IPC messages transmitted to the device must be marked as
allocated - status field must be set to 1. The VPU driver
has IVPU_IPC_HDR_ALLOCATED incorrectly defined. Future VPU
firmware versions will reject all IPC messages with invalid
status and will not work with a VPU driver that is missing
this fix.
Fixes: 5d7422cfb4 ("accel/ivpu: Add IPC driver and JSM messages")
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323125504.2586442-9-stanislaw.gruszka@linux.intel.com
The driver calculates the wrong frequency because it ignores
the workpoint config and this cause undesired power/performance
characteristics. Fix this by using the workpoint config in
the freq calculations.
Fixes: 35b137630f ("accel/ivpu: Introduce a new DRM driver for Intel VPU")
Co-developed-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323125504.2586442-8-stanislaw.gruszka@linux.intel.com
The support for single tile SKUs was dropped from MTL.
Note that we can still boot the VPU with 1-tile work point
config - this is independent from number of tiles present
in the VPU.
Co-developed-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323125504.2586442-7-stanislaw.gruszka@linux.intel.com
Use pci_set_power_state() to disable buttress when device is removed.
This is workaround of hardware bug that hangs the system.
Additionally not disabling buttress prevents CPU enter deeper Pkg-C
states when the driver is unloaded or fail to probe.
Fixes: 35b137630f ("accel/ivpu: Introduce a new DRM driver for Intel VPU")
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323125504.2586442-6-stanislaw.gruszka@linux.intel.com
Remove FPGA workaround on power_down to skip checking for noc
quiescent state.
Put VPU in reset before powering it down and skip manipulating
registers that are reset by the VPU reset.
This fixes power down errors where VPU is powered down just after VPU
is booted.
Fixes: 35b137630f ("accel/ivpu: Introduce a new DRM driver for Intel VPU")
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323125504.2586442-5-stanislaw.gruszka@linux.intel.com
The SSID=1 is used by the firmware as default value in
case SSID mapping is not initialized. This allows
detecting use of miss-configured memory contexts.
The future FW versions may not allow using SSID=1.
SSID=65 is valid value, number of contexts are limited
by number of available command queues, but SSID can be
any u16 value.
Fixes: 35b137630f ("accel/ivpu: Introduce a new DRM driver for Intel VPU")
Co-developed-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323125504.2586442-4-stanislaw.gruszka@linux.intel.com
We should not access hardware after we unbind from the bus.
Use drm_dev_enter() / drm_dev_exit() to mark code sections where
hardware is accessed (and not already protected by other locks)
and drm_dev_unplug() to mark device is gone.
Fixes: 35b137630f ("accel/ivpu: Introduce a new DRM driver for Intel VPU")
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323125504.2586442-2-stanislaw.gruszka@linux.intel.com
When accel drivers are disabled do not process into
sub-directories and create built-in archives:
AR drivers/accel/habanalabs/built-in.a
AR drivers/accel/ivpu/built-in.a
Fixes: 35b137630f ("accel/ivpu: Introduce a new DRM driver for Intel VPU")
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230301162508.3963484-1-stanislaw.gruszka@linux.intel.com
(cherry picked from commit dd61bbd0d1)
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
F_SEAL_EXEC") which permits the setting of the memfd execute bit at
memfd creation time, with the option of sealing the state of the X bit.
- Peter Xu adds a patch series ("mm/hugetlb: Make huge_pte_offset()
thread-safe for pmd unshare") which addresses a rare race condition
related to PMD unsharing.
- Several folioification patch serieses from Matthew Wilcox, Vishal
Moola, Sidhartha Kumar and Lorenzo Stoakes
- Johannes Weiner has a series ("mm: push down lock_page_memcg()") which
does perform some memcg maintenance and cleanup work.
- SeongJae Park has added DAMOS filtering to DAMON, with the series
"mm/damon/core: implement damos filter". These filters provide users
with finer-grained control over DAMOS's actions. SeongJae has also done
some DAMON cleanup work.
- Kairui Song adds a series ("Clean up and fixes for swap").
- Vernon Yang contributed the series "Clean up and refinement for maple
tree".
- Yu Zhao has contributed the "mm: multi-gen LRU: memcg LRU" series. It
adds to MGLRU an LRU of memcgs, to improve the scalability of global
reclaim.
- David Hildenbrand has added some userfaultfd cleanup work in the
series "mm: uffd-wp + change_protection() cleanups".
