat.o
-cxl_core-y += ras.o
 cxl_core-$(CONFIG_TRACING) += trace.o
 cxl_core-$(CONFIG_CXL_REGION) += region.o
 cxl_core-$(CONFIG_CXL_MCE) += mce.o
 cxl_core-$(CONFIG_CXL_FEATURES) += features.o
 cxl_core-$(CONFIG_CXL_EDAC_MEM_FEATURES) += edac.o
+cxl_core-$(CONFIG_CXL_RAS) += ras.o
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 1fb66132b77771..bc818de87ccccf 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -144,8 +144,39 @@ int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c);
 int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
 					struct access_coordinate *c);
 
+#ifdef CONFIG_CXL_RAS
 int cxl_ras_init(void);
 void cxl_ras_exit(void);
+bool cxl_handle_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base);
+void cxl_handle_cor_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base);
+#else
+static inline int cxl_ras_init(void)
+{
+	return 0;
+}
+
+static inline void cxl_ras_exit(void)
+{
+}
+
+static inline bool cxl_handle_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base)
+{
+	return false;
+}
+static inline void cxl_handle_cor_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base) { }
+#endif /* CONFIG_CXL_RAS */
+
+/* Restricted CXL Host specific RAS functions */
+#ifdef CONFIG_CXL_RAS
+void cxl_dport_map_rch_aer(struct cxl_dport *dport);
+void cxl_disable_rch_root_ints(struct cxl_dport *dport);
+void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds);
+#else
+static inline void cxl_dport_map_rch_aer(struct cxl_dport *dport) { }
+static inline void cxl_disable_rch_root_ints(struct cxl_dport *dport) { }
+static inline void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds) { }
+#endif /* CONFIG_CXL_RAS */
+
 int cxl_gpf_port_setup(struct cxl_dport *dport);
 
 struct cxl_hdm;
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 3fb9462954da20..bd7d7e382d041b 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -711,81 +711,8 @@ void read_cdat_data(struct cxl_port *port)
 }
 EXPORT_SYMBOL_NS_GPL(read_cdat_data, "CXL");
 
-static void cxl_handle_cor_ras(struct cxl_dev_state *cxlds,
-			       void __iomem *ras_base)
-{
-	void __iomem *addr;
-	u32 status;
-
-	if (!ras_base)
-		return;
-
-	addr = ras_base + CXL_RAS_CORRECTABLE_STATUS_OFFSET;
-	status = readl(addr);
-	if (status & CXL_RAS_CORRECTABLE_STATUS_MASK) {
-		writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
-		trace_cxl_aer_correctable_error(cxlds->cxlmd, status);
-	}
-}
-
-/* CXL spec rev3.0 8.2.4.16.1 */
-static void header_log_copy(void __iomem *ras_base, u32 *log)
-{
-	void __iomem *addr;
-	u32 *log_addr;
-	int i, log_u32_size = CXL_HEADERLOG_SIZE / sizeof(u32);
-
-	addr = ras_base + CXL_RAS_HEADER_LOG_OFFSET;
-	log_addr = log;
-
-	for (i = 0; i < log_u32_size; i++) {
-		*log_addr = readl(addr);
-		log_addr++;
-		addr += sizeof(u32);
-	}
-}
-
-/*
- * Log the state of the RAS status registers and prepare them to log the
- * next error status. Return 1 if reset needed.
- */
-static bool cxl_handle_ras(struct cxl_dev_state *cxlds,
-			   void __iomem *ras_base)
-{
-	u32 hl[CXL_HEADERLOG_SIZE_U32];
-	void __iomem *addr;
-	u32 status;
-	u32 fe;
-
-	if (!ras_base)
-		return false;
-
-	addr = ras_base + CXL_RAS_UNCORRECTABLE_STATUS_OFFSET;
-	status = readl(addr);
-	if (!(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK))
-		return false;
-
-	/* If multiple errors, log header points to first error from ctrl reg */
-	if (hweight32(status) > 1) {
-		void __iomem *rcc_addr =
-			ras_base + CXL_RAS_CAP_CONTROL_OFFSET;
-
-		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
-				   readl(rcc_addr)));
-	} else {
-		fe = status;
-	}
-
-	header_log_copy(ras_base, hl);
-	trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe, hl);
-	writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
-
-	return true;
-}
-
-#ifdef CONFIG_PCIEAER_CXL
-
-static void cxl_dport_map_rch_aer(struct cxl_dport *dport)
+#ifdef CONFIG_CXL_RAS
+void cxl_dport_map_rch_aer(struct cxl_dport *dport)
 {
 	resource_size_t aer_phys;
 	struct device *host;
@@ -800,19 +727,7 @@ static void cxl_dport_map_rch_aer(struct cxl_dport *dport)
 	}
 }
 
