[Intel-gfx] [PATCH 10/14] drm/i915: Support to create write combined type vmaps

akash.goel at intel.com akash.goel at intel.com
Sat Jul 2 18:51:27 UTC 2016


From: Chris Wilson <chris at chris-wilson.co.uk>

vmaps has a provision for controlling the page protection bits, with which
we can use to control the mapping type, e.g. WB, WC, UC or even WT.
To allow the caller to choose their mapping type, we add a parameter to
i915_gem_object_pin_map - but we still only allow one vmap to be cached
per object. If the object is currently not pinned, then we recreate the
previous vmap with the new access type, but if it was pinned we report an
error. This effectively limits the access via i915_gem_object_pin_map to a
single mapping type for the lifetime of the object. Not usually a problem,
but something to be aware of when setting up the object's vmap.

We will want to vary the access type to enable WC mappings of ringbuffer
and context objects on !llc platforms, as well as other objects where we
need coherent access to the GPU's pages without going through the GTT

v2: Remove the redundant braces around pin count check and fix the marker
    in documentation (Chris)

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Akash Goel <akash.goel at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h         |  4 ++-
 drivers/gpu/drm/i915/i915_gem.c         | 57 +++++++++++++++++++++++++--------
 drivers/gpu/drm/i915/i915_gem_dmabuf.c  |  2 +-
 drivers/gpu/drm/i915/intel_lrc.c        |  8 ++---
 drivers/gpu/drm/i915/intel_ringbuffer.c |  2 +-
 5 files changed, 53 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 20c701c..7aa11de 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3197,6 +3197,7 @@ static inline void i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj)
 /**
  * i915_gem_object_pin_map - return a contiguous mapping of the entire object
  * @obj - the object to map into kernel address space
+ * @use_wc - whether the mapping should be using WC or WB pgprot_t
  *
  * Calls i915_gem_object_pin_pages() to prevent reaping of the object's
  * pages and then returns a contiguous mapping of the backing storage into
@@ -3208,7 +3209,8 @@ static inline void i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj)
  * Returns the pointer through which to access the mapped object, or an
  * ERR_PTR() on error.
  */
-void *__must_check i915_gem_object_pin_map(struct drm_i915_gem_object *obj);
+void *__must_check i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
+					 bool use_wc);
 
 /**
  * i915_gem_object_unpin_map - releases an earlier mapping
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 51191b87..2ab7e8f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2469,10 +2469,11 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	list_del(&obj->global_list);
 
 	if (obj->mapping) {
-		if (is_vmalloc_addr(obj->mapping))
-			vunmap(obj->mapping);
+		void *ptr = (void *)((uintptr_t)obj->mapping & ~1);
+		if (is_vmalloc_addr(ptr))
+			vunmap(ptr);
 		else
-			kunmap(kmap_to_page(obj->mapping));
+			kunmap(kmap_to_page(ptr));
 		obj->mapping = NULL;
 	}
 
@@ -2645,7 +2646,8 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
 }
 
 /* The 'mapping' part of i915_gem_object_pin_map() below */
-static void *i915_gem_object_map(const struct drm_i915_gem_object *obj)
+static void *i915_gem_object_map(const struct drm_i915_gem_object *obj,
+				bool use_wc)
 {
 	unsigned long n_pages = obj->base.size >> PAGE_SHIFT;
 	struct sg_table *sgt = obj->pages;
@@ -2657,7 +2659,7 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj)
 	void *addr;
 
 	/* A single page can always be kmapped */
-	if (n_pages == 1)
+	if (n_pages == 1 && !use_wc)
 		return kmap(sg_page(sgt->sgl));
 
 	if (n_pages > ARRAY_SIZE(stack_pages)) {
@@ -2673,7 +2675,8 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj)
 	/* Check that we have the expected number of pages */
 	GEM_BUG_ON(i != n_pages);
 
-	addr = vmap(pages, n_pages, 0, PAGE_KERNEL);
+	addr = vmap(pages, n_pages, VM_NO_GUARD,
+		    use_wc ? pgprot_writecombine(PAGE_KERNEL_IO) : PAGE_KERNEL);
 
 	if (pages != stack_pages)
 		drm_free_large(pages);
@@ -2682,27 +2685,55 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj)
 }
 
