drm/i915/gem: Implement legacy MI_STORE_DATA_IMM

The older arches did not convert MI_STORE_DATA_IMM to using the GTT, but
left them writing to a physical address. The notes suggest that the
primary reason would be so that the writes were cache coherent, as the
CPU cache uses physical tagging. As such we did not implement the
legacy variant of MI_STORE_DATA_IMM and so left all the relocations
synchronous -- but with a small function to convert from the vma address
into the physical address, we can implement asynchronous relocs on these
older arches, fixing up a few tests that require them.

In order to be able to test the legacy paths, refactor the gpu
relocations so that we can hook them up to a selftest.

v2: Use an array of offsets not enum labels for the selftest
v3: Refactor the common igt_hexdump()

Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/757
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200504140629.28240-1-chris@chris-wilson.co.uk

3 files changed, 302 insertions, 104 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 1c247ad0971a..966523a8503f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -955,7 +955,7 @@ static void reloc_cache_init(struct reloc_cache *cache,
 	cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
 	cache->node.flags = 0;
 	cache->rq = NULL;
-	cache->rq_size = 0;
+	cache->target = NULL;
 }
 
 static inline void *unmask_page(unsigned long p)
@@ -1325,7 +1325,7 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 
 		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
-			err = PTR_ERR(rq);
+			err = PTR_ERR(ce);
 			goto err_unpin;
 		}
 
@@ -1376,6 +1376,11 @@ out_pool:
 	return err;
 }
 
+static bool reloc_can_use_engine(const struct intel_engine_cs *engine)
+{
+	return engine->class != VIDEO_DECODE_CLASS || !IS_GEN(engine->i915, 6);
+}
+
 static u32 *reloc_gpu(struct i915_execbuffer *eb,
 		      struct i915_vma *vma,
 		      unsigned int len)
@@ -1387,9 +1392,9 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
 	if (unlikely(!cache->rq)) {
 		struct intel_engine_cs *engine = eb->engine;
 
-		if (!intel_engine_can_store_dword(engine)) {
+		if (!reloc_can_use_engine(engine)) {
 			engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0];
-			if (!engine || !intel_engine_can_store_dword(engine))
+			if (!engine)
 				return ERR_PTR(-ENODEV);
 		}
 
@@ -1435,91 +1440,138 @@ static inline bool use_reloc_gpu(struct i915_vma *vma)
 	return !dma_resv_test_signaled_rcu(vma->resv, true);
 }
 
-static u64
-relocate_entry(struct i915_vma *vma,
-	       const struct drm_i915_gem_relocation_entry *reloc,
-	       struct i915_execbuffer *eb,
-	       const struct i915_vma *target)
+static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset)
 {
-	u64 offset = reloc->offset;
-	u64 target_offset = relocation_target(reloc, target);
-	bool wide = eb->reloc_cache.use_64bit_reloc;
-	void *vaddr;
+	struct page *page;
+	unsigned long addr;
 
-	if (!eb->reloc_cache.vaddr && use_reloc_gpu(vma)) {
-		const unsigned int gen = eb->reloc_cache.gen;
-		unsigned int len;
-		u32 *batch;
-		u64 addr;
+	GEM_BUG_ON(vma->pages != vma->obj->mm.pages);
 
-		if (wide)
-			len = offset & 7 ? 8 : 5;
-		else if (gen >= 4)
-			len = 4;
-		else
-			len = 3;
+	page = i915_gem_object_get_page(vma->obj, offset >> PAGE_SHIFT);
+	addr = PFN_PHYS(page_to_pfn(page));
+	GEM_BUG_ON(overflows_type(addr, u32)); /* expected dma32 */
 
-		batch = reloc_gpu(eb, vma, len);
-		if (IS_ERR(batch))
-			goto repeat;
+	return addr + offset_in_page(offset);
+}
+
+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;
+	u32 *batch;
+	u64 addr;
+
+	if (gen >= 8)
+		len = offset & 7 ? 8 : 5;
+	else if (gen >= 4)
+		len = 4;
+	else
+		len = 3;
+
+	batch = reloc_gpu(eb, vma, len);
+	if (IS_ERR(batch))
+		return false;
+
+	addr = gen8_canonical_addr(vma->node.start + offset);
+	if (gen >= 8) {
+		if (offset & 7) {
+			*batch++ = MI_STORE_DWORD_IMM_GEN4;
+			*batch++ = lower_32_bits(addr);
+			*batch++ = upper_32_bits(addr);
+			*batch++ = lower_32_bits(target_addr);
+
+			addr = gen8_canonical_addr(addr + 4);
 
