diff options
| author | Nirmoy Das <nirmoy.das@intel.com> | 2022-12-23 10:20:11 +0100 |
|---|---|---|
| committer | Rodrigo Vivi <rodrigo.vivi@intel.com> | 2023-01-09 10:36:12 -0500 |
| commit | 476fdcdaaae7b06c780cdfc234c704107f16c529 (patch) | |
| tree | aed8b99dbac1d40b13883bcc86f7f512f3f64757 /drivers/gpu/drm/i915/gem/i915_gem_context.c | |
| parent | b7bfaa761d760e72a969d116517eaa12e404c262 (diff) | |
| download | linux-476fdcdaaae7b06c780cdfc234c704107f16c529.tar.bz2 | |
drm/i915: Reserve enough fence slot for i915_vma_unbind_async
A nested dma_resv_reserve_fences(1) will not reserve slot from the
2nd call onwards and folowing dma_resv_add_fence() might hit the
"BUG_ON(fobj->num_fences >= fobj->max_fences)" check.
I915 hit above nested dma_resv case in ttm_bo_handle_move_mem() with
async unbind:
dma_resv_reserve_fences() from --> ttm_bo_handle_move_mem()
dma_resv_reserve_fences() from --> i915_vma_unbind_async()
dma_resv_add_fence() from --> i915_vma_unbind_async()
dma_resv_add_fence() from -->ttm_bo_move_accel_cleanup()
Resolve this by adding an extra fence in i915_vma_unbind_async().
Suggested-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Fixes: 2f6b90da9192 ("drm/i915: Use vma resources for async unbinding")
Cc: <stable@vger.kernel.org> # v5.18+
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221223092011.11657-1-nirmoy.das@intel.com
(cherry picked from commit 4f0755c2faf7388616109717facc5bbde6850e60)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Diffstat (limited to 'drivers/gpu/drm/i915/gem/i915_gem_context.c')
0 files changed, 0 insertions, 0 deletions