Backmerge drm-fixes merge into drm-next

Commit '6f6a73c8' from Linus' tree

The fixes reverts cause a bit of a conflict pain with intel next,
start fixing it up here.
Signed-off-by: Dave Airlie <airlied@redhat.com>

Makefile

@@ -882,10 +882,6 @@ KBUILD_CFLAGS_KERNEL += -ffunction-sections -fdata-sections
 LDFLAGS_vmlinux += --gc-sections
 endif
 
-ifdef CONFIG_LIVEPATCH
-KBUILD_CFLAGS += $(call cc-option, -flive-patching=inline-clone)
-endif
-
 ifdef CONFIG_SHADOW_CALL_STACK
 CC_FLAGS_SCS	:= -fsanitize=shadow-call-stack
 KBUILD_CFLAGS	+= $(CC_FLAGS_SCS)

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

@@ -46,6 +46,13 @@ struct eb_vma_array {
 	struct eb_vma vma[];
 };
 
+enum {
+	FORCE_CPU_RELOC = 1,
+	FORCE_GTT_RELOC,
+	FORCE_GPU_RELOC,
+#define DBG_FORCE_RELOC 0 /* choose one of the above! */
+};
+
 #define __EXEC_OBJECT_HAS_PIN		BIT(31)
 #define __EXEC_OBJECT_HAS_FENCE		BIT(30)
 #define __EXEC_OBJECT_NEEDS_MAP		BIT(29)
@@ -261,6 +268,8 @@ struct i915_execbuffer {
 	 */
 	struct reloc_cache {
 		struct drm_mm_node node; /** temporary GTT binding */
+		unsigned long vaddr; /** Current kmap address */
+		unsigned long page; /** Currently mapped page index */
 		unsigned int gen; /** Cached value of INTEL_GEN */
 		bool use_64bit_reloc : 1;
 		bool has_llc : 1;
@@ -607,6 +616,23 @@ eb_add_vma(struct i915_execbuffer *eb,
 	}
 }
 
+static inline int use_cpu_reloc(const struct reloc_cache *cache,
+				const struct drm_i915_gem_object *obj)
+{
+	if (!i915_gem_object_has_struct_page(obj))
+		return false;
+
+	if (DBG_FORCE_RELOC == FORCE_CPU_RELOC)
+		return true;
+
+	if (DBG_FORCE_RELOC == FORCE_GTT_RELOC)
+		return false;
+
+	return (cache->has_llc ||
+		obj->cache_dirty ||
+		obj->cache_level != I915_CACHE_NONE);
+}
+
 static int eb_reserve_vma(const struct i915_execbuffer *eb,
 			  struct eb_vma *ev,
 			  u64 pin_flags)
@@ -937,6 +963,8 @@ relocation_target(const struct drm_i915_gem_relocation_entry *reloc,
 static void reloc_cache_init(struct reloc_cache *cache,
 			     struct drm_i915_private *i915)
 {
+	cache->page = -1;
+	cache->vaddr = 0;
 	/* Must be a variable in the struct to allow GCC to unroll. */
 	cache->gen = INTEL_GEN(i915);
 	cache->has_llc = HAS_LLC(i915);
@@ -948,6 +976,25 @@ static void reloc_cache_init(struct reloc_cache *cache,
 	cache->target = NULL;
 }
 
+static inline void *unmask_page(unsigned long p)
+{
+	return (void *)(uintptr_t)(p & PAGE_MASK);
+}
+
+static inline unsigned int unmask_flags(unsigned long p)
+{
+	return p & ~PAGE_MASK;
+}
+
+#define KMAP 0x4 /* after CLFLUSH_FLAGS */
+
+static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache)
+{
+	struct drm_i915_private *i915 =
+		container_of(cache, struct i915_execbuffer, reloc_cache)->i915;
+	return &i915->ggtt;
+}
+
 #define RELOC_TAIL 4
 
 static int reloc_gpu_chain(struct reloc_cache *cache)
@@ -1060,6 +1107,181 @@ static int reloc_gpu_flush(struct reloc_cache *cache)
 	return err;
 }
 
