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>
Subject: [PATCH v11 05/23] cxl: Move CXL driver RCH error handling into CONFIG_CXL_RCH_RAS conditional block
Date: Tue, 26 Aug 2025 20:35:20 -0500 [thread overview]
Message-ID: <20250827013539.903682-6-terry.bowman@amd.com> (raw)
In-Reply-To: <20250827013539.903682-1-terry.bowman@amd.com>
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>
---
v10->v11:
- New patch
---
drivers/cxl/core/ras.c | 175 +++++++++++++++++++++--------------------
1 file changed, 90 insertions(+), 85 deletions(-)
diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
index 0875ce8116ff..f42f9a255ef8 100644
--- a/drivers/cxl/core/ras.c
+++ b/drivers/cxl/core/ras.c
@@ -126,6 +126,7 @@ void cxl_ras_exit(void)
cancel_work_sync(&cxl_cper_prot_err_work);
}
+#ifdef CONFIG_CXL_RCH_RAS
static void cxl_dport_map_rch_aer(struct cxl_dport *dport)
{
resource_size_t aer_phys;
@@ -141,18 +142,6 @@ 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 __iomem *aer_base = dport->regs.dport_aer;
@@ -177,6 +166,95 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
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;
+}
+
+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 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
+
+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
@@ -270,79 +348,6 @@ static bool cxl_handle_ras(struct cxl_dev_state *cxlds, void __iomem *ras_base)
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);
--
2.51.0.rc2.21.ge5ab6b3e5a
next prev parent reply other threads:[~2025-08-27 1:36 UTC|newest]
Thread overview: 89+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-27 1:35 [PATCH v11 00/23] Enable CXL PCIe Port Protocol Error handling and logging Terry Bowman
2025-08-27 1:35 ` [PATCH v11 01/23] cxl: Remove ifdef blocks of CONFIG_PCIEAER_CXL from core/pci.c Terry Bowman
2025-08-27 1:35 ` [PATCH v11 02/23] CXL/AER: Remove CONFIG_PCIEAER_CXL and replace with CONFIG_CXL_RAS Terry Bowman
2025-08-29 15:24 ` Jonathan Cameron
2025-08-29 18:16 ` Sathyanarayanan Kuppuswamy
2025-08-27 1:35 ` [PATCH v11 03/23] cxl/pci: Remove unnecessary CXL Endpoint handling helper functions Terry Bowman
2025-08-28 15:28 ` Dave Jiang
2025-08-27 1:35 ` [PATCH v11 04/23] cxl/pci: Remove unnecessary CXL RCH " Terry Bowman
2025-08-28 8:35 ` Alejandro Lucero Palau
2025-08-28 17:32 ` Dave Jiang
2025-08-27 1:35 ` Terry Bowman [this message]
2025-08-28 8:57 ` [PATCH v11 05/23] cxl: Move CXL driver RCH error handling into CONFIG_CXL_RCH_RAS conditional block Alejandro Lucero Palau
2025-09-10 16:43 ` Bowman, Terry
2025-08-29 15:33 ` Jonathan Cameron
2025-09-11 17:48 ` Bowman, Terry
2025-09-11 19:41 ` Dave Jiang
2025-09-15 13:32 ` Bowman, Terry
2025-08-27 1:35 ` [PATCH v11 06/23] CXL/AER: Introduce rch_aer.c into AER driver for handling CXL RCH errors Terry Bowman
2025-08-28 20:53 ` Dave Jiang
2025-08-29 8:39 ` Lukas Wunner
2025-09-10 17:01 ` Bowman, Terry
2025-09-10 17:26 ` Dave Jiang
2025-09-12 13:59 ` Bowman, Terry
2025-09-12 19:09 ` Lukas Wunner
2025-09-10 16:56 ` Bowman, Terry
2025-09-10 12:43 ` Jonathan Cameron
2025-08-27 1:35 ` [PATCH v11 07/23] CXL/PCI: Move CXL DVSEC definitions into uapi/linux/pci_regs.h Terry Bowman
2025-08-27 14:51 ` Lukas Wunner
2025-08-29 15:42 ` Jonathan Cameron
2025-08-29 15:47 ` Jonathan Cameron
2025-08-28 21:07 ` Dave Jiang
