iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
a6685b573c
linux/drivers
History
Koby Elbaz a6685b573c habanalabs: block soft-reset on an unusable device 
A device with status malfunction indicates that it can't be used.
In such a case we do not support certain reset types, e.g.,
all kinds of soft-resets (compute reset, inference soft-reset),
and reset upon device release.

A hard-reset is the only way that an unusable device can change its
status. All other reset procedures can't put the device in a reset
procedure, which might ultimately cause the device to change its
status, unintentionally, to become operational again.

Such a scenario has recently occurred, when a user requested
a hard-reset while another heavy user workload was ongoing (reset
request is queued).
Since the workload couldn't finish within reset's timeout limits, the
reset has failed and set a device status malfunction.
Eventually, when the user released the FD, an unsuccessful soft-reset
occurred, hence followed by an additional hard-reset that changed the
ASICs status back to be operational.

Signed-off-by: Koby Elbaz <kelbaz@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2023-01-26 11:52:13 +02:00
..
accel habanalabs: block soft-reset on an unusable device 2023-01-26 11:52:13 +02:00
accessibility
acpi ACPI fixes for 6.2-rc2 2022-12-30 10:47:25 -08:00
amba ARM updates for 6.2 2022-12-13 15:22:14 -08:00
android
ata ata: ahci: Fix PCS quirk application for suspend 2022-12-27 11:06:57 +09:00
atm treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
auxdisplay
base Kbuild updates for v6.2 2022-12-19 12:33:32 -06:00
bcma
block treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
bluetooth treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
bus Char/Misc driver changes for 6.2-rc1 2022-12-16 03:49:24 -08:00
cdrom
char random: do not include <asm/archrandom.h> from random.h 2022-12-20 03:13:45 +01:00
clk A pile of clk driver updates with a small tracepoint patch to the clk core this 2022-12-13 13:46:07 -08:00
clocksource Updates for timers, timekeeping and drivers: 2022-12-12 12:52:02 -08:00
comedi
connector
counter counter: stm32-lptimer-cnt: fix the check on arr and cmp registers update 2022-11-26 16:49:28 -05:00
cpufreq linux-kselftest-next-6.2-rc1 2022-12-12 16:39:38 -08:00
cpuidle powerpc updates for 6.2 2022-12-19 07:13:33 -06:00
crypto powerpc updates for 6.2 2022-12-19 07:13:33 -06:00
cxl cxl/region: Fix memdev reuse check 2022-12-08 13:03:47 -08:00
dax
dca
devfreq PM / devfreq: event: use devm_platform_get_and_ioremap_resource() 2022-12-05 21:57:20 +09:00
dio
dma dmaengine updates for v6.2 2022-12-19 08:54:17 -06:00
dma-buf drm-misc-next for v6.3: 2023-01-04 14:59:25 +01:00
edac Merge branches 'edac-ghes' and 'edac-misc' into edac-updates-for-v6.2 2022-12-12 15:40:03 +01:00
eisa
extcon Char/Misc driver changes for 6.2-rc1 2022-12-16 03:49:24 -08:00
firewire
firmware drm-misc-next for v6.3: 2023-01-16 15:33:28 +10:00
fpga Char/Misc driver changes for 6.2-rc1 2022-12-16 03:49:24 -08:00
fsi use less confusing names for iov_iter direction initializers 2022-11-25 13:01:55 -05:00
gnss
gpio pwm: Changes for v6.2-rc1 2022-12-21 09:41:28 -08:00
gpu drm-misc-next for v6.3: 2023-01-25 12:14:08 +10:00
greybus
hid treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
hsi
hte
hv Networking changes for 6.2. 2022-12-13 15:47:48 -08:00
hwmon hwmon updates for v6.2 merge window 2022-12-13 13:09:38 -08:00
hwspinlock
hwtracing coresight: etm4x: fix repeated words in comments 2022-11-28 18:29:53 +00:00
i2c Core got a new helper 'i2c_client_get_device_id', designware got some 2022-12-15 14:47:10 -08:00
i3c i3c: export SETDASA method 2022-12-11 21:25:58 +01:00
idle
iio Char/Misc driver changes for 6.2-rc1 2022-12-16 03:49:24 -08:00
infiniband v6.2 merge window 2nd pull request 2022-12-17 08:23:42 -06:00
input treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
interconnect
