nel_io_frozen);
edev->in_error = true;
- pci_uevent_ers(pdev, PCI_ERS_RESULT_NONE);
+ pci_uevent_ers(pdev, rc);
return rc;
}
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
On 8/4/25 8:35 AM, Breno Leitao wrote:
Hello Sathyanarayanan,
On Mon, Aug 04, 2025 at 06:50:30AM -0700, Sathyanarayanan Kuppuswamy wrote:
On 8/4/25 2:17 AM, Breno Leitao wrote:
Similarly to pci_dev_aer_stats_incr(), pci_print_aer() may be called
when dev->aer_info is NULL. Add a NULL ch
dev->aer_info)
+ return 1;
+
switch (severity) {
case AER_NONFATAL:
return __ratelimit(&dev->aer_info->nonfatal_ratelimit);
---
base-commit: 89748acdf226fd1a8775ff6fa2703f8412b286c8
change-id: 20250801-aer_crash_2-b21cc2ef0d00
Best regards,
--
Breno Le
Hi Lukas,
On 7/31/25 10:44 PM, Lukas Wunner wrote:
On Thu, Jul 31, 2025 at 10:04:38AM -0700, Sathyanarayanan Kuppuswamy wrote:
On 7/31/25 6:01 AM, Lukas Wunner wrote:
+++ b/drivers/pci/pcie/err.c
@@ -165,6 +165,12 @@ static int report_resume(struct pci_dev *dev, void *data)
return 0
h may be a Port, an RCEC, or an RCiEP
@@ -272,7 +278,7 @@ 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_disconnect, NULL);
t cxl_cper_prot_err_kfifo_get(struct
cxl_cper_prot_err_work_data
}
#endif
+void cxl_cper_ras_handle_prot_err(struct cxl_cper_prot_err_work_data *wd);
+
#endif /* _LINUX_CXL_EVENT_H */
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
struct aer_capability_regs *aer);
int cper_severity_to_aer(int cper_severity);
void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
int severity, struct aer_capability_regs *aer_regs);
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
ecover_queue(int domain, unsigned int bus, unsigned int devfn,
int severity, struct aer_capability_regs *aer_regs);
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
status);
if (dpc_get_aer_uncorrect_severity(pdev, &info) &&
- aer_get_device_error_info(pdev, &info)) {
- aer_print_error(pdev, &info);
+ aer_get_device_error_info(&info, 0)) {
+ aer_print_error(&info,
}
- return -ENOSPC;
+ int i = e_info->error_dev_num;
+
+ if (i >= AER_MAX_MULTI_ERR_DEVICES)
+ return -ENOSPC;
+
+ e_info->dev[i] = pci_dev_get(dev);
+ e_info->error_dev_num++;
+
+ return 0;
}
/**
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
n error logged in its AER
+* Capability.
+*
+* If we didn't find the Error Source device, at least log the
+* Requester ID from the ERR_* Message received by the Root Port or
+* RCEC, ratelimited by the RP or RCEC.
