drm/xe: Add fault injection for xe_sync_entry_parse

Add fault injection for xe_sync_entry_parse to allow it to fail while
executing xe_vm_bind_ioctl(). This needs to be added as it cannot be
reached

drm/xe: Add fault injection for xe_sync_entry_parse

Add fault injection for xe_sync_entry_parse to allow it to fail while
executing xe_vm_bind_ioctl(). This needs to be added as it cannot be
reached by injecting error through IOCTL arguments.

Signed-off-by: Priyanka Dandamudi <[email protected]>
Reviewed-by: Satyanarayana K V P <[email protected]>
Reviewed-by: Himal Prasad Ghimiray <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Himal Prasad Ghimiray <[email protected]>

show more ...

drm/xe/ufence: Wake up waiters after setting ufence->signalled

If a previous ufence is not signalled, vm_bind will return -EBUSY.
Delaying the modification of ufence->signalled can cause issues if t

drm/xe/ufence: Wake up waiters after setting ufence->signalled

If a previous ufence is not signalled, vm_bind will return -EBUSY.
Delaying the modification of ufence->signalled can cause issues if the
UMD reuses the same ufence so update ufence->signalled before waking up
waiters.

Cc: Matthew Brost <[email protected]>
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/3233
Fixes: 977e5b82e090 ("drm/xe: Expose user fence from xe_sync_entry")
Reviewed-by: Matthew Brost <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Nirmoy Das <[email protected]>
(cherry picked from commit 553a5d14fcd927194c409b10faced6a6dbc678d1)
Signed-off-by: Thomas Hellström <[email protected]>

show more ...

drm/xe/ufence: Wake up waiters after setting ufence->signalled

If a previous ufence is not signalled, vm_bind will return -EBUSY.
Delaying the modification of ufence->signalled can cause issues if t

drm/xe/ufence: Wake up waiters after setting ufence->signalled

If a previous ufence is not signalled, vm_bind will return -EBUSY.
Delaying the modification of ufence->signalled can cause issues if the
UMD reuses the same ufence so update ufence->signalled before waking up
waiters.

Cc: Matthew Brost <[email protected]>
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/3233
Fixes: 977e5b82e090 ("drm/xe: Expose user fence from xe_sync_entry")
Reviewed-by: Matthew Brost <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Nirmoy Das <[email protected]>

show more ...

drm/xe/ufence: Prefetch ufence addr to catch bogus address

access_ok() only checks for addr overflow so also try to read the addr
to catch invalid addr sent from userspace.

Link: https://gitlab.fre

drm/xe/ufence: Prefetch ufence addr to catch bogus address

access_ok() only checks for addr overflow so also try to read the addr
to catch invalid addr sent from userspace.

Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/1630
Cc: Francois Dugast <[email protected]>
Cc: Maarten Lankhorst <[email protected]>
Cc: Matthew Auld <[email protected]>
Cc: Matthew Brost <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Nirmoy Das <[email protected]>
(cherry picked from commit 9408c4508483ffc60811e910a93d6425b8e63928)
Signed-off-by: Lucas De Marchi <[email protected]>

show more ...

drm/xe/ufence: Warn if mmget_not_zero() fails

This shouldn't happen but seen this while debugging ufence timeout
issue time to time so log it to isolate this particular case.

v2: s/XE_WARN_ON/drm_d

drm/xe/ufence: Warn if mmget_not_zero() fails

This shouldn't happen but seen this while debugging ufence timeout
issue time to time so log it to isolate this particular case.

v2: s/XE_WARN_ON/drm_dbg(Maarten)

Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/1630
Cc: Francois Dugast <[email protected]>
Cc: Maarten Lankhorst <[email protected]>
Cc: Matthew Auld <[email protected]>
Cc: Matthew Brost <[email protected]>
Reviewed-by: Francois Dugast <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Nirmoy Das <[email protected]>

show more ...

drm/xe/ufence: Prefetch ufence addr to catch bogus address

access_ok() only checks for addr overflow so also try to read the addr
to catch invalid addr sent from userspace.

Link: https://gitlab.fre

drm/xe/ufence: Prefetch ufence addr to catch bogus address

access_ok() only checks for addr overflow so also try to read the addr
to catch invalid addr sent from userspace.

Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/1630
Cc: Francois Dugast <[email protected]>
Cc: Maarten Lankhorst <[email protected]>
Cc: Matthew Auld <[email protected]>
Cc: Matthew Brost <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Nirmoy Das <[email protected]>

show more ...

drm/xe/xe_sync: initialise ufence.signalled

We can incorrectly think that the fence has signalled, if we get a
non-zero value here from the kmalloc, which is quite plausible. Just use
kzalloc to pre

drm/xe/xe_sync: initialise ufence.signalled

We can incorrectly think that the fence has signalled, if we get a
non-zero value here from the kmalloc, which is quite plausible. Just use
kzalloc to prevent stuff like this.

Fixes: 977e5b82e090 ("drm/xe: Expose user fence from xe_sync_entry")
Signed-off-by: Matthew Auld <[email protected]>
Cc: Mika Kuoppala <[email protected]>
Cc: Matthew Brost <[email protected]>
Cc: Nirmoy Das <[email protected]>
Cc: <[email protected]> # v6.10+
Reviewed-by: Nirmoy Das <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
(cherry picked from commit 26f69e88dcc95fffc62ed2aea30ad7b1fdf31fdb)
Signed-off-by: Lucas De Marchi <[email protected]>

show more ...

drm/xe/xe_sync: initialise ufence.signalled

We can incorrectly think that the fence has signalled, if we get a
non-zero value here from the kmalloc, which is quite plausible. Just use
kzalloc to pre

drm/xe/xe_sync: initialise ufence.signalled

We can incorrectly think that the fence has signalled, if we get a
non-zero value here from the kmalloc, which is quite plausible. Just use
kzalloc to prevent stuff like this.

Fixes: 977e5b82e090 ("drm/xe: Expose user fence from xe_sync_entry")
Signed-off-by: Matthew Auld <[email protected]>
Cc: Mika Kuoppala <[email protected]>
Cc: Matthew Brost <[email protected]>
Cc: Nirmoy Das <[email protected]>
Cc: <[email protected]> # v6.10+
Reviewed-by: Nirmoy Das <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/xe: Fix access_ok check in user_fence_create

Check size of the data not size of the pointer.

Reported-by: kernel test robot <[email protected]>
Closes: https://lore.kernel.org/oe-kbuild-all/2024073

drm/xe: Fix access_ok check in user_fence_create

Check size of the data not size of the pointer.

Reported-by: kernel test robot <[email protected]>
Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
Fixes: ddeb7989a98f ("drm/xe: Validate user fence during creation")
Cc: Matthew Auld <[email protected]>
Cc: Matthew Brost <[email protected]>
Reviewed-by: Matthew Auld <[email protected]>
Reviewed-by: Tejas Upadhyay <[email protected]>
Reviewed-by: Apoorva Singh <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Nirmoy Das <[email protected]>
(cherry picked from commit e102b5ed6e283a144793cab8fcd95f61d0ddbadb)
Signed-off-by: Rodrigo Vivi <[email protected]>

show more ...

drm/xe: replace #include <drm/xe_drm.h> with <uapi/drm/xe_drm.h>

include/drm/xe_drm.h does not exist. Prefer the explicit uapi include.

Signed-off-by: Jani Nikula <[email protected]>
Reviewed-b

drm/xe: replace #include <drm/xe_drm.h> with <uapi/drm/xe_drm.h>

include/drm/xe_drm.h does not exist. Prefer the explicit uapi include.

Signed-off-by: Jani Nikula <[email protected]>
Reviewed-by: Rodrigo Vivi <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Rodrigo Vivi <[email protected]>

show more ...

drm/xe: Remove unrequired NULL checks in xe_sync_entry_cleanup

dma_fence_put() and dma_fence_chain_free() can handle NULL input,
there is no need for NULL check by caller.

Signed-off-by: Himal Pras

drm/xe: Remove unrequired NULL checks in xe_sync_entry_cleanup

dma_fence_put() and dma_fence_chain_free() can handle NULL input,
there is no need for NULL check by caller.

Signed-off-by: Himal Prasad Ghimiray <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Reviewed-by: Nirmoy Das <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Nirmoy Das <[email protected]>

show more ...

drm/xe: Remove extra dma_fence_put on xe_sync_entry_add_deps failure

drm_sched_job_add_dependency() drops references even in case of error,
no need for caller to call dma_fence_put.

