leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

drm/i915: Move obj->active:5 to obj->flags

Browse Source 
We are motivated to avoid using a bitfield for obj->active for a couple
of reasons. Firstly, we wish to document our lockless read of obj->active
using READ_ONCE inside i915_gem_busy_ioctl() and that requires an
integral type (i.e. not a bitfield). Secondly, gcc produces abysmal code
when presented with a bitfield and that shows up high on the profiles of
request tracking (mainly due to excess memory traffic as it converts
the bitfield to a register and back and generates frequent AGI in the
process).

v2: BIT, break up a long line in compute the other engines, new paint
for i915_gem_object_is_active (now i915_gem_object_get_active).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-23-git-send-email-chris@chris-wilson.co.uk
This commit is contained in:
Chris Wilson
2016-08-04 16:32:39 +01:00
parent 5748b6a1f4
commit 573adb3962
6 changed files with 64 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
drivers/gpu/drm/i915/i915_gem_execbuffer.c
View File

@@ -434,7 +434,7 @@ relocate_entry_clflush(struct drm_i915_gem_object *obj,
static bool object_is_idle(struct drm_i915_gem_object *obj)
{
unsigned long active = obj->active;
unsigned long active = i915_gem_object_get_active(obj);
int idx;
for_each_active(active, idx) {
@@ -990,11 +990,21 @@ err:
return ret;
}
static unsigned int eb_other_engines(struct drm_i915_gem_request *req)
{
unsigned int mask;
mask = ~intel_engine_flag(req->engine) & I915_BO_ACTIVE_MASK;
mask <<= I915_BO_ACTIVE_SHIFT;
return mask;
}
static int
i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
struct list_head *vmas)
{
const unsigned other_rings = ~intel_engine_flag(req->engine);
const unsigned int other_rings = eb_other_engines(req);
struct i915_vma *vma;
uint32_t flush_domains = 0;
bool flush_chipset = false;
@@ -1003,7 +1013,7 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
list_for_each_entry(vma, vmas, exec_list) {
struct drm_i915_gem_object *obj = vma->obj;
if (obj->active & other_rings) {
if (obj->flags & other_rings) {
ret = i915_gem_object_sync(obj, req);
if (ret)
return ret;
@@ -1166,9 +1176,9 @@ void i915_vma_move_to_active(struct i915_vma *vma,
* add the active reference first and queue for it to be dropped
* *last*.
*/
if (obj->active == 0)
if (!i915_gem_object_is_active(obj))
i915_gem_object_get(obj);
obj->active |= 1 << idx;
i915_gem_object_set_active(obj, idx);
i915_gem_active_set(&obj->last_read[idx], req);
if (flags & EXEC_OBJECT_WRITE) {