+*/
+ if (info->root_ratelimit_print ||
+ (!found && aer_ratelimit(root, info->severity)))
+ aer_print_source(root, info, found);
+
if (found)
aer_process_err_devices(info);
}
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
+ if (!pdev->aer_info)
+ return 0;
+
+ return a->mode;
+}
+
+const struct attribute_group aer_attr_group = {
+ .name = "aer",
+ .attrs = aer_attrs,
+ .is_visible = aer_attrs_are_visible,
+};
+
static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
struct aer_err_info *info)
{
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
@@ -130,6 +132,6 @@ void pcie_print_tlp_log(const struct pci_dev *dev,
}
}
- pci_err(dev, "%sTLP Header%s: %s\n", pfx,
+ dev_printk(level, &dev->dev, "%sTLP Header%s: %s\n", pfx,
log->flit ? " (Flit)" : "", buf);
}
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
On 5/21/25 7:54 AM, Hans Zhang wrote:
On 2025/5/21 00:09, Sathyanarayanan Kuppuswamy wrote:
On 5/19/25 7:41 AM, Hans Zhang wrote:
On 2025/5/19 22:21, Hans Zhang wrote:
On 2025/5/17 02:10, Sathyanarayanan Kuppuswamy wrote:
On 5/16/25 9:55 AM, Hans Zhang wrote:
The following series
v *pdev)
status);
if (dpc_get_aer_uncorrect_severity(pdev, &info) &&
aer_get_device_error_info(pdev, &info)) {
+ info.ratelimit = 1; /* ERR_FATAL; no ratelimit */
aer_print_error(pdev, &info);
pci_aer_clear_nonfatal_status(pdev);
pci_aer_clear_fatal_status(pdev);
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
(dev);
+
+ if (!pdev->aer_info)
+ return 0;
+
+ return a->mode;
+}
+
+const struct attribute_group aer_attr_group = {
+ .name = "aer",
+ .attrs = aer_attrs,
+ .is_visible = aer_attrs_are_visible,
+};
+
static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
struct aer_err_info *info)
{
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
& ~mask),
+ trace_aer_event(pci_name(dev), (status & ~mask),
aer_severity, tlp_header_valid, &aer->header_log);
}
EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL");
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
er_isr_one_error(rpc->rpd, &e_src);
return IRQ_HANDLED;
}
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
On 5/20/25 12:48 PM, Bjorn Helgaas wrote:
On Mon, May 19, 2025 at 10:01:09PM -0700, Sathyanarayanan Kuppuswamy wrote:
On 5/19/25 2:35 PM, Bjorn Helgaas wrote:
From: Jon Pan-Doh
Add ratelimits section for rationale and defaults.
+AER Ratelimits
+--
+
+Since error messages can be
On 5/20/25 11:31 AM, Bjorn Helgaas wrote:
On Mon, May 19, 2025 at 09:59:29PM -0700, Sathyanarayanan Kuppuswamy wrote:
On 5/19/25 2:35 PM, Bjorn Helgaas wrote:
From: Jon Pan-Doh
Spammy devices can flood kernel logs with AER errors and slow/stall
execution. Add per-device ratelimits for AER
On 5/19/25 7:41 AM, Hans Zhang wrote:
On 2025/5/19 22:21, Hans Zhang wrote:
On 2025/5/17 02:10, Sathyanarayanan Kuppuswamy wrote:
On 5/16/25 9:55 AM, Hans Zhang wrote:
The following series introduces a new kernel command-line option aer_panic
to enhance error handling for PCIe Advanced
(10 events) over
+DEFAULT_RATELIMIT_INTERVAL (5 seconds).
+
AER Statistics / Counters
-
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
de;
+}
+
+const struct attribute_group aer_attr_group = {
+ .name = "aer",
+ .attrs = aer_attrs,
+ .is_visible = aer_attrs_are_visible,
+};
+
static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
struct aer_err_info *info)
{
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
mit = 1; /* no ratelimiting */
aer_print_error(pdev, &info);
pci_aer_clear_nonfatal_status(pdev);
pci_aer_clear_fatal_status(pdev);
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
_cap;/* AER capability offset */
- struct aer_stats *aer_stats;/* AER stats for this device */
+ struct aer_report *aer_report; /* AER report for this device */
#endif
#ifdef CONFIG_PCIEPORTBUS
struct rcec_ea *rcec_ea; /* RCEC cached endpoint association */
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
alid is set, and info.level is always KERN_ERR in
+* that case.