+static void reloc_cache_reset(struct reloc_cache *cache)
+{
+	void *vaddr;
+
+	if (!cache->vaddr)
+		return;
+
+	vaddr = unmask_page(cache->vaddr);
+	if (cache->vaddr & KMAP) {
+		if (cache->vaddr & CLFLUSH_AFTER)
+			mb();
+
+		kunmap_atomic(vaddr);
+		i915_gem_object_finish_access((struct drm_i915_gem_object *)cache->node.mm);
+	} else {
+		struct i915_ggtt *ggtt = cache_to_ggtt(cache);
+
+		intel_gt_flush_ggtt_writes(ggtt->vm.gt);
+		io_mapping_unmap_atomic((void __iomem *)vaddr);
+
+		if (drm_mm_node_allocated(&cache->node)) {
+			ggtt->vm.clear_range(&ggtt->vm,
+					     cache->node.start,
+					     cache->node.size);
+			mutex_lock(&ggtt->vm.mutex);
+			drm_mm_remove_node(&cache->node);
+			mutex_unlock(&ggtt->vm.mutex);
+		} else {
+			i915_vma_unpin((struct i915_vma *)cache->node.mm);
+		}
+	}
+
+	cache->vaddr = 0;
+	cache->page = -1;
+}
+
+static void *reloc_kmap(struct drm_i915_gem_object *obj,
+			struct reloc_cache *cache,
+			unsigned long page)
+{
+	void *vaddr;
+
+	if (cache->vaddr) {
+		kunmap_atomic(unmask_page(cache->vaddr));
+	} else {
+		unsigned int flushes;
+		int err;
+
+		err = i915_gem_object_prepare_write(obj, &flushes);
+		if (err)
+			return ERR_PTR(err);
+
+		BUILD_BUG_ON(KMAP & CLFLUSH_FLAGS);
+		BUILD_BUG_ON((KMAP | CLFLUSH_FLAGS) & PAGE_MASK);
+
+		cache->vaddr = flushes | KMAP;
+		cache->node.mm = (void *)obj;
+		if (flushes)
+			mb();
+	}
+
+	vaddr = kmap_atomic(i915_gem_object_get_dirty_page(obj, page));
+	cache->vaddr = unmask_flags(cache->vaddr) | (unsigned long)vaddr;
+	cache->page = page;
+
+	return vaddr;
+}
+
+static void *reloc_iomap(struct drm_i915_gem_object *obj,
+			 struct reloc_cache *cache,
+			 unsigned long page)
+{
+	struct i915_ggtt *ggtt = cache_to_ggtt(cache);
+	unsigned long offset;
+	void *vaddr;
+
+	if (cache->vaddr) {
+		intel_gt_flush_ggtt_writes(ggtt->vm.gt);
+		io_mapping_unmap_atomic((void __force __iomem *) unmask_page(cache->vaddr));
+	} else {
+		struct i915_vma *vma;
+		int err;
+
+		if (i915_gem_object_is_tiled(obj))
+			return ERR_PTR(-EINVAL);
+
+		if (use_cpu_reloc(cache, obj))
+			return NULL;
+
+		i915_gem_object_lock(obj);
+		err = i915_gem_object_set_to_gtt_domain(obj, true);
+		i915_gem_object_unlock(obj);
+		if (err)
+			return ERR_PTR(err);
+
+		vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
+					       PIN_MAPPABLE |
+					       PIN_NONBLOCK /* NOWARN */ |
+					       PIN_NOEVICT);
+		if (IS_ERR(vma)) {
+			memset(&cache->node, 0, sizeof(cache->node));
+			mutex_lock(&ggtt->vm.mutex);
+			err = drm_mm_insert_node_in_range
+				(&ggtt->vm.mm, &cache->node,
+				 PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
+				 0, ggtt->mappable_end,
+				 DRM_MM_INSERT_LOW);
+			mutex_unlock(&ggtt->vm.mutex);
+			if (err) /* no inactive aperture space, use cpu reloc */
+				return NULL;
+		} else {
+			cache->node.start = vma->node.start;
+			cache->node.mm = (void *)vma;
+		}
+	}
+
+	offset = cache->node.start;
+	if (drm_mm_node_allocated(&cache->node)) {
+		ggtt->vm.insert_page(&ggtt->vm,
+				     i915_gem_object_get_dma_address(obj, page),
+				     offset, I915_CACHE_NONE, 0);
+	} else {
+		offset += page << PAGE_SHIFT;
+	}
+
+	vaddr = (void __force *)io_mapping_map_atomic_wc(&ggtt->iomap,
+							 offset);
+	cache->page = page;
+	cache->vaddr = (unsigned long)vaddr;
+
+	return vaddr;
+}
+
+static void *reloc_vaddr(struct drm_i915_gem_object *obj,
+			 struct reloc_cache *cache,
+			 unsigned long page)
+{
+	void *vaddr;
+
+	if (cache->page == page) {
+		vaddr = unmask_page(cache->vaddr);
+	} else {
+		vaddr = NULL;
+		if ((cache->vaddr & KMAP) == 0)
+			vaddr = reloc_iomap(obj, cache, page);
+		if (!vaddr)
+			vaddr = reloc_kmap(obj, cache, page);
+	}
+
+	return vaddr;
+}
+
+static void clflush_write32(u32 *addr, u32 value, unsigned int flushes)
+{
+	if (unlikely(flushes & (CLFLUSH_BEFORE | CLFLUSH_AFTER))) {
+		if (flushes & CLFLUSH_BEFORE) {
+			clflushopt(addr);
+			mb();
+		}
+
+		*addr = value;
+
+		/*
+		 * Writes to the same cacheline are serialised by the CPU
+		 * (including clflush). On the write path, we only require
+		 * that it hits memory in an orderly fashion and place
+		 * mb barriers at the start and end of the relocation phase
+		 * to ensure ordering of clflush wrt to the system.
+		 */
+		if (flushes & CLFLUSH_AFTER)
+			clflushopt(addr);
+	} else
+		*addr = value;
+}
+
 static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
@@ -1225,6 +1447,17 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
 	return cmd;
 }
 
