The PCI error recovery code will printk diagnostic info when
a PCI error event occurs. Change the messages to include the slot
location code, which is how most sysadmins will know the device.
Signed-off-by: NLinas Vepstas <linas@austin.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

When a PCI device driver does not support PCI error recovery,
the powerpc/pseries code takes a walk through a branch of code
that resets the failure counter. Because of this, if a broken
PCI card is present, the kernel will attempt to reset it an
infinite number of times. (This is annoying but mostly harmless:
each reset takes about 10-20 seconds, and uses almost no CPU time).

This patch preserves the failure count across resets.
Signed-off-by: NLinas Vepstas <linas@austin.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

The current PCI error recovery system keeps track of the number of PCI card
resets, and refuses to bring a card back up if this number is too large.
The goal of doing this was to avoid an infinite loop of resets if a card is
obviously dead.  However, if the failures are rare, but the machine has a
high uptime, this mechanism might still be triggered; this is too harsh.

This patch will avoids this problem by decrementing the fail count after an
hour.  Thus, as long as a pci card BSOD's less than 6 times an hour, it
will continue to be reset indefinitely.  If it's failure rate is greater
than that, it will be taken off-line permanently.

This patch is larger than it might otherwise be because it changes
indentation by removing a pointless while-loop.  The while loop is not
needed, as the handler is invoked once fo each event (by schedule_work());
the loop is leftover cruft from an earlier implementation.
Signed-off-by: NLinas Vepstas <linas@austin.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

The recent patch to print device names in EEH reset messages
was lacking ... this patch works better.
Signed-off-by: NLinas Vepstas <linas@linas.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

The current code prints an ambiguous message if the recovery
of a failed PCI device fails. Give this special case its own
unique message.
Signed-off-by: NLinas Vepstas <linas@austin.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

This avoids printk'ing a NULL string.
Signed-off-by: NLinas Vepstas <linas@linas.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

This patch fixes a crash in handle_eeh_events,
but ethtool -t still doesnt work right.

...
pepino:~ # cpu 0x3: Vector: 300 (Data Access) at [c00000005192bbe0]
    pc: c00000000004a380: .handle_eeh_events+0xe0/0x23c
    lr: c00000000004a374: .handle_eeh_events+0xd4/0x23c
    sp: c00000005192be60
   msr: 9000000000009032
   dar: 268
 dsisr: 40000000
  current = 0xc0000001fe7bf1a0
  paca    = 0xc00000000048b280
    pid   = 16322, comm = eehd
enter ? for help
[c00000005192bf00] c00000000004a808 .eeh_event_handler+0xcc/0x130
[c00000005192bf90] c000000000025e00 .kernel_thread+0x4c/0x68

...

(none):/# /usr/sbin/ethtool -i eth0
driver: e100
version: 3.5.10-k2-NAPI
firmware-version: N/A
bus-info: 0000:21:01.0
(none):/# /usr/sbin/ethtool -t eth0
Call Trace:
[C00000000F8DEFF0] [C00000000000F270] .show_stack+0x74/0x1b4 (unreliable)
[C00000000F8DF0A0] [C000000000049D04] .eeh_dn_check_failure+0x290/0x2d8
[C00000000F8DF150] [C000000000049E58] .eeh_check_failure+0x10c/0x138
[C00000000F8DF1E0] [C0000000002DFDB0] .e100_hw_reset+0x70/0xf4
[C00000000F8DF270] [C0000000002E1BBC] .e100_hw_init+0x2c/0x260
[C00000000F8DF310] [C0000000002E2464] .e100_loopback_test+0x8c/0x220
[C00000000F8DF3C0] [C0000000002E28DC] .e100_diag_test+0xdc/0x16c
[C00000000F8DF490] [C000000000420BE0] .dev_ethtool+0xf24/0x14f8
[C00000000F8DF8F0] [C00000000041F4A8] .dev_ioctl+0x5cc/0x740
[C00000000F8DFA20] [C00000000040FEFC] .sock_ioctl+0x3d0/0x404
[C00000000F8DFAC0] [C0000000000D513C] .do_ioctl+0x68/0x108
[C00000000F8DFB50] [C0000000000D56B0] .vfs_ioctl+0x4d4/0x510
[C00000000F8DFC10] [C0000000000D5740] .sys_ioctl+0x54/0x94
[C00000000F8DFCC0] [C0000000000FB6EC] .ethtool_ioctl+0x11c/0x150
[C00000000F8DFD60] [C0000000000F7E40] .compat_sys_ioctl+0x338/0x3bc
[C00000000F8DFE30] [C00000000000871C] syscall_exit+0x0/0x40
EEH: Detected PCI bus error on device 0000:21:01.0
EEH: This PCI device has failed 1 times since last reboot: <NULL> -

modprobe: FATAL: Could not load /lib/modules/2.6.16-rc4-git7/modules.dep: No such file or directory

Cannot get strings: No such device
(none):/#
(none):/# EEH: Unable to configure device bridge (-3) for /pci@400000000110/pci@2,2