Signed-off-by:

drm/xe: Remove extra dma_fence_put on xe_sync_entry_add_deps failure

drm_sched_job_add_dependency() drops references even in case of error,
no need for caller to call dma_fence_put.

Signed-off-by: Himal Prasad Ghimiray <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Reviewed-by: Ashutosh Dixit <[email protected]>
Acked-by: Nirmoy Das <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Nirmoy Das <[email protected]>

show more ...

drm/xe: Validate user fence during creation

Fail invalid addresses during user fence creation.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost

drm/xe: Validate user fence during creation

Fail invalid addresses during user fence creation.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: Thomas Hellström <[email protected]>
Reviewed-by: Nirmoy Das <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
(cherry picked from commit 0fde907da2d5fd4da68845e96c6842497159c858)
Signed-off-by: Rodrigo Vivi <[email protected]>

show more ...

drm/xe: Use dma_fence_chain_free in chain fence unused as a sync

A chain fence is uninitialized if not installed in a drm sync obj. Thus
if xe_sync_entry_cleanup is called and sync->chain_fence is n

drm/xe: Use dma_fence_chain_free in chain fence unused as a sync

A chain fence is uninitialized if not installed in a drm sync obj. Thus
if xe_sync_entry_cleanup is called and sync->chain_fence is non-NULL the
proper cleanup is dma_fence_chain_free rather than a dma-fence put.

Reported-by: Paulo Zanoni <[email protected]>
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2411
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2261
Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: Matthew Auld <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
(cherry picked from commit 7f7a2da3bf8bc0e0f6c239af495b7050056e889c)
Signed-off-by: Rodrigo Vivi <[email protected]>

show more ...

drm/xe: Fix access_ok check in user_fence_create

Check size of the data not size of the pointer.

Reported-by: kernel test robot <[email protected]>
Closes: https://lore.kernel.org/oe-kbuild-all/2024073

drm/xe: Fix access_ok check in user_fence_create

Check size of the data not size of the pointer.

Reported-by: kernel test robot <[email protected]>
Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
Fixes: 0fde907da2d5 ("drm/xe: Validate user fence during creation")
Cc: Matthew Auld <[email protected]>
Cc: Matthew Brost <[email protected]>
Reviewed-by: Matthew Auld <[email protected]>
Reviewed-by: Tejas Upadhyay <[email protected]>
Reviewed-by: Apoorva Singh <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Nirmoy Das <[email protected]>

show more ...

drm/xe: Use dma_fence_chain_free in chain fence unused as a sync

A chain fence is uninitialized if not installed in a drm sync obj. Thus
if xe_sync_entry_cleanup is called and sync->chain_fence is n

drm/xe: Use dma_fence_chain_free in chain fence unused as a sync

A chain fence is uninitialized if not installed in a drm sync obj. Thus
if xe_sync_entry_cleanup is called and sync->chain_fence is non-NULL the
proper cleanup is dma_fence_chain_free rather than a dma-fence put.

Reported-by: Paulo Zanoni <[email protected]>
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2411
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2261
Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: Matthew Auld <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/xe: Remove unused xe_sync_entry_wait

xe_sync_entry_wait is no longer used, remove it.

Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linu

drm/xe: Remove unused xe_sync_entry_wait

xe_sync_entry_wait is no longer used, remove it.

Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: Thomas Hellström <[email protected]>
Reviewed-by: Nirmoy Das <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/xe: Validate user fence during creation

Fail invalid addresses during user fence creation.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost

drm/xe: Validate user fence during creation

Fail invalid addresses during user fence creation.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: Thomas Hellström <[email protected]>
Reviewed-by: Nirmoy Das <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/xe: Move ufence add to vm_bind_ioctl_ops_fini

Rather than adding a ufence to a VMA in the bind function, add the
ufence to all VMAs in the IOCTL that require binds in
vm_bind_ioctl_ops_fini. Thi

drm/xe: Move ufence add to vm_bind_ioctl_ops_fini

Rather than adding a ufence to a VMA in the bind function, add the
ufence to all VMAs in the IOCTL that require binds in
vm_bind_ioctl_ops_fini. This help withs the transition to job 1 per VM
bind IOCTL.

v2:
- Rebase
v3:
- Fix typo in commit (Oak)

Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: Oak Zeng <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/xe: Create a helper function to init job's user fence

