clang-16 warns about a cast between incompatible function types:
drivers/gpu/drm/xe/xe_range_fence.c:155:10: error: cast from 'void (*)(const void *)' to 'void (*)(struct xe_range_fence *)' converts to incompatible function type [-Werror,-Wcast-function-type-strict]
155 | .free = (void (*)(struct xe_range_fence *rfence)) kfree,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Avoid this with a trivial helper function that calls kfree() here.
v2:
- s/* rfence/*rfence/ (Thomas)
Fixes: 845f64bdbf ("drm/xe: Introduce a range-fence utility")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240213095719.454865-1-arnd@kernel.org
(cherry picked from commit f2c9364db5)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
The function xe_vm_prepare_vma was blindly accepting zero as the
number of fences and forwarded that to drm_exec_prepare_obj.
However, that leads to an out-of-bounds shift in the
dma_resv_reserve_fences() and while one could argue that the
dma_resv code should be robust against that, avoid attempting
to reserve zero fences.
Relevant stack trace:
[773.183188] ------------[ cut here ]------------
[773.183199] UBSAN: shift-out-of-bounds in ../include/linux/log2.h:57:13
[773.183241] shift exponent 64 is too large for 64-bit type 'long unsigned int'
[773.183254] CPU: 2 PID: 1816 Comm: xe_evict Tainted: G U 6.8.0-rc3-xe #1
[773.183256] Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 2014 10/14/2022
[773.183257] Call Trace:
[773.183258] <TASK>
[773.183260] dump_stack_lvl+0xaf/0xd0
[773.183266] dump_stack+0x10/0x20
[773.183283] ubsan_epilogue+0x9/0x40
[773.183286] __ubsan_handle_shift_out_of_bounds+0x10f/0x170
[773.183293] dma_resv_reserve_fences.cold+0x2b/0x48
[773.183295] ? ww_mutex_lock+0x3c/0x110
[773.183301] drm_exec_prepare_obj+0x45/0x60 [drm_exec]
[773.183313] xe_vm_prepare_vma+0x33/0x70 [xe]
[773.183375] xe_vma_destroy_unlocked+0x55/0xa0 [xe]
[773.183427] xe_vm_close_and_put+0x526/0x940 [xe]
Fixes: 2714d50936 ("drm/xe: Convert pagefaulting code to use drm_exec")
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240208132115.3132-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit eb538b5574)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
intel_power_domains_init is called twice in xe_device_probe:
1) intel_power_domains_init()
xe_display_init_nommio()
xe_device_probe()
2) intel_power_domains_init()
intel_display_driver_probe_noirq()
xe_display_init_noirq()
xe_device_probe()
It needs remove one to avoid power_domains->power_wells double malloc.
unreferenced object 0xffff88811150ee00 (size 512):
comm "systemd-udevd", pid 506, jiffies 4294674198 (age 3605.560s)
hex dump (first 32 bytes):
10 b4 9d a0 ff ff ff ff ff ff ff ff ff ff ff ff ................
ff ff ff ff ff ff ff ff 00 00 00 00 00 00 00 00 ................
backtrace:
[<ffffffff8134b901>] __kmem_cache_alloc_node+0x1c1/0x2b0
[<ffffffff812c98b2>] __kmalloc+0x52/0x150
[<ffffffffa08b0033>] __set_power_wells+0xc3/0x360 [xe]
[<ffffffffa08562fc>] xe_display_init_nommio+0x4c/0x70 [xe]
[<ffffffffa07f0d1c>] xe_device_probe+0x3c/0x5a0 [xe]
[<ffffffffa082e48f>] xe_pci_probe+0x33f/0x5a0 [xe]
[<ffffffff817f2187>] local_pci_probe+0x47/0xa0
[<ffffffff817f3db3>] pci_device_probe+0xc3/0x1f0
[<ffffffff8192f2a2>] really_probe+0x1a2/0x410
[<ffffffff8192f598>] __driver_probe_device+0x78/0x160
[<ffffffff8192f6ae>] driver_probe_device+0x1e/0x90
[<ffffffff8192f92a>] __driver_attach+0xda/0x1d0
[<ffffffff8192c95c>] bus_for_each_dev+0x7c/0xd0
[<ffffffff8192e159>] bus_add_driver+0x119/0x220
[<ffffffff81930d00>] driver_register+0x60/0x120
[<ffffffffa05e50a0>] 0xffffffffa05e50a0
The call to intel_power_domains_cleanup() needs to stay where it is for
now. The main issue is that while the init is called by the display
side, shared by i915 and xe, the cleanup is called by a non-shared code
path. Fixing that will be done as a separate commit.