iommu IOMMU Updates for Linux v6.2 2022-12-19 08:34:39 -06:00
ipack
irqchip RISC-V Patches for the 6.2 Merge Window, Part 1 2022-12-14 15:23:49 -08:00
isdn treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
leds treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
macintosh
mailbox - qcom: enable sc8280xp, sm8550 and sm4250 support 2022-12-21 09:31:18 -08:00
mcb mcb: mcb-parse: fix error handing in chameleon_parse_gdd() 2022-12-02 17:48:04 +01:00
md - Fix use-after-free races due to missing resource cleanup during DM 2022-12-13 10:58:09 -08:00
media treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
memory ARM updates for 6.2 2022-12-13 15:22:14 -08:00
memstick memstick/mspro_block: Convert to use sysfs_emit()/sysfs_emit_at() APIs 2022-12-09 10:29:58 +01:00
message
mfd - New Drivers 2022-12-21 09:19:24 -08:00
misc habanalabs: move driver to accel subsystem 2023-01-26 11:52:10 +02:00
mmc MMC core: 2022-12-13 13:41:26 -08:00
most
mtd MTD core changes: 2022-12-13 12:32:07 -08:00
mux
net treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
nfc treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
ntb
nubus
nvdimm nvdimm/region: Move cache management to the region driver 2022-12-02 23:52:32 -08:00
nvme block-6.2-2022-12-29 2022-12-29 16:57:29 -08:00
nvmem Char/Misc driver changes for 6.2-rc1 2022-12-16 03:49:24 -08:00
of Devicetree updates for v6.2, part 2: 2022-12-20 08:48:24 -06:00
opp
parisc parisc: led: Fix potential null-ptr-deref in start_task() 2022-12-17 23:19:38 +01:00
parport
pci phy-for-6.2 2022-12-19 08:40:58 -06:00
pcmcia treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
peci
perf RISC-V Patches for the 6.2 Merge Window, Part 1 2022-12-14 15:23:49 -08:00
phy phy-for-6.2 2022-12-19 08:40:58 -06:00
pinctrl Pin control changes for the v6.2 kernel cycle: 2022-12-13 13:03:06 -08:00
platform USB/Thunderbolt driver changes for 6.2-rc1 2022-12-16 03:22:53 -08:00
pnp PNP: Do not disable devices on suspend when they cannot be re-enabled on resume 2022-11-25 19:36:52 +01:00
power power supply and reset changes for the v6.2 series 2022-12-17 08:39:31 -06:00
powercap powercap: idle_inject: Fix warnings with make W=1 2022-12-02 20:49:49 +01:00
pps
ps3
ptp Networking changes for 6.2. 2022-12-13 15:47:48 -08:00
pwm pwm: Changes for v6.2-rc1 2022-12-21 09:41:28 -08:00
rapidio rapidio: devices: fix missing put_device in mport_cdev_open 2022-12-11 19:30:20 -08:00
ras
regulator regulator: Fixes for v6.2 2022-12-23 14:38:00 -08:00
remoteproc remoteproc: core: Do pm_relax when in RPROC_OFFLINE state 2022-12-07 11:20:55 -07:00
reset
rpmsg
rtc - New Drivers 2022-12-21 09:19:24 -08:00
s390 Driver Core changes for 6.2-rc1 2022-12-16 03:54:54 -08:00
sbus
scsi treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
sh
siox
slimbus
soc ARM: SoC fixes for 6.2 2022-12-19 16:07:59 -06:00
soundwire soundwire updates for 6.2 2022-12-19 08:47:33 -06:00
spi spi: Fix for v6.2 2022-12-23 14:44:08 -08:00
spmi
ssb
staging treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
target SCSI misc on 20221213 2022-12-14 08:58:51 -08:00
tc
tee SoC driver updates for 6.2 2022-12-12 10:17:08 -08:00
thermal More thermal control updates for 6.2-rc1 2022-12-15 10:16:04 -08:00
thunderbolt
tty treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
ufs SCSI misc on 20221213 2022-12-14 08:58:51 -08:00
uio
usb treewide: Convert del_timer*() to timer_shutdown*() 2022-12-25 13:38:09 -08:00
vdpa
vfio Driver Core changes for 6.2-rc1 2022-12-16 03:54:54 -08:00
vhost use less confusing names for iov_iter direction initializers 2022-11-25 13:01:55 -05:00
video drm-misc-next for $kernel-version: 2023-01-24 17:36:29 +01:00
virt Char/Misc driver changes for 6.2-rc1 2022-12-16 03:49:24 -08:00
virtio
vlynq
w1
watchdog linux-watchdog 6.2-rc1 tag 2022-12-17 08:34:01 -06:00
xen drm for 6.2: 2022-12-13 11:59:58 -08:00
zorro
Kconfig
Makefile habanalabs: move driver to accel subsystem 2023-01-26 11:52:10 +02:00