- Christoph Hellwig has removed the generic_writepages() library
function in the series "remove generic_writepages".
- Baolin Wang has performed some maintenance on the compaction code in
his series "Some small improvements for compaction".
- Sidhartha Kumar is doing some maintenance work on struct page in his
series "Get rid of tail page fields".
- David Hildenbrand contributed some cleanup, bugfixing and
generalization of pte management and of pte debugging in his series "mm:
support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on all architectures with swap
PTEs".
- Mel Gorman and Neil Brown have removed the __GFP_ATOMIC allocation
flag in the series "Discard __GFP_ATOMIC".
- Sergey Senozhatsky has improved zsmalloc's memory utilization with his
series "zsmalloc: make zspage chain size configurable".
- Joey Gouly has added prctl() support for prohibiting the creation of
writeable+executable mappings. The previous BPF-based approach had
shortcomings. See "mm: In-kernel support for memory-deny-write-execute
(MDWE)".
- Waiman Long did some kmemleak cleanup and bugfixing in the series
"mm/kmemleak: Simplify kmemleak_cond_resched() & fix UAF".
- T.J. Alumbaugh has contributed some MGLRU cleanup work in his series
"mm: multi-gen LRU: improve".
- Jiaqi Yan has provided some enhancements to our memory error
statistics reporting, mainly by presenting the statistics on a per-node
basis. See the series "Introduce per NUMA node memory error
statistics".
- Mel Gorman has a second and hopefully final shot at fixing a CPU-hog
regression in compaction via his series "Fix excessive CPU usage during
compaction".
- Christoph Hellwig does some vmalloc maintenance work in the series
"cleanup vfree and vunmap".
- Christoph Hellwig has removed block_device_operations.rw_page() in ths
series "remove ->rw_page".
- We get some maple_tree improvements and cleanups in Liam Howlett's
series "VMA tree type safety and remove __vma_adjust()".
- Suren Baghdasaryan has done some work on the maintainability of our
vm_flags handling in the series "introduce vm_flags modifier functions".
- Some pagemap cleanup and generalization work in Mike Rapoport's series
"mm, arch: add generic implementation of pfn_valid() for FLATMEM" and
"fixups for generic implementation of pfn_valid()"
- Baoquan He has done some work to make /proc/vmallocinfo and
/proc/kcore better represent the real state of things in his series
"mm/vmalloc.c: allow vread() to read out vm_map_ram areas".
- Jason Gunthorpe rationalized the GUP system's interface to the rest of
the kernel in the series "Simplify the external interface for GUP".
- SeongJae Park wishes to migrate people from DAMON's debugfs interface
over to its sysfs interface. To support this, we'll temporarily be
printing warnings when people use the debugfs interface. See the series
"mm/damon: deprecate DAMON debugfs interface".
- Andrey Konovalov provided the accurately named "lib/stackdepot: fixes
and clean-ups" series.
- Huang Ying has provided a dramatic reduction in migration's TLB flush
IPI rates with the series "migrate_pages(): batch TLB flushing".
- Arnd Bergmann has some objtool fixups in "objtool warning fixes".
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCY/PoPQAKCRDdBJ7gKXxA
jlvpAPsFECUBBl20qSue2zCYWnHC7Yk4q9ytTkPB/MMDrFEN9wD/SNKEm2UoK6/K
DmxHkn0LAitGgJRS/W9w81yrgig9tAQ=
=MlGs
-----END PGP SIGNATURE-----
Merge tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
F_SEAL_EXEC") which permits the setting of the memfd execute bit at
memfd creation time, with the option of sealing the state of the X
bit.
- Peter Xu adds a patch series ("mm/hugetlb: Make huge_pte_offset()
thread-safe for pmd unshare") which addresses a rare race condition
related to PMD unsharing.
- Several folioification patch serieses from Matthew Wilcox, Vishal
Moola, Sidhartha Kumar and Lorenzo Stoakes
- Johannes Weiner has a series ("mm: push down lock_page_memcg()")
which does perform some memcg maintenance and cleanup work.
- SeongJae Park has added DAMOS filtering to DAMON, with the series
"mm/damon/core: implement damos filter".
These filters provide users with finer-grained control over DAMOS's
actions. SeongJae has also done some DAMON cleanup work.
- Kairui Song adds a series ("Clean up and fixes for swap").
- Vernon Yang contributed the series "Clean up and refinement for maple
tree".