-static void cxl_dport_map_ras(struct cxl_dport *dport)
-{
-	struct cxl_register_map *map = &dport->reg_map;
-	struct device *dev = dport->dport_dev;
-
-	if (!map->component_map.ras.valid)
-		dev_dbg(dev, "RAS registers not found\n");
-	else if (cxl_map_component_regs(map, &dport->regs.component,
-					BIT(CXL_CM_CAP_CAP_ID_RAS)))
-		dev_dbg(dev, "Failed to map RAS capability.\n");
-}
-
-static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
+void cxl_disable_rch_root_ints(struct cxl_dport *dport)
 {
 	void __iomem *aer_base = dport->regs.dport_aer;
 	u32 aer_cmd_mask, aer_cmd;
@@ -836,28 +751,6 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
 	writel(aer_cmd, aer_base + PCI_ERR_ROOT_COMMAND);
 }
 
-/**
- * cxl_dport_init_ras_reporting - Setup CXL RAS report on this dport
- * @dport: the cxl_dport that needs to be initialized
- * @host: host device for devm operations
- */
-void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
-{
-	dport->reg_map.host = host;
-	cxl_dport_map_ras(dport);
-
-	if (dport->rch) {
-		struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport->dport_dev);
-
-		if (!host_bridge->native_aer)
-			return;
-
-		cxl_dport_map_rch_aer(dport);
-		cxl_disable_rch_root_ints(dport);
-	}
-}
-EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
-
 /*
  * Copy the AER capability registers using 32 bit read accesses.
  * This is necessary because RCRB AER capability is MMIO mapped. Clear the
@@ -906,7 +799,7 @@ static bool cxl_rch_get_aer_severity(struct aer_capability_regs *aer_regs,
 	return false;
 }
 
-static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds)
+void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds)
 {
 	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
 	struct aer_capability_regs aer_regs;
@@ -931,82 +824,8 @@ static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds)
 	else
 		cxl_handle_ras(cxlds, dport->regs.ras);
 }
-
-#else
-static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds) { }
 #endif
 
-void cxl_cor_error_detected(struct pci_dev *pdev)
-{
-	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
-	struct device *dev = &cxlds->cxlmd->dev;
-
-	scoped_guard(device, dev) {
-		if (!dev->driver) {
-			dev_warn(&pdev->dev,
-				 "%s: memdev disabled, abort error handling\n",
-				 dev_name(dev));
-			return;
-		}
-
-		if (cxlds->rcd)
-			cxl_handle_rdport_errors(cxlds);
-
-		cxl_handle_cor_ras(cxlds, cxlds->regs.ras);
-	}
-}
-EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, "CXL");
-
-pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
-				    pci_channel_state_t state)
-{
-	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
-	struct cxl_memdev *cxlmd = cxlds->cxlmd;
-	struct device *dev = &cxlmd->dev;
-	bool ue;
-
-	scoped_guard(device, dev) {
-		if (!dev->driver) {
-			dev_warn(&pdev->dev,
-				 "%s: memdev disabled, abort error handling\n",
-				 dev_name(dev));
-			return PCI_ERS_RESULT_DISCONNECT;
-		}
-
-		if (cxlds->rcd)
-			cxl_handle_rdport_errors(cxlds);
-		/*
-		 * A frozen channel indicates an impending reset which is fatal to
-		 * CXL.mem operation, and will likely crash the system. On the off
-		 * chance the situation is recoverable dump the status of the RAS
-		 * capability registers and bounce the active state of the memdev.
-		 */
-		ue = cxl_handle_ras(cxlds, cxlds->regs.ras);
-	}
-
-
-	switch (state) {
-	case pci_channel_io_normal:
-		if (ue) {
-			device_release_driver(dev);
-			return PCI_ERS_RESULT_NEED_RESET;
-		}
-		return PCI_ERS_RESULT_CAN_RECOVER;
-	case pci_channel_io_frozen:
-		dev_warn(&pdev->dev,
-			 "%s: frozen state error detected, disable CXL.mem\n",
-			 dev_name(dev));
-		device_release_driver(dev);
-		return PCI_ERS_RESULT_NEED_RESET;
-	case pci_channel_io_perm_failure:
-		dev_warn(&pdev->dev,
-			 "failure state error detected, request disconnect\n");
-		return PCI_ERS_RESULT_DISCONNECT;
-	}
-	return PCI_ERS_RESULT_NEED_RESET;
-}
-EXPORT_SYMBOL_NS_GPL(cxl_error_detected, "CXL");
-
 static int cxl_flit_size(struct pci_dev *pdev)
 {
 	if (cxl_pci_flit_256(pdev))
diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
index 2731ba3a07993c..b933030b8e1e77 100644
--- a/drivers/cxl/core/ras.c
+++ b/drivers/cxl/core/ras.c
@@ -5,6 +5,7 @@
 #include <linux/aer.h>
 #include <cxl/event.h>
 #include <cxlmem.h>
+#include <cxlpci.h>
 #include "trace.h"
 