+static inline bool use_reloc_gpu(struct i915_vma *vma)
+{
+	if (DBG_FORCE_RELOC == FORCE_GPU_RELOC)
+		return true;
+
+	if (DBG_FORCE_RELOC)
+		return false;
+
+	return !dma_resv_test_signaled_rcu(vma->resv, true);
+}
+
 static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset)
 {
 	struct page *page;
@@ -1239,10 +1472,10 @@ static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset)
 	return addr + offset_in_page(offset);
 }
 
-static int __reloc_entry_gpu(struct i915_execbuffer *eb,
-			     struct i915_vma *vma,
-			     u64 offset,
-			     u64 target_addr)
+static bool __reloc_entry_gpu(struct i915_execbuffer *eb,
+			      struct i915_vma *vma,
+			      u64 offset,
+			      u64 target_addr)
 {
 	const unsigned int gen = eb->reloc_cache.gen;
 	unsigned int len;
@@ -1258,7 +1491,7 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb,
 
 	batch = reloc_gpu(eb, vma, len);
 	if (IS_ERR(batch))
-		return PTR_ERR(batch);
+		return false;
 
 	addr = gen8_canonical_addr(vma->node.start + offset);
 	if (gen >= 8) {
@@ -1307,21 +1540,55 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb,
 		*batch++ = target_addr;
 	}
 
-	return 0;
+	return true;
+}
+
+static bool reloc_entry_gpu(struct i915_execbuffer *eb,
+			    struct i915_vma *vma,
+			    u64 offset,
+			    u64 target_addr)
+{
+	if (eb->reloc_cache.vaddr)
+		return false;
+
+	if (!use_reloc_gpu(vma))
+		return false;
+
+	return __reloc_entry_gpu(eb, vma, offset, target_addr);
 }
 