- Yu Zhao has contributed the "mm: multi-gen LRU: memcg LRU" series. It
adds to MGLRU an LRU of memcgs, to improve the scalability of global
reclaim.
- David Hildenbrand has added some userfaultfd cleanup work in the
series "mm: uffd-wp + change_protection() cleanups".
- Christoph Hellwig has removed the generic_writepages() library
function in the series "remove generic_writepages".
- Baolin Wang has performed some maintenance on the compaction code in
his series "Some small improvements for compaction".
- Sidhartha Kumar is doing some maintenance work on struct page in his
series "Get rid of tail page fields".
- David Hildenbrand contributed some cleanup, bugfixing and
generalization of pte management and of pte debugging in his series
"mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on all architectures with
swap PTEs".
- Mel Gorman and Neil Brown have removed the __GFP_ATOMIC allocation
flag in the series "Discard __GFP_ATOMIC".
- Sergey Senozhatsky has improved zsmalloc's memory utilization with
his series "zsmalloc: make zspage chain size configurable".
- Joey Gouly has added prctl() support for prohibiting the creation of
writeable+executable mappings.
The previous BPF-based approach had shortcomings. See "mm: In-kernel
support for memory-deny-write-execute (MDWE)".
- Waiman Long did some kmemleak cleanup and bugfixing in the series
"mm/kmemleak: Simplify kmemleak_cond_resched() & fix UAF".
- T.J. Alumbaugh has contributed some MGLRU cleanup work in his series
"mm: multi-gen LRU: improve".
- Jiaqi Yan has provided some enhancements to our memory error
statistics reporting, mainly by presenting the statistics on a
per-node basis. See the series "Introduce per NUMA node memory error
statistics".
- Mel Gorman has a second and hopefully final shot at fixing a CPU-hog
regression in compaction via his series "Fix excessive CPU usage
during compaction".
- Christoph Hellwig does some vmalloc maintenance work in the series
"cleanup vfree and vunmap".
- Christoph Hellwig has removed block_device_operations.rw_page() in
ths series "remove ->rw_page".
- We get some maple_tree improvements and cleanups in Liam Howlett's
series "VMA tree type safety and remove __vma_adjust()".
- Suren Baghdasaryan has done some work on the maintainability of our
vm_flags handling in the series "introduce vm_flags modifier
functions".
- Some pagemap cleanup and generalization work in Mike Rapoport's
series "mm, arch: add generic implementation of pfn_valid() for
FLATMEM" and "fixups for generic implementation of pfn_valid()"
- Baoquan He has done some work to make /proc/vmallocinfo and
/proc/kcore better represent the real state of things in his series
"mm/vmalloc.c: allow vread() to read out vm_map_ram areas".
- Jason Gunthorpe rationalized the GUP system's interface to the rest
of the kernel in the series "Simplify the external interface for
GUP".
- SeongJae Park wishes to migrate people from DAMON's debugfs interface
over to its sysfs interface. To support this, we'll temporarily be
printing warnings when people use the debugfs interface. See the
series "mm/damon: deprecate DAMON debugfs interface".
- Andrey Konovalov provided the accurately named "lib/stackdepot: fixes
and clean-ups" series.
- Huang Ying has provided a dramatic reduction in migration's TLB flush
IPI rates with the series "migrate_pages(): batch TLB flushing".
- Arnd Bergmann has some objtool fixups in "objtool warning fixes".
* tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (505 commits)
include/linux/migrate.h: remove unneeded externs
mm/memory_hotplug: cleanup return value handing in do_migrate_range()
mm/uffd: fix comment in handling pte markers
mm: change to return bool for isolate_movable_page()
mm: hugetlb: change to return bool for isolate_hugetlb()
mm: change to return bool for isolate_lru_page()
mm: change to return bool for folio_isolate_lru()
objtool: add UACCESS exceptions for __tsan_volatile_read/write
kmsan: disable ftrace in kmsan core code
kasan: mark addr_has_metadata __always_inline
mm: memcontrol: rename memcg_kmem_enabled()
sh: initialize max_mapnr
m68k/nommu: add missing definition of ARCH_PFN_OFFSET
mm: percpu: fix incorrect size in pcpu_obj_full_size()
maple_tree: reduce stack usage with gcc-9 and earlier
mm: page_alloc: call panic() when memoryless node allocation fails
mm: multi-gen LRU: avoid futile retries
migrate_pages: move THP/hugetlb migration support check to simplify code
migrate_pages: batch flushing TLB
migrate_pages: share more code between _unmap and _move
...