Fixes: 44e694958b ("drm/xe/display: Implement display support")
Signed-off-by: Xiaoming Wang <xiaoming.wang@intel.com>
[ reword commit message and explain why the fini needs to stay
where it is ]
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202215658.561298-1-lucas.demarchi@intel.com
(cherry picked from commit 86c99abb5f)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
gcc-13 warns about an array overflow that it sees but that is
prevented by the "asid % NUM_PF_QUEUE" calculation:
drivers/gpu/drm/xe/xe_gt_pagefault.c: In function 'xe_guc_pagefault_handler':
include/linux/fortify-string.h:57:33: error: writing 16 bytes into a region of size 0 [-Werror=stringop-overflow=]
include/linux/fortify-string.h:689:26: note: in expansion of macro '__fortify_memcpy_chk'
689 | #define memcpy(p, q, s) __fortify_memcpy_chk(p, q, s, \
| ^~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/xe/xe_gt_pagefault.c:341:17: note: in expansion of macro 'memcpy'
341 | memcpy(pf_queue->data + pf_queue->tail, msg, len * sizeof(u32));
| ^~~~~~
drivers/gpu/drm/xe/xe_gt_types.h:102:25: note: at offset [1144, 265324] into destination object 'tile' of size 8
I found that rewriting the assignment using pointer addition rather than the
equivalent array index calculation prevents the warning, so use that instead.
I sent a bug report against gcc for the false positive warning.
Fixes: dd08ebf6c3 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113214
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240103114819.2913937-1-arnd@kernel.org
(cherry picked from commit 774ef5dfc9)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Since the PCI IDs for PVC weren't added to the xe driver, the xe_wa
tests should not try to create a fake PVC device since they can't find
the right PCI ID. Fix bugs when running kunit:
# xe_wa_gt: ASSERTION FAILED at drivers/gpu/drm/xe/tests/xe_wa_test.c:111
Expected ret == 0, but
ret == -19 (0xffffffffffffffed)
[FAILED] PVC (B0)
# xe_wa_gt: ASSERTION FAILED at drivers/gpu/drm/xe/tests/xe_wa_test.c:111
Expected ret == 0, but
ret == -19 (0xffffffffffffffed)
[FAILED] PVC (B1)
# xe_wa_gt: ASSERTION FAILED at drivers/gpu/drm/xe/tests/xe_wa_test.c:111
Expected ret == 0, but
ret == -19 (0xffffffffffffffed)
[FAILED] PVC (C0)
Fixes: dd08ebf6c3 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240123031242.3548724-1-lucas.demarchi@intel.com
(cherry picked from commit ab5ae65fb2)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
readq() is not available in 32bits and i915_gem_object_read_from_page()
is supposed to allow reading arbitrary sizes determined by the `size`
argument. Currently the only caller only passes a size == 8 so the
second problem is not that big. Migrate to calling
memcpy()/memcpy_fromio() to allow possible changes in the display side
and to fix the build on 32b architectures.
v2: Use memcpy/memcpy_fromio directly rather than using iosys-map with
the same size == 8 bytes restriction (Matt Roper)
Fixes: 44e694958b ("drm/xe/display: Implement display support")
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240119001612.2991381-4-lucas.demarchi@intel.com
(cherry picked from commit 406663f777)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Requesting all memory regions on PVC will fill bo->placements up to
XE_BO_MAX_PLACEMENTS. The subsequent call to try_add_stolen() will trip
over the bounds checking even though XE_PL_STOLEN is not expected to
be used in this case.
This is hit with igt@xe_exec_fault_mode@once-basic-prefetch:
xe 0000:8c:00.0: [drm] Assertion `*c < (sizeof(bo->placements) / sizeof((bo->placements)[0]) + ((int)(sizeof(struct { int:(-!!(__builtin_types_compatible_p(typeof((bo->placements)), typeof(&(bo->placements)[0])))); }))))` failed!
WARNING: CPU: 30 PID: 6161 at drivers/gpu/drm/xe/xe_bo.c:203 __xe_bo_placement_for_flags+0x218/0x240 [xe]
Is fixed here by moving the bounds checks closer to where we actually
write into the bo->placement array.
Fixes: 8c54ee8a86 ("drm/xe: Ensure that we don't access the placements array out-of-bounds")
Link: https://patchwork.freedesktop.org/patch/msgid/20240111002111.10190-1-brian.welty@intel.com
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Brian Welty <brian.welty@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
(cherry picked from commit 52e3fa3e3e)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Since the migrate code is using the identity map for addressing VRAM,
copy chunks may become as small as 64K if the VRAM resource is fragmented.
