linux_dsm_epyc7002/drivers/pci/pcie/aer/aerdrv.h
Hidetoshi Seto b1c089b7ca 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>
2009-09-09 13:50:13 -07:00

138 lines
3.3 KiB
C

/*
* Copyright (C) 2006 Intel Corp.
* Tom Long Nguyen (tom.l.nguyen@intel.com)
* Zhang Yanmin (yanmin.zhang@intel.com)
*
*/
#ifndef _AERDRV_H_
#define _AERDRV_H_
#include <linux/workqueue.h>
#include <linux/pcieport_if.h>
#include <linux/aer.h>
#include <linux/interrupt.h>
#define AER_NONFATAL 0
#define AER_FATAL 1
#define AER_CORRECTABLE 2
/* Root Error Status Register Bits */
#define ROOT_ERR_STATUS_MASKS 0x0f
#define SYSTEM_ERROR_INTR_ON_MESG_MASK (PCI_EXP_RTCTL_SECEE| \
PCI_EXP_RTCTL_SENFEE| \
PCI_EXP_RTCTL_SEFEE)
#define ROOT_PORT_INTR_ON_MESG_MASK (PCI_ERR_ROOT_CMD_COR_EN| \
PCI_ERR_ROOT_CMD_NONFATAL_EN| \
PCI_ERR_ROOT_CMD_FATAL_EN)
#define ERR_COR_ID(d) (d & 0xffff)
#define ERR_UNCOR_ID(d) (d >> 16)
#define AER_ERROR_SOURCES_MAX 100
#define AER_LOG_TLP_MASKS (PCI_ERR_UNC_POISON_TLP| \
PCI_ERR_UNC_ECRC| \
PCI_ERR_UNC_UNSUP| \
PCI_ERR_UNC_COMP_ABORT| \
PCI_ERR_UNC_UNX_COMP| \
PCI_ERR_UNC_MALF_TLP)
struct header_log_regs {
unsigned int dw0;
unsigned int dw1;
unsigned int dw2;
unsigned int dw3;
};
#define AER_MAX_MULTI_ERR_DEVICES 5 /* Not likely to have more */
struct aer_err_info {
struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
int error_dev_num;
unsigned int id:16;
unsigned int severity:2; /* 0:NONFATAL | 1:FATAL | 2:COR */
unsigned int __pad1:5;
unsigned int multi_error_valid:1;
unsigned int first_error:5;
unsigned int __pad2:2;
unsigned int tlp_header_valid:1;
unsigned int status; /* COR/UNCOR Error Status */
unsigned int mask; /* COR/UNCOR Error Mask */
struct header_log_regs tlp; /* TLP Header */
};
struct aer_err_source {
unsigned int status;
unsigned int id;
};
struct aer_rpc {
struct pcie_device *rpd; /* Root Port device */
struct work_struct dpc_handler;
struct aer_err_source e_sources[AER_ERROR_SOURCES_MAX];
unsigned short prod_idx; /* Error Producer Index */
unsigned short cons_idx; /* Error Consumer Index */
int isr;
spinlock_t e_lock; /*
* Lock access to Error Status/ID Regs
* and error producer/consumer index
*/
struct mutex rpc_mutex; /*
* only one thread could do
* recovery on the same
* root port hierarchy
*/
wait_queue_head_t wait_release;
};
struct aer_broadcast_data {
enum pci_channel_state state;
enum pci_ers_result result;
};
static inline pci_ers_result_t merge_result(enum pci_ers_result orig,
enum pci_ers_result new)
{
if (new == PCI_ERS_RESULT_NONE)
return orig;
switch (orig) {
case PCI_ERS_RESULT_CAN_RECOVER:
case PCI_ERS_RESULT_RECOVERED:
orig = new;
break;
case PCI_ERS_RESULT_DISCONNECT:
if (new == PCI_ERS_RESULT_NEED_RESET)
orig = new;
break;
default:
break;
}
return orig;
}
extern struct bus_type pcie_port_bus_type;
extern void aer_enable_rootport(struct aer_rpc *rpc);
extern void aer_delete_rootport(struct aer_rpc *rpc);
extern int aer_init(struct pcie_device *dev);
extern void aer_isr(struct work_struct *work);
extern void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
extern void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info);
extern irqreturn_t aer_irq(int irq, void *context);
#ifdef CONFIG_ACPI
extern int aer_osc_setup(struct pcie_device *pciedev);
#else
static inline int aer_osc_setup(struct pcie_device *pciedev)
{
return 0;
}
#endif
#endif /* _AERDRV_H_ */