Update according to new dma-buf locking scheme.
Remove redundant WARN_ON()'s, dma_buf functions internally
have the same warnings already.
Fixes: 647371a660 ("accel/ivpu: Add GEM buffer object management")
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230202092114.2637452-5-stanislaw.gruszka@linux.intel.com
(cherry picked from commit ec6ec9c6ca)
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
The VPU_JSM_MSG_CONTEXT_DELETE will remove any resources associated
with the SSID, that included any blobs create by the user space
application.
The command can also remove doorbell registrations, but since this
does not work in HW scheduling case, we do not depend on this
capability and unregister the doorbells explicitly.
Fixes: cd7272215c ("accel/ivpu: Add command buffer submission logic")
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230202092114.2637452-3-stanislaw.gruszka@linux.intel.com
(cherry picked from commit 38257f514d)
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
FW API structures have been updated to fix misaligned
structure members.
Also changed JSM message header format to account for
future improvements.
Added explicit check for minimum supported JSM API version.
Fixes: 5d7422cfb4 ("accel/ivpu: Add IPC driver and JSM messages")
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230202092114.2637452-2-stanislaw.gruszka@linux.intel.com
(cherry picked from commit 4ea1e504db)
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
With extra warnings enabled, gcc warns about two assignments
of the same .mmap callback:
In file included from drivers/accel/ivpu/ivpu_drv.c:10:
include/drm/drm_accel.h:31:27: error: initialized field overwritten [-Werror=override-init]
31 | .mmap = drm_gem_mmap
| ^~~~~~~~~~~~
drivers/accel/ivpu/ivpu_drv.c:360:9: note: in expansion of macro 'DRM_ACCEL_FOPS'
360 | DRM_ACCEL_FOPS,
| ^~~~~~~~~~~~~~
Remove the unused local assignment.
Fixes: e868cc591e ("accel: Add .mmap to DRM_ACCEL_FOPS")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230126163804.3648051-2-arnd@kernel.org
(cherry picked from commit 918b8f7eee)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
At the moment, accel drivers can be built-in even with CONFIG_DRM=m,
but this causes a link failure:
x86_64-linux-ld: drivers/accel/ivpu/ivpu_drv.o: in function `ivpu_dev_init':
ivpu_drv.c:(.text+0x1535): undefined reference to `drmm_kmalloc'
x86_64-linux-ld: ivpu_drv.c:(.text+0x1562): undefined reference to `drmm_kmalloc'
x86_64-linux-ld: drivers/accel/ivpu/ivpu_drv.o: in function `ivpu_remove':
ivpu_drv.c:(.text+0x1faa): undefined reference to `drm_dev_unregister'
x86_64-linux-ld: drivers/accel/ivpu/ivpu_drv.o: in function `ivpu_probe':
ivpu_drv.c:(.text+0x1fef): undefined reference to `__devm_drm_dev_alloc'
The problem is that DRM_ACCEL is a 'bool' symbol, so driver that
only depend on DRM_ACCEL but not also on DRM do not see the restriction
to =m configs.
To ensure that each accel driver has an implied dependency on CONFIG_DRM,
enclose the entire Kconfig file in an if/endif check.
Fixes: 8bf4889762 ("drivers/accel: define kconfig and register a new major")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230127221504.2522909-1-arnd@kernel.org
(cherry picked from commit 3524c96a12)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
- Moved the driver to the accel subsystem. Currently only the files were
moved (including the uapi file which was also renamed). This doesn't
include registering to the accel subsystem. This will probably be only
in the next kernel version.
- In case of decoder error (axi error) in Gaudi2, we can now find the exact
IP that initiated the erroneous transaction and print the details for
better debug.
- Add more trace events. We now can trace mmio transactions and communication
with the preboot firmware.
- Add to Gaudi2 support for abrupt reset that is done by the firmware. This
was support so far only for Gaudi1.
- Add uAPI to flush memory transactions (to the device memory). This is
needed by the communications library in case of doing p2p with a host NIC
which access our HBM directly through the PCI BAR.
- Add uAPI to pass-through a request from user-space to firmware and get the
result back to user-space. This will allow the driver code to avoid the
need to add new packet (in the communication channel with the firmware) for
every new request type.
- Remove the option to export dma-buf by memory allocation handle in our uAPI.