+*/
if (tlp_header_valid)
pcie_print_tlp_log(dev, &aer->header_log, dev_fmt(" "));
}
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
t_severity(struct pci_dev
*dev,
else
info->severity = AER_NONFATAL;
+ info->level = KERN_WARNING;
As Weinan pointed out, it should be KERN_ERR.
return 1;
}
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
ing[info->severity]);
@@ -782,6 +783,8 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
info.status = status;
info.mask = mask;
+ pci_dev_aer_stats_incr(dev, &info);
+
layer = AER_GET_LAYER_ERROR(aer_severity, status);
agent = AER_GET_AGENT(aer_severi
pcie_print_tlp_log(dev, &aer->header_log, dev_fmt(" "));
-
- trace_aer_event(pci_name(dev), (status & ~mask),
- aer_severity, tlp_header_valid, &aer->header_log);
}
EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL");
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
er_log, dev_fmt(" "));
- trace_aer_event(dev_name(&dev->dev), (status & ~mask),
+ trace_aer_event(pci_name(dev), (status & ~mask),
aer_severity, tlp_header_valid, &aer->header_log);
}
EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL");
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
.id = ERR_UNCOR_ID(e_src->id),
+ .severity = fatal ? AER_FATAL : AER_NONFATAL,
+ .multi_error_valid = multi ? 1 : 0,
+ };
if (find_source_device(pdev, &e_info)) {
aer_print_source(pdev, &e_info, "");
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
or_valid ? "Multiple " : "",
-aer_error_severity_string[info->severity],
-pci_domain_nr(dev->bus), PCI_BUS_NUM(source),
-PCI_SLOT(source), PCI_FUNC(source), details);
-}
-
#ifdef CONFIG_ACPI_APEI_PCIEAER
int cper_severity_to_aer(int cper_severity)
{
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
aer_print_source(pdev, &e_info, "");
aer_process_err_devices(&e_info);
}
}
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
ource), PCI_FUNC(source), details);
}
#ifdef CONFIG_ACPI_APEI_PCIEAER
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
tus & PCI_ERR_ROOT_UNCOR_RCV) {
@@ -1316,10 +1318,10 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
else
e_info.multi_error_valid = 0;
- aer_print_port_info(pdev, &e_info);
-
- if (find_source_device(pdev, &e_info))
+
t_reason ==
PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ?
+ "software trigger" :
+"reserved error");
+ break;
+ }
/* show RP PIO error detail information */
if (pdev->dpc_rp_extensions &&
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
struct aer_err_info info;
+ struct aer_err_info info = { 0 };
pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source);
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
I bridge quirks
currently, right? If yes, just list what is currently supported.
+ */
+bool pci_aer_panic_enabled(void)
+{
+ return pcie_aer_panic;
+}
+EXPORT_SYMBOL(pci_aer_panic_enabled);
+
bool pci_aer_available(void)
{
return !pcie_aer_disable && pci_msi_enabled(
ce2d0116e6
prerequisite-patch-id: 482ad0609459a7654a4100cdc9f9aa4b671be50b
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
ned intignore_reset_delay:1; /* For entire hierarchy */
unsigned intno_ext_tags:1; /* No Extended Tags */
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
+271,6 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
pci_uevent_ers(bridge, PCI_ERS_RESULT_DISCONNECT);
- /* TODO: Should kernel panic here? */
pci_info(bridge, "device recovery failed\n");
return status;
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
pcie_clear_device_status(dev);
pci_aer_clear_nonfatal_status(dev);
+ pci_aer_clear_fatal_status(dev);
Add some info about above change in the commit log.
}
pci_walk_bridge(bridge, pci_pm_runtime_put, NULL);
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
zen,
dpc_reset_link);
send_ost:
@@ -216,6 +216,7 @@ static void edr_handle_event(acpi_handle handle, u32 event, void *data)
}
pci_dev_put(err_port);
+ pci_dev_put(err_dev);
}
void pci_acpi_add_edr_notifier(struct pci_dev *pdev)
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
7 @@ static void edr_handle_event(acpi_handle handle, u32 event, void *data)
}
pci_dev_put(err_port);
+ pci_dev_put(err_dev);
}
void pci_acpi_add_edr_notifier(struct pci_dev *pdev)
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
ozen, dpc_reset_link);
return IRQ_HANDLED;
}
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
On 1/23/25 5:45 PM, Shuai Xue wrote:
在 2025/1/24 04:10, Sathyanarayanan Kuppuswamy 写道:
Hi,
On 11/12/24 5:54 AM, Shuai Xue wrote:
The AER driver has historically avoided reading the configuration
space of
an endpoint or RCiEP that reported a fatal error, considering the
link to
that
);
}
@@ -259,6 +267,7 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
if (host->native_aer || pcie_ports_native) {
pcie_clear_device_status(dev);
pci_aer_clear_nonfatal_status(dev);
+ pci_aer_clear_fatal_status(dev);
I think we clear fatal status in DPC driver, why do it again?
