summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
Diffstat (limited to 'drivers')
-rw-r--r--drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c1
-rw-r--r--drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c2
-rw-r--r--drivers/net/ethernet/sfc/efx_common.c3
-rw-r--r--drivers/net/ethernet/sfc/falcon/efx.c3
-rw-r--r--drivers/net/ethernet/sfc/siena/efx_common.c3
-rw-r--r--drivers/pci/pci-driver.c3
-rw-r--r--drivers/pci/pcie/aer.c49
-rw-r--r--drivers/pci/pcie/err.c40
-rw-r--r--drivers/scsi/lpfc/lpfc_init.c2
-rw-r--r--drivers/scsi/qla2xxx/qla_os.c5
10 files changed, 74 insertions, 37 deletions
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index d7cdea8f604d..91e7b38143ea 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -4215,7 +4215,6 @@ static pci_ers_result_t qlcnic_83xx_io_slot_reset(struct pci_dev *pdev)
struct qlcnic_adapter *adapter = pci_get_drvdata(pdev);
int err = 0;
- pdev->error_state = pci_channel_io_normal;
err = pci_enable_device(pdev);
if (err)
goto disconnect;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 53cdd36c4123..e051d8c7a28d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -3766,8 +3766,6 @@ static int qlcnic_attach_func(struct pci_dev *pdev)
struct qlcnic_adapter *adapter = pci_get_drvdata(pdev);
struct net_device *netdev = adapter->netdev;
- pdev->error_state = pci_channel_io_normal;
-
err = pci_enable_device(pdev);
if (err)
return err;
diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c
index 5a14d94163b1..e8fdbb62d872 100644
--- a/drivers/net/ethernet/sfc/efx_common.c
+++ b/drivers/net/ethernet/sfc/efx_common.c
@@ -1258,9 +1258,6 @@ out:
/* For simplicity and reliability, we always require a slot reset and try to
* reset the hardware when a pci error affecting the device is detected.
- * We leave both the link_reset and mmio_enabled callback unimplemented:
- * with our request for slot reset the mmio_enabled callback will never be
- * called, and the link_reset callback is not used by AER or EEH mechanisms.
*/
const struct pci_error_handlers efx_err_handlers = {
.error_detected = efx_io_error_detected,
diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c
index b07f7e4e2877..0c784656fde9 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.c
+++ b/drivers/net/ethernet/sfc/falcon/efx.c
@@ -3128,9 +3128,6 @@ out:
/* For simplicity and reliability, we always require a slot reset and try to
* reset the hardware when a pci error affecting the device is detected.
- * We leave both the link_reset and mmio_enabled callback unimplemented:
- * with our request for slot reset the mmio_enabled callback will never be
- * called, and the link_reset callback is not used by AER or EEH mechanisms.
*/
static const struct pci_error_handlers ef4_err_handlers = {
.error_detected = ef4_io_error_detected,
diff --git a/drivers/net/ethernet/sfc/siena/efx_common.c b/drivers/net/ethernet/sfc/siena/efx_common.c
index a0966f879664..35036cc902fe 100644
--- a/drivers/net/ethernet/sfc/siena/efx_common.c
+++ b/drivers/net/ethernet/sfc/siena/efx_common.c
@@ -1285,9 +1285,6 @@ out:
/* For simplicity and reliability, we always require a slot reset and try to
* reset the hardware when a pci error affecting the device is detected.
- * We leave both the link_reset and mmio_enabled callback unimplemented:
- * with our request for slot reset the mmio_enabled callback will never be
- * called, and the link_reset callback is not used by AER or EEH mechanisms.
