linux/drivers/pci/pcie/aer/aerdrv.h
Vijay Mohan Pandarathil 918b405318 PCI/AER: Report success only when every device has AER-aware driver
When an error is detected on a PCIe device which does not have an
AER-aware driver, prevent AER infrastructure from reporting
successful error recovery.

This is because the report_error_detected() function that gets
called in the first phase of recovery process allows forward
progress even when the driver for the device does not have AER
capabilities. It seems that all callbacks (in pci_error_handlers
structure) registered by drivers that gets called during error
recovery are not mandatory. So the intention of the infrastructure
design seems to be to allow forward progress even when a specific
callback has not been registered by a driver. However, if error
handler structure itself has not been registered, it doesn't make
sense to allow forward progress.

As a result of the current design, in the case of a single device
having an AER-unaware driver or in the case of any function in a
multi-function card having an AER-unaware driver, a successful
recovery is reported.

Typical scenario this happens is when a PCI device is detached
from a KVM host and the pci-stub driver on the host claims the
device. The pci-stub driver does not have error handling capabilities
but the AER infrastructure still reports that the device recovered
successfully.

The changes proposed here leaves the device(s)in an unrecovered state
if the driver for the device or for any device in the subtree
does not have error handler structure registered. This reflects
the true state of the device and prevents any partial recovery (or no
recovery at all) reported as successful.

[bhelgaas: changelog]
Signed-off-by: Vijay Mohan Pandarathil <vijaymohan.pandarathil@hp.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Linas Vepstas <linasvepstas@gmail.com>
Reviewed-by: Myron Stowe <myron.stowe@redhat.com>
2012-11-26 14:46:28 -07:00

138 lines
3.5 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
#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)
#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 aer_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_NO_AER_DRIVER)
return PCI_ERS_RESULT_NO_AER_DRIVER;
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 = PCI_ERS_RESULT_NEED_RESET;
break;
default:
break;
}
return orig;
}
extern struct bus_type pcie_port_bus_type;
extern void aer_do_secondary_bus_reset(struct pci_dev *dev);
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_APEI
extern int pcie_aer_get_firmware_first(struct pci_dev *pci_dev);
#else
static inline int pcie_aer_get_firmware_first(struct pci_dev *pci_dev)
{
if (pci_dev->__aer_firmware_first_valid)
return pci_dev->__aer_firmware_first;
return 0;
}
#endif
static inline void pcie_aer_force_firmware_first(struct pci_dev *pci_dev,
int enable)
{
pci_dev->__aer_firmware_first = !!enable;
pci_dev->__aer_firmware_first_valid = 1;
}
#endif /* _AERDRV_H_ */