}
pci_walk_bridge(bridge, pci_pm_runtime_put, NULL);
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
} else {
- pci_dbg(edev, "DPC port recovery failed\n");
- acpi_send_edr_status(pdev, edev, EDR_OST_FAILED);
+ pci_dbg(err_port, "DPC port recovery failed\n");
+ acpi_send_edr_status(pdev, err_port, EDR_OST_FAILED);
}
- pci_dev_put(edev);
+ pci_dev_put(err_port);
+ pci_dev_put(err_dev);
}
void pci_acpi_add_edr_notifier(struct pci_dev *pdev)
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
> Bjorn Helgaas (2):
> PCI/AER: Drop unused pci_disable_pcie_error_reporting()
> PCI/AER: Unexport pci_enable_pcie_error_reporting()
>
> drivers/pci/pcie/aer.c | 15 +--
> include/linux/aer.h| 11 ---
> 2 files changed, 1 insertion(+), 25 deletions(-)
&
reset Root Port hierarchy, RCEC, or RCiEP
> * @dev: pointer to Root Port, RCEC, or RCiEP
> @@ -1420,6 +1440,8 @@ static struct pcie_port_service_driver aerdriver = {
> .service= PCIE_PORT_SERVICE_AER,
>
> .probe = aer_probe,
> + .suspend= aer_suspend,
> + .resume = aer_resume,
> .remove = aer_remove,
> };
>
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
Hi,
On 4/24/23 10:55 PM, Kai-Heng Feng wrote:
> On Tue, Apr 25, 2023 at 7:47 AM Sathyanarayanan Kuppuswamy
> wrote:
>>
>>
>>
>> On 4/23/23 10:52 PM, Kai-Heng Feng wrote:
>>> PCIe service that shares IRQ with PME may cause spurious wakeup on
>>> sys
= PCIE_PORT_SERVICE_AER,
>
> .probe = aer_probe,
> + .suspend= aer_suspend,
> + .resume = aer_resume,
> .remove = aer_remove,
> };
>
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
t, RCEC, or RCiEP
> @@ -1420,6 +1440,8 @@ static struct pcie_port_service_driver aerdriver = {
> .service= PCIE_PORT_SERVICE_AER,
>
> .probe = aer_probe,
> + .suspend= aer_suspend,
> + .resume = aer_resume,
> .remove = aer_remove,
> };
>
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
t aer_root_reset(struct pci_dev
> *dev)
> pci_read_config_dword(root, aer + PCI_ERR_ROOT_STATUS, ®32);
> pci_write_config_dword(root, aer + PCI_ERR_ROOT_STATUS, reg32);
>
> - /* Enable Root Port's interrupt in response to error messages */
>
quot;,
> - aer_error_layer[layer], aer_agent_string[agent]);
>
> - if (aer_severity != AER_CORRECTABLE)
> + if (aer_severity == AER_CORRECTABLE) {
> + pci_info(dev, "aer_layer=%s, aer_agent=%s\n",
> + aer_error_layer[layer], aer_agent_string[agent]);
> + } else {
> + pci_err(dev, "aer_layer=%s, aer_agent=%s\n",
> + aer_error_layer[layer], aer_agent_string[agent]);
> pci_err(dev, "aer_uncor_severity: 0x%08x\n",
> aer->uncor_severity);
> + }
>
> if (tlp_header_valid)
> __print_tlp_header(dev, &aer->header_log);
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
On 1/11/23 8:59 PM, Vidya Sagar wrote:
>
>
> On 1/12/2023 9:18 AM, Sathyanarayanan Kuppuswamy wrote:
>> External email: Use caution opening links or attachments
>>
>>
>> On 1/11/23 7:33 PM, Vidya Sagar wrote:
>>> I think we still need bios op
agree that "on" and "off" option makes sense. Since the kernel defaults ecrc
setting to "bios", why again allow it as a command line option?