 static u64
-relocate_entry(struct i915_execbuffer *eb,
-	       struct i915_vma *vma,
+relocate_entry(struct i915_vma *vma,
 	       const struct drm_i915_gem_relocation_entry *reloc,
+	       struct i915_execbuffer *eb,
 	       const struct i915_vma *target)
 {
 	u64 target_addr = relocation_target(reloc, target);
-	int err;
-
-	err = __reloc_entry_gpu(eb, vma, reloc->offset, target_addr);
-	if (err)
-		return err;
+	u64 offset = reloc->offset;
+
+	if (!reloc_entry_gpu(eb, vma, offset, target_addr)) {
+		bool wide = eb->reloc_cache.use_64bit_reloc;
+		void *vaddr;
+
+repeat:
+		vaddr = reloc_vaddr(vma->obj,
+				    &eb->reloc_cache,
+				    offset >> PAGE_SHIFT);
+		if (IS_ERR(vaddr))
+			return PTR_ERR(vaddr);
+
+		GEM_BUG_ON(!IS_ALIGNED(offset, sizeof(u32)));
+		clflush_write32(vaddr + offset_in_page(offset),
+				lower_32_bits(target_addr),
+				eb->reloc_cache.vaddr);
+
+		if (wide) {
+			offset += sizeof(u32);
+			target_addr >>= 32;
+			wide = false;
+			goto repeat;
+		}
+	}
 
 	return target->node.start | UPDATE;
 }
@@ -1386,7 +1653,8 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 	 * If the relocation already has the right value in it, no
 	 * more work needs to be done.
 	 */
-	if (gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset)
+	if (!DBG_FORCE_RELOC &&
+	    gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset)
 		return 0;
 
 	/* Check that the relocation address is valid... */
@@ -1418,7 +1686,7 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 	ev->flags &= ~EXEC_OBJECT_ASYNC;
 
 	/* and update the user's relocation entry */
-	return relocate_entry(eb, ev->vma, reloc, target->vma);
+	return relocate_entry(ev->vma, reloc, eb, target->vma);
 }
 
 static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
@@ -1456,8 +1724,10 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 		 * this is bad and so lockdep complains vehemently.
 		 */
 		copied = __copy_from_user(r, urelocs, count * sizeof(r[0]));
-		if (unlikely(copied))
-			return -EFAULT;
+		if (unlikely(copied)) {
+			remain = -EFAULT;
+			goto out;
+		}
 
 		remain -= count;
 		do {
@@ -1465,7 +1735,8 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 
 			if (likely(offset == 0)) {
 			} else if ((s64)offset < 0) {
-				return (int)offset;
+				remain = (int)offset;
+				goto out;
 			} else {
 				/*
 				 * Note that reporting an error now
@@ -1495,8 +1766,9 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 		} while (r++, --count);
 		urelocs += ARRAY_SIZE(stack);
 	} while (remain);
-
-	return 0;
+out:
+	reloc_cache_reset(&eb->reloc_cache);
+	return remain;
 }
 
 static int eb_relocate(struct i915_execbuffer *eb)
@@ -2584,7 +2856,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.i915 = i915;
 	eb.file = file;
 	eb.args = args;
-	if (!(args->flags & I915_EXEC_NO_RELOC))
+	if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC))
 		args->flags |= __EXEC_HAS_RELOC;
 
 	eb.exec = exec;

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

@@ -258,6 +258,10 @@ struct page *
 i915_gem_object_get_page(struct drm_i915_gem_object *obj,
 			 unsigned int n);
 
+struct page *
+i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj,
+			       unsigned int n);
+
 dma_addr_t
 i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj,
 				    unsigned long n,

drivers/gpu/drm/i915/gem/i915_gem_pages.c

@@ -548,6 +548,20 @@ i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n)
 	return nth_page(sg_page(sg), offset);
 }
 
+/* Like i915_gem_object_get_page(), but mark the returned page dirty */
+struct page *
+i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj,
+			       unsigned int n)
+{
+	struct page *page;
+
+	page = i915_gem_object_get_page(obj, n);
+	if (!obj->mm.dirty)
+		set_page_dirty(page);
+
+	return page;
+}
+
 dma_addr_t
 i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj,
 				    unsigned long n,

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

@@ -37,14 +37,20 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
 		return err;
 