This was planned for Gaudi2 but was never used. Instead, we will do export
by memory address (same as Gaudi1). In addition, we added the option to
specify an offset to the address. This is needed in Gaudi2 because there
the user allocates the entire HBM in one allocation, but would like to
export only small part of it.
- Multiple bug fixes, refactors and small optimizations.
-----BEGIN PGP SIGNATURE-----
iQEzBAABCgAdFiEE7TEboABC71LctBLFZR1NuKta54AFAmPS7fYACgkQZR1NuKta
54Bu/wf+I4dySZslvWhjqom9zYlubnwKLpLxuKGeR2OeMZxe5AJSyNCohmMXjl4S
ac+2qktRbecYXwNHCZBFjybKUgqBN5VuxRNRjV3/It+koON82QkMvBB48CeD7W/P
9y5b38LYOxqFixd5U5e7MpNhU1/AAKGnqEtQZgub0h0IeOrZM0RkTL6PJoUdQAcn
ap3pNXm6cpNKo5EZYlyRwEJRw1YlUKt3lcsKNnBDjij1j+IOtQ0sPA7Ii0YMdtqh
/gL81JkyZmgQBq9aGjr8vGyILvVTfm8qJu7t4hGEZ165bAP4bQaU9W+YMDgpKmgM
Bc+NghtCz13gmKPY/gudP5fDbPHUdA==
=fOxf
-----END PGP SIGNATURE-----
Merge tag 'drm-habanalabs-next-2023-01-26' of https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux into drm-next
This tag contains habanalabs driver and accel changes for v6.3:
- Moved the driver to the accel subsystem. Currently only the files were
moved (including the uapi file which was also renamed). This doesn't
include registering to the accel subsystem. This will probably be only
in the next kernel version.
- In case of decoder error (axi error) in Gaudi2, we can now find the exact
IP that initiated the erroneous transaction and print the details for
better debug.
- Add more trace events. We now can trace mmio transactions and communication
with the preboot firmware.
- Add to Gaudi2 support for abrupt reset that is done by the firmware. This
was support so far only for Gaudi1.
- Add uAPI to flush memory transactions (to the device memory). This is
needed by the communications library in case of doing p2p with a host NIC
which access our HBM directly through the PCI BAR.
- Add uAPI to pass-through a request from user-space to firmware and get the
result back to user-space. This will allow the driver code to avoid the
need to add new packet (in the communication channel with the firmware) for
every new request type.
- Remove the option to export dma-buf by memory allocation handle in our uAPI.
This was planned for Gaudi2 but was never used. Instead, we will do export
by memory address (same as Gaudi1). In addition, we added the option to
specify an offset to the address. This is needed in Gaudi2 because there
the user allocates the entire HBM in one allocation, but would like to
export only small part of it.
- Multiple bug fixes, refactors and small optimizations.
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Oded Gabbay <ogabbay@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20230126213317.GA1520525@ogabbay-vm-u20.habana-labs.com
When a decode error happens, we often don't know the exact root
cause (the erroneous address that was accessed) and the exact engine
that created the erroneous transaction.
To find out, we need to go over all the relevant register blocks
in the ASIC. Once we find the relevant engine, we print its details
and the offending address.
This helps tremendously when debugging an error that was created
by running a user workload.
Signed-off-by: Koby Elbaz <kelbaz@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This is required in order to allow the kernel to control relevant
configuration space via load and store instructions.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
If resetting device upon release while the release watchdog work is
scheduled, the compute reset is replaced with hard reset.
In this case, need to clear the in_compute_reset indication in the
device reset information structure.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
If device memory scrubbing from hl_device_reset() fails, we return with
an error code but not perform error handling code.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This commit enhances the following error messages to also provide the
type of error occurred, this in order to ease debugging of errors
detected during firmware-load.
Signed-off-by: Moti Haimovski <mhaimovski@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Completion timestamp is taken during the actual command submission
release. As the release happens in a work queue, the timestamp taken
is not accurate. Hence, we will take the timestamp in the interrupt
handler itself while propagating it to the release function.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
In order to support more user interrupt types in the future, we
enumerate the user interrupt type instead of using a boolean.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Handling edma razwi is different than all other engines since edma
uses sft routers. For hbw transactions sft router contain separate
interface for each edma and for lbw there is common interface for
both edma engines of the same dcore.
