Re: [Mesa-dev] [PATCH 08/15] winsys/radeon: implement and enable 32-bit VM allocations

2018-01-08 Thread Samuel Pitoiset 

Patches 5-8 are:

Reviewed-by: Samuel Pitoiset 

On 01/06/2018 12:12 PM, Marek Olšák wrote:

From: Marek Olšák 

---
  src/gallium/winsys/radeon/drm/radeon_drm_bo.c | 42 +++
  src/gallium/winsys/radeon/drm/radeon_drm_winsys.c | 28 ++-
  src/gallium/winsys/radeon/drm/radeon_drm_winsys.h |  2 ++
  3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/gallium/winsys/radeon/drm/radeon_drm_bo.c 
b/src/gallium/winsys/radeon/drm/radeon_drm_bo.c
index bbfe5cc..06842a4 100644
--- a/src/gallium/winsys/radeon/drm/radeon_drm_bo.c
+++ b/src/gallium/winsys/radeon/drm/radeon_drm_bo.c
@@ -242,32 +242,54 @@ static uint64_t radeon_bomgr_find_va(const struct 
radeon_info *info,
  if ((hole->size - waste) == size) {
  hole->size = waste;
  mtx_unlock(>mutex);
  return offset;
  }
  }
  
  offset = heap->start;

  waste = offset % alignment;
  waste = waste ? alignment - waste : 0;
+
+if (offset + waste + size > heap->end) {
+mtx_unlock(>mutex);
+return 0;
+}
+
  if (waste) {
  n = CALLOC_STRUCT(radeon_bo_va_hole);
  n->size = waste;
  n->offset = offset;
  list_add(>list, >holes);
  }
  offset += waste;
  heap->start += size + waste;
  mtx_unlock(>mutex);
  return offset;
  }
  
+static uint64_t radeon_bomgr_find_va64(struct radeon_drm_winsys *ws,

+   uint64_t size, uint64_t alignment)
+{
+uint64_t va = 0;
+
+/* Try to allocate from the 64-bit address space first.
+ * If it doesn't exist (start = 0) or if it doesn't have enough space,
+ * fall back to the 32-bit address space.
+ */
+if (ws->vm64.start)
+va = radeon_bomgr_find_va(>info, >vm64, size, alignment);
+if (!va)
+va = radeon_bomgr_find_va(>info, >vm32, size, alignment);
+return va;
+}
+
  static void radeon_bomgr_free_va(const struct radeon_info *info,
   struct radeon_vm_heap *heap,
   uint64_t va, uint64_t size)
  {
  struct radeon_bo_va_hole *hole = NULL;
  
  size = align(size, info->gart_page_size);
  
  mtx_lock(>mutex);

  if ((va + size) == heap->start) {
@@ -363,21 +385,23 @@ void radeon_bo_destroy(struct pb_buffer *_buf)
  
  if (drmCommandWriteRead(rws->fd, DRM_RADEON_GEM_VA, ,

sizeof(va)) != 0 &&
va.operation == RADEON_VA_RESULT_ERROR) {
  fprintf(stderr, "radeon: Failed to deallocate virtual address for 
buffer:\n");
  fprintf(stderr, "radeon:size  : %"PRIu64" bytes\n", 
bo->base.size);
  fprintf(stderr, "radeon:va: 0x%"PRIx64"\n", 
bo->va);
  }
}
  
-	radeon_bomgr_free_va(>info, >vm64, bo->va, bo->base.size);

+   radeon_bomgr_free_va(>info,
+ bo->va < rws->vm32.end ? >vm32 : >vm64,
+ bo->va, bo->base.size);
  }
  