 	/* 8-Byte aligned */
-	err = __reloc_entry_gpu(eb, vma, offsets[0] * sizeof(u32), 0);
-	if (err)
+	if (!__reloc_entry_gpu(eb, vma,
+			       offsets[0] * sizeof(u32),
+			       0)) {
+		err = -EIO;
 		goto unpin_vma;
+	}
 
 	/* !8-Byte aligned */
-	err = __reloc_entry_gpu(eb, vma, offsets[1] * sizeof(u32), 1);
-	if (err)
+	if (!__reloc_entry_gpu(eb, vma,
+			       offsets[1] * sizeof(u32),
+			       1)) {
+		err = -EIO;
 		goto unpin_vma;
+	}
 
 	/* Skip to the end of the cmd page */
 	i = PAGE_SIZE / sizeof(u32) - RELOC_TAIL - 1;
@@ -54,9 +60,12 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
 	eb->reloc_cache.rq_size += i;
 
 	/* Force batch chaining */
-	err = __reloc_entry_gpu(eb, vma, offsets[2] * sizeof(u32), 2);
-	if (err)
+	if (!__reloc_entry_gpu(eb, vma,
+			       offsets[2] * sizeof(u32),
+			       2)) {
+		err = -EIO;
 		goto unpin_vma;
+	}
 
 	GEM_BUG_ON(!eb->reloc_cache.rq);
 	rq = i915_request_get(eb->reloc_cache.rq);

drivers/gpu/drm/msm/adreno/a2xx_gpu.c

@@ -164,6 +164,11 @@ static int a2xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	gpu_write(gpu, REG_AXXX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* NOTE: PM4/micro-engine firmware registers look to be the same
 	 * for a2xx and a3xx.. we could possibly push that part down to
 	 * adreno_gpu base class.  Or push both PM4 and PFP but

drivers/gpu/drm/msm/adreno/a3xx_gpu.c

@@ -211,6 +211,16 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	/*
+	 * Use the default ringbuffer size and block size but disable the RPTR
+	 * shadow
+	 */
+	gpu_write(gpu, REG_AXXX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	/* Set the ringbuffer address */
+	gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* setup access protection: */
 	gpu_write(gpu, REG_A3XX_CP_PROTECT_CTRL, 0x00000007);
 

drivers/gpu/drm/msm/adreno/a4xx_gpu.c

@@ -267,6 +267,16 @@ static int a4xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	/*
+	 * Use the default ringbuffer size and block size but disable the RPTR
+	 * shadow
+	 */
+	gpu_write(gpu, REG_A4XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	/* Set the ringbuffer address */
+	gpu_write(gpu, REG_A4XX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* Load PM4: */
 	ptr = (uint32_t *)(adreno_gpu->fw[ADRENO_FW_PM4]->data);
 	len = adreno_gpu->fw[ADRENO_FW_PM4]->size / 4;

drivers/gpu/drm/msm/adreno/a5xx_gpu.c

@@ -703,8 +703,6 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
-	a5xx_preempt_hw_init(gpu);
-
 	if (!adreno_is_a510(adreno_gpu))
 		a5xx_gpmu_ucode_init(gpu);
 
@@ -712,6 +710,15 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	/* Set the ringbuffer address */
+	gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI,
+		gpu->rb[0]->iova);
+
+	gpu_write(gpu, REG_A5XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	a5xx_preempt_hw_init(gpu);
+
 	/* Disable the interrupts through the initial bringup stage */
 	gpu_write(gpu, REG_A5XX_RBBM_INT_0_MASK, A5XX_INT_MASK);
 
@@ -1511,7 +1518,8 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev)
 
 	check_speed_bin(&pdev->dev);
 
