lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <fe1daf3b-162e-4132-8cdc-c89305391090@linux.intel.com>
Date: Mon, 20 Oct 2025 11:38:06 -0700
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@...ux.intel.com>
To: Shuai Xue <xueshuai@...ux.alibaba.com>, linux-pci@...r.kernel.org,
 linux-kernel@...r.kernel.org, linuxppc-dev@...ts.ozlabs.org,
 bhelgaas@...gle.com, kbusch@...nel.org
Cc: mahesh@...ux.ibm.com, oohall@...il.com, Jonathan.Cameron@...wei.com,
 terry.bowman@....com, tianruidong@...ux.alibaba.com, lukas@...ner.de
Subject: Re: [PATCH v6 3/5] PCI/AER: Report fatal errors of RCiEP and EP if
 link recoverd


On 10/14/25 19:41, 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 device unreliable. Consequently, when a fatal error occurs, the AER
> and DPC drivers do not report specific error types, resulting in logs like:
>
>    pcieport 0015:00:00.0: EDR: EDR event received
>    pcieport 0015:00:00.0: EDR: Reported EDR dev: 0015:00:00.0
>    pcieport 0015:00:00.0: DPC: containment event, status:0x200d, ERR_FATAL received from 0015:01:00.0
>    pcieport 0015:00:00.0: AER: broadcast error_detected message
>    pcieport 0015:00:00.0: AER: broadcast mmio_enabled message
>    pcieport 0015:00:00.0: AER: broadcast resume message
>    pcieport 0015:00:00.0: pciehp: Slot(21): Link Down/Up ignored
>    pcieport 0015:00:00.0: AER: device recovery successful
>    pcieport 0015:00:00.0: EDR: DPC port successfully recovered
>    pcieport 0015:00:00.0: EDR: Status for 0015:00:00.0: 0x80
>
> AER status registers are sticky and Write-1-to-clear. If the link recovered
> after hot reset, we can still safely access AER status and TLP header of the
> error device. In such case, report fatal errors which helps to figure out the
> error root case.
>
> After this patch, the logs like:
>
>    pcieport 0015:00:00.0: EDR: EDR event received
>    pcieport 0015:00:00.0: EDR: Reported EDR dev: 0015:00:00.0
>    pcieport 0015:00:00.0: DPC: containment event, status:0x200d, ERR_FATAL received from 0015:01:00.0
>    pcieport 0015:00:00.0: AER: broadcast error_detected message
>    vfio-pci 0015:01:00.0: PCIe Bus Error: severity=Uncorrectable (Fatal), type=Transaction Layer, (Receiver ID)
>    pcieport 0015:00:00.0: pciehp: Slot(21): Link Down/Up ignored

It would be more clear if you follow the same order of the log as before section
and highlight the new logs that are getting added.

>    vfio-pci 0015:01:00.0:   device [144d:a80a] error status/mask=00001000/00400000
>    vfio-pci 0015:01:00.0:    [12] TLP                    (First)
>    vfio-pci 0015:01:00.0: AER:   TLP Header: 0x4a004010 0x00000040 0x01000000 0xffffffff
>    pcieport 0015:00:00.0: AER: broadcast mmio_enabled message
>    pcieport 0015:00:00.0: AER: broadcast resume message
>    pcieport 0015:00:00.0: AER: device recovery successful
>    pcieport 0015:00:00.0: EDR: DPC port successfully recovered
>    pcieport 0015:00:00.0: EDR: Status for 0015:00:00.0: 0x80
>
> Signed-off-by: Shuai Xue <xueshuai@...ux.alibaba.com>
> ---
>   drivers/pci/pci.h      |  4 +++-
>   drivers/pci/pcie/aer.c | 18 +++++++++++-------
>   drivers/pci/pcie/dpc.c |  2 +-
>   drivers/pci/pcie/err.c | 11 +++++++++++
>   4 files changed, 26 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
> index 6b0c55bed15b..3eccef2d25a3 100644
> --- a/drivers/pci/pci.h
> +++ b/drivers/pci/pci.h
> @@ -739,8 +739,10 @@ struct aer_err_info {
>   	struct pcie_tlp_log tlp;	/* TLP Header */
>   };
>   
> -int aer_get_device_error_info(struct aer_err_info *info, int i);
> +int aer_get_device_error_info(struct aer_err_info *info, int i,
> +			      bool link_healthy);
>   void aer_print_error(struct aer_err_info *info, int i);
> +int aer_add_error_device(struct aer_err_info *e_info, struct pci_dev *dev);
>   
>   int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2,
>   		      unsigned int tlp_len, bool flit,
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index 0b5ed4722ac3..aaea9902cbb7 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -978,7 +978,7 @@ EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL");
>    * @e_info: pointer to error info
>    * @dev: pointer to pci_dev to be added
>    */
> -static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
> +int aer_add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)

I don't think you need this rename.