To handle the razwi correctly we need to:
1. Simplify the calculation of the sft router address.
2. Add razwi handling for edma qm errors, since edma qman doesn't
reports axi error response.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
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>
AXI transaction id holds information about the initiator which caused
the page fault. In the future it will be translated automatically by
driver to an initiator name.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Captured addresses of low b/w razwi information contains only the
offset from the cfg base. To make it more user readable, add the cfg
base to it.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
In gaudi2 there night be different routers for low b/w and high b/w
transactions. But in the code that collects razwi information, we used
the same router for high b/w and low b/w.
Fixed it by reading the information also from low b/w routers.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Protect re-using the same timestamp buffer record before actually
adding it to the to interrupt wait list.
Mark ts buff offset as in use in the spinlock protection area of the
interrupt wait list to avoid getting in the re-use section in
ts_buff_get_kernel_ts_record before adding the node to the list.
this scenario might happen when multiple threads are racing on
same offset and one thread could set data in the ts buff in
ts_buff_get_kernel_ts_record then the other thread takes over
and get to ts_buff_get_kernel_ts_record and we will try
to re-use the same ts buff offset then we will try to
delete a non existing node from the list.
Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
use argument instead of fixed GFP value for allocation
in Timestamps buffers alloc function.
change data type of size to size_t.
Fixes: 9158bf69e7 ("habanalabs: Timestamps buffers registration")
Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Make sure all reserved/pad fields in uapi input structures
are set to 0.
Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
data is a void * type and does not require a cast.
Signed-off-by: XU pengfei <xupengfei@nfschina.com>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This commit attaches the PCI device address to driver fatal messages
in order to ease debugging in multi-device setups.
Signed-off-by: Moti Haimovski <mhaimovski@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Because f/w does not update razwi info when sending events, remove the
use of it.
The driver is responsible to check if razwi happened and to
collect razwi data.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Add traces to LBW reads/writes.
This may be handy when debugging configuration failure or events when
tracking configuration flow.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
The value in SM_SEI_CAUSE includes the SOB index and not the SOB group
index.
Remove usage of log_mask in sm_sei_cause structure as it was never
used.
Signed-off-by: Carmit Carmel <ccarmel@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This function shall be used whenever components enable/binning masks
should be updated.
Usage is in one of the below cases:
- update user (or default) component masks
- update when getting the masks from FW (either CPUCP or COMMS)
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
When HL_INFO_USER_MAPPINGS IOCTL is called, we copy_to_user from
a dynamically allocated memory - 'user_mappings'.
Since freeing/allocating it happens in runtime (upon a page fault),
it not unlikely to access it even before being initially allocated
(i.e., accessing a NULL pointer).
The solution is to simply mark the spot when the err info has been
collected, and that way to know whether err info (either page fault
or RAZWI) is available to be read.
Signed-off-by: Koby Elbaz <kelbaz@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
From reviewing the code, the line
memset(kdata, 0, usize);
is not needed because kdata is either zeroed by
kdata = kzalloc(asize, GFP_KERNEL);
when allocated at runtime or by
char stack_kdata[128] = {0};
at compile time.
Signed-off-by: Tom Rix <trix@redhat.com>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This refactor makes the code clearer and the new variables' names
better describe their roles.
Signed-off-by: Koby Elbaz <kelbaz@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
It appears that, within the sync manager security configuration,
we reconfigure PB registers over and over without any need to do that.
Signed-off-by: Koby Elbaz <kelbaz@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
During device acquire, the driver is using a QMAN for clearing some
registers. In order to avoid internal races, the driver verifies
the device is idle before submitting the register clear job.
This check introduces an issue, as debug mode will cause the device
to be non-idle which will lead to device acquire failure.
In order to overcome this issue we can entirely remove the idle
check as the driver is using the QMAN only when there is no active
context.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
When entering an IOCTL, the driver prints a message in case device is
not operational. This message should be printed in debug level as
it can spam the kernel log and it is not an error.
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Remove the distinction between user CB and kernel CB, and verify for
both that they are not destroyed more than once.
As kernel CB might be taken from the pre-allocated CB pool, so we need
to clear the handle destroyed indication when returning a CB to the
pool.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
When doing p2p with a NIC device, the NIC needs to make sure all the
writes to the HBM (through the PCI bar of the Gaudi device) were
flushed.
It can be done by either the NIC or the host reading through the PCI
bar.
To support the host side, we supply a simple uapi to perform this flush
through the driver, because the user can't create such a transaction
by itself (the PCI bar isn't exposed to normal users).
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Andrzej Kacprowski