-		addr = gen8_canonical_addr(vma->node.start + offset);
-		if (wide) {
-			if (offset & 7) {
-				*batch++ = MI_STORE_DWORD_IMM_GEN4;
-				*batch++ = lower_32_bits(addr);
-				*batch++ = upper_32_bits(addr);
-				*batch++ = lower_32_bits(target_offset);
-
-				addr = gen8_canonical_addr(addr + 4);
-
-				*batch++ = MI_STORE_DWORD_IMM_GEN4;
-				*batch++ = lower_32_bits(addr);
-				*batch++ = upper_32_bits(addr);
-				*batch++ = upper_32_bits(target_offset);
-			} else {
-				*batch++ = (MI_STORE_DWORD_IMM_GEN4 | (1 << 21)) + 1;
-				*batch++ = lower_32_bits(addr);
-				*batch++ = upper_32_bits(addr);
-				*batch++ = lower_32_bits(target_offset);
-				*batch++ = upper_32_bits(target_offset);
-			}
-		} else if (gen >= 6) {
 			*batch++ = MI_STORE_DWORD_IMM_GEN4;
-			*batch++ = 0;
-			*batch++ = addr;
-			*batch++ = target_offset;
-		} else if (gen >= 4) {
-			*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
-			*batch++ = 0;
-			*batch++ = addr;
-			*batch++ = target_offset;
+			*batch++ = lower_32_bits(addr);
+			*batch++ = upper_32_bits(addr);
+			*batch++ = upper_32_bits(target_addr);
 		} else {
-			*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
-			*batch++ = addr;
-			*batch++ = target_offset;
+			*batch++ = (MI_STORE_DWORD_IMM_GEN4 | (1 << 21)) + 1;
+			*batch++ = lower_32_bits(addr);
+			*batch++ = upper_32_bits(addr);
+			*batch++ = lower_32_bits(target_addr);
+			*batch++ = upper_32_bits(target_addr);
 		}
-
-		goto out;
+	} else if (gen >= 6) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4;
+		*batch++ = 0;
+		*batch++ = addr;
+		*batch++ = target_addr;
+	} else if (IS_I965G(eb->i915)) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4;
+		*batch++ = 0;
+		*batch++ = vma_phys_addr(vma, offset);
+		*batch++ = target_addr;
+	} else if (gen >= 4) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+		*batch++ = 0;
+		*batch++ = addr;
+		*batch++ = target_addr;
+	} else if (gen >= 3 &&
+		   !(IS_I915G(eb->i915) || IS_I915GM(eb->i915))) {
+		*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
+		*batch++ = addr;
+		*batch++ = target_addr;
+	} else {
+		*batch++ = MI_STORE_DWORD_IMM;
+		*batch++ = vma_phys_addr(vma, offset);
+		*batch++ = target_addr;
 	}
 
+	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_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);
+	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);
+		vaddr = reloc_vaddr(vma->obj,
+				    &eb->reloc_cache,
+				    offset >> PAGE_SHIFT);
+		if (IS_ERR(vaddr))
+			return PTR_ERR(vaddr);
 
-	clflush_write32(vaddr + offset_in_page(offset),
-			lower_32_bits(target_offset),
-			eb->reloc_cache.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_offset >>= 32;
-		wide = false;
-		goto repeat;
+		if (wide) {
+			offset += sizeof(u32);
+			target_addr >>= 32;
+			wide = false;
+			goto repeat;
+		}
 	}
 
-out:
 	return target->node.start | UPDATE;
 }
 
@@ -3022,3 +3074,7 @@ end:;
 	kvfree(exec2_list);
 	return err;
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/i915_gem_execbuffer.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index be268511cb6d..8fe3ad2ee34e 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -302,35 +302,6 @@ static void fill_scratch(struct tiled_blits *t, u32 *vaddr, u32 val)
 	i915_gem_object_flush_map(t->scratch.vma->obj);
 }
 
-static void hexdump(const void *buf, size_t len)
-{
-	const size_t rowsize = 8 * sizeof(u32);
-	const void *prev = NULL;
-	bool skip = false;
-	size_t pos;
-
-	for (pos = 0; pos < len; pos += rowsize) {
-		char line[128];
-
-		if (prev && !memcmp(prev, buf + pos, rowsize)) {
-			if (!skip) {
-				pr_info("*\n");
-				skip = true;
-			}
-			continue;
-		}
-
-		WARN_ON_ONCE(hex_dump_to_buffer(buf + pos, len - pos,
-						rowsize, sizeof(u32),
-						line, sizeof(line),
-						false) >= sizeof(line));
-		pr_info("[%04zx] %s\n", pos, line);
-
-		prev = buf + pos;
-		skip = false;
-	}
-}
-
 static u64 swizzle_bit(unsigned int bit, u64 offset)
 {
 	return (offset & BIT_ULL(bit)) >> (bit - 6);
@@ -426,7 +397,7 @@ static int verify_buffer(const struct tiled_blits *t,
 		pr_err("Invalid %s tiling detected at (%d, %d), start_val %x\n",
 		       repr_tiling(buf->tiling),
 		       x, y, buf->start_val);
-		hexdump(vaddr, 4096);
+		igt_hexdump(vaddr, 4096);
 	}
 