-	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 4);
+	/* Restricting nr_rings to 1 to temporarily disable preemption */
+	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
 	if (ret) {
 		a5xx_destroy(&(a5xx_gpu->base.base));
 		return ERR_PTR(ret);

drivers/gpu/drm/msm/adreno/a5xx_gpu.h

@@ -31,6 +31,7 @@ struct a5xx_gpu {
 	struct msm_ringbuffer *next_ring;
 
 	struct drm_gem_object *preempt_bo[MSM_GPU_MAX_RINGS];
+	struct drm_gem_object *preempt_counters_bo[MSM_GPU_MAX_RINGS];
 	struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS];
 	uint64_t preempt_iova[MSM_GPU_MAX_RINGS];
 

drivers/gpu/drm/msm/adreno/a5xx_preempt.c

@@ -226,19 +226,31 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu,
 	struct adreno_gpu *adreno_gpu = &a5xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
 	struct a5xx_preempt_record *ptr;
-	struct drm_gem_object *bo = NULL;
-	u64 iova = 0;
+	void *counters;
+	struct drm_gem_object *bo = NULL, *counters_bo = NULL;
+	u64 iova = 0, counters_iova = 0;
 
 	ptr = msm_gem_kernel_new(gpu->dev,
 		A5XX_PREEMPT_RECORD_SIZE + A5XX_PREEMPT_COUNTER_SIZE,
-		MSM_BO_UNCACHED, gpu->aspace, &bo, &iova);
+		MSM_BO_UNCACHED | MSM_BO_MAP_PRIV, gpu->aspace, &bo, &iova);
 
 	if (IS_ERR(ptr))
 		return PTR_ERR(ptr);
 
+	/* The buffer to store counters needs to be unprivileged */
+	counters = msm_gem_kernel_new(gpu->dev,
+		A5XX_PREEMPT_COUNTER_SIZE,
+		MSM_BO_UNCACHED, gpu->aspace, &counters_bo, &counters_iova);
+	if (IS_ERR(counters)) {
+		msm_gem_kernel_put(bo, gpu->aspace, true);
+		return PTR_ERR(counters);
+	}
+
 	msm_gem_object_set_name(bo, "preempt");
+	msm_gem_object_set_name(counters_bo, "preempt_counters");
 
 	a5xx_gpu->preempt_bo[ring->id] = bo;
+	a5xx_gpu->preempt_counters_bo[ring->id] = counters_bo;
 	a5xx_gpu->preempt_iova[ring->id] = iova;
 	a5xx_gpu->preempt[ring->id] = ptr;
 
@@ -249,7 +261,7 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu,
 	ptr->data = 0;
 	ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT;
 	ptr->rptr_addr = rbmemptr(ring, rptr);
-	ptr->counter = iova + A5XX_PREEMPT_RECORD_SIZE;
+	ptr->counter = counters_iova;
 
 	return 0;
 }
@@ -260,8 +272,11 @@ void a5xx_preempt_fini(struct msm_gpu *gpu)
 	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
 	int i;
 
-	for (i = 0; i < gpu->nr_rings; i++)
+	for (i = 0; i < gpu->nr_rings; i++) {
 		msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true);
+		msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i],
+			gpu->aspace, true);
+	}
 }
 
 void a5xx_preempt_init(struct msm_gpu *gpu)

drivers/gpu/drm/msm/adreno/a6xx_gpu.c

@@ -678,7 +678,8 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 			A6XX_PROTECT_RDONLY(0x980, 0x4));
 	gpu_write(gpu, REG_A6XX_CP_PROTECT(25), A6XX_PROTECT_RW(0xa630, 0x0));
 
-	if (adreno_is_a650(adreno_gpu)) {
+	/* Enable expanded apriv for targets that support it */
+	if (gpu->hw_apriv) {
 		gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL,
 			(1 << 6) | (1 << 5) | (1 << 3) | (1 << 2) | (1 << 1));
 	}
@@ -694,6 +695,13 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		goto out;
 
+	/* Set the ringbuffer address */
+	gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI,
+		gpu->rb[0]->iova);
+
+	gpu_write(gpu, REG_A6XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
 	/* Always come up on rb 0 */
 	a6xx_gpu->cur_ring = gpu->rb[0];
 
@@ -1056,6 +1064,9 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	adreno_gpu->registers = NULL;
 	adreno_gpu->reg_offsets = a6xx_register_offsets;
 
