Commit b1c089b7 authored Sep 07, 2009 by Hidetoshi Seto Committed by Jesse Barnes Sep 09, 2009

PCI: pcie, aer: report all error before recovery



This patch is required not to lost error records by action invoked on
error recovery, such as slot reset etc.

Following sample (real machine + dummy record injected by aer-inject)
shows that record of 28:00.1 could not be retrieved by recovery of 28:00.0:

- Before:

pcieport-driver 0000:00:02.0: AER: Multiple Uncorrected (Non-Fatal) error received: id=2801
e1000e 0000:28:00.0: PCIE Bus Error: severity=Uncorrected (Non-Fatal), type=Transaction Layer, id=2800(Receiver ID)
e1000e 0000:28:00.0:   device [8086:1096] error status/mask=00001000/00100000
e1000e 0000:28:00.0:    [12] Poisoned TLP           (First)
e1000e 0000:28:00.0:   TLP Header: 00000000 00000001 00000002 00000003
e1000e 0000:28:00.0: broadcast error_detected message
e1000e 0000:28:00.0: broadcast slot_reset message
e1000e 0000:28:00.0: setting latency timer to 64
e1000e 0000:28:00.0: restoring config space at offset 0x1 (was 0x100547, writing 0x100147)
e1000e 0000:28:00.0: PME# disabled
e1000e 0000:28:00.0: PME# disabled
e1000e 0000:28:00.1: setting latency timer to 64
e1000e 0000:28:00.1: restoring config space at offset 0x1 (was 0x100547, writing 0x100147)
e1000e 0000:28:00.1: PME# disabled
e1000e 0000:28:00.1: PME# disabled
e1000e 0000:28:00.0: broadcast resume message
e1000e 0000:28:00.0: AER driver successfully recovered
e1000e: eth0 NIC Link is Up 1000 Mbps Full Duplex, Flow Control: RX/TX

- After:

pcieport-driver 0000:00:02.0: AER: Multiple Uncorrected (Non-Fatal) error received: id=2801
e1000e 0000:28:00.0: PCIE Bus Error: severity=Uncorrected (Non-Fatal), type=Transaction Layer, id=2800(Receiver ID)
e1000e 0000:28:00.0:   device [8086:1096] error status/mask=00001000/00100000
e1000e 0000:28:00.0:    [12] Poisoned TLP           (First)
e1000e 0000:28:00.0:   TLP Header: 00000000 00000001 00000002 00000003
e1000e 0000:28:00.1: PCIE Bus Error: severity=Uncorrected (Non-Fatal), type=Transaction Layer, id=2801(Receiver ID)
e1000e 0000:28:00.1:   device [8086:1096] error status/mask=00081000/00100000
e1000e 0000:28:00.1:    [12] Poisoned TLP           (First)
e1000e 0000:28:00.1:    [19] ECRC
e1000e 0000:28:00.1:   TLP Header: 00000000 00000001 00000002 00000003
e1000e 0000:28:00.1:   Error of this Agent(2801) is reported first
e1000e 0000:28:00.0: broadcast error_detected message
e1000e 0000:28:00.0: broadcast slot_reset message
e1000e 0000:28:00.0: setting latency timer to 64
e1000e 0000:28:00.0: restoring config space at offset 0x1 (was 0x100547, writing 0x100147)
e1000e 0000:28:00.0: PME# disabled
e1000e 0000:28:00.0: PME# disabled
e1000e 0000:28:00.1: setting latency timer to 64
e1000e 0000:28:00.1: restoring config space at offset 0x1 (was 0x100547, writing 0x100147)
e1000e 0000:28:00.1: PME# disabled
e1000e 0000:28:00.1: PME# disabled
e1000e 0000:28:00.0: broadcast resume message
e1000e 0000:28:00.0: AER driver successfully recovered
e1000e: eth0 NIC Link is Up 1000 Mbps Full Duplex, Flow Control: RX/TX

Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>

parent 79e4b89b

drivers/pci/pcie/aer/aerdrv.h

+0 −2

Original line number	Diff line number	Diff line
		@@ -29,8 +29,6 @@
		#define ERR_COR_ID(d) (d & 0xffff)
		#define ERR_UNCOR_ID(d) (d >> 16)

		#define AER_SUCCESS 0
		#define AER_UNSUCCESS 1
		#define AER_ERROR_SOURCES_MAX 100

		#define AER_LOG_TLP_MASKS (PCI_ERR_UNC_POISON_TLP\| \

drivers/pci/pcie/aer/aerdrv_core.c

+18 −11

Original line number	Diff line number	Diff line
		@@ -696,6 +696,13 @@ static struct aer_err_source get_e_source(struct aer_rpc rpc)
		return e_source;
		}

		/**
		* get_device_error_info - read error status from dev and store it to info
		* @dev: pointer to the device expected to have a error record
		* @info: pointer to structure to store the error record
		*
		* Return 1 on success, 0 on error.
		*/
		static int get_device_error_info(struct pci_dev dev, struct aer_err_info info)
		{
		int pos, temp;
		@@ -707,7 +714,7 @@ static int get_device_error_info(struct pci_dev dev, struct aer_err_info info)

		/* The device might not support AER */
		if (!pos)
		return AER_SUCCESS;
		return 1;

		if (info->severity == AER_CORRECTABLE) {
		pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS,
		@@ -715,7 +722,7 @@ static int get_device_error_info(struct pci_dev dev, struct aer_err_info info)
		pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK,
		&info->mask);
		if (!(info->status & ~info->mask))
		return AER_UNSUCCESS;
		return 0;
		} else if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE \|\|
		info->severity == AER_NONFATAL) {

		@@ -725,7 +732,7 @@ static int get_device_error_info(struct pci_dev dev, struct aer_err_info info)
		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK,
		&info->mask);
		if (!(info->status & ~info->mask))
		return AER_UNSUCCESS;
		return 0;

		/* Get First Error Pointer */
		pci_read_config_dword(dev, pos + PCI_ERR_CAP, &temp);
		@@ -744,7 +751,7 @@ static int get_device_error_info(struct pci_dev dev, struct aer_err_info info)
		}
		}

		return AER_SUCCESS;
		return 1;
		}

		static inline void aer_process_err_devices(struct pcie_device *p_device,
		@@ -758,14 +765,14 @@ static inline void aer_process_err_devices(struct pcie_device *p_device,
		e_info->id);
		}

		/* Report all before handle them, not to lost records by reset etc. */
		for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
		if (get_device_error_info(e_info->dev[i], e_info) ==
		AER_SUCCESS) {
		if (get_device_error_info(e_info->dev[i], e_info))
		aer_print_error(e_info->dev[i], e_info);
		handle_error_source(p_device,
		e_info->dev[i],
		e_info);
		}
		for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
		if (get_device_error_info(e_info->dev[i], e_info))
		handle_error_source(p_device, e_info->dev[i], e_info);
		}
		}

		@@ -870,5 +877,5 @@ int aer_init(struct pcie_device *dev)
		if (aer_osc_setup(dev) && !forceload)
		return -ENXIO;

		return AER_SUCCESS;
		return 0;
		}