However, a chunk size smaller that 1MiB may lead to the *next* chunk's
offset into the CCS metadata backup memory may not be page-aligned, and
the XY_CTRL_SURF_COPY_BLT command can't handle that, and even if it could,
the current code doesn't handle the offset calculaton correctly.
To fix this, make sure we align the size of VRAM copy chunks to 1MiB. If
the remaining data to copy is smaller than that, that's not a problem,
so use the remaining size. If the VRAM copy cunk becomes fragmented due
to the size alignment restriction, don't use the identity map, but instead
emit PTEs into the page-table like we do for system memory.
v2:
- Rebase
v3:
- Future proof somewhat by taking into account the real data size to
flat CCS metadata size ratio. (Matt Roper)
- Invert a couple of if-statements for better readability.
- Fix support for 4K-granularity VRAM sizes. (Tested on DG1).
v4:
- Fix up code comments
- Fix debug printout format typo.
v5:
- Add a Fixes: tag.
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Fixes: e89b384cde ("drm/xe/migrate: Update emit_pte to cope with a size level than 4k")
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240110163415.524165-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit ef51d7542d)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
This error path should clean up before returning.
Smatch detected this bug:
drivers/gpu/drm/xe/xe_device.c:487 xe_device_probe() warn: missing unwind goto?
Fixes: 4cb12b7192 ("drm/xe/xe2: Determine bios enablement for flat ccs on igfx")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
(cherry picked from commit c10da95afa)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Building drivers/gpu/drm/xe/xe_gt_pagefault.c with GCC 11 results
in the following build errors:
./include/linux/fortify-string.h:57:33: error: writing 16 bytes into a region of size 0 [-Werror=stringop-overflow=]
57 | #define __underlying_memcpy __builtin_memcpy
| ^
./include/linux/fortify-string.h:644:9: note: in expansion of macro ‘__underlying_memcpy’
644 | __underlying_##op(p, q, __fortify_size); \
| ^~~~~~~~~~~~~
./include/linux/fortify-string.h:689:26: note: in expansion of macro ‘__fortify_memcpy_chk’
689 | #define memcpy(p, q, s) __fortify_memcpy_chk(p, q, s, \
| ^~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/xe/xe_gt_pagefault.c:340:17: note: in expansion of macro ‘memcpy’
340 | memcpy(pf_queue->data + pf_queue->tail, msg, len * sizeof(u32));
| ^~~~~~
In file included from drivers/gpu/drm/xe/xe_device_types.h:17,
from drivers/gpu/drm/xe/xe_vm_types.h:16,
from drivers/gpu/drm/xe/xe_bo.h:13,
from drivers/gpu/drm/xe/xe_gt_pagefault.c:16:
drivers/gpu/drm/xe/xe_gt_types.h:102:25: note: at offset [1144, 265324] into destination object ‘tile’ of size 8
102 | struct xe_tile *tile;
| ^~~~
Fix these by removing -Wstringop-overflow from drm/xe builds.
Closes: https://lore.kernel.org/all/45ad1d0f-a10f-483e-848a-76a30252edbe@paulmck-laptop/
Fixes: 7a8bc11782 ("drm/xe: Enable W=1 warnings by default")
Suggested-by: Stephen Rothwell <sfr@rothwell.id.au>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
[ This particular warning is broken on GCC11. In future changes it will
be moved to the normal C flags in the top level Makefile (out of
Makefile.extrawarn), but accounting for the compiler support. Just
remove it out of xe's forced extra warnings for now ]
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit a109d19992)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
After exec_queue has been created, we cannot simply modify q->priority.
This needs to be done by the backend via q->ops. However in this case,
it would be more efficient to simply pass a flag when creating the
exec_queue and set the desired priority upfront during queue creation.
To that end: new flag EXEC_QUEUE_FLAG_HIGH_PRIORITY is introduced.
The priority field is moved to be with other scheduling properties and
is now exec_queue.sched_props.priority. This is no longer set to initial
value by the backend, but is now set within __xe_exec_queue_create().
Fixes: b4eecedc75 ("drm/xe: Fix potential deadlock handling page faults")
Signed-off-by: Brian Welty <brian.welty@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
(cherry picked from commit a8004af338)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
We need to set q->priority prior to calling guc_exec_queue_add_msg() as
that will call init_policies() and sets the scheduling properties to those
stored in the exec_queue.
Fixes: dd08ebf6c3 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Brian Welty <brian.welty@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
(cherry picked from commit b16483f9f8)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