+	if (adreno_is_a650(adreno_gpu))
+		adreno_gpu->base.hw_apriv = true;
+
 	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
 	if (ret) {
 		a6xx_destroy(&(a6xx_gpu->base.base));

drivers/gpu/drm/msm/adreno/adreno_gpu.c

@@ -400,26 +400,6 @@ int adreno_hw_init(struct msm_gpu *gpu)
 		ring->memptrs->rptr = 0;
 	}
 
-	/*
-	 * Setup REG_CP_RB_CNTL.  The same value is used across targets (with
-	 * the excpetion of A430 that disables the RPTR shadow) - the cacluation
-	 * for the ringbuffer size and block size is moved to msm_gpu.h for the
-	 * pre-processor to deal with and the A430 variant is ORed in here
-	 */
-	adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL,
-		MSM_GPU_RB_CNTL_DEFAULT |
-		(adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0));
-
-	/* Setup ringbuffer address - use ringbuffer[0] for GPU init */
-	adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_BASE,
-		REG_ADRENO_CP_RB_BASE_HI, gpu->rb[0]->iova);
-
-	if (!adreno_is_a430(adreno_gpu)) {
-		adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_RPTR_ADDR,
-			REG_ADRENO_CP_RB_RPTR_ADDR_HI,
-			rbmemptr(gpu->rb[0], rptr));
-	}
-
 	return 0;
 }
 
@@ -427,11 +407,8 @@ int adreno_hw_init(struct msm_gpu *gpu)
 static uint32_t get_rptr(struct adreno_gpu *adreno_gpu,
 		struct msm_ringbuffer *ring)
 {
-	if (adreno_is_a430(adreno_gpu))
-		return ring->memptrs->rptr = adreno_gpu_read(
-			adreno_gpu, REG_ADRENO_CP_RB_RPTR);
-	else
-		return ring->memptrs->rptr;
+	return ring->memptrs->rptr = adreno_gpu_read(
+		adreno_gpu, REG_ADRENO_CP_RB_RPTR);
 }
 
 struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu)

drivers/gpu/drm/msm/msm_gpu.c

@@ -908,7 +908,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 	memptrs = msm_gem_kernel_new(drm,
 		sizeof(struct msm_rbmemptrs) * nr_rings,
-		MSM_BO_UNCACHED, gpu->aspace, &gpu->memptrs_bo,
+		check_apriv(gpu, MSM_BO_UNCACHED), gpu->aspace, &gpu->memptrs_bo,
 		&memptrs_iova);
 
 	if (IS_ERR(memptrs)) {

drivers/gpu/drm/msm/msm_gpu.h

@@ -15,6 +15,7 @@
 #include "msm_drv.h"
 #include "msm_fence.h"
 #include "msm_ringbuffer.h"
+#include "msm_gem.h"
 
 struct msm_gem_submit;
 struct msm_gpu_perfcntr;
@@ -139,6 +140,8 @@ struct msm_gpu {
 	} devfreq;
 
 	struct msm_gpu_state *crashstate;
+	/* True if the hardware supports expanded apriv (a650 and newer) */
+	bool hw_apriv;
 };
 
 /* It turns out that all targets use the same ringbuffer size */
@@ -327,4 +330,12 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
 	mutex_unlock(&gpu->dev->struct_mutex);
 }
 
+/*
+ * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can
+ * support expanded privileges
+ */
+#define check_apriv(gpu, flags) \
+	(((gpu)->hw_apriv ? MSM_BO_MAP_PRIV : 0) | (flags))
+
+
 #endif /* __MSM_GPU_H__ */

drivers/gpu/drm/msm/msm_ringbuffer.c

@@ -27,8 +27,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 	ring->id = id;
 
 	ring->start = msm_gem_kernel_new(gpu->dev, MSM_GPU_RINGBUFFER_SZ,
-		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &ring->bo,
-		&ring->iova);
+		check_apriv(gpu, MSM_BO_WC | MSM_BO_GPU_READONLY),
+		gpu->aspace, &ring->bo, &ring->iova);
 
 	if (IS_ERR(ring->start)) {
 		ret = PTR_ERR(ring->start);