 static void cxl_cper_trace_corr_port_prot_err(struct pci_dev *pdev,
@@ -124,3 +125,178 @@ 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)
+{
+	struct cxl_register_map *map = &dport->reg_map;
+	struct device *dev = dport->dport_dev;
+
+	if (!map->component_map.ras.valid)
+		dev_dbg(dev, "RAS registers not found\n");
+	else if (cxl_map_component_regs(map, &dport->regs.component,
+					BIT(CXL_CM_CAP_CAP_ID_RAS)))
+		dev_dbg(dev, "Failed to map RAS capability.\n");
+}
+
+/**
+ * cxl_dport_init_ras_reporting - Setup CXL RAS report on this dport
+ * @dport: the cxl_dport that needs to be initialized
+ * @host: host device for devm operations
+ */
+void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
+{
+	dport->reg_map.host = host;
+	cxl_dport_map_ras(dport);
+
+	if (dport->rch) {
+		struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport->dport_dev);
+
+		if (!host_bridge->native_aer)
+			return;
+
+		cxl_dport_map_rch_aer(dport);
+		cxl_disable_rch_root_ints(dport);
+	}
+}
+EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
+
+void cxl_handle_cor_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base)
+{
+	void __iomem *addr;
+	u32 status;
+
+	if (!ras_base)
+		return;
+
+	addr = ras_base + CXL_RAS_CORRECTABLE_STATUS_OFFSET;
+	status = readl(addr);
+	if (status & CXL_RAS_CORRECTABLE_STATUS_MASK) {
+		writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
+		trace_cxl_aer_correctable_error(cxlds->cxlmd, status);
+	}
+}
+
+/* CXL spec rev3.0 8.2.4.16.1 */
+static void header_log_copy(void __iomem *ras_base, u32 *log)
+{
+	void __iomem *addr;
+	u32 *log_addr;
+	int i, log_u32_size = CXL_HEADERLOG_SIZE / sizeof(u32);
+
+	addr = ras_base + CXL_RAS_HEADER_LOG_OFFSET;
+	log_addr = log;
+
+	for (i = 0; i < log_u32_size; i++) {
+		*log_addr = readl(addr);
+		log_addr++;
+		addr += sizeof(u32);
+	}
+}
+
+/*
+ * Log the state of the RAS status registers and prepare them to log the
+ * next error status. Return 1 if reset needed.
+ */
+bool cxl_handle_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base)
+{
+	u32 hl[CXL_HEADERLOG_SIZE_U32];
+	void __iomem *addr;
+	u32 status;
+	u32 fe;
+
+	if (!ras_base)
+		return false;
+
+	addr = ras_base + CXL_RAS_UNCORRECTABLE_STATUS_OFFSET;
+	status = readl(addr);
+	if (!(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK))
+		return false;
+
+	/* If multiple errors, log header points to first error from ctrl reg */
+	if (hweight32(status) > 1) {
+		void __iomem *rcc_addr =
+			ras_base + CXL_RAS_CAP_CONTROL_OFFSET;
+
+		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
+				   readl(rcc_addr)));
+	} else {
+		fe = status;
+	}
+
+	header_log_copy(ras_base, hl);
+	trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe, hl);
+	writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
+
+	return true;
+}
+
+void cxl_cor_error_detected(struct pci_dev *pdev)
+{
+	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	struct device *dev = &cxlds->cxlmd->dev;
+
+	scoped_guard(device, dev) {
+		if (!dev->driver) {
+			dev_warn(&pdev->dev,
+				 "%s: memdev disabled, abort error handling\n",
+				 dev_name(dev));
+			return;
+		}
+
+		if (cxlds->rcd)
+			cxl_handle_rdport_errors(cxlds);
+
+		cxl_handle_cor_ras(cxlds, cxlds->regs.ras);
+	}
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, "CXL");
+
+pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
+				    pci_channel_state_t state)
+{
+	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	struct cxl_memdev *cxlmd = cxlds->cxlmd;
+	struct device *dev = &cxlmd->dev;
+	bool ue;
+
+	scoped_guard(device, dev) {
+		if (!dev->driver) {
+			dev_warn(&pdev->dev,
+				 "%s: memdev disabled, abort error handling\n",
+				 dev_name(dev));
+			return PCI_ERS_RESULT_DISCONNECT;
+		}
+
+		if (cxlds->rcd)
+			cxl_handle_rdport_errors(cxlds);
+		/*
+		 * A frozen channel indicates an impending reset which is fatal to
+		 * CXL.mem operation, and will likely crash the system. On the off
+		 * chance the situation is recoverable dump the status of the RAS
+		 * capability registers and bounce the active state of the memdev.
+		 */
+		ue = cxl_handle_ras(cxlds, cxlds->regs.ras);
+	}
+
+
+	switch (state) {
+	case pci_channel_io_normal:
+		if (ue) {
+			device_release_driver(dev);
+			return PCI_ERS_RESULT_NEED_RESET;
+		}
+		return PCI_ERS_RESULT_CAN_RECOVER;
+	case pci_channel_io_frozen:
+		dev_warn(&pdev->dev,
+			 "%s: frozen state error detected, disable CXL.mem\n",
+			 dev_name(dev));
+		device_release_driver(dev);
+		return PCI_ERS_RESULT_NEED_RESET;
+	case pci_channel_io_perm_failure:
+		dev_warn(&pdev->dev,
+			 "failure state error detected, request disconnect\n");
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_error_detected, "CXL");
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 3a794278cc7fef..05c49133e9e035 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -781,14 +781,6 @@ struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port,
 					 struct device *dport_dev, int port_id,
 					 resource_size_t rcrb);
 
