From: Terry Bowman <terry.bowman@amd.com>
To: <dave@stgolabs.net>, <jonathan.cameron@huawei.com>,
<dave.jiang@intel.com>, <alison.schofield@intel.com>,
<dan.j.williams@intel.com>, <bhelgaas@google.com>,
<shiju.jose@huawei.com>, <ming.li@zohomail.com>,
<Smita.KoralahalliChannabasappa@amd.com>, <rrichter@amd.com>,
<dan.carpenter@linaro.org>, <PradeepVineshReddy.Kodamati@amd.com>,
<lukas@wunner.de>, <Benjamin.Cheatham@amd.com>,
<sathyanarayanan.kuppuswamy@linux.intel.com>,
<linux-cxl@vger.kernel.org>, <alucerop@amd.com>,
<ira.weiny@intel.com>
Cc: <linux-kernel@vger.kernel.org>, <linux-pci@vger.kernel.org>,
<terry.bowman@amd.com>
Subject: [PATCH v12 03/25] cxl: Remove ifdef blocks of CONFIG_PCIEAER_CXL from core/pci.c
Date: Thu, 25 Sep 2025 17:34:18 -0500 [thread overview]
Message-ID: <20250925223440.3539069-4-terry.bowman@amd.com> (raw)
In-Reply-To: <20250925223440.3539069-1-terry.bowman@amd.com>
From: Dave Jiang <dave.jiang@intel.com>
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 RAS code from core/pci.c to core/ras.c.
Cc: Robert Richter <rrichter@amd.com>
Cc: Terry Bowman <terry.bowman@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: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Signed-off-by: Terry Bowman <terry.bowman@amd.com>
---
Changes in v11->v12:
- None
Changes in v10->v11:
- New patch
- Updated by Terry Bowman to use (ACPI_APEI_GHES && PCIEAER_CXL) dependency
in Kconfig. Otherwise checks will be reauired for CONFIG_PCIEAER because
AER driver functions are called.
---
drivers/cxl/Kconfig | 3 +
drivers/cxl/core/Makefile | 2 +-
drivers/cxl/core/core.h | 12 ++
drivers/cxl/core/pci.c | 297 --------------------------------------
drivers/cxl/core/ras.c | 289 +++++++++++++++++++++++++++++++++++++
drivers/cxl/cxl.h | 8 -
drivers/cxl/cxlpci.h | 16 ++
tools/testing/cxl/Kbuild | 2 +-
8 files changed, 322 insertions(+), 307 deletions(-)
diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig
index 48b7314afdb8..9246f734e6ca 100644
--- a/drivers/cxl/Kconfig
+++ b/drivers/cxl/Kconfig
@@ -233,4 +233,7 @@ 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 && CXL_PCI
endif
diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile
index 5ad8fef210b5..b2930cc54f8b 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 1fb66132b777..9f4eb7e2feba 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -144,8 +144,20 @@ 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);
+#else
+static inline int cxl_ras_init(void)
+{
+ return 0;
+}
+
+static inline void cxl_ras_exit(void)
+{
+}
+#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 3fb9462954da..a009a51cb0de 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -6,7 +6,6 @@
#include <linux/delay.h>
#include <linux/pci.h>
#include <linux/pci-doe.h>
-#include <linux/aer.h>
#include <cxlpci.h>
#include <cxlmem.h>
#include <cxl.h>
@@ -711,302 +710,6 @@ 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)
-{
- resource_size_t aer_phys;
- struct device *host;
- u16 aer_cap;
-
- aer_cap = cxl_rcrb_to_aer(dport->dport_dev, dport->rcrb.base);
- if (aer_cap) {
- host = dport->reg_map.host;
- aer_phys = aer_cap + dport->rcrb.base;
- dport->regs.dport_aer = devm_cxl_iomap_block(host, aer_phys,
- sizeof(struct aer_capability_regs));
- }
-}
-
-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 __iomem *aer_base = dport->regs.dport_aer;
- u32 aer_cmd_mask, aer_cmd;
-
- if (!aer_base)
- return;
-
- /*
- * Disable RCH root port command interrupts.
- * CXL 3.0 12.2.1.1 - RCH Downstream Port-detected Errors
- *
- * This sequence may not be necessary. CXL spec states disabling
- * the root cmd register's interrupts is required. But, PCI spec
- * shows these are disabled by default on reset.
- */
- aer_cmd_mask = (PCI_ERR_ROOT_CMD_COR_EN |
- PCI_ERR_ROOT_CMD_NONFATAL_EN |
- PCI_ERR_ROOT_CMD_FATAL_EN);
- aer_cmd = readl(aer_base + PCI_ERR_ROOT_COMMAND);
- aer_cmd &= ~aer_cmd_mask;
- 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
- * status after copying.
