* [PATCH 6.18.y 1/2] cxl/pci: Move CXL driver's RCH error handling into core/ras_rch.c
2026-09-03 13:54 FAILED: patch "[PATCH] cxl/ras: Fix cxl_rch_get_aer_severity() wrong severity" failed to apply to 6.18-stable tree gregkh
@ 2026-09-08 13:26 ` Sasha Levin
2026-09-08 13:26 ` [PATCH 6.18.y 2/2] cxl/ras: Fix cxl_rch_get_aer_severity() wrong severity register Sasha Levin
0 siblings, 1 reply; 3+ messages in thread
From: Sasha Levin @ 2026-09-08 13:26 UTC (permalink / raw)
To: stable
Cc: Terry Bowman, Jonathan Cameron, Dave Jiang, Dan Williams,
Sasha Levin
From: Terry Bowman <terry.bowman@amd.com>
[ Upstream commit 0ff60f2ec3e4043a442e805f80f8a2445113ec8f ]
Restricted CXL Host (RCH) protocol error handling uses a procedure distinct
from the CXL Virtual Hierarchy (VH) handling. This is because of the
differences in the RCH and VH topologies. Improve the maintainability and
add ability to enable/disable RCH handling.
Move and combine the RCH handling code into a single block conditionally
compiled with the CONFIG_CXL_RCH_RAS kernel config.
Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://patch.msgid.link/20260114182055.46029-9-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: 9d399526128b ("cxl/ras: Fix cxl_rch_get_aer_severity() wrong severity register")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/cxl/core/Makefile | 1 +
drivers/cxl/core/core.h | 11 +---
drivers/cxl/core/pci.c | 115 -----------------------------------
drivers/cxl/core/ras_rch.c | 121 +++++++++++++++++++++++++++++++++++++
tools/testing/cxl/Kbuild | 1 +
5 files changed, 126 insertions(+), 123 deletions(-)
create mode 100644 drivers/cxl/core/ras_rch.c
diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile
index b2930cc54f8ba..b37f38d502d8c 100644
--- a/drivers/cxl/core/Makefile
+++ b/drivers/cxl/core/Makefile
@@ -20,3 +20,4 @@ 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
+cxl_core-$(CONFIG_CXL_RAS) += ras_rch.o
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index bc818de87cccc..724361195057e 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -149,6 +149,9 @@ 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);
+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 int cxl_ras_init(void)
{
@@ -164,14 +167,6 @@ static inline bool cxl_handle_ras(struct cxl_dev_state *cxlds, void __iomem *ras
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) { }
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index bd7d7e382d041..68859eba30db3 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -711,121 +711,6 @@ void read_cdat_data(struct cxl_port *port)
}
EXPORT_SYMBOL_NS_GPL(read_cdat_data, "CXL");
-#ifdef CONFIG_CXL_RAS
-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);
-}
-#endif
-
static int cxl_flit_size(struct pci_dev *pdev)
{
if (cxl_pci_flit_256(pdev))
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 927fbb6c061f3..950335b3c128f 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -64,6 +64,7 @@ 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) += $(CXL_CORE_SRC)/ras.o
+cxl_core-$(CONFIG_CXL_RAS) += $(CXL_CORE_SRC)/ras_rch.o
cxl_core-y += config_check.o
cxl_core-y += cxl_core_test.o
cxl_core-y += cxl_core_exports.o
--
2.53.0
^ permalink raw reply related [flat|nested] 3+ messages in thread