  /* Close object. */

  args.handle = bo->handle;
  drmIoctl(rws->fd, DRM_IOCTL_GEM_CLOSE, );
  
  mtx_destroy(>u.real.map_mutex);
  
  if (bo->initial_domain & RADEON_DOMAIN_VRAM)

  rws->allocated_vram -= align(bo->base.size, rws->info.gart_page_size);
@@ -653,22 +677,28 @@ static struct radeon_bo *radeon_create_bo(struct 
radeon_drm_winsys *rws,
  if (heap >= 0) {
  pb_cache_init_entry(>bo_cache, >u.real.cache_entry, 
>base,
  heap);
  }
  
  if (rws->info.has_virtual_memory) {

  struct drm_radeon_gem_va va;
  unsigned va_gap_size;
  
  va_gap_size = rws->check_vm ? MAX2(4 * alignment, 64 * 1024) : 0;

-bo->va = radeon_bomgr_find_va(>info, >vm64,
-  size + va_gap_size, alignment);
+
+if (flags & RADEON_FLAG_32BIT) {
+bo->va = radeon_bomgr_find_va(>info, >vm32,
+  size + va_gap_size, alignment);
+assert(bo->va + size < rws->vm32.end);
+} else {
+bo->va = radeon_bomgr_find_va64(rws, size + va_gap_size, 
alignment);
+}
  
  va.handle = bo->handle;

  va.vm_id = 0;
  va.operation = RADEON_VA_MAP;
  va.flags = RADEON_VM_PAGE_READABLE |
 RADEON_VM_PAGE_WRITEABLE |
 RADEON_VM_PAGE_SNOOPED;
  va.offset = bo->va;
  r = drmCommandWriteRead(rws->fd, DRM_RADEON_GEM_VA, , sizeof(va));
  if (r && va.operation == RADEON_VA_RESULT_ERROR) {
@@ -1055,22 +1085,21 @@ static struct pb_buffer 
*radeon_winsys_bo_from_ptr(struct radeon_winsys *rws,
  bo->hash = __sync_fetch_and_add(>next_bo_hash, 1);
  (void) mtx_init(>u.real.map_mutex, mtx_plain);
  
  util_hash_table_set(ws->bo_handles,

[Mesa-dev] [PATCH 08/15] winsys/radeon: implement and enable 32-bit VM allocations

2018-01-06 Thread Marek Olšák 
From: Marek Olšák 

---
 src/gallium/winsys/radeon/drm/radeon_drm_bo.c | 42 +++
 src/gallium/winsys/radeon/drm/radeon_drm_winsys.c | 28 ++-
 src/gallium/winsys/radeon/drm/radeon_drm_winsys.h |  2 ++
 3 files changed, 64 insertions(+), 8 deletions(-)

diff --git a/src/gallium/winsys/radeon/drm/radeon_drm_bo.c 
b/src/gallium/winsys/radeon/drm/radeon_drm_bo.c
index bbfe5cc..06842a4 100644
--- a/src/gallium/winsys/radeon/drm/radeon_drm_bo.c
+++ b/src/gallium/winsys/radeon/drm/radeon_drm_bo.c
@@ -242,32 +242,54 @@ static uint64_t radeon_bomgr_find_va(const struct 
radeon_info *info,
 if ((hole->size - waste) == size) {
 hole->size = waste;
 mtx_unlock(>mutex);
 return offset;
 }
 }
 
 offset = heap->start;
 waste = offset % alignment;
 waste = waste ? alignment - waste : 0;
+
+if (offset + waste + size > heap->end) {
+mtx_unlock(>mutex);
+return 0;
+}
+
 if (waste) {
 n = CALLOC_STRUCT(radeon_bo_va_hole);
 n->size = waste;
 n->offset = offset;
 list_add(>list, >holes);
 }
 offset += waste;
 heap->start += size + waste;
 mtx_unlock(>mutex);
 return offset;
 }
 