-#ifdef CONFIG_PCIEAER_CXL
-void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport);
-void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host);
-#else
-static inline void cxl_dport_init_ras_reporting(struct cxl_dport *dport,
-						struct device *host) { }
-#endif
-
 struct cxl_decoder *to_cxl_decoder(struct device *dev);
 struct cxl_root_decoder *to_cxl_root_decoder(struct device *dev);
 struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev);
diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
index 7ae621e618e79a..970e84cf49e9ac 100644
--- a/drivers/cxl/cxlpci.h
+++ b/drivers/cxl/cxlpci.h
@@ -130,7 +130,23 @@ static inline bool cxl_pci_flit_256(struct pci_dev *pdev)
 int devm_cxl_port_enumerate_dports(struct cxl_port *port);
 struct cxl_dev_state;
 void read_cdat_data(struct cxl_port *port);
+
+#ifdef CONFIG_CXL_RAS
 void cxl_cor_error_detected(struct pci_dev *pdev);
 pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
 				    pci_channel_state_t state);
+void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host);
+#else
+static inline void cxl_cor_error_detected(struct pci_dev *pdev) { }
+
+static inline pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
+						  pci_channel_state_t state)
+{
+	return PCI_ERS_RESULT_NONE;
+}
+
+static inline void cxl_dport_init_ras_reporting(struct cxl_dport *dport,
+						struct device *host) { }
+#endif
+
 #endif /* __CXL_PCI_H__ */
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index 0d5ce4b74b9f7d..927fbb6c061f3a 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -58,12 +58,12 @@ cxl_core-y += $(CXL_CORE_SRC)/pci.o
 cxl_core-y += $(CXL_CORE_SRC)/hdm.o
 cxl_core-y += $(CXL_CORE_SRC)/pmu.o
 cxl_core-y += $(CXL_CORE_SRC)/cdat.o
-cxl_core-y += $(CXL_CORE_SRC)/ras.o
 cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o
 cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
 cxl_core-$(CONFIG_CXL_MCE) += $(CXL_CORE_SRC)/mce.o
 cxl_core-$(CONFIG_CXL_FEATURES) += $(CXL_CORE_SRC)/features.o
 cxl_core-$(CONFIG_CXL_EDAC_MEM_FEATURES) += $(CXL_CORE_SRC)/edac.o
+cxl_core-$(CONFIG_CXL_RAS) += $(CXL_CORE_SRC)/ras.o
 cxl_core-y += config_check.o
 cxl_core-y += cxl_core_test.o
 cxl_core-y += cxl_core_exports.o
-- 
2.53.0

