[Intel-gfx] [PATCH] drm/i915: Support 64b relocations

[Ben Widawsky]

All the rest of the code to enable this is in my branch. Without my
branch, hitting > 32b offsets is impossible. The code has always
"supported" 64b, but it's never actually been run of tested. This change
doesn't actually fix anything. [1] I am not sure why X won't work yet. I
do not get hangs or obvious errors.

There are 3 fixes grouped together here. First is to remove the
hardcoded 0 for the upper dword of the relocation. The next fix is to
use a 64b value for target_offset. The final fix is to not directly
apply target_offset to reloc->delta. reloc->delta is part of ABI, and so
we cannot change it. As it stands, 32b is enough to represent everything
we're interested in representing anyway. The main problem is, we cannot
add greater than 32b values to it directly.

[1] Almost all of intel-gpu-tools is not yet ready to test 64b
relocations. There are a few places that expect 32b values for offsets
and these all won't work.

Cc: Rafael Barbalho <rafael.barbalho at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 0d806fc..6ffecd2 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -262,10 +262,12 @@ static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
 
 static int
 relocate_entry_cpu(struct drm_i915_gem_object *obj,
-		   struct drm_i915_gem_relocation_entry *reloc)
+		   struct drm_i915_gem_relocation_entry *reloc,
+		   uint64_t target_offset)
 {
 	struct drm_device *dev = obj->base.dev;
 	uint32_t page_offset = offset_in_page(reloc->offset);
+	uint64_t delta = reloc->delta + target_offset;
 	char *vaddr;
 	int ret;
 
@@ -275,7 +277,7 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
 
 	vaddr = kmap_atomic(i915_gem_object_get_page(obj,
 				reloc->offset >> PAGE_SHIFT));
-	*(uint32_t *)(vaddr + page_offset) = reloc->delta;
+	*(uint32_t *)(vaddr + page_offset) = lower_32_bits(delta);
 
 	if (INTEL_INFO(dev)->gen >= 8) {
 		page_offset = offset_in_page(page_offset + sizeof(uint32_t));
@@ -286,7 +288,7 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
 			    (reloc->offset + sizeof(uint32_t)) >> PAGE_SHIFT));
 		}
 
-		*(uint32_t *)(vaddr + page_offset) = 0;
+		*(uint32_t *)(vaddr + page_offset) = upper_32_bits(delta);
 	}
 
 	kunmap_atomic(vaddr);
@@ -296,10 +298,12 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
 
 static int
 relocate_entry_gtt(struct drm_i915_gem_object *obj,
-		   struct drm_i915_gem_relocation_entry *reloc)
+		   struct drm_i915_gem_relocation_entry *reloc,
+		   uint64_t target_offset)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint64_t delta = reloc->delta + target_offset;
 	uint32_t __iomem *reloc_entry;
 	void __iomem *reloc_page;
 	int ret;
@@ -318,7 +322,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 			reloc->offset & PAGE_MASK);
 	reloc_entry = (uint32_t __iomem *)
 		(reloc_page + offset_in_page(reloc->offset));
-	iowrite32(reloc->delta, reloc_entry);
+	iowrite32(lower_32_bits(delta), reloc_entry);
 
 	if (INTEL_INFO(dev)->gen >= 8) {
 		reloc_entry += 1;
@@ -331,7 +335,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 			reloc_entry = reloc_page;
 		}
 
-		iowrite32(0, reloc_entry);
+		iowrite32(upper_32_bits(delta), reloc_entry);
 	}
 
 	io_mapping_unmap_atomic(reloc_page);
@@ -348,7 +352,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	struct drm_gem_object *target_obj;
 	struct drm_i915_gem_object *target_i915_obj;
 	struct i915_vma *target_vma;
-	uint32_t target_offset;
+	uint64_t target_offset;
 	int ret;
 
 	/* we've already hold a reference to all valid objects */
@@ -427,11 +431,10 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	if (obj->active && in_atomic())
 		return -EFAULT;
 
-	reloc->delta += target_offset;
 	if (use_cpu_reloc(obj))
-		ret = relocate_entry_cpu(obj, reloc);
+		ret = relocate_entry_cpu(obj, reloc, target_offset);
 	else
-		ret = relocate_entry_gtt(obj, reloc);
+		ret = relocate_entry_gtt(obj, reloc, target_offset);
 
 	if (ret)
 		return ret;
-- 
1.9.2