*/
const struct pci_error_handlers efx_siena_err_handlers = {
.error_detected = efx_io_error_detected,
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 63665240ae87..302d61783f6c 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -1582,7 +1582,7 @@ static int pci_uevent(const struct device *dev, struct kobj_uevent_env *env)
return 0;
}
-#if defined(CONFIG_PCIEAER) || defined(CONFIG_EEH)
+#if defined(CONFIG_PCIEAER) || defined(CONFIG_EEH) || defined(CONFIG_S390)
/**
* pci_uevent_ers - emit a uevent during recovery path of PCI device
* @pdev: PCI device undergoing error recovery
@@ -1596,6 +1596,7 @@ void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type)
switch (err_type) {
case PCI_ERS_RESULT_NONE:
case PCI_ERS_RESULT_CAN_RECOVER:
+ case PCI_ERS_RESULT_NEED_RESET:
envp[idx++] = "ERROR_EVENT=BEGIN_RECOVERY";
envp[idx++] = "DEVICE_ONLINE=0";
break;
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index e286c197d716..0b5ed4722ac3 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -43,7 +43,7 @@
#define AER_ERROR_SOURCES_MAX 128
#define AER_MAX_TYPEOF_COR_ERRS 16 /* as per PCI_ERR_COR_STATUS */
-#define AER_MAX_TYPEOF_UNCOR_ERRS 27 /* as per PCI_ERR_UNCOR_STATUS*/
+#define AER_MAX_TYPEOF_UNCOR_ERRS 32 /* as per PCI_ERR_UNCOR_STATUS*/
struct aer_err_source {
u32 status; /* PCI_ERR_ROOT_STATUS */
@@ -96,11 +96,21 @@ struct aer_info {
};
#define AER_LOG_TLP_MASKS (PCI_ERR_UNC_POISON_TLP| \
+ PCI_ERR_UNC_POISON_BLK | \
PCI_ERR_UNC_ECRC| \
PCI_ERR_UNC_UNSUP| \
PCI_ERR_UNC_COMP_ABORT| \
PCI_ERR_UNC_UNX_COMP| \
- PCI_ERR_UNC_MALF_TLP)
+ PCI_ERR_UNC_ACSV | \
+ PCI_ERR_UNC_MCBTLP | \
+ PCI_ERR_UNC_ATOMEG | \
+ PCI_ERR_UNC_DMWR_BLK | \
+ PCI_ERR_UNC_XLAT_BLK | \
+ PCI_ERR_UNC_TLPPRE | \
+ PCI_ERR_UNC_MALF_TLP | \
+ PCI_ERR_UNC_IDE_CHECK | \
+ PCI_ERR_UNC_MISR_IDE | \
+ PCI_ERR_UNC_PCRC_CHECK)
#define SYSTEM_ERROR_INTR_ON_MESG_MASK (PCI_EXP_RTCTL_SECEE| \
PCI_EXP_RTCTL_SENFEE| \
@@ -383,6 +393,10 @@ void pci_aer_init(struct pci_dev *dev)
return;
dev->aer_info = kzalloc(sizeof(*dev->aer_info), GFP_KERNEL);
+ if (!dev->aer_info) {
+ dev->aer_cap = 0;
+ return;
+ }
ratelimit_state_init(&dev->aer_info->correctable_ratelimit,
DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);
@@ -525,11 +539,11 @@ static const char *aer_uncorrectable_error_string[] = {
"AtomicOpBlocked", /* Bit Position 24 */
"TLPBlockedErr", /* Bit Position 25 */
"PoisonTLPBlocked", /* Bit Position 26 */
- NULL, /* Bit Position 27 */
- NULL, /* Bit Position 28 */
- NULL, /* Bit Position 29 */
- NULL, /* Bit Position 30 */
- NULL, /* Bit Position 31 */
+ "DMWrReqBlocked", /* Bit Position 27 */
+ "IDECheck", /* Bit Position 28 */
+ "MisIDETLP", /* Bit Position 29 */
+ "PCRC_CHECK", /* Bit Position 30 */
+ "TLPXlatBlocked", /* Bit Position 31 */
};
static const char *aer_agent_string[] = {
@@ -786,6 +800,9 @@ static void pci_rootport_aer_stats_incr(struct pci_dev *pdev,
static int aer_ratelimit(struct pci_dev *dev, unsigned int severity)
{
+ if (!dev->aer_info)
+ return 1;
+
switch (severity) {
case AER_NONFATAL:
return __ratelimit(&dev->aer_info->nonfatal_ratelimit);
@@ -796,6 +813,20 @@ static int aer_ratelimit(struct pci_dev *dev, unsigned int severity)
}
}
+static bool tlp_header_logged(u32 status, u32 capctl)
+{
+ /* Errors for which a header is always logged (PCIe r7.0 sec 6.2.7) */
+ if (status & AER_LOG_TLP_MASKS)
+ return true;
+
+ /* Completion Timeout header is only logged on capable devices */
+ if (status & PCI_ERR_UNC_COMP_TIME &&
+ capctl & PCI_ERR_CAP_COMP_TIME_LOG)
+ return true;
+
+ return false;
+}
+
static void __aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
{
const char **strings;
@@ -910,7 +941,7 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
status = aer->uncor_status;
mask = aer->uncor_mask;
info.level = KERN_ERR;
- tlp_header_valid = status & AER_LOG_TLP_MASKS;
+ tlp_header_valid = tlp_header_logged(status, aer->cap_control);
}
info.status = status;
@@ -1401,7 +1432,7 @@ int aer_get_device_error_info(struct aer_err_info *info, int i)
