diff options
author | Chris Wilson <chris.p.wilson@intel.com> | 2022-07-27 14:29:55 +0200 |
---|---|---|
committer | Andi Shyti <andi.shyti@linux.intel.com> | 2022-07-28 14:02:14 +0200 |
commit | 5d36acb7198b0e5eb88e6b701f9ad7b9448f8df9 (patch) | |
tree | 254b6164b05b482c510b6ff9c9f5414db639bedf /drivers/gpu/drm/i915/i915_vma.c | |
parent | drm/i915/gt: Skip TLB invalidations once wedged (diff) | |
download | linux-dev-5d36acb7198b0e5eb88e6b701f9ad7b9448f8df9.tar.xz linux-dev-5d36acb7198b0e5eb88e6b701f9ad7b9448f8df9.zip |
drm/i915/gt: Batch TLB invalidations
Invalidate TLB in batches, in order to reduce performance regressions.
Currently, every caller performs a full barrier around a TLB
invalidation, ignoring all other invalidations that may have already
removed their PTEs from the cache. As this is a synchronous operation
and can be quite slow, we cause multiple threads to contend on the TLB
invalidate mutex blocking userspace.
We only need to invalidate the TLB once after replacing our PTE to
ensure that there is no possible continued access to the physical
address before releasing our pages. By tracking a seqno for each full
TLB invalidate we can quickly determine if one has been performed since
rewriting the PTE, and only if necessary trigger one for ourselves.
That helps to reduce the performance regression introduced by TLB
invalidate logic.
[mchehab: rebased to not require moving the code to a separate file]
Cc: stable@vger.kernel.org
Fixes: 7938d61591d3 ("drm/i915: Flush TLBs before releasing backing store")
Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Chris Wilson <chris.p.wilson@intel.com>
Cc: Fei Yang <fei.yang@intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/4e97ef5deb6739cadaaf40aa45620547e9c4ec06.1658924372.git.mchehab@kernel.org
Diffstat (limited to 'drivers/gpu/drm/i915/i915_vma.c')
-rw-r--r-- | drivers/gpu/drm/i915/i915_vma.c | 33 |
1 files changed, 26 insertions, 7 deletions
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index ef3b04c7e153..84a9ccbc5fc5 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -538,8 +538,6 @@ int i915_vma_bind(struct i915_vma *vma, bind_flags); } - set_bit(I915_BO_WAS_BOUND_BIT, &vma->obj->flags); - atomic_or(bind_flags, &vma->flags); return 0; } @@ -1310,6 +1308,19 @@ err_unpin: return err; } +void vma_invalidate_tlb(struct i915_address_space *vm, u32 tlb) +{ + /* + * Before we release the pages that were bound by this vma, we + * must invalidate all the TLBs that may still have a reference + * back to our physical address. It only needs to be done once, + * so after updating the PTE to point away from the pages, record + * the most recent TLB invalidation seqno, and if we have not yet + * flushed the TLBs upon release, perform a full invalidation. + */ + WRITE_ONCE(tlb, intel_gt_next_invalidate_tlb_full(vm->gt)); +} + static void __vma_put_pages(struct i915_vma *vma, unsigned int count) { /* We allocate under vma_get_pages, so beware the shrinker */ @@ -1941,7 +1952,12 @@ struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async) vma->vm->skip_pte_rewrite; trace_i915_vma_unbind(vma); - unbind_fence = i915_vma_resource_unbind(vma_res); + if (async) + unbind_fence = i915_vma_resource_unbind(vma_res, + &vma->obj->mm.tlb); + else + unbind_fence = i915_vma_resource_unbind(vma_res, NULL); + vma->resource = NULL; atomic_and(~(I915_VMA_BIND_MASK | I915_VMA_ERROR | I915_VMA_GGTT_WRITE), @@ -1949,10 +1965,13 @@ struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async) i915_vma_detach(vma); - if (!async && unbind_fence) { - dma_fence_wait(unbind_fence, false); - dma_fence_put(unbind_fence); - unbind_fence = NULL; + if (!async) { + if (unbind_fence) { + dma_fence_wait(unbind_fence, false); + dma_fence_put(unbind_fence); + unbind_fence = NULL; + } + vma_invalidate_tlb(vma->vm, vma->obj->mm.tlb); } /* |