[PATCH 6.18.y 4/4] cxl: Fix CXL_HEADERLOG_SIZE to match RAS Capability size

[Sasha Levin]

From: Terry Bowman <terry.bowman@amd.com>

[ Upstream commit c268f949e219f9e179558e836f457f6c5fbec416 ]

The CXL r4.0 8.2.4.17.7 RAS Capability Structure has total length 0x58
bytes (CXL_RAS_CAPABILITY_LENGTH); the Header Log occupies the trailing
64 bytes at offset 0x18.  CXL_HEADERLOG_SIZE was defined as SZ_512,
eight times the actual on-device size.

header_log_copy() reads CXL_HEADERLOG_SIZE_U32 (128) dwords from the
RAS capability iomap, overrunning the 88-byte mapping by 448 bytes.
The cxl_aer_uncorrectable_error trace event memcpy()s CXL_HEADERLOG_SIZE
(512) bytes from its source.  For the CPER caller the source is
struct cxl_ras_capability_regs::header_log[16] (64 bytes) embedded in a
stack-local cxl_cper_prot_err_work_data, so the memcpy reads 448 bytes
of kernel stack into the trace event ring buffer where userspace can
read it via tracefs.

Set CXL_HEADERLOG_SIZE to 64 and derive CXL_HEADERLOG_SIZE_U32 from it,
bringing all iomap readers into agreement on 16 dwords.  Userspace tools
such as rasdaemon have grown a dependency on the buggy 512-byte (128 u32)
header_log layout in the cxl_aer_uncorrectable_error trace event.  Add
CXL_HEADERLOG_TRACE_SIZE_U32 = 128 and use it for the trace event
__array and its memcpy to preserve that ABI.  Both callers now pass a
zero-filled u32[CXL_HEADERLOG_TRACE_SIZE_U32] staging buffer with only
the first CXL_HEADERLOG_SIZE_U32 (16) entries populated from hardware;
the remaining 112 u32s are zero-padded, keeping the 512-byte trace ring
buffer layout intact.

[ dj: Replaced 64 with SZ_64 per RichardC ]

Fixes: 36f257e3b0ba ("acpi/ghes, cxl/pci: Process CXL CPER Protocol Errors")
Fixes: 2905cb5236cb ("cxl/pci: Add (hopeful) error handling support")
Cc: stable@vger.kernel.org
Reported-by: Sashiko
Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Ben Cheatham <benjamin.cheatham@amd.com>
Reviewed-by: Richard Cheng <icheng@nvidia.com>
Link: https://patch.msgid.link/20260605180610.2249458-1-terry.bowman@amd.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/cxl/core/ras.c   | 27 ++++++++++++++++++++-------
 drivers/cxl/core/trace.h | 24 ++++++++++++++++--------
 drivers/cxl/cxl.h        | 14 ++++++++++++--
 3 files changed, 48 insertions(+), 17 deletions(-)

diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
index b933030b8e1e77..7056a79bff4d14 100644
--- a/drivers/cxl/core/ras.c
+++ b/drivers/cxl/core/ras.c
@@ -8,6 +8,10 @@
 #include <cxlpci.h>
 #include "trace.h"
 