Refactor xe_sync_entry_signal so it doesn't have to
modify xe_sched_job struct instead create a new helper function
to set user fence values

drm/xe: Create a helper function to init job's user fence

Refactor xe_sync_entry_signal so it doesn't have to
modify xe_sched_job struct instead create a new helper function
to set user fence values for a job.

v2: Move the sync type check to xe_sched_job_init_user_fence(Lucas)

Cc: Lucas De Marchi <[email protected]>
Cc: Matthew Auld <[email protected]>
Cc: Matthew Brost <[email protected]>
Cc: Michal Wajdeczko <[email protected]>
Signed-off-by: Nirmoy Das <[email protected]>
Reviewed-by: Lucas De Marchi <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Lucas De Marchi <[email protected]>

show more ...

drm/xe: Expose user fence from xe_sync_entry

By allowing getting reference to user fence, we can
control the lifetime outside of sync entries.

This is needed to allow vma to track the associated
us

drm/xe: Expose user fence from xe_sync_entry

By allowing getting reference to user fence, we can
control the lifetime outside of sync entries.

This is needed to allow vma to track the associated
user fence that was provided with bind ioctl.

v2: xe_user_fence can be kept opaque (Jani, Matt)
v3: indent fix (Matt)

Cc: Thomas Hellström <[email protected]>
Cc: Matthew Brost <[email protected]>
Cc: Jani Nikula <[email protected]>
Signed-off-by: Mika Kuoppala <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Signed-off-by: Thomas Hellström <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
(cherry picked from commit 977e5b82e0901480bc201342d39f855fc0a2ef47)
Signed-off-by: Thomas Hellström <[email protected]>

show more ...

drm/xe: Expose user fence from xe_sync_entry

By allowing getting reference to user fence, we can
control the lifetime outside of sync entries.

This is needed to allow vma to track the associated
us

drm/xe: Expose user fence from xe_sync_entry

By allowing getting reference to user fence, we can
control the lifetime outside of sync entries.

This is needed to allow vma to track the associated
user fence that was provided with bind ioctl.

v2: xe_user_fence can be kept opaque (Jani, Matt)
v3: indent fix (Matt)

Cc: Thomas Hellström <[email protected]>
Cc: Matthew Brost <[email protected]>
Cc: Jani Nikula <[email protected]>
Signed-off-by: Mika Kuoppala <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Signed-off-by: Thomas Hellström <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/xe: Take a reference in xe_exec_queue_last_fence_get()

Take a reference in xe_exec_queue_last_fence_get(). Also fix a reference
counting underflow bug VM bind and unbind.

Fixes: dd08ebf6c352 ("

drm/xe: Take a reference in xe_exec_queue_last_fence_get()

Take a reference in xe_exec_queue_last_fence_get(). Also fix a reference
counting underflow bug VM bind and unbind.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: Maarten Lankhorst <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
(cherry picked from commit a856b67a84169e065ebbeee50258936b1eacc9eb)
Signed-off-by: Thomas Hellström <[email protected]>

show more ...

drm/xe: Take a reference in xe_exec_queue_last_fence_get()

Take a reference in xe_exec_queue_last_fence_get(). Also fix a reference
counting underflow bug VM bind and unbind.

Fixes: dd08ebf6c352 ("

drm/xe: Take a reference in xe_exec_queue_last_fence_get()

Take a reference in xe_exec_queue_last_fence_get(). Also fix a reference
counting underflow bug VM bind and unbind.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: Maarten Lankhorst <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/xe: Allow num_batch_buffer / num_binds == 0 in IOCTLs

The idea being out-syncs can signal indicating all previous operations
on the bind queue are complete. An example use case of this would be

drm/xe: Allow num_batch_buffer / num_binds == 0 in IOCTLs

The idea being out-syncs can signal indicating all previous operations
on the bind queue are complete. An example use case of this would be
support for implementing vkQueueWaitIdle easily.

All in-syncs are waited on before signaling out-syncs. This is
implemented by forming a composite software fence of in-syncs and
installing this fence in the out-syncs and exec queue last fence slot.

The last fence must be added as a dependency for jobs on user exec
queues as it is possible for the last fence to be a composite software
fence (unordered, ioctl with zero bb or binds) rather than hardware
fence (ordered, previous job on queue).

Cc: Thomas Hellström <[email protected]>
Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: Thomas Hellström <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>

show more ...