>   {
>   	int i = e_info->error_dev_num;
>   
> @@ -1068,7 +1068,7 @@ static int find_device_iter(struct pci_dev *dev, void *data)
>   
>   	if (is_error_source(dev, e_info)) {
>   		/* List this device */
> -		if (add_error_device(e_info, dev)) {
> +		if (aer_add_error_device(e_info, dev)) {
>   			/* We cannot handle more... Stop iteration */
>   			pci_err(dev, "Exceeded max supported (%d) devices with errors logged\n",
>   				AER_MAX_MULTI_ERR_DEVICES);
> @@ -1382,12 +1382,14 @@ EXPORT_SYMBOL_GPL(aer_recover_queue);
>    * aer_get_device_error_info - read error status from dev and store it to info
>    * @info: pointer to structure to store the error record
>    * @i: index into info->dev[]
> + * @link_healthy: link is healthy or not
>    *
>    * Return: 1 on success, 0 on error.
>    *
>    * Note that @info is reused among all error devices. Clear fields properly.
>    */
> -int aer_get_device_error_info(struct aer_err_info *info, int i)
> +int aer_get_device_error_info(struct aer_err_info *info, int i,
> +			      bool link_healthy)
>   {
>   	struct pci_dev *dev;
>   	int type, aer;
> @@ -1415,10 +1417,12 @@ int aer_get_device_error_info(struct aer_err_info *info, int i)
>   			&info->mask);
>   		if (!(info->status & ~info->mask))
>   			return 0;
> +		info->level = KERN_WARNING;

I recommend setting this when initializing the info->level at the caller end (to match
other callers)

>   	} else if (type == PCI_EXP_TYPE_ROOT_PORT ||
>   		   type == PCI_EXP_TYPE_RC_EC ||
>   		   type == PCI_EXP_TYPE_DOWNSTREAM ||
> -		   info->severity == AER_NONFATAL) {
> +		   info->severity == AER_NONFATAL ||
> +		   (info->severity == AER_FATAL && link_healthy)) {
>   
>   		/* Link is still healthy for IO reads */
>   		pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_STATUS,
> @@ -1427,7 +1431,7 @@ int aer_get_device_error_info(struct aer_err_info *info, int i)
>   			&info->mask);
>   		if (!(info->status & ~info->mask))
>   			return 0;
> -
> +		info->level = KERN_ERR;
>   		/* Get First Error Pointer */
>   		pci_read_config_dword(dev, aer + PCI_ERR_CAP, &aercc);
>   		info->first_error = PCI_ERR_CAP_FEP(aercc);
> @@ -1451,11 +1455,11 @@ static inline void aer_process_err_devices(struct aer_err_info *e_info)
>   
>   	/* Report all before handling them, to not lose records by reset etc. */
>   	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
> -		if (aer_get_device_error_info(e_info, i))
> +		if (aer_get_device_error_info(e_info, i, false))
>   			aer_print_error(e_info, i);
>   	}
>   	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
> -		if (aer_get_device_error_info(e_info, i))
> +		if (aer_get_device_error_info(e_info, i, false))
>   			handle_error_source(e_info->dev[i], e_info);
>   	}
>   }
> diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
> index f6069f621683..21c4e8371279 100644
> --- a/drivers/pci/pcie/dpc.c
> +++ b/drivers/pci/pcie/dpc.c
> @@ -284,7 +284,7 @@ struct pci_dev *dpc_process_error(struct pci_dev *pdev)
>   		pci_warn(pdev, "containment event, status:%#06x: unmasked uncorrectable error detected\n",
>   			 status);
>   		if (dpc_get_aer_uncorrect_severity(pdev, &info) &&
> -		    aer_get_device_error_info(&info, 0)) {
> +		    aer_get_device_error_info(&info, 0, false)) {
>   			aer_print_error(&info, 0);
>   			pci_aer_clear_nonfatal_status(pdev);
>   			pci_aer_clear_fatal_status(pdev);
> diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
> index bebe4bc111d7..4e65eac809d1 100644
> --- a/drivers/pci/pcie/err.c
> +++ b/drivers/pci/pcie/err.c
> @@ -215,6 +215,7 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
>   	struct pci_dev *bridge;
>   	pci_ers_result_t status = PCI_ERS_RESULT_CAN_RECOVER;
>   	struct pci_host_bridge *host = pci_find_host_bridge(dev->bus);
> +	struct aer_err_info info;
>   
>   	/*
>   	 * If the error was detected by a Root Port, Downstream Port, RCEC,
> @@ -253,6 +254,16 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
>   			pci_warn(bridge, "subordinate device reset failed\n");
>   			goto failed;
>   		}
> +
> +		/* Link recovered, report fatal errors of RCiEP or EP */
> +		if (state == pci_channel_io_frozen &&
> +		    (type == PCI_EXP_TYPE_ENDPOINT || type == PCI_EXP_TYPE_RC_END)) {
> +			aer_add_error_device(&info, dev);
> +			info.severity = AER_FATAL;
info.level = KERN_ERR ?
> +			if (aer_get_device_error_info(&info, 0, true))
> +				aer_print_error(&info, 0);
> +			pci_dev_put(dev);

Like Lukas mentioned, it needs a comment about why you need this.

> +		}
>   	}
>   
>   	if (status == PCI_ERS_RESULT_NEED_RESET) {

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