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
Hi,
On 1/11/23 3:10 PM, Bjorn Helgaas wrote:
> On Wed, Jan 11, 2023 at 01:42:21PM -0800, Sathyanarayanan Kuppuswamy wrote:
>> On 1/11/23 12:31 PM, Vidya Sagar wrote:
>>> As the ECRC configuration bits are part of AER registers, configure
>>> ECRC only if AER is n
ing(struct pci_dev *dev)
> {
> + if (!pcie_aer_is_native(dev))
> + return;
> +
> switch (ecrc_policy) {
> case ECRC_POLICY_DEFAULT:
> return;
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
On 9/27/22 9:20 PM, Zhuo Chen wrote:
>
>
> On 9/28/22 3:39 AM, Sathyanarayanan Kuppuswamy wrote:
>>
>>
>> On 9/27/22 8:35 AM, Zhuo Chen wrote:
>>> Status bits for ERR_NONFATAL errors only are cleared in
>>> pci_aer_clear_nonfatal_status(), but we
int pci_aer_clear_uncorrect_error_status(struct pci_dev *dev);
> void pci_save_aer_state(struct pci_dev *dev);
> void pci_restore_aer_state(struct pci_dev *dev);
> @@ -57,10 +56,6 @@ static inline int pci_disable_pcie_error_reporting(struct
> pci_dev *dev)
> {
> return -EINV
@@ -4715,7 +4715,7 @@ lpfc_aer_cleanup_state(struct device *dev, struct
> device_attribute *attr,
> return -EINVAL;
>
> if (phba->hba_flag & HBA_AER_ENABLED)
> - rc = pci_aer_clear_nonfatal_status(phba->pcidev);
> + rc = pci_aer_clear_uncor
fatal_status(pdev);
> + else /* Cleanup uncorrectable error status before getting to init */
> + pci_aer_clear_uncorrect_error_status(pdev);
>
> /* First enable the PCI device */
> ret = pcim_enable_device(pdev);
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
; +static inline int pci_aer_clear_uncorrect_error_status(struct pci_dev *dev)
> +{
> + return -EINVAL;
> +}
> static inline void pci_save_aer_state(struct pci_dev *dev) {}
> static inline void pci_restore_aer_state(struct pci_dev *dev) {}
> #endif
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
pdev, &info);
> - pci_aer_clear_nonfatal_status(pdev);
> - pci_aer_clear_fatal_status(pdev);
> + pci_aer_clear_uncorrect_error_status(pdev);
> }
> }
>
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
tive_aer || pcie_ports_native)".
>
> Or we can change "if ((host->native_aer || pcie_ports_native) && aer)" into
> "if (pcie_aer_is_native(root))". But in this way, argument NULL pointer check
> should be added in pcie_aer_is_native().
Looking into it again, I think it is better to leave it as it is. Please ignore
my comment.