+/* Check that UCE header definition is maintained to keep ABI intact  */
+static_assert(CXL_HEADERLOG_TRACE_SIZE_U32 == 128,
+	      "rasdaemon ABI requires exactly 128 u32s");
+
 static void cxl_cper_trace_corr_port_prot_err(struct pci_dev *pdev,
 					      struct cxl_ras_capability_regs ras_cap)
 {
@@ -19,6 +23,7 @@ static void cxl_cper_trace_corr_port_prot_err(struct pci_dev *pdev,
 static void cxl_cper_trace_uncorr_port_prot_err(struct pci_dev *pdev,
 						struct cxl_ras_capability_regs ras_cap)
 {
+	u32 hl[CXL_HEADERLOG_TRACE_SIZE_U32] = {};
 	u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask;
 	u32 fe;
 
@@ -28,8 +33,8 @@ static void cxl_cper_trace_uncorr_port_prot_err(struct pci_dev *pdev,
 	else
 		fe = status;
 
-	trace_cxl_port_aer_uncorrectable_error(&pdev->dev, status, fe,
-					       ras_cap.header_log);
+	memcpy(hl, ras_cap.header_log, CXL_HEADERLOG_SIZE);
+	trace_cxl_port_aer_uncorrectable_error(&pdev->dev, status, fe, hl);
 }
 
 static void cxl_cper_trace_corr_prot_err(struct cxl_memdev *cxlmd,
@@ -44,6 +49,7 @@ static void
 cxl_cper_trace_uncorr_prot_err(struct cxl_memdev *cxlmd,
 			       struct cxl_ras_capability_regs ras_cap)
 {
+	u32 hl[CXL_HEADERLOG_TRACE_SIZE_U32] = {};
 	u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask;
 	u32 fe;
 
@@ -53,8 +59,15 @@ cxl_cper_trace_uncorr_prot_err(struct cxl_memdev *cxlmd,
 	else
 		fe = status;
 
-	trace_cxl_aer_uncorrectable_error(cxlmd, status, fe,
-					  ras_cap.header_log);
+	/*
+	 * ras_cap.header_log[] holds CXL_HEADERLOG_SIZE_U32 (16) hardware
+	 * dwords.  Copy them into the front of a zero-filled
+	 * CXL_HEADERLOG_TRACE_SIZE_U32 (128) u32 staging buffer so the trace
+	 * event memcpy sees a full 512-byte source and the userspace ABI
+	 * (rasdaemon) is preserved.
+	 */
+	memcpy(hl, ras_cap.header_log, CXL_HEADERLOG_SIZE);
+	trace_cxl_aer_uncorrectable_error(cxlmd, status, fe, hl);
 }
 
 static int match_memdev_by_parent(struct device *dev, const void *uport)
@@ -181,12 +194,12 @@ static void header_log_copy(void __iomem *ras_base, u32 *log)
 {
 	void __iomem *addr;
 	u32 *log_addr;
-	int i, log_u32_size = CXL_HEADERLOG_SIZE / sizeof(u32);
+	int i;
 
 	addr = ras_base + CXL_RAS_HEADER_LOG_OFFSET;
 	log_addr = log;
 