 /* get, pin, and map the pages of the object into kernel space */
-void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj)
+void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, bool use_wc)
 {
+	void *ptr;
+	bool has_wc;
+	bool pinned;
 	int ret;
 
 	lockdep_assert_held(&obj->base.dev->struct_mutex);
+	GEM_BUG_ON((obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE) == 0);
 
 	ret = i915_gem_object_get_pages(obj);
 	if (ret)
 		return ERR_PTR(ret);
 
+	GEM_BUG_ON(obj->pages == NULL);
 	i915_gem_object_pin_pages(obj);
 
-	if (!obj->mapping) {
-		obj->mapping = i915_gem_object_map(obj);
-		if (!obj->mapping) {
-			i915_gem_object_unpin_pages(obj);
-			return ERR_PTR(-ENOMEM);
+	pinned = obj->pages_pin_count > 1;
+	ptr = (void *)((uintptr_t)obj->mapping & ~1);
+	has_wc = (uintptr_t)obj->mapping & 1;
+
+	if (ptr && has_wc != use_wc) {
+		if (pinned) {
+			ret = -EBUSY;
+			goto err;
+		}
+
+		if (is_vmalloc_addr(ptr))
+			vunmap(ptr);
+		else
+			kunmap(kmap_to_page(ptr));
+		ptr = obj->mapping = NULL;
+	}
+
+	if (!ptr) {
+		ptr = i915_gem_object_map(obj, use_wc);
+		if (!ptr) {
+			ret = -ENOMEM;
+			goto err;
 		}
+
+		obj->mapping = (void *)((uintptr_t)ptr | use_wc);
 	}
 
-	return obj->mapping;
+	return ptr;
+
+err:
+	i915_gem_object_unpin_pages(obj);
+	return ERR_PTR(ret);
 }
 
 void i915_vma_move_to_active(struct i915_vma *vma,
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index 80bbe43..edcadce 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -115,7 +115,7 @@ static void *i915_gem_dmabuf_vmap(struct dma_buf *dma_buf)
 	if (ret)
 		return ERR_PTR(ret);
 
-	addr = i915_gem_object_pin_map(obj);
+	addr = i915_gem_object_pin_map(obj, false);
 	mutex_unlock(&dev->struct_mutex);
 
 	return addr;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 62b0dc6..b6397a7 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -971,7 +971,7 @@ static int intel_lr_context_pin(struct i915_gem_context *ctx,
 	if (ret)
 		goto err;
 
-	vaddr = i915_gem_object_pin_map(ce->state);
+	vaddr = i915_gem_object_pin_map(ce->state, false);
 	if (IS_ERR(vaddr)) {
 		ret = PTR_ERR(vaddr);
 		goto unpin_ctx_obj;
@@ -2007,7 +2007,7 @@ lrc_setup_hws(struct intel_engine_cs *engine,
 	/* The HWSP is part of the default context object in LRC mode. */
 	engine->status_page.gfx_addr = i915_gem_obj_ggtt_offset(dctx_obj) +
 				       LRC_PPHWSP_PN * PAGE_SIZE;
-	hws = i915_gem_object_pin_map(dctx_obj);
+	hws = i915_gem_object_pin_map(dctx_obj, false);
 	if (IS_ERR(hws))
 		return PTR_ERR(hws);
 	engine->status_page.page_addr = hws + LRC_PPHWSP_PN * PAGE_SIZE;
@@ -2334,7 +2334,7 @@ populate_lr_context(struct i915_gem_context *ctx,
 		return ret;
 	}
 
-	vaddr = i915_gem_object_pin_map(ctx_obj);
+	vaddr = i915_gem_object_pin_map(ctx_obj, false);
 	if (IS_ERR(vaddr)) {
 		ret = PTR_ERR(vaddr);
 		DRM_DEBUG_DRIVER("Could not map object pages! (%d)\n", ret);
@@ -2568,7 +2568,7 @@ void intel_lr_context_reset(struct drm_i915_private *dev_priv,
 		if (!ctx_obj)
 			continue;
 
-		vaddr = i915_gem_object_pin_map(ctx_obj);
+		vaddr = i915_gem_object_pin_map(ctx_obj, false);
 		if (WARN_ON(IS_ERR(vaddr)))
 			continue;
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 13544f8..59df3da 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2212,7 +2212,7 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_i915_private *dev_priv,
 		if (ret)
 			goto err_unpin;
 
-		addr = i915_gem_object_pin_map(obj);
+		addr = i915_gem_object_pin_map(obj, false);
 		if (IS_ERR(addr)) {
 			ret = PTR_ERR(addr);
 			goto err_unpin;
-- 
1.9.2



More information about the Intel-gfx mailing list