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
@ -221,8 +221,7 @@ static int get_port_device_capability(struct pci_dev *dev)
> }
>
> #ifdef CONFIG_PCIEAER
> - if (dev->aer_cap && pci_aer_available() &&
> - (pcie_ports_native || host->native_aer)) {
> + if (pcie_aer_is_native(dev) && pci_aer_available()) {
> services |= PCIE_PORT_SERVICE_AER;
>
> /*
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
rs/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
> index 604feeb84ee4..98c18f4a01b2 100644
> --- a/drivers/pci/pcie/portdrv_core.c
> +++ b/drivers/pci/pcie/portdrv_core.c
> @@ -221,8 +221,7 @@ static int get_port_device_capability(struct pci_dev *dev)
> }
>
> #
int get_port_device_capability(struct pci_dev *dev)
> }
>
> #ifdef CONFIG_PCIEAER
> - if (dev->aer_cap && pci_aer_available() &&
> - (pcie_ports_native || host->native_aer)) {
> + if (pcie_aer_is_native(dev) && pci_aer_available()) {
> services |= PCIE_PORT_SERVICE_AER;
>
> /*
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
PCI_ERS_RESULT_NO_AER_DRIVER prevents subsequent
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
return IRQ_NONE;
+ mdelay(5000);
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
elated.
I think the actual change of interest is e167bfcaa4cd ("PCI: aerdrv:
remove magical ROOT_ERR_STATUS_MASKS") [1]. It looks like we did
exactly what you propose before that commit.
I can update this unless you disagree.
[1]https://git.kernel.org/linus/e167bfcaa4cd
Agree. Please
_err_source e_src = {};
pci_read_config_dword(rp, aer + PCI_ERR_ROOT_STATUS, &e_src.status);
- if (!(e_src.status & (PCI_ERR_ROOT_UNCOR_RCV|PCI_ERR_ROOT_COR_RCV)))
+ if (!(e_src.status & AER_ERR_STATUS_MASK))
return IRQ_NONE;
pci_read_config_d
nce AER is disabled in previous patch for a Link in L2/L3 Ready, L2
and L3, also disable DPC here as DPC depends on AER to work.
Bugzilla:https://bugzilla.kernel.org/show_bug.cgi?id=215453
Reviewed-by: Mika Westerberg
Signed-off-by: Kai-Heng Feng
Reviewed-by: Kuppuswamy Sathyanarayanan
--
Sathy
= aer_suspend,
+ .resume = aer_resume,
+ .runtime_suspend= aer_suspend,
+ .runtime_resume = aer_resume,
+ .remove = aer_remove,
};
/**
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
On 3/20/22 7:38 PM, Kai-Heng Feng wrote:
On Sun, Mar 20, 2022 at 4:38 AM Sathyanarayanan Kuppuswamy
wrote:
On 1/26/22 6:54 PM, Kai-Heng Feng wrote:
Commit 50310600ebda ("iommu/vt-d: Enable PCI ACS for platform opt in
hint") enables ACS, and some platforms lose its NVMe after r
ume,
+ .runtime_suspend= dpc_suspend,
+ .runtime_resume = dpc_resume,
+ .remove = dpc_remove,
};
int __init pcie_dpc_init(void)
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
= aer_suspend,
+ .resume = aer_resume,
+ .runtime_suspend= aer_suspend,
+ .runtime_resume = aer_resume,
+ .remove = aer_remove,
};
/**
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
& AER_ERR_STATUS_MASK))
return IRQ_NONE;
- pci_read_config_dword(rp, aer + PCI_ERR_ROOT_ERR_SRC, &e_src.id);
pci_write_config_dword(rp, aer + PCI_ERR_ROOT_STATUS,
e_src.status);
+ pci_read_config_dword(rp, aer + PCI_ERR_ROOT_ERR_SRC, &e_src.id)
--
Sat
On 3/15/22 12:52 PM, Eric Badger wrote:
On Tue, Mar 15, 2022 at 10:26:46AM -0700, Sathyanarayanan Kuppuswamy wrote:
On 3/15/22 10:14 AM, Eric Badger wrote:
# Prep injection data for a correctable error.
$ cd /sys/kernel/debug/apei/einj
$ echo 0x0040 > error_type
$ echo
he last 3 steps with following?
# Inject another error (within 5 seconds)
$ echo 1 > error_inject
# You will get a new IRQ with only multiple ERR_COR bit set
pcieport : AER: Root Error Status 0002
--
Sathyanarayanan Kuppuswamy
Linux Kernel Developer
82 matches
Mail list logo