(none):/# Call Trace:
[C00000000FA17940] [C00000000000F270] .show_stack+0x74/0x1b4 (unreliable)
[C00000000FA179F0] [C000000000049D04] .eeh_dn_check_failure+0x290/0x2d8
[C00000000FA17AA0] [C00000000001E114] .rtas_read_config+0x120/0x154
[C00000000FA17B40] [C000000000049664] .early_enable_eeh+0x274/0x2bc
[C00000000FA17C00] [C000000000049708] .eeh_add_device_early+0x5c/0x6c
[C00000000FA17C90] [C000000000049748] .eeh_add_device_tree_early+0x30/0x5c
[C00000000FA17D20] [C000000000046568] .pcibios_add_pci_devices+0x8c/0x1f8
[C00000000FA17DD0] [C00000000004A528] .eeh_reset_device+0xe0/0x110
[C00000000FA17E60] [C00000000004A698] .handle_eeh_events+0x140/0x250
[C00000000FA17F00] [C00000000004AC7C] .eeh_event_handler+0xe8/0x140
[C00000000FA17F90] [C000000000025784] .kernel_thread+0x4c/0x68
EEH: Detected PCI bus error on device <NULL>
EEH: This PCI device has failed 1 times since last reboot: <NULL> -
EEH: Unable to configure device bridge (-3) for /pci@400000000110/pci@2,2
Call Trace:
[C00000000FA17940] [C00000000000F270] .show_stack+0x74/0x1b4 (unreliable)
[C00000000FA179F0] [C000000000049D04] .eeh_dn_check_failure+0x290/0x2d8
[C00000000FA17AA0] [C00000000001E114] .rtas_read_config+0x120/0x154
[C00000000FA17B40] [C000000000049664] .early_enable_eeh+0x274/0x2bc
[C00000000FA17C00] [C000000000049708] .eeh_add_device_early+0x5c/0x6c
[C00000000FA17C90] [C000000000049748] .eeh_add_device_tree_early+0x30/0x5c
[C00000000FA17D20] [C000000000046568] .pcibios_add_pci_devices+0x8c/0x1f8
[C00000000FA17DD0] [C00000000004A528] .eeh_reset_device+0xe0/0x110
[C00000000FA17E60] [C00000000004A698] .handle_eeh_events+0x140/0x250
[C00000000FA17F00] [C00000000004AC7C] .eeh_event_handler+0xe8/0x140
[C00000000FA17F90] [C000000000025784] .kernel_thread+0x4c/0x68
EEH: Detected PCI bus error on device <NULL>
EEH: This PCI device has failed 1 times since last reboot: <NULL> -
EEH: Unable to configure device bridge (-3) for /pci@400000000110/pci@2,2
Call Trace:
[C00000000FA17940] [C00000000000F270] .show_stack+0x74/0x1b4 (unreliable)
[C00000000FA179F0] [C000000000049D04] .eeh_dn_check_failure+0x290/0x2d8
[C00000000FA17AA0] [C00000000001E114] .rtas_read_config+0x120/0x154
[C00000000FA17B40] [C000000000049664] .early_enable_eeh+0x274/0x2bc
[C00000000FA17C00] [C000000000049708] .eeh_add_device_early+0x5c/0x6c
[C00000000FA17C90] [C000000000049748] .eeh_add_device_tree_early+0x30/0x5c
[C00000000FA17D20] [C000000000046568] .pcibios_add_pci_devices+0x8c/0x1f8
[C00000000FA17DD0] [C00000000004A528] .eeh_reset_device+0xe0/0x110
[C00000000FA17E60] [C00000000004A698] .handle_eeh_events+0x140/0x250
[C00000000FA17F00] [C00000000004AC7C] .eeh_event_handler+0xe8/0x140
[C00000000FA17F90] [C000000000025784] .kernel_thread+0x4c/0x68
EEH: Detected PCI bus error on device <NULL>
and so on
Signed-off-by: NOlaf Hering <olh@suse.de>
Acked-by: NLinas Vepstas <linas@austin.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

<asm/systemcfg.h> is gone now, and the PCI error recovery constants
in include/linux/pci.h changed their names in the process of getting
accepted.
Signed-off-by: NPaul Mackerras <paulus@samba.org>
(cherry picked from 5a2516156c591fc3d2059fbd93f97e15eb6010d6 commit)

239-eeh-multifunction-consolidate.patch

New-style firmware will often place multiple different functions
under a non-EEH-aware parent.  However, these devices might share
a common PE "partition endpoint" and config address, ad thus any
EEH events will affect all of the devices in common.  This patch
makes the effort to find all of these common devices and handle
them together.
Signed-off-by: NLinas Vepstas <linas@austin.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>
(cherry picked from 216810296bb97d39da8e176822e9de78d2f00187 commit)

238-eeh-stop-if-reset_failed.patch

If the firmware is unable to reset the PCI slot for some reason, then
don't attempt any further recovery steps after that point.  Instead,
mark the device as permanently failed.
Signed-off-by: NLinas Vepstas <linas@austin.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>
(cherry picked from e06b942521eb2cdaf232726f45a820d5837acb12 commit)

234-eeh-find-pe.patch

The find_device_pe() routine is duplicated in two files. Remove one of
the two copies, declare the other extern.
Signed-off-by: NLinas Vepstas <linas@austin.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>
(cherry picked from 48408e708282d4d0269136ff27ea5acbd9410b5a commit)

Various PCI bus errors can be signaled by newer PCI controllers.  The
core error recovery routines are architecture dependent.  This patch adds
a recovery infrastructure for the  PPC64 pSeries systems.
Signed-off-by: NLinas Vepstas <linas@austin.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>
(cherry picked from e8ca11b460c4c9c7fa6b529be221529ebd770e38 commit)