pci_read_config_dword(dev, aer + PCI_ERR_CAP, &aercc);
info->first_error = PCI_ERR_CAP_FEP(aercc);
- if (info->status & AER_LOG_TLP_MASKS) {
+ if (tlp_header_logged(info->status, aercc)) {
info->tlp_header_valid = 1;
pcie_read_tlp_log(dev, aer + PCI_ERR_HEADER_LOG,
aer + PCI_ERR_PREFIX_LOG,
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index de6381c690f5..bebe4bc111d7 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -108,6 +108,24 @@ static int report_normal_detected(struct pci_dev *dev, void *data)
return report_error_detected(dev, pci_channel_io_normal, data);
}
+static int report_perm_failure_detected(struct pci_dev *dev, void *data)
+{
+ struct pci_driver *pdrv;
+ const struct pci_error_handlers *err_handler;
+
+ device_lock(&dev->dev);
+ pdrv = dev->driver;
+ if (!pdrv || !pdrv->err_handler || !pdrv->err_handler->error_detected)
+ goto out;
+
+ err_handler = pdrv->err_handler;
+ err_handler->error_detected(dev, pci_channel_io_perm_failure);
+out:
+ pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT);
+ device_unlock(&dev->dev);
+ return 0;
+}
+
static int report_mmio_enabled(struct pci_dev *dev, void *data)
{
struct pci_driver *pdrv;
@@ -135,7 +153,8 @@ static int report_slot_reset(struct pci_dev *dev, void *data)
device_lock(&dev->dev);
pdrv = dev->driver;
- if (!pdrv || !pdrv->err_handler || !pdrv->err_handler->slot_reset)
+ if (!pci_dev_set_io_state(dev, pci_channel_io_normal) ||
+ !pdrv || !pdrv->err_handler || !pdrv->err_handler->slot_reset)
goto out;
err_handler = pdrv->err_handler;
@@ -217,15 +236,10 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
pci_walk_bridge(bridge, pci_pm_runtime_get_sync, NULL);
pci_dbg(bridge, "broadcast error_detected message\n");
- if (state == pci_channel_io_frozen) {
+ if (state == pci_channel_io_frozen)
pci_walk_bridge(bridge, report_frozen_detected, &status);
- if (reset_subordinates(bridge) != PCI_ERS_RESULT_RECOVERED) {
- pci_warn(bridge, "subordinate device reset failed\n");
- goto failed;
- }
- } else {
+ else
pci_walk_bridge(bridge, report_normal_detected, &status);
- }
if (status == PCI_ERS_RESULT_CAN_RECOVER) {
status = PCI_ERS_RESULT_RECOVERED;
@@ -233,6 +247,14 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
pci_walk_bridge(bridge, report_mmio_enabled, &status);
}
+ if (status == PCI_ERS_RESULT_NEED_RESET ||
+ state == pci_channel_io_frozen) {
+ if (reset_subordinates(bridge) != PCI_ERS_RESULT_RECOVERED) {
+ pci_warn(bridge, "subordinate device reset failed\n");
+ goto failed;
+ }
+ }
+
if (status == PCI_ERS_RESULT_NEED_RESET) {
/*
* TODO: Should call platform-specific
@@ -269,7 +291,7 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
failed:
pci_walk_bridge(bridge, pci_pm_runtime_put, NULL);
- pci_uevent_ers(bridge, PCI_ERS_RESULT_DISCONNECT);
+ pci_walk_bridge(bridge, report_perm_failure_detected, NULL);
pci_info(bridge, "device recovery failed\n");
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 4081d2a358ee..cf08bb5b37c3 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -14377,7 +14377,7 @@ lpfc_sli_prep_dev_for_perm_failure(struct lpfc_hba *phba)
* as desired.
*
* Return codes
- * PCI_ERS_RESULT_CAN_RECOVER - can be recovered with reset_link
+ * PCI_ERS_RESULT_CAN_RECOVER - can be recovered without reset
* PCI_ERS_RESULT_NEED_RESET - need to reset before recovery
* PCI_ERS_RESULT_DISCONNECT - device could not be recovered
**/
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index d4b484c0fd9d..4460421834cb 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -7883,11 +7883,6 @@ qla2xxx_pci_slot_reset(struct pci_dev *pdev)
"Slot Reset.\n");
ha->pci_error_state = QLA_PCI_SLOT_RESET;
- /* Workaround: qla2xxx driver which access hardware earlier
- * needs error state to be pci_channel_io_online.
- * Otherwise mailbox command timesout.
- */
- pdev->error_state = pci_channel_io_normal;
pci_restore_state(pdev);
generated by cgit (git 2.34.1) at 2026-01-05 13:07:01 +0000