diff options
| author | Chris Wilson <chris@chris-wilson.co.uk> | 2016-08-04 18:32:39 +0300 |
|---|---|---|
| committer | Chris Wilson <chris@chris-wilson.co.uk> | 2016-08-04 22:20:04 +0300 |
| commit | 573adb396241e2aa46401529abdba93bc1886a48 (patch) | |
| tree | 329d217776c51c5a7a71e7532994098977cdd072 /drivers/gpu/drm/i915/i915_gem_execbuffer.c | |
| parent | 5748b6a1f48eae5b8513dd88ab6da4c176686665 (diff) | |
| download | linux-573adb396241e2aa46401529abdba93bc1886a48.tar.xz | |
drm/i915: Move obj->active:5 to obj->flags
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
Diffstat (limited to 'drivers/gpu/drm/i915/i915_gem_execbuffer.c')
| -rw-r--r-- | drivers/gpu/drm/i915/i915_gem_execbuffer.c | 20 |
1 files changed, 15 insertions, 5 deletions
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index e8e194fa2e65..a1da3028a949 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -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) { |