- *
- * @aer_base: base address of AER capability block in RCRB
- * @aer_regs: destination for copying AER capability
- */
-static bool cxl_rch_get_aer_info(void __iomem *aer_base,
- struct aer_capability_regs *aer_regs)
-{
- int read_cnt = sizeof(struct aer_capability_regs) / sizeof(u32);
- u32 *aer_regs_buf = (u32 *)aer_regs;
- int n;
-
- if (!aer_base)
- return false;
-
- /* Use readl() to guarantee 32-bit accesses */
- for (n = 0; n < read_cnt; n++)
- aer_regs_buf[n] = readl(aer_base + n * sizeof(u32));
-
- writel(aer_regs->uncor_status, aer_base + PCI_ERR_UNCOR_STATUS);
- writel(aer_regs->cor_status, aer_base + PCI_ERR_COR_STATUS);
-
- return true;
-}
-
-/* Get AER severity. Return false if there is no error. */
-static bool cxl_rch_get_aer_severity(struct aer_capability_regs *aer_regs,
- int *severity)
-{
- if (aer_regs->uncor_status & ~aer_regs->uncor_mask) {
- if (aer_regs->uncor_status & PCI_ERR_ROOT_FATAL_RCV)
- *severity = AER_FATAL;
- else
- *severity = AER_NONFATAL;
- return true;
- }
-
- if (aer_regs->cor_status & ~aer_regs->cor_mask) {
- *severity = AER_CORRECTABLE;
- return true;
- }
-
- return false;
-}
-
-static 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;
- struct cxl_dport *dport;
- int severity;
-
- struct cxl_port *port __free(put_cxl_port) =
- cxl_pci_find_port(pdev, &dport);
- if (!port)
- return;
-
- if (!cxl_rch_get_aer_info(dport->regs.dport_aer, &aer_regs))
- return;
-
- if (!cxl_rch_get_aer_severity(&aer_regs, &severity))
- return;
-
- pci_print_aer(pdev, severity, &aer_regs);
-
- if (severity == AER_CORRECTABLE)
- cxl_handle_cor_ras(cxlds, dport->regs.ras);
- 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 2731ba3a0799..0875ce8116ff 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 +125,291 @@ 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_rch_aer(struct cxl_dport *dport)
+{
+ resource_size_t aer_phys;
+ struct device *host;
+ u16 aer_cap;
+
+ aer_cap = cxl_rcrb_to_aer(dport->dport_dev, dport->rcrb.base);
+ if (aer_cap) {
+ host = dport->reg_map.host;
+ aer_phys = aer_cap + dport->rcrb.base;
+ dport->regs.dport_aer = devm_cxl_iomap_block(host, aer_phys,
+ sizeof(struct aer_capability_regs));
+ }
+}
+
+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 __iomem *aer_base = dport->regs.dport_aer;
+ u32 aer_cmd_mask, aer_cmd;
+
+ if (!aer_base)
+ return;
+
+ /*
+ * Disable RCH root port command interrupts.
+ * CXL 3.0 12.2.1.1 - RCH Downstream Port-detected Errors
+ *
+ * This sequence may not be necessary. CXL spec states disabling
+ * the root cmd register's interrupts is required. But, PCI spec
+ * shows these are disabled by default on reset.
+ */
+ aer_cmd_mask = (PCI_ERR_ROOT_CMD_COR_EN |
+ PCI_ERR_ROOT_CMD_NONFATAL_EN |
+ PCI_ERR_ROOT_CMD_FATAL_EN);
+ aer_cmd = readl(aer_base + PCI_ERR_ROOT_COMMAND);
+ aer_cmd &= ~aer_cmd_mask;
+ 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");
+
+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;
+}
+
+/*
+ * Copy the AER capability registers using 32 bit read accesses.
+ * This is necessary because RCRB AER capability is MMIO mapped. Clear the
+ * status after copying.