2025-09-10 18:11 ` Bowman, Terry
2025-09-10 20:06 ` Dave Jiang
2025-08-27 1:35 ` [PATCH v11 08/23] PCI/CXL: Introduce pcie_is_cxl() Terry Bowman
2025-08-28 8:18 ` Alejandro Lucero Palau
2025-09-10 16:24 ` Bowman, Terry
2025-09-11 3:48 ` Lukas Wunner
2025-09-10 13:10 ` Jonathan Cameron
2025-08-27 1:35 ` [PATCH v11 09/23] PCI/AER: Report CXL or PCIe bus error type in trace logging Terry Bowman
2025-08-27 7:37 ` Lukas Wunner
2025-09-10 15:26 ` Bowman, Terry
2025-09-10 15:33 ` Lukas Wunner
2025-09-11 5:07 ` Lukas Wunner
2025-08-27 1:35 ` [PATCH v11 10/23] CXL/AER: Update PCI class code check to use FIELD_GET() Terry Bowman
2025-08-29 16:03 ` Jonathan Cameron
2025-09-11 18:18 ` Bowman, Terry
2025-08-27 1:35 ` [PATCH v11 11/23] cxl/pci: Update RAS handler interfaces to also support CXL Ports Terry Bowman
2025-08-27 1:35 ` [PATCH v11 12/23] cxl/pci: Log message if RAS registers are unmapped Terry Bowman
2025-08-27 1:35 ` [PATCH v11 13/23] cxl/pci: Unify CXL trace logging for CXL Endpoints and CXL Ports Terry Bowman
2025-08-27 11:55 ` Shiju Jose
2025-08-29 16:06 ` Jonathan Cameron
2025-08-27 1:35 ` [PATCH v11 14/23] cxl/pci: Update cxl_handle_cor_ras() to return early if no RAS errors Terry Bowman
2025-08-27 1:35 ` [PATCH v11 15/23] cxl/pci: Map CXL Endpoint Port and CXL Switch Port RAS registers Terry Bowman
2025-08-28 23:05 ` Dave Jiang
2025-09-10 18:40 ` Bowman, Terry
2025-08-27 1:35 ` [PATCH v11 16/23] cxl/pci: Introduce CXL Endpoint protocol error handlers Terry Bowman
2025-08-27 7:48 ` Lukas Wunner
2025-09-10 13:23 ` Jonathan Cameron
2025-08-27 1:35 ` [PATCH v11 17/23] CXL/AER: Introduce cxl_aer.c into AER driver for forwarding CXL errors Terry Bowman
2025-08-27 7:56 ` Lukas Wunner
2025-08-27 1:35 ` [PATCH v11 18/23] PCI/AER: Dequeue forwarded CXL error Terry Bowman
2025-08-29 0:43 ` Dave Jiang
2025-08-29 7:10 ` Lukas Wunner
2025-09-16 15:18 ` Bowman, Terry
2025-09-11 14:33 ` Bowman, Terry
2025-09-11 15:41 ` Dave Jiang
2025-09-11 16:47 ` Bowman, Terry
2025-09-11 19:45 ` Dave Jiang
2025-09-10 13:29 ` Jonathan Cameron
2025-08-27 1:35 ` [PATCH v11 19/23] CXL/PCI: Introduce CXL Port protocol error handlers Terry Bowman
2025-08-30 0:17 ` Dave Jiang
2025-08-27 1:35 ` [PATCH v11 20/23] CXL/PCI: Export and rename merge_result() to pci_ers_merge_result() Terry Bowman
2025-08-27 8:04 ` Lukas Wunner
2025-09-10 15:57 ` Bowman, Terry
2025-09-11 3:44 ` Lukas Wunner
2025-08-27 12:19 ` kernel test robot
2025-08-27 1:35 ` [PATCH v11 21/23] CXL/PCI: Introduce CXL uncorrectable protocol error recovery Terry Bowman
2025-09-03 22:30 ` Dave Jiang
2025-09-11 19:19 ` Bowman, Terry
2025-09-11 19:48 ` Dave Jiang
2025-09-10 13:33 ` Jonathan Cameron
2025-08-27 1:35 ` [PATCH v11 22/23] CXL/PCI: Enable CXL protocol errors during CXL Port probe Terry Bowman
2025-09-03 23:23 ` Dave Jiang
2025-08-27 1:35 ` [PATCH v11 23/23] CXL/PCI: Disable CXL protocol error interrupts during CXL Port cleanup Terry Bowman
2025-09-10 15:07 ` Gregory Price
2025-09-11 20:19 ` Bowman, Terry
2025-08-29 0:07 ` [PATCH v11 00/23] Enable CXL PCIe Port Protocol Error handling and logging Dave Jiang
2025-09-23 3:29 ` Gregory Price
2025-09-23 9:21 ` Srinivasulu Thanneeru
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=20250827013539.903682-6-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
all inboxes | Powered by JetHome®