mirrors/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2024-09-27 12:57:53 +00:00
Code Issues Releases Wiki Activity

cxl/pci: Add (hopeful) error handling support

Browse source 
Add nominal error handling that tears down CXL.mem in response to error
notifications that imply a device reset. Given some CXL.mem may be
operating as System RAM, there is a high likelihood that these error
events are fatal. However, if the system survives the notification the
expectation is that the driver behavior is equivalent to a hot-unplug
and re-plug of an endpoint.

Note that this does not change the mask values from the default. That
awaits CXL _OSC support to determine whether platform firmware is in
control of the mask registers.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/166974413966.1608150.15522782911404473932.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This commit is contained in:
Dan Williams 2022-11-29 10:48:59 -07:00
parent 2f6e9c3051
commit 2905cb5236
4 changed files with 141 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
drivers/cxl/core/memdev.c
View file

@ -344,6 +344,7 @@ struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds)
* needed as this is ordered with cdev_add() publishing the device.
*/
cxlmd->cxlds = cxlds;
cxlds->cxlmd = cxlmd;
cdev = &cxlmd->cdev;
rc = cdev_device_add(cdev, dev);

1
drivers/cxl/cxl.h
View file

@ -132,6 +132,7 @@ static inline int ways_to_cxl(unsigned int ways, u8 *iw)
#define CXL_RAS_CORRECTABLE_MASK_OFFSET 0x10
#define CXL_RAS_CORRECTABLE_MASK_MASK GENMASK(6, 0)
#define CXL_RAS_CAP_CONTROL_OFFSET 0x14
#define CXL_RAS_CAP_CONTROL_FE_MASK GENMASK(5, 0)
#define CXL_RAS_HEADER_LOG_OFFSET 0x18
#define CXL_RAS_CAPABILITY_LENGTH 0x58

2
drivers/cxl/cxlmem.h
View file

@ -186,6 +186,7 @@ struct cxl_endpoint_dvsec_info {
* Currently only memory devices are represented.
*
* @dev: The device associated with this CXL state
* @cxlmd: The device representing the CXL.mem capabilities of @dev
* @regs: Parsed register blocks
* @cxl_dvsec: Offset to the PCIe device DVSEC
* @payload_size: Size of space for payload
@ -218,6 +219,7 @@ struct cxl_endpoint_dvsec_info {
*/
struct cxl_dev_state {
struct device *dev;
struct cxl_memdev *cxlmd;
struct cxl_regs regs;
int cxl_dvsec;

137
drivers/cxl/pci.c
View file

@ -9,6 +9,7 @@
#include <linux/list.h>
#include <linux/pci.h>
#include <linux/pci-doe.h>
#include <linux/aer.h>
#include <linux/io.h>
#include "cxlmem.h"
#include "cxlpci.h"
@ -399,6 +400,11 @@ static void devm_cxl_pci_create_doe(struct cxl_dev_state *cxlds)
}
}
static void disable_aer(void *pdev)
{
pci_disable_pcie_error_reporting(pdev);
}
static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct cxl_register_map map;
@ -420,6 +426,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
cxlds = cxl_dev_state_create(&pdev->dev);
if (IS_ERR(cxlds))
return PTR_ERR(cxlds);
pci_set_drvdata(pdev, cxlds);
cxlds->serial = pci_get_dsn(pdev);
cxlds->cxl_dvsec = pci_find_dvsec_capability(
@ -474,6 +481,14 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (IS_ERR(cxlmd))
return PTR_ERR(cxlmd);
if (cxlds->regs.ras) {
pci_enable_pcie_error_reporting(pdev);
rc = devm_add_action_or_reset(&pdev->dev, disable_aer, pdev);
if (rc)
return rc;
}
pci_save_state(pdev);
if (resource_size(&cxlds->pmem_res) && IS_ENABLED(CONFIG_CXL_PMEM))
rc = devm_cxl_add_nvdimm(&pdev->dev, cxlmd);
@ -487,10 +502,132 @@ static const struct pci_device_id cxl_mem_pci_tbl[] = {
};
MODULE_DEVICE_TABLE(pci, cxl_mem_pci_tbl);
/* CXL spec rev3.0 8.2.4.16.1 */
static void header_log_copy(struct cxl_dev_state *cxlds, 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;
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_report_and_clear(struct cxl_dev_state *cxlds)
{
struct cxl_memdev *cxlmd = cxlds->cxlmd;
struct device *dev = &cxlmd->dev;
u32 hl[CXL_HEADERLOG_SIZE_U32];
void __iomem *addr;
u32 status;
u32 fe;
if (!cxlds->regs.ras)
return false;
addr = cxlds->regs.ras + CXL_RAS_UNCORRECTABLE_STATUS_OFFSET;
status = le32_to_cpu((__force __le32)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) {
addr = cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET;
fe = BIT(le32_to_cpu((__force __le32)readl(addr)) &
CXL_RAS_CAP_CONTROL_FE_MASK);
} else {
fe = status;
}
header_log_copy(cxlds, hl);
trace_cxl_aer_uncorrectable_error(dev_name(dev), status, fe, hl);
writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
return true;
}
static 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;
/*
* 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_report_and_clear(cxlds);
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;
}
static pci_ers_result_t cxl_slot_reset(struct pci_dev *pdev)
{
struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
struct cxl_memdev *cxlmd = cxlds->cxlmd;
struct device *dev = &cxlmd->dev;
dev_info(&pdev->dev, "%s: restart CXL.mem after slot reset\n",
dev_name(dev));
pci_restore_state(pdev);
if (device_attach(dev) <= 0)
return PCI_ERS_RESULT_DISCONNECT;
return PCI_ERS_RESULT_RECOVERED;
}
static void cxl_error_resume(struct pci_dev *pdev)
{
struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
struct cxl_memdev *cxlmd = cxlds->cxlmd;
struct device *dev = &cxlmd->dev;
dev_info(&pdev->dev, "%s: error resume %s\n", dev_name(dev),
dev->driver ? "successful" : "failed");
}
static const struct pci_error_handlers cxl_error_handlers = {
.error_detected = cxl_error_detected,
.slot_reset = cxl_slot_reset,
.resume = cxl_error_resume,
};
static struct pci_driver cxl_pci_driver = {
.name = KBUILD_MODNAME,
.id_table = cxl_mem_pci_tbl,
.probe = cxl_pci_probe,
.err_handler = &cxl_error_handlers,
.driver = {
.probe_type = PROBE_PREFER_ASYNCHRONOUS,
},