+ *
+ * @aer_base: base address of AER capability block in RCRB
+ * @aer_regs: destination for copying AER capability
+ */
+static bool cxl_rch_get_aer_info(void __iomem *aer_base,
+ struct aer_capability_regs *aer_regs)
+{
+ int read_cnt = sizeof(struct aer_capability_regs) / sizeof(u32);
+ u32 *aer_regs_buf = (u32 *)aer_regs;
+ int n;
+
+ if (!aer_base)
+ return false;
+
+ /* Use readl() to guarantee 32-bit accesses */
+ for (n = 0; n < read_cnt; n++)
+ aer_regs_buf[n] = readl(aer_base + n * sizeof(u32));
+
+ writel(aer_regs->uncor_status, aer_base + PCI_ERR_UNCOR_STATUS);
+ writel(aer_regs->cor_status, aer_base + PCI_ERR_COR_STATUS);
+
+ return true;
+}
+
+/* Get AER severity. Return false if there is no error. */
+static bool cxl_rch_get_aer_severity(struct aer_capability_regs *aer_regs,
+ int *severity)
+{
+ if (aer_regs->uncor_status & ~aer_regs->uncor_mask) {
+ if (aer_regs->uncor_status & PCI_ERR_ROOT_FATAL_RCV)
+ *severity = AER_FATAL;
+ else
+ *severity = AER_NONFATAL;
+ return true;
+ }
+
+ if (aer_regs->cor_status & ~aer_regs->cor_mask) {
+ *severity = AER_CORRECTABLE;
+ return true;
+ }
+
+ return false;
+}
+
+static 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;
+ struct cxl_dport *dport;
+ int severity;
+
+ struct cxl_port *port __free(put_cxl_port) =
+ cxl_pci_find_port(pdev, &dport);
+ if (!port)
+ return;
+
+ if (!cxl_rch_get_aer_info(dport->regs.dport_aer, &aer_regs))
+ return;
+
+ if (!cxl_rch_get_aer_severity(&aer_regs, &severity))
+ return;
+
+ pci_print_aer(pdev, severity, &aer_regs);
+ if (severity == AER_CORRECTABLE)
+ cxl_handle_cor_ras(cxlds, dport->regs.ras);
+ else
+ cxl_handle_ras(cxlds, dport->regs.ras);
+}
+
+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 231ddccf8977..259ed4b676e1 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -776,14 +776,6 @@ 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 7ae621e618e7..970e84cf49e9 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 0d5ce4b74b9f..927fbb6c061f 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
--
2.34.1
next prev parent reply other threads:[~2025-09-25 22:35 UTC|newest]
Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-25 22:34 [PATCH v12 00/25] Enable CXL PCIe Port Protocol Error handling and logging Terry Bowman
2025-09-25 22:34 ` [PATCH v12 01/25] cxl/pci: Remove unnecessary CXL Endpoint handling helper functions Terry Bowman
2025-09-25 22:34 ` [PATCH v12 02/25] cxl/pci: Remove unnecessary CXL RCH " Terry Bowman
2025-10-01 15:09 ` Jonathan Cameron
2025-09-25 22:34 ` Terry Bowman [this message]
2025-10-03 20:11 ` [PATCH v12 03/25] cxl: Remove ifdef blocks of CONFIG_PCIEAER_CXL from core/pci.c Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 04/25] CXL/AER: Remove CONFIG_PCIEAER_CXL and replace with CONFIG_CXL_RAS Terry Bowman
2025-09-25 23:17 ` Dave Jiang
2025-10-01 15:11 ` Jonathan Cameron
2025-10-03 20:11 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 05/25] cxl: Move CXL driver RCH error handling into CONFIG_CXL_RCH_RAS conditional block Terry Bowman
2025-09-25 23:31 ` Dave Jiang
2025-10-01 15:23 ` Jonathan Cameron
2025-10-03 20:11 ` Cheatham, Benjamin
2025-10-06 18:52 ` Bowman, Terry
2025-09-25 22:34 ` [PATCH v12 06/25] CXL/AER: Introduce aer_cxl_rch.c into AER driver for handling CXL RCH errors Terry Bowman
2025-09-25 23:36 ` Dave Jiang
2025-09-26 12:32 ` kernel test robot
2025-10-01 15:42 ` Jonathan Cameron
2025-10-03 20:11 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 07/25] CXL/PCI: Move CXL DVSEC definitions into uapi/linux/pci_regs.h Terry Bowman
2025-09-25 23:53 ` Dave Jiang
2025-10-01 15:58 ` Jonathan Cameron
2025-10-02 15:25 ` Bowman, Terry
2025-10-03 20:11 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 08/25] PCI/CXL: Introduce pcie_is_cxl() Terry Bowman
2025-10-03 20:11 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 09/25] PCI/AER: Report CXL or PCIe bus error type in trace logging Terry Bowman
2025-10-03 20:11 ` Cheatham, Benjamin
2025-10-06 19:59 ` Bowman, Terry
