drm/i915/gtt: map the PD up front

We need to generalise our accessor for the page directories and tables from
using the simple kmap_atomic to support local memory, and this setup
must be done on acquisition of the backing storage prior to entering
fence execution contexts. Here we replace the kmap with the object
mapping code that for simple single page shmemfs object will return a
plain kmap, that is then kept for the lifetime of the page directory.

Note that keeping the mapping around is a potential concern here, since
while the vma is pinned the mapping remains there for the PDs
underneath, or at least until the used_count reaches zero, at which
point we can safely destroy the mapping. For 32b this will be even worse
since the address space is more limited, but since this change mostly
impacts full ppGTT platforms, the justification is that for modern
platforms we shouldn't care too much about 32b.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210427085417.120246-3-matthew.auld@intel.com

1 files changed, 22 insertions, 26 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 941f8af016d6..d386b89e2758 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -25,27 +25,25 @@ struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz)
 	return obj;
 }
 
-int pin_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj)
+int map_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj)
 {
-	int err;
+	void *vaddr;
 
-	i915_gem_object_lock(obj, NULL);
-	err = i915_gem_object_pin_pages(obj);
-	i915_gem_object_unlock(obj);
-	if (err)
-		return err;
+	vaddr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
 
 	i915_gem_object_make_unshrinkable(obj);
 	return 0;
 }
 
-int pin_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj)
+int map_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj)
 {
-	int err;
+	void *vaddr;
 
-	err = i915_gem_object_pin_pages(obj);
-	if (err)
-		return err;
+	vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
 
 	i915_gem_object_make_unshrinkable(obj);
 	return 0;
@@ -155,6 +153,14 @@ void clear_pages(struct i915_vma *vma)
 	memset(&vma->page_sizes, 0, sizeof(vma->page_sizes));
 }
 
+void *__px_vaddr(struct drm_i915_gem_object *p)
+{
+	enum i915_map_type type;
+
+	GEM_BUG_ON(!i915_gem_object_has_pages(p));
+	return page_unpack_bits(p->mm.mapping, &type);
+}
+
 dma_addr_t __px_dma(struct drm_i915_gem_object *p)
 {
 	GEM_BUG_ON(!i915_gem_object_has_pages(p));
@@ -170,32 +176,22 @@ struct page *__px_page(struct drm_i915_gem_object *p)
 void
 fill_page_dma(struct drm_i915_gem_object *p, const u64 val, unsigned int count)
 {
-	struct page *page = __px_page(p);
-	void *vaddr;
+	void *vaddr = __px_vaddr(p);
 
-	vaddr = kmap(page);
 	memset64(vaddr, val, count);
 	clflush_cache_range(vaddr, PAGE_SIZE);
-	kunmap(page);
 }
 
 static void poison_scratch_page(struct drm_i915_gem_object *scratch)
 {
-	struct sgt_iter sgt;
-	struct page *page;
+	void *vaddr = __px_vaddr(scratch);
 	u8 val;
 
 	val = 0;
 	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		val = POISON_FREE;
 
-	for_each_sgt_page(page, sgt, scratch->mm.pages) {
-		void *vaddr;
-
-		vaddr = kmap(page);
-		memset(vaddr, val, PAGE_SIZE);
-		kunmap(page);
-	}
+	memset(vaddr, val, scratch->base.size);
 }
 
 int setup_scratch_page(struct i915_address_space *vm)
@@ -225,7 +221,7 @@ int setup_scratch_page(struct i915_address_space *vm)
 		if (IS_ERR(obj))
 			goto skip;
 
-		if (pin_pt_dma(vm, obj))
+		if (map_pt_dma(vm, obj))
 			goto skip_obj;
 
 		/* We need a single contiguous page for our scratch */