+static uint64_t radeon_bomgr_find_va64(struct radeon_drm_winsys *ws,
+   uint64_t size, uint64_t alignment)
+{
+uint64_t va = 0;
+
+/* Try to allocate from the 64-bit address space first.
+ * If it doesn't exist (start = 0) or if it doesn't have enough space,
+ * fall back to the 32-bit address space.
+ */
+if (ws->vm64.start)
+va = radeon_bomgr_find_va(>info, >vm64, size, alignment);
+if (!va)
+va = radeon_bomgr_find_va(>info, >vm32, size, alignment);
+return va;
+}
+
 static void radeon_bomgr_free_va(const struct radeon_info *info,
  struct radeon_vm_heap *heap,
  uint64_t va, uint64_t size)
 {
 struct radeon_bo_va_hole *hole = NULL;
 
 size = align(size, info->gart_page_size);
 
 mtx_lock(>mutex);
 if ((va + size) == heap->start) {
@@ -363,21 +385,23 @@ void radeon_bo_destroy(struct pb_buffer *_buf)
 
 if (drmCommandWriteRead(rws->fd, DRM_RADEON_GEM_VA, ,
sizeof(va)) != 0 &&
va.operation == RADEON_VA_RESULT_ERROR) {
 fprintf(stderr, "radeon: Failed to deallocate virtual address 
for buffer:\n");
 fprintf(stderr, "radeon:size  : %"PRIu64" bytes\n", 
bo->base.size);
 fprintf(stderr, "radeon:va: 0x%"PRIx64"\n", 
bo->va);
 }
}
 
-   radeon_bomgr_free_va(>info, >vm64, bo->va, bo->base.size);
+   radeon_bomgr_free_va(>info,
+ bo->va < rws->vm32.end ? >vm32 : >vm64,
+ bo->va, bo->base.size);
 }
 
 /* Close object. */
 args.handle = bo->handle;
 drmIoctl(rws->fd, DRM_IOCTL_GEM_CLOSE, );
 
 mtx_destroy(>u.real.map_mutex);
 
 if (bo->initial_domain & RADEON_DOMAIN_VRAM)
 rws->allocated_vram -= align(bo->base.size, rws->info.gart_page_size);
@@ -653,22 +677,28 @@ static struct radeon_bo *radeon_create_bo(struct 
radeon_drm_winsys *rws,
 if (heap >= 0) {
 pb_cache_init_entry(>bo_cache, >u.real.cache_entry, >base,
 heap);
 }
 
 if (rws->info.has_virtual_memory) {
 struct drm_radeon_gem_va va;
 unsigned va_gap_size;
 
 va_gap_size = rws->check_vm ? MAX2(4 * alignment, 64 * 1024) : 0;
-bo->va = radeon_bomgr_find_va(>info, >vm64,
-  size + va_gap_size, alignment);
+
+if (flags & RADEON_FLAG_32BIT) {
+bo->va = radeon_bomgr_find_va(>info, >vm32,
+  size + va_gap_size, alignment);
+assert(bo->va + size < rws->vm32.end);
+} else {
+bo->va = radeon_bomgr_find_va64(rws, size + va_gap_size, 
alignment);
+}
 
 va.handle = bo->handle;
 va.vm_id = 0;
 va.operation = RADEON_VA_MAP;
 va.flags = RADEON_VM_PAGE_READABLE |
RADEON_VM_PAGE_WRITEABLE |
RADEON_VM_PAGE_SNOOPED;
 va.offset = bo->va;
 r = drmCommandWriteRead(rws->fd, DRM_RADEON_GEM_VA, , sizeof(va));
 if (r && va.operation == RADEON_VA_RESULT_ERROR) {
@@ -1055,22 +1085,21 @@ static struct pb_buffer 
*radeon_winsys_bo_from_ptr(struct radeon_winsys *rws,
 bo->hash = __sync_fetch_and_add(>next_bo_hash, 1);
 (void) mtx_init(>u.real.map_mutex, mtx_plain);
 
 util_hash_table_set(ws->bo_handles, (void*)(uintptr_t)bo->handle, bo);
 
 mtx_unlock(>bo_handles_mutex);
 
 if (ws->info.has_virtual_memory) {
 struct drm_radeon_gem_va va;
 
-bo->va = radeon_bomgr_find_va(>info, >vm64,
-