linux_dsm_epyc7002/drivers
Jack Morgenstein 3b4a8cd51e IB/mlx4: Don't allow userspace open while recovering from catastrophic error
Userspace apps are supposed to release all ib device resources if they
receive a fatal async event (IBV_EVENT_DEVICE_FATAL).  However, the
app has no way of knowing when the device has come back up, except to
repeatedly attempt ibv_open_device() until it succeeds.

However, currently there is no protection against the open succeeding
while the device is in being removed following the fatal event.  In
this case, the open will succeed, but as a result the device waits in
the middle of its removal until the new app releases its resources --
and the new app will not do so, since the open succeeded at a point
following the fatal event generation.

This patch adds an "active" flag to the device. The active flag is set
to false (in the fatal event flow) before the "fatal" event is
generated, so any subsequent ibv_dev_open() call to the device will
fail until the device comes back up, thus preventing the above
deadlock.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:24:50 -07:00
..
accessibility
acpi ACPI: don't free non-existent backlight in acpi video module 2009-08-28 15:17:07 -04:00
amba
ata ata_piix: parallel scanning on PATA needs an extra locking 2009-08-31 17:25:00 -10:00
atm
auxdisplay
base PM / Driver Core: Kill dev_pm_ops platform warning for now 2009-08-10 23:41:18 +02:00
block mg_disk: Add missing ready status check on mg_write() 2009-07-28 08:57:33 +02:00
bluetooth
cdrom
char pty: don't limit the writes to 'pty_space()' inside 'pty_write()' 2009-09-05 13:27:10 -07:00
clocksource sh: CMT suspend/resume 2009-08-15 12:58:45 +09:00
connector connector: maintainer/mail update. 2009-07-21 12:43:51 -07:00
cpufreq [CPUFREQ] Re-enable cpufreq suspend and resume code 2009-09-01 12:45:08 -04:00
cpuidle
crypto
dca
dio
dma Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx 2009-07-30 16:46:31 -07:00
edac amd64_edac: print debug statements only on error 2009-08-04 12:10:06 +02:00
eisa
firewire Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394-2.6 2009-09-05 14:59:00 -07:00
firmware
gpio
gpu Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/anholt/drm-intel 2009-08-31 17:22:10 -10:00
hid Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid 2009-07-22 09:30:07 -07:00
hwmon hwmon: (asus_atk0110) Fix upper limit readings 2009-07-28 16:31:39 +02:00
i2c i2c-stu300: I2C STU300 stability updates 2009-08-20 22:27:58 +01:00
ide ide-tape: Don't leak kernel stack information 2009-07-21 20:36:25 -07:00
idle
ieee1394
ieee802154
infiniband IB/mlx4: Don't allow userspace open while recovering from catastrophic error 2009-09-05 20:24:50 -07:00
input Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input 2009-09-05 13:41:29 -07:00
isdn Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6 2009-08-04 15:38:34 -07:00
leds leds: after setting inverted attribute, we must update the LED 2009-08-26 20:06:53 -07:00
lguest lguest and virtio: cleanup struct definitions to Linux style. 2009-07-30 16:03:46 +09:30
macintosh m68k: count can reach 51, not 50 2009-08-26 23:14:49 +02:00
mca
md dm snapshot: fix on disk chunk size validation 2009-09-04 20:40:43 +01:00
media V4L/DVB (12502): gspca - sn9c20x: Fix gscpa sn9c20x build errors. 2009-08-31 02:24:54 -03:00
memstick
message
mfd mfd: twl4030 irq fixes 2009-08-04 20:31:32 +02:00
misc cb710: use SG_MITER_TO_SG/SG_MITER_FROM_SG 2009-07-31 12:28:46 +02:00
mmc drivers/mmc: correct error-handling code 2009-08-07 10:39:56 -07:00
mtd mtd: nftl: fix offset alignments 2009-09-03 14:59:16 +01:00
net mlx4_core: Distinguish multiple devices in /proc/interrupts 2009-09-05 20:24:50 -07:00
nubus
of of/mdio: Add support function for Ethernet fixed-link property 2009-07-22 09:27:18 -07:00
oprofile
parisc parisc: hppb.c - fix printk format strings 2009-08-02 15:42:39 +02:00
parport
pci PCI SR-IOV: correct broken resource alignment calculations 2009-08-30 08:37:25 -07:00
pcmcia
platform toshiba_acpi: return on a fail path 2009-08-28 15:17:07 -04:00
pnp
power Merge git://git.infradead.org/users/cbou/battery-2.6.31 2009-07-30 16:45:53 -07:00
pps pps: fix incorrect verdict check 2009-08-26 20:06:52 -07:00
ps3
rapidio
regulator
rtc rtc: mark if rtc-cmos drivers were successfully registered 2009-07-29 19:10:35 -07:00
s390 [S390] drivers/s390: put NULL test before dereference 2009-08-23 18:10:00 +02:00
sbus
scsi [SCSI] mpt2sas: fix config request and diag reset deadlock 2009-08-14 09:16:05 -05:00
serial ARM: S3C64XX: serial: Fix a typo in Kconfig 2009-08-14 00:43:46 +01:00
sh
sn
spi spi_s3c24xx: fix transfer setup code 2009-08-18 16:31:13 -07:00
ssb
staging Staging: rspiusb: Fix buffer overflow 2009-08-07 16:12:03 -07:00
tc
telephony
thermal thermal_sys: check get_temp return value 2009-08-26 20:06:52 -07:00
uio
usb USB: fix oops on disconnect in cdc-acm 2009-08-07 16:05:14 -07:00
uwb
video xenfb: connect to backend before registering fb 2009-08-27 12:31:18 -07:00
virtio virtio: refactor find_vqs 2009-07-30 16:03:45 +09:30
vlynq
w1 drivers/w1/masters/omap_hdq.c: fix missing mutex unlock 2009-08-07 10:39:55 -07:00
watchdog [WATCHDOG] ar7_wdt: fix path to ar7-specific headers 2009-08-15 13:05:01 +00:00
xen
zorro
Kconfig
Makefile