-	for (i = 0; i < log_u32_size; i++) {
+	for (i = 0; i < CXL_HEADERLOG_SIZE_U32; i++) {
 		*log_addr = readl(addr);
 		log_addr++;
 		addr += sizeof(u32);
@@ -199,7 +212,7 @@ static void header_log_copy(void __iomem *ras_base, u32 *log)
  */
 bool cxl_handle_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base)
 {
-	u32 hl[CXL_HEADERLOG_SIZE_U32];
+	u32 hl[CXL_HEADERLOG_TRACE_SIZE_U32] = {};
 	void __iomem *addr;
 	u32 status;
 	u32 fe;
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index a972e4ef193686..d37876096dd7cb 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -56,7 +56,7 @@ TRACE_EVENT(cxl_port_aer_uncorrectable_error,
 		__string(host, dev_name(dev->parent))
 		__field(u32, status)
 		__field(u32, first_error)
-		__array(u32, header_log, CXL_HEADERLOG_SIZE_U32)
+		__array(u32, header_log, CXL_HEADERLOG_TRACE_SIZE_U32)
 	),
 	TP_fast_assign(
 		__assign_str(device);
@@ -64,10 +64,14 @@ TRACE_EVENT(cxl_port_aer_uncorrectable_error,
 		__entry->status = status;
 		__entry->first_error = fe;
 		/*
-		 * Embed the 512B headerlog data for user app retrieval and
-		 * parsing, but no need to print this in the trace buffer.
+		 * Embed headerlog data for user app retrieval and parsing,
+		 * but no need to print in the trace buffer. Only
+		 * CXL_HEADERLOG_SIZE_U32 (16) dwords are hardware data;
+		 * the remaining entries preserve the 512-byte ABI layout
+		 * rasdaemon depends on and are zero-filled by the caller.
 		 */
-		memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE);
+		memcpy(__entry->header_log, hl,
+			CXL_HEADERLOG_TRACE_SIZE_U32 * sizeof(u32));
 	),
 	TP_printk("device=%s host=%s status: '%s' first_error: '%s'",
 		  __get_str(device), __get_str(host),
@@ -85,7 +89,7 @@ TRACE_EVENT(cxl_aer_uncorrectable_error,
 		__field(u64, serial)
 		__field(u32, status)
 		__field(u32, first_error)
-		__array(u32, header_log, CXL_HEADERLOG_SIZE_U32)
+		__array(u32, header_log, CXL_HEADERLOG_TRACE_SIZE_U32)
 	),
 	TP_fast_assign(
 		__assign_str(memdev);
@@ -94,10 +98,14 @@ TRACE_EVENT(cxl_aer_uncorrectable_error,
 		__entry->status = status;
 		__entry->first_error = fe;
 		/*
-		 * Embed the 512B headerlog data for user app retrieval and
-		 * parsing, but no need to print this in the trace buffer.
+		 * Embed headerlog data for user app retrieval and parsing,
+		 * but no need to print in the trace buffer. Only
+		 * CXL_HEADERLOG_SIZE_U32 (16) dwords are hardware data;
+		 * the remaining entries preserve the 512-byte ABI layout
+		 * rasdaemon depends on and are zero-filled by the caller.
 		 */
-		memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE);
+		memcpy(__entry->header_log, hl,
+			CXL_HEADERLOG_TRACE_SIZE_U32 * sizeof(u32));
 	),
 	TP_printk("memdev=%s host=%s serial=%lld: status: '%s' first_error: '%s'",
 		  __get_str(memdev), __get_str(host), __entry->serial,
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 05c49133e9e035..a5b00c3b044477 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -148,8 +148,18 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
 #define CXL_RAS_CAP_CONTROL_FE_MASK GENMASK(5, 0)
 #define CXL_RAS_HEADER_LOG_OFFSET 0x18
 #define CXL_RAS_CAPABILITY_LENGTH 0x58
-#define CXL_HEADERLOG_SIZE SZ_512
-#define CXL_HEADERLOG_SIZE_U32 SZ_512 / sizeof(u32)
+#define CXL_HEADERLOG_SIZE SZ_64
+#define CXL_HEADERLOG_SIZE_U32 (CXL_HEADERLOG_SIZE / sizeof(u32))
+
+/*
+ * The RAS UCE trace event header array was originally sized at SZ_512/sizeof(u32)
+ * = 128 u32s due to a bug. Userspace tools (rasdaemon) have grown a dependency
+ * on that 512-byte layout. Keep the trace array at 128 u32s to preserve the
+ * ABI; only CXL_HEADERLOG_SIZE_U32 (16) dwords are valid hardware data, the
+ * remainder are zero-filled.
+ */
+#define CXL_HEADERLOG_TRACE_SIZE SZ_512
+#define CXL_HEADERLOG_TRACE_SIZE_U32 (CXL_HEADERLOG_TRACE_SIZE / sizeof(u32))
 
 /* CXL 2.0 8.2.8.1 Device Capabilities Array Register */
 #define CXLDEV_CAP_ARRAY_OFFSET 0x0
-- 
2.53.0