path: root/arch/powerpc/platforms/pseries/eeh.c

/*
 * eeh.c
 * Copyright IBM Corporation 2001, 2005, 2006
 * Copyright Dave Engebretsen & Todd Inglett 2001
 * Copyright Linas Vepstas 2005, 2006
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
 *
 * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com>
 */

#include <linux/delay.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/pci.h>
#include <linux/proc_fs.h>
#include <linux/rbtree.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
#include <linux/of.h>

#include <asm/atomic.h>
#include <asm/eeh.h>
#include <asm/eeh_event.h>
#include <asm/io.h>
#include <asm/machdep.h>
#include <asm/ppc-pci.h>
#include <asm/rtas.h>


/** Overview:
 *  EEH, or "Extended Error Handling" is a PCI bridge technology for
 *  dealing with PCI bus errors that can't be dealt with within the
 *  usual PCI framework, except by check-stopping the CPU.  Systems
 *  that are designed for high-availability/reliability cannot afford
 *  to crash due to a "mere" PCI error, thus the need for EEH.
 *  An EEH-capable bridge operates by converting a detected error
 *  into a "slot freeze", taking the PCI adapter off-line, making
 *  the slot behave, from the OS'es point of view, as if the slot
 *  were "empty": all reads return 0xff's and all writes are silently
 *  ignored.  EEH slot isolation events can be triggered by parity
 *  errors on the address or data busses (e.g. during posted writes),
 *  which in turn might be caused by low voltage on the bus, dust,
 *  vibration, humidity, radioactivity or plain-old failed hardware.
 *
 *  Note, however, that one of the leading causes of EEH slot
 *  freeze events are buggy device drivers, buggy device microcode,
 *  or buggy device hardware.  This is because any attempt by the
 *  device to bus-master data to a memory address that is not
 *  assigned to the device will trigger a slot freeze.   (The idea
 *  is to prevent devices-gone-wild from corrupting system memory).
 *  Buggy hardware/drivers will have a miserable time co-existing
 *  with EEH.
 *
 *  Ideally, a PCI device driver, when suspecting that an isolation
 *  event has occurred (e.g. by reading 0xff's), will then ask EEH
 *  whether this is the case, and then take appropriate steps to
 *  reset the PCI slot, the PCI device, and then resume operations.
 *  However, until that day,  the checking is done here, with the
 *  eeh_check_failure() routine embedded in the MMIO macros.  If
 *  the slot is found to be isolated, an "EEH Event" is synthesized
 *  and sent out for processing.
 */

/* If a device driver keeps reading an MMIO register in an interrupt
 * handler after a slot isolation event, it might be broken.
 * This sets the threshold for how many read attempts we allow
 * before printing an error message.
 */
#define EEH_MAX_FAILS	2100000

/* Time to wait for a PCI slot to report status, in milliseconds */
#define PCI_BUS_RESET_WAIT_MSEC (60*1000)

/* RTAS tokens */
static int ibm_set_eeh_option;
static int ibm_set_slot_reset;
static int ibm_read_slot_reset_state;
static int ibm_read_slot_reset_state2;
static int ibm_slot_error_detail;
static int ibm_get_config_addr_info;
static int ibm_get_config_addr_info2;
static int ibm_configure_bridge;

int eeh_subsystem_enabled;
EXPORT_SYMBOL(eeh_subsystem_enabled);

/* Lock to avoid races due to multiple reports of an error */
static DEFINE_RAW_SPINLOCK(confirm_error_lock);

/* Buffer for reporting slot-error-detail rtas calls. Its here
 * in BSS, and not dynamically alloced, so that it ends up in
 * RMO where RTAS can access it.
 */
static unsigned char slot_errbuf[RTAS_ERROR_LOG_MAX];
static DEFINE_SPINLOCK(slot_errbuf_lock);
static int eeh_error_buf_size;

/* Buffer for reporting pci register dumps. Its here in BSS, and
 * not dynamically alloced, so that it ends up in RMO where RTAS
 * can access it.
 */
#define EEH_PCI_REGS_LOG_LEN 4096
static unsigned char pci_regs_buf[EEH_PCI_REGS_LOG_LEN];

/* System monitoring statistics */
static unsigned long no_device;
static unsigned long no_dn;
static unsigned long no_cfg_addr;
static unsigned long ignored_check;
static unsigned long total_mmio_ffs;
static unsigned long false_positives;
static unsigned long slot_resets;

#define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE)

/* --------------------------------------------------------------- */
/* Below lies the EEH event infrastructure */

static void rtas_slot_error_detail(struct pci_dn *pdn, int <