 	i915_gem_object_unpin_map(buf->vma->obj);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
new file mode 100644
index 000000000000..a49016f8ee0d
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include "i915_selftest.h"
+
+#include "gt/intel_engine_pm.h"
+#include "selftests/igt_flush_test.h"
+
+static u64 read_reloc(const u32 *map, int x, const u64 mask)
+{
+	u64 reloc;
+
+	memcpy(&reloc, &map[x], sizeof(reloc));
+	return reloc & mask;
+}
+
+static int __igt_gpu_reloc(struct i915_execbuffer *eb,
+			   struct drm_i915_gem_object *obj)
+{
+	const unsigned int offsets[] = { 8, 3, 0 };
+	const u64 mask =
+		GENMASK_ULL(eb->reloc_cache.use_64bit_reloc ? 63 : 31, 0);
+	const u32 *map = page_mask_bits(obj->mm.mapping);
+	struct i915_request *rq;
+	struct i915_vma *vma;
+	int err;
+	int i;
+
+	vma = i915_vma_instance(obj, eb->context->vm, NULL);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_HIGH);
+	if (err)
+		return err;
+
+	/* 8-Byte aligned */
+	if (!__reloc_entry_gpu(eb, vma,
+			       offsets[0] * sizeof(u32),
+			       0)) {
+		err = -EIO;
+		goto unpin_vma;
+	}
+
+	/* !8-Byte aligned */
+	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;
+	i -= eb->reloc_cache.rq_size;
+	memset32(eb->reloc_cache.rq_cmd + eb->reloc_cache.rq_size,
+		 MI_NOOP, i);
+	eb->reloc_cache.rq_size += i;
+
+	/* Force batch chaining */
+	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);
+	err = reloc_gpu_flush(&eb->reloc_cache);
+	if (err)
+		goto put_rq;
+	GEM_BUG_ON(eb->reloc_cache.rq);
+
+	err = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE, HZ / 2);
+	if (err) {
+		intel_gt_set_wedged(eb->engine->gt);
+		goto put_rq;
+	}
+
+	if (!i915_request_completed(rq)) {
+		pr_err("%s: did not wait for relocations!\n", eb->engine->name);
+		err = -EINVAL;
+		goto put_rq;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(offsets); i++) {
+		u64 reloc = read_reloc(map, offsets[i], mask);
+
+		if (reloc != i) {
+			pr_err("%s[%d]: map[%d] %llx != %x\n",
+			       eb->engine->name, i, offsets[i], reloc, i);
+			err = -EINVAL;
+		}
+	}
+	if (err)
+		igt_hexdump(map, 4096);
+
+put_rq:
+	i915_request_put(rq);
+unpin_vma:
+	i915_vma_unpin(vma);
+	return err;
+}
+
+static int igt_gpu_reloc(void *arg)
+{
+	struct i915_execbuffer eb;
+	struct drm_i915_gem_object *scratch;
+	int err = 0;
+	u32 *map;
+
+	eb.i915 = arg;
+
+	scratch = i915_gem_object_create_internal(eb.i915, 4096);
+	if (IS_ERR(scratch))
+		return PTR_ERR(scratch);
+
+	map = i915_gem_object_pin_map(scratch, I915_MAP_WC);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto err_scratch;
+	}
+
+	for_each_uabi_engine(eb.engine, eb.i915) {
+		reloc_cache_init(&eb.reloc_cache, eb.i915);
+		memset(map, POISON_INUSE, 4096);
+
+		intel_engine_pm_get(eb.engine);
+		eb.context = intel_context_create(eb.engine);
+		if (IS_ERR(eb.context)) {
+			err = PTR_ERR(eb.context);
+			goto err_pm;
+		}
+
+		err = intel_context_pin(eb.context);
+		if (err)
+			goto err_put;
+
+		err = __igt_gpu_reloc(&eb, scratch);
+
+		intel_context_unpin(eb.context);
+err_put:
+		intel_context_put(eb.context);
+err_pm:
+		intel_engine_pm_put(eb.engine);
+		if (err)
+			break;
+	}
+
+	if (igt_flush_test(eb.i915))
+		err = -EIO;
+
+err_scratch:
+	i915_gem_object_put(scratch);
+	return err;
+}
+
+int i915_gem_execbuffer_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_gpu_reloc),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return i915_live_subtests(tests, i915);
+}