Commit 1af343cd authored by Maarten Lankhorst's avatar Maarten Lankhorst Committed by Joonas Lahtinen
Browse files

drm/i915: Remove locking from i915_gem_object_prepare_read/write 



Execbuffer submission will perform its own WW locking, and we
cannot rely on the implicit lock there.

This also makes it clear that the GVT code will get a lockdep splat when
multiple batchbuffer shadows need to be performed in the same instance,
fix that up.

Signed-off-by: default avatarMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: default avatarTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-7-maarten.lankhorst@linux.intel.com


Signed-off-by: default avatarJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
parent 80f0b679

drivers/gpu/drm/i915/gem/i915_gem_domain.c

+6 −14
Original line number Diff line number Diff line
@@ -576,19 +576,17 @@ int i915_gem_object_prepare_read(struct drm_i915_gem_object *obj, 
	if (!i915_gem_object_has_struct_page(obj))

		return -ENODEV;



	ret = i915_gem_object_lock_interruptible(obj, NULL);

	if (ret)

		return ret;

	assert_object_held(obj);



	ret = i915_gem_object_wait(obj,

				   I915_WAIT_INTERRUPTIBLE,

				   MAX_SCHEDULE_TIMEOUT);

	if (ret)

		goto err_unlock;

		return ret;



	ret = i915_gem_object_pin_pages(obj);

	if (ret)

		goto err_unlock;

		return ret;



	if (obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ ||

	    !static_cpu_has(X86_FEATURE_CLFLUSH)) {
@@ -616,8 +614,6 @@ int i915_gem_object_prepare_read(struct drm_i915_gem_object *obj, 


err_unpin:

	i915_gem_object_unpin_pages(obj);

err_unlock:

	i915_gem_object_unlock(obj);

	return ret;

}
@@ -630,20 +626,18 @@ int i915_gem_object_prepare_write(struct drm_i915_gem_object *obj, 
	if (!i915_gem_object_has_struct_page(obj))

		return -ENODEV;



	ret = i915_gem_object_lock_interruptible(obj, NULL);

	if (ret)

		return ret;

	assert_object_held(obj);



	ret = i915_gem_object_wait(obj,

				   I915_WAIT_INTERRUPTIBLE |

				   I915_WAIT_ALL,

				   MAX_SCHEDULE_TIMEOUT);

	if (ret)

		goto err_unlock;

		return ret;



	ret = i915_gem_object_pin_pages(obj);

	if (ret)

		goto err_unlock;

		return ret;



	if (obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE ||

	    !static_cpu_has(X86_FEATURE_CLFLUSH)) {
@@ -680,7 +674,5 @@ int i915_gem_object_prepare_write(struct drm_i915_gem_object *obj, 


err_unpin:

	i915_gem_object_unpin_pages(obj);

err_unlock:

	i915_gem_object_unlock(obj);

	return ret;

}

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

+11 −2
Original line number Diff line number Diff line
@@ -991,11 +991,14 @@ static void reloc_cache_reset(struct reloc_cache *cache) 


	vaddr = unmask_page(cache->vaddr);

	if (cache->vaddr & KMAP) {

		struct drm_i915_gem_object *obj =

			(struct drm_i915_gem_object *)cache->node.mm;

		if (cache->vaddr & CLFLUSH_AFTER)

			mb();



		kunmap_atomic(vaddr);

		i915_gem_object_finish_access((struct drm_i915_gem_object *)cache->node.mm);

		i915_gem_object_finish_access(obj);

		i915_gem_object_unlock(obj);

	} else {

		struct i915_ggtt *ggtt = cache_to_ggtt(cache);
@@ -1031,10 +1034,16 @@ static void *reloc_kmap(struct drm_i915_gem_object *obj, 
		unsigned int flushes;

		int err;



		err = i915_gem_object_prepare_write(obj, &flushes);

		err = i915_gem_object_lock_interruptible(obj, NULL);

		if (err)

			return ERR_PTR(err);



		err = i915_gem_object_prepare_write(obj, &flushes);

		if (err) {

			i915_gem_object_unlock(obj);

			return ERR_PTR(err);

		}



		BUILD_BUG_ON(KMAP & CLFLUSH_FLAGS);

		BUILD_BUG_ON((KMAP | CLFLUSH_FLAGS) & PAGE_MASK);

drivers/gpu/drm/i915/gem/i915_gem_object.h

+0 −1
Original line number Diff line number Diff line
@@ -432,7 +432,6 @@ static inline void 
i915_gem_object_finish_access(struct drm_i915_gem_object *obj)

{

	i915_gem_object_unpin_pages(obj);

	i915_gem_object_unlock(obj);

}



static inline struct intel_engine_cs *

drivers/gpu/drm/i915/gem/selftests/huge_pages.c

+4 −1
Original line number Diff line number Diff line
@@ -964,9 +964,10 @@ __cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val) 
	unsigned long n;

	int err;



	i915_gem_object_lock(obj, NULL);

	err = i915_gem_object_prepare_read(obj, &needs_flush);

	if (err)

		return err;

		goto err_unlock;



	for (n = 0; n < obj->base.size >> PAGE_SHIFT; ++n) {

		u32 *ptr = kmap_atomic(i915_gem_object_get_page(obj, n));
@@ -986,6 +987,8 @@ __cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val) 
	}



	i915_gem_object_finish_access(obj);

err_unlock:

	i915_gem_object_unlock(obj);



	return err;

}

drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c

+10 −4
Original line number Diff line number Diff line
@@ -27,9 +27,10 @@ static int cpu_set(struct context *ctx, unsigned long offset, u32 v) 
	u32 *cpu;

	int err;



	i915_gem_object_lock(ctx->obj, NULL);

	err = i915_gem_object_prepare_write(ctx->obj, &needs_clflush);

	if (err)

		return err;

		goto out;



	page = i915_gem_object_get_page(ctx->obj, offset >> PAGE_SHIFT);

	map = kmap_atomic(page);
@@ -46,7 +47,9 @@ static int cpu_set(struct context *ctx, unsigned long offset, u32 v) 
	kunmap_atomic(map);

	i915_gem_object_finish_access(ctx->obj);



	return 0;

out:

	i915_gem_object_unlock(ctx->obj);

	return err;

}



static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
@@ -57,9 +60,10 @@ static int cpu_get(struct context *ctx, unsigned long offset, u32 *v) 
	u32 *cpu;

	int err;



	i915_gem_object_lock(ctx->obj, NULL);

	err = i915_gem_object_prepare_read(ctx->obj, &needs_clflush);

	if (err)

		return err;

		goto out;



	page = i915_gem_object_get_page(ctx->obj, offset >> PAGE_SHIFT);

	map = kmap_atomic(page);
@@ -73,7 +77,9 @@ static int cpu_get(struct context *ctx, unsigned long offset, u32 *v) 
	kunmap_atomic(map);

	i915_gem_object_finish_access(ctx->obj);



	return 0;

out:

	i915_gem_object_unlock(ctx->obj);

	return err;

}



static int gtt_set(struct context *ctx, unsigned long offset, u32 v)