drm/i915: Fix DMA mapped scatterlist walks

When walking DMA mapped scatterlists sg_dma_len has to be used since it
can be different (coalesced) from the backing store entry.

This also means we have to end the walk when encountering a zero length
DMA entry and cannot rely on the normal sg list end marker.

Both issues were there in theory for some time but were hidden by the fact
Intel IOMMU driver was never coalescing entries. As there are ongoing
efforts to change this we need to start handling it.

v2:
 * Use unsigned int for local storing sg_dma_len. (Logan)
Signed-off-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
References: 85d1225e ("drm/i915: Introduce & use new lightweight SGL iterators")
References: b31144c0 ("drm/i915: Micro-optimise gen6_ppgtt_insert_entries()")
Reported-by: NTom Murphy <murphyt7@tcd.ie>
Suggested-by: Tom Murphy <murphyt7@tcd.ie> # __sgt_iter
Suggested-by: Logan Gunthorpe <logang@deltatee.com> # __sgt_iter
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: NLogan Gunthorpe <logang@deltatee.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201006092508.1064287-1-tvrtko.ursulin@linux.intel.com

drivers/gpu/drm/i915/gt/gen6_ppgtt.c

@@ -131,17 +131,17 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 
 	vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));
 	do {
-		GEM_BUG_ON(iter.sg->length < I915_GTT_PAGE_SIZE);
+		GEM_BUG_ON(sg_dma_len(iter.sg) < I915_GTT_PAGE_SIZE);
 		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
 
 		iter.dma += I915_GTT_PAGE_SIZE;
 		if (iter.dma == iter.max) {
 			iter.sg = __sg_next(iter.sg);
-			if (!iter.sg)
+			if (!iter.sg || sg_dma_len(iter.sg) == 0)
 				break;
 
 			iter.dma = sg_dma_address(iter.sg);
-			iter.max = iter.dma + iter.sg->length;
+			iter.max = iter.dma + sg_dma_len(iter.sg);
 		}
 
 		if (++act_pte == GEN6_PTES) {

drivers/gpu/drm/i915/gt/gen8_ppgtt.c

@@ -372,19 +372,19 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 	pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2));
 	vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
 	do {
-		GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE);
+		GEM_BUG_ON(sg_dma_len(iter->sg) < I915_GTT_PAGE_SIZE);
 		vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma;
 
 		iter->dma += I915_GTT_PAGE_SIZE;
 		if (iter->dma >= iter->max) {
 			iter->sg = __sg_next(iter->sg);
-			if (!iter->sg) {
+			if (!iter->sg || sg_dma_len(iter->sg) == 0) {
 				idx = 0;
 				break;
 			}
 
 			iter->dma = sg_dma_address(iter->sg);
-			iter->max = iter->dma + iter->sg->length;
+			iter->max = iter->dma + sg_dma_len(iter->sg);
 		}
 
 		if (gen8_pd_index(++idx, 0) == 0) {
@@ -413,8 +413,8 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 				   u32 flags)
 {
 	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
+	unsigned int rem = sg_dma_len(iter->sg);
 	u64 start = vma->node.start;
-	dma_addr_t rem = iter->sg->length;
 
 	GEM_BUG_ON(!i915_vm_is_4lvl(vma->vm));
 
@@ -456,7 +456,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 		}
 
 		do {
-			GEM_BUG_ON(iter->sg->length < page_size);
+			GEM_BUG_ON(sg_dma_len(iter->sg) < page_size);
 			vaddr[index++] = encode | iter->dma;
 
 			start += page_size;
@@ -467,7 +467,10 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 				if (!iter->sg)
 					break;
 
-				rem = iter->sg->length;
+				rem = sg_dma_len(iter->sg);
+				if (!rem)
+					break;
+
 				iter->dma = sg_dma_address(iter->sg);
 				iter->max = iter->dma + rem;
 
@@ -525,7 +528,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
 		}
 
 		vma->page_sizes.gtt |= page_size;
-	} while (iter->sg);
+	} while (iter->sg && sg_dma_len(iter->sg));
 }
 
 static void gen8_ppgtt_insert(struct i915_address_space *vm,

drivers/gpu/drm/i915/gt/intel_gtt.h

@@ -580,7 +580,7 @@ static inline struct sgt_dma {
 	struct scatterlist *sg = vma->pages->sgl;
 	dma_addr_t addr = sg_dma_address(sg);
 
-	return (struct sgt_dma){ sg, addr, addr + sg->length };
+	return (struct sgt_dma){ sg, addr, addr + sg_dma_len(sg) };
 }
 
 #endif

drivers/gpu/drm/i915/i915_scatterlist.h

@@ -27,13 +27,17 @@ static __always_inline struct sgt_iter {
 } __sgt_iter(struct scatterlist *sgl, bool dma) {
 	struct sgt_iter s = { .sgp = sgl };
 
-	if (s.sgp) {
+	if (dma && s.sgp && sg_dma_len(s.sgp) == 0) {
+		s.sgp = NULL;
+	} else if (s.sgp) {
 		s.max = s.curr = s.sgp->offset;
-		s.max += s.sgp->length;
-		if (dma)
+		if (dma) {
 			s.dma = sg_dma_address(s.sgp);
-		else
+			s.max += sg_dma_len(s.sgp);
+		} else {
 			s.pfn = page_to_pfn(sg_page(s.sgp));
+			s.max += s.sgp->length;
+		}
 	}
 
 	return s;