2025-09-25 22:34 ` [PATCH v12 10/25] CXL/AER: Update PCI class code check to use FIELD_GET() Terry Bowman
2025-09-26 0:02 ` Dave Jiang
2025-10-01 16:12 ` Jonathan Cameron
2025-10-02 7:40 ` Lukas Wunner
2025-10-30 17:16 ` Bowman, Terry
2025-10-31 5:30 ` Lukas Wunner
2025-09-25 22:34 ` [PATCH v12 11/25] cxl/pci: Update RAS handler interfaces to also support CXL Ports Terry Bowman
2025-10-03 20:11 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 12/25] cxl/pci: Log message if RAS registers are unmapped Terry Bowman
2025-10-03 20:11 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 13/25] cxl/pci: Unify CXL trace logging for CXL Endpoints and CXL Ports Terry Bowman
2025-09-26 20:44 ` Dave Jiang
2025-09-25 22:34 ` [PATCH v12 14/25] cxl/pci: Update cxl_handle_cor_ras() to return early if no RAS errors Terry Bowman
2025-10-03 20:11 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 15/25] cxl/pci: Map CXL Endpoint Port and CXL Switch Port RAS registers Terry Bowman
2025-09-26 21:10 ` Dave Jiang
2025-10-24 10:25 ` Alejandro Lucero Palau
2025-10-24 17:15 ` Dave Jiang
2025-10-24 19:40 ` Bowman, Terry
2025-10-27 16:33 ` Alejandro Lucero Palau
2025-09-25 22:34 ` [PATCH v12 16/25] CXL/PCI: Introduce PCI_ERS_RESULT_PANIC Terry Bowman
2025-09-26 21:26 ` Dave Jiang
2025-10-01 16:14 ` Jonathan Cameron
2025-10-03 20:11 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 17/25] cxl/pci: Introduce CXL Endpoint protocol error handlers Terry Bowman
2025-09-26 22:04 ` Dave Jiang
2025-09-30 14:06 ` Bowman, Terry
2025-09-30 16:09 ` Dave Jiang
2025-10-03 20:12 ` Cheatham, Benjamin
2025-10-06 21:07 ` Bowman, Terry
2025-09-25 22:34 ` [PATCH v12 18/25] CXL/AER: Introduce aer_cxl_vh.c in AER driver for forwarding CXL errors Terry Bowman
2025-09-26 22:56 ` Dave Jiang
2025-10-03 20:12 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 19/25] cxl: Introduce cxl_pci_drv_bound() to check for bound driver Terry Bowman
2025-09-26 23:02 ` Dave Jiang
2025-10-02 12:27 ` Jonathan Cameron
2025-10-03 20:12 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 20/25] PCI/AER: Dequeue forwarded CXL error Terry Bowman
2025-09-26 23:26 ` Dave Jiang
2025-10-03 20:12 ` Cheatham, Benjamin
2025-10-06 20:17 ` Dave Jiang
2025-09-25 22:34 ` [PATCH v12 21/25] CXL/PCI: Introduce CXL Port protocol error handlers Terry Bowman
2025-09-29 23:32 ` Dave Jiang
2025-10-03 20:12 ` Cheatham, Benjamin
2025-10-06 21:28 ` Bowman, Terry
2025-09-25 22:34 ` [PATCH v12 22/25] CXL/PCI: Export and rename merge_result() to pci_ers_merge_result() Terry Bowman
2025-09-26 15:01 ` kernel test robot
2025-09-26 18:10 ` kernel test robot
2025-09-25 22:34 ` [PATCH v12 23/25] CXL/PCI: Introduce CXL uncorrectable protocol error recovery Terry Bowman
2025-09-30 0:26 ` Dave Jiang
2025-09-30 14:38 ` Bowman, Terry
2025-09-30 16:13 ` Dave Jiang
2025-09-30 16:43 ` Bowman, Terry
2025-09-30 16:46 ` Dave Jiang
2025-10-01 13:58 ` Bowman, Terry
2025-10-01 15:33 ` Dave Jiang
2025-10-03 20:12 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 24/25] CXL/PCI: Enable CXL protocol errors during CXL Port probe Terry Bowman
2025-09-30 0:28 ` Dave Jiang
2025-10-03 20:12 ` Cheatham, Benjamin
2025-09-25 22:34 ` [PATCH v12 25/25] CXL/PCI: Disable CXL protocol error interrupts during CXL Port cleanup Terry Bowman
2025-10-03 20:12 ` Cheatham, Benjamin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250925223440.3539069-4-terry.bowman@amd.com \
--to=terry.bowman@amd.com \
--cc=Benjamin.Cheatham@amd.com \
--cc=PradeepVineshReddy.Kodamati@amd.com \
--cc=Smita.KoralahalliChannabasappa@amd.com \
--cc=alison.schofield@intel.com \
--cc=alucerop@amd.com \
--cc=bhelgaas@google.com \
--cc=dan.carpenter@linaro.org \
--cc=dan.j.williams@intel.com \
--cc=dave.jiang@intel.com \
--cc=dave@stgolabs.net \
--cc=ira.weiny@intel.com \
--cc=jonathan.cameron@huawei.com \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=lukas@wunner.de \
--cc=ming.li@zohomail.com \
--cc=rrichter@amd.com \
--cc=sathyanarayanan.kuppuswamy@linux.intel.com \
--cc=shiju.jose@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox