From: Terry Bowman <terry.bowman@amd.com>
To: <alison.schofield@intel.com>, <vishal.l.verma@intel.com>,
<ira.weiny@intel.com>, <bwidawsk@kernel.org>,
<dan.j.williams@intel.com>, <dave.jiang@intel.com>,
<Jonathan.Cameron@huawei.com>, <linux-cxl@vger.kernel.org>
Cc: <terry.bowman@amd.com>, <rrichter@amd.com>,
<linux-kernel@vger.kernel.org>, <bhelgaas@google.com>
Subject: [PATCH v7 21/27] cxl/pci: Update CXL error logging to use RAS register address
Date: Thu, 22 Jun 2023 15:55:17 -0500 [thread overview]
Message-ID: <20230622205523.85375-22-terry.bowman@amd.com> (raw)
In-Reply-To: <20230622205523.85375-1-terry.bowman@amd.com>
The CXL error handler currently only logs endpoint RAS status. The CXL
topology includes several components providing RAS details to be logged
during error handling.[1] Update the current handler's RAS logging to use a
RAS register address. Also, update the error handler function names to be
consistent with correctable and uncorrecable RAS. This will allow for
adding support to log other CXL component's RAS details in the future.
[1] CXL3.0 Table 8-22 CXL_Capability_ID Assignment
Co-developed-by: Robert Richter <rrichter@amd.com>
Signed-off-by: Robert Richter <rrichter@amd.com>
Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/cxl/core/pci.c | 44 +++++++++++++++++++++++++++++-------------
1 file changed, 31 insertions(+), 13 deletions(-)
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 375f01c6cad6..9cb39835e154 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -665,32 +665,36 @@ void read_cdat_data(struct cxl_port *port)
}
EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
-void cxl_cor_error_detected(struct pci_dev *pdev)
+static void __cxl_handle_cor_ras(struct cxl_dev_state *cxlds,
+ void __iomem *ras_base)
{
- struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
void __iomem *addr;
u32 status;
- if (!cxlds->regs.ras)
+ if (!ras_base)
return;
- addr = cxlds->regs.ras + CXL_RAS_CORRECTABLE_STATUS_OFFSET;
+ 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);
}
}
-EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, CXL);
+
+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(struct cxl_dev_state *cxlds, u32 *log)
+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 = cxlds->regs.ras + CXL_RAS_HEADER_LOG_OFFSET;
+ addr = ras_base + CXL_RAS_HEADER_LOG_OFFSET;
log_addr = log;
for (i = 0; i < log_u32_size; i++) {
@@ -704,17 +708,18 @@ static void header_log_copy(struct cxl_dev_state *cxlds, 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_report_and_clear(struct cxl_dev_state *cxlds)
+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 (!cxlds->regs.ras)
+ if (!ras_base)
return false;
- addr = cxlds->regs.ras + CXL_RAS_UNCORRECTABLE_STATUS_OFFSET;
+ addr = ras_base + CXL_RAS_UNCORRECTABLE_STATUS_OFFSET;
status = readl(addr);
if (!(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK))
return false;
@@ -722,7 +727,7 @@ static bool cxl_report_and_clear(struct cxl_dev_state *cxlds)
/* If multiple errors, log header points to first error from ctrl reg */
if (hweight32(status) > 1) {
void __iomem *rcc_addr =
- cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET;
+ ras_base + CXL_RAS_CAP_CONTROL_OFFSET;
fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
readl(rcc_addr)));
@@ -730,13 +735,26 @@ static bool cxl_report_and_clear(struct cxl_dev_state *cxlds)
fe = status;
}
- header_log_copy(cxlds, hl);
+ 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;
}
+static bool cxl_handle_endpoint_ras(struct cxl_dev_state *cxlds)
+{
+ return __cxl_handle_ras(cxlds, cxlds->regs.ras);
+}
+
+void cxl_cor_error_detected(struct pci_dev *pdev)
+{
+ struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+
+ cxl_handle_endpoint_cor_ras(cxlds);
+}
+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)
{
@@ -751,7 +769,7 @@ 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_report_and_clear(cxlds);
+ ue = cxl_handle_endpoint_ras(cxlds);
switch (state) {
case pci_channel_io_normal:
--
2.34.1
next prev parent reply other threads:[~2023-06-22 21:05 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-22 20:54 [PATCH v7 00/27] cxl/pci: Add support for RCH RAS error handling Terry Bowman
2023-06-22 20:54 ` [PATCH v7 01/27] cxl/acpi: Probe RCRB later during RCH downstream port creation Terry Bowman
2023-06-25 19:34 ` Dan Williams
2023-06-22 20:54 ` [PATCH v7 02/27] cxl: Updates for CXL Test to work with RCH Terry Bowman
2023-06-22 20:54 ` [PATCH v7 03/27] cxl/rch: Prepare for caching the MMIO mapped PCIe AER capability Terry Bowman
2023-06-22 20:55 ` [PATCH v7 04/27] cxl: Rename member @dport of struct cxl_dport to @dport_dev Terry Bowman
2023-06-22 20:55 ` [PATCH v7 05/27] cxl: Rename 'uport' to 'uport_dev' Terry Bowman
2023-06-22 20:55 ` [PATCH v7 06/27] cxl/core/regs: Add @dev to cxl_register_map Terry Bowman
2023-06-22 20:55 ` [PATCH v7 07/27] cxl/pci: Refactor component register discovery for reuse Terry Bowman
2023-06-22 20:55 ` [PATCH v7 08/27] cxl/acpi: Move add_host_bridge_uport() after cxl_get_chbs() Terry Bowman
2023-06-22 20:55 ` [PATCH v7 09/27] cxl/acpi: Directly bind the CEDT detected CHBCR to the Host Bridge's port Terry Bowman
2023-06-22 20:55 ` [PATCH v7 10/27] cxl/port: Remove Component Register base address from struct cxl_dport Terry Bowman
2023-06-22 20:55 ` [PATCH v7 11/27] cxl/regs: Remove early capability checks in Component Register setup Terry Bowman
2023-06-22 20:55 ` [PATCH v7 12/27] cxl/mem: Prepare for early RCH dport component register setup Terry Bowman
2023-06-22 20:55 ` [PATCH v7 13/27] cxl/pci: Early setup RCH dport component registers from RCRB Terry Bowman
2023-06-22 20:55 ` [PATCH v7 14/27] cxl/port: Store the port's Component Register mappings in struct cxl_port Terry Bowman
2023-06-23 13:32 ` Jonathan Cameron
2023-06-22 20:55 ` [PATCH v7 15/27] cxl/port: Store the downstream port's Component Register mappings in struct cxl_dport Terry Bowman
2023-06-22 20:55 ` [PATCH v7 16/27] cxl/pci: Store the endpoint's Component Register mappings in struct cxl_dev_state Terry Bowman
2023-06-25 17:38 ` Dan Williams
2023-06-26 14:16 ` Terry Bowman
2023-06-30 19:51 ` Robert Richter
2023-06-30 19:56 ` Robert Richter
2023-07-03 3:55 ` Jonathan Cameron
2023-06-22 20:55 ` [PATCH v7 17/27] cxl/hdm: Use stored Component Register mappings to map HDM decoder capability Terry Bowman
2023-06-22 20:55 ` [PATCH v7 18/27] cxl/port: Remove Component Register base address from struct cxl_port Terry Bowman
2023-06-22 20:55 ` [PATCH v7 19/27] cxl/pci: Add RCH downstream port AER register discovery Terry Bowman
2023-06-22 20:55 ` [PATCH v7 20/27] PCI/AER: Refactor cper_print_aer() for use by CXL driver module Terry Bowman
2023-06-23 21:22 ` Dave Jiang
2023-06-22 20:55 ` Terry Bowman [this message]
2023-06-23 21:43 ` [PATCH v7 21/27] cxl/pci: Update CXL error logging to use RAS register address Dave Jiang
2023-06-22 20:55 ` [PATCH v7 22/27] cxl/pci: Map RCH downstream AER registers for logging protocol errors Terry Bowman
2023-06-23 21:58 ` Dave Jiang
2023-06-22 20:55 ` [PATCH v7 23/27] cxl/pci: Add RCH downstream port error logging Terry Bowman
2023-06-23 22:07 ` Dave Jiang
2023-06-22 20:55 ` [PATCH v7 24/27] cxl/pci: Disable root port interrupts in RCH mode Terry Bowman
2023-06-23 22:08 ` Dave Jiang
2023-06-22 20:55 ` [PATCH v7 25/27] PCI/AER: Forward RCH downstream port-detected errors to the CXL.mem dev handler Terry Bowman
2023-06-23 22:16 ` Dave Jiang
2023-06-25 5:47 ` Dan Williams
2023-06-22 20:55 ` [PATCH v7 26/27] PCI/AER: Unmask RCEC internal errors to enable RCH downstream port error handling Terry Bowman
2023-06-23 22:18 ` Dave Jiang
2023-06-22 20:55 ` [PATCH v7 27/27] cxl/core/regs: Rename phys_addr in cxl_map_component_regs() Terry Bowman
2023-06-23 13:30 ` Jonathan Cameron
2023-06-23 22:19 ` Dave Jiang
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=20230622205523.85375-22-terry.bowman@amd.com \
--to=terry.bowman@amd.com \
--cc=Jonathan.Cameron@huawei.com \
--cc=alison.schofield@intel.com \
--cc=bhelgaas@google.com \
--cc=bwidawsk@kernel.org \
--cc=dan.j.williams@intel.com \
--cc=dave.jiang@intel.com \
--cc=ira.weiny@intel.com \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=rrichter@amd.com \
--cc=vishal.l.verma@intel.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