* [PATCH 6.12.y 3/4] cxl/pci: Remove CXL VH handling in CONFIG_PCIEAER_CXL conditional blocks from core/pci.c
2026-09-04 15:28 ` [PATCH 6.12.y 1/4] cxl/pci: Remove unnecessary CXL Endpoint handling helper functions Sasha Levin
2026-09-04 15:28 ` [PATCH 6.12.y 2/4] cxl/pci: Remove unnecessary CXL RCH " Sasha Levin
@ 2026-09-04 15:28 ` Sasha Levin
2026-09-04 15:28 ` [PATCH 6.12.y 4/4] cxl/ras: Fix cxl_rch_get_aer_info() out-of-bounds AER register read Sasha Levin
2 siblings, 0 replies; 5+ messages in thread
From: Sasha Levin @ 2026-09-04 15:28 UTC (permalink / raw)
To: stable
Cc: Dave Jiang, Robert Richter, Joshua Hahn, Jonathan Cameron,
Alison Schofield, Terry Bowman, Dan Williams, 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>
[ sashal: Reduced backport -- upstream 7ff8b1d60881c touches 8 file(s), this
backport carries 6. Not backported here:
drivers/cxl/cxl.h
drivers/cxl/cxlpci.h
drivers/cxl/Kconfig
This note is generated from the file lists only; see the resolution record
for the reasoning. ]
Stable-dep-of: 29458e62d082 ("cxl/ras: Fix cxl_rch_get_aer_info() out-of-bounds AER register read")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/cxl/core/Makefile | 2 +
drivers/cxl/core/core.h | 12 ++
drivers/cxl/core/pci.c | 296 -------------------------------------
drivers/cxl/core/ras.c | 186 +++++++++++++++++++++++
drivers/cxl/core/ras_rch.c | 121 +++++++++++++++
tools/testing/cxl/Kbuild | 2 +
6 files changed, 323 insertions(+), 296 deletions(-)
create mode 100644 drivers/cxl/core/ras.c
create mode 100644 drivers/cxl/core/ras_rch.c
diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile
index 9259bcc6773c8..c673775cd1917 100644
--- a/drivers/cxl/core/Makefile
+++ b/drivers/cxl/core/Makefile
@@ -14,5 +14,7 @@ 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-$(CONFIG_PCIEAER_CXL) += ras_rch.o
cxl_core-$(CONFIG_TRACING) += trace.o
cxl_core-$(CONFIG_CXL_REGION) += region.o
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 0c62b4069ba00..efe567c679a20 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -110,4 +110,16 @@ bool cxl_need_node_perf_attrs_update(int nid);
int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
struct access_coordinate *c);
+struct cxl_dev_state;
+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);
+
+#ifdef CONFIG_PCIEAER_CXL
+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_handle_rdport_errors(struct cxl_dev_state *cxlds) { }
+#endif
+
#endif /* __CXL_CORE_H__ */
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 42fc18878b0d6..caecc07665057 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -650,302 +650,6 @@ 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
new file mode 100644
index 0000000000000..6256b145a517f
--- /dev/null
+++ b/drivers/cxl/core/ras.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2021 Intel Corporation. All rights reserved. */
+
+#include <linux/aer.h>
+#include <cxlmem.h>
+#include <cxlpci.h>
+#include "core.h"
+#include "trace.h"
+
+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;
+}
+
+#ifdef CONFIG_PCIEAER_CXL
+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);
+#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);
diff --git a/drivers/cxl/core/ras_rch.c b/drivers/cxl/core/ras_rch.c
new file mode 100644
index 0000000000000..ed58afd18ecc9
--- /dev/null
+++ b/drivers/cxl/core/ras_rch.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2025 AMD Corporation. All rights reserved. */
+
+#include <linux/types.h>
+#include <linux/aer.h>
+#include "cxl.h"
+#include "core.h"
+#include "cxlmem.h"
+
+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));
+ }
+}
+
+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);
+}
+
+/*
+ * 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;
+}
+
+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);
+}
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index b1256fee3567f..773e56e3aa1d4 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -61,6 +61,8 @@ 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_PCIEAER_CXL) += $(CXL_CORE_SRC)/ras_rch.o
cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o
cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
cxl_core-y += config_check.o
--
2.53.0
^ permalink raw reply related [flat|nested] 5+ messages in thread