提交 a2bc4695 编写于 作者: C Chris Wilson

drm/i915: Prepare object synchronisation for asynchronicity

We are about to specialize object synchronisation to enable nonblocking
execbuf submission. First we make a copy of the current object
synchronisation for execbuffer. The general i915_gem_object_sync() will
be removed following the removal of CS flips in the near future.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJohn Harrison <john.c.harrison@intel.com>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-16-chris@chris-wilson.co.uk
上级 0f25dff6
master alk-4.19.24 alk-4.19.30 alk-4.19.34 alk-4.19.36 alk-4.19.43 alk-4.19.48 alk-4.19.57 ck-4.19.67 ck-4.19.81 ck-4.19.91 github/fork/deepanshu1422/fix-typo-in-comment github/fork/haosdent/fix-typo linux-next v4.19.91 v4.19.90 v4.19.89 v4.19.88 v4.19.87 v4.19.86 v4.19.85 v4.19.84 v4.19.83 v4.19.82 v4.19.81 v4.19.80 v4.19.79 v4.19.78 v4.19.77 v4.19.76 v4.19.75 v4.19.74 v4.19.73 v4.19.72 v4.19.71 v4.19.70 v4.19.69 v4.19.68 v4.19.67 v4.19.66 v4.19.65 v4.19.64 v4.19.63 v4.19.62 v4.19.61 v4.19.60 v4.19.59 v4.19.58 v4.19.57 v4.19.56 v4.19.55 v4.19.54 v4.19.53 v4.19.52 v4.19.51 v4.19.50 v4.19.49 v4.19.48 v4.19.47 v4.19.46 v4.19.45 v4.19.44 v4.19.43 v4.19.42 v4.19.41 v4.19.40 v4.19.39 v4.19.38 v4.19.37 v4.19.36 v4.19.35 v4.19.34 v4.19.33 v4.19.32 v4.19.31 v4.19.30 v4.19.29 v4.19.28 v4.19.27 v4.19.26 v4.19.25 v4.19.24 v4.19.23 v4.19.22 v4.19.21 v4.19.20 v4.19.19 v4.19.18 v4.19.17 v4.19.16 v4.19.15 v4.19.14 v4.19.13 v4.19.12 v4.19.11 v4.19.10 v4.19.9 v4.19.8 v4.19.7 v4.19.6 v4.19.5 v4.19.4 v4.19.3 v4.19.2 v4.19.1 v4.19 v4.19-rc8 v4.19-rc7 v4.19-rc6 v4.19-rc5 v4.19-rc4 v4.19-rc3 v4.19-rc2 v4.19-rc1 ck-release-21 ck-release-20 ck-release-19.2 ck-release-19.1 ck-release-19 ck-release-18 ck-release-17.2 ck-release-17.1 ck-release-17 ck-release-16 ck-release-15.1 ck-release-15 ck-release-14 ck-release-13.2 ck-release-13 ck-release-12 ck-release-11 ck-release-10 ck-release-9 ck-release-7 alk-release-15 alk-release-14 alk-release-13.2 alk-release-13 alk-release-12 alk-release-11 alk-release-10 alk-release-9 alk-release-7
无相关合并请求
......@@ -3221,8 +3221,6 @@ i915_gem_obj_finish_shmem_access(struct drm_i915_gem_object *obj)
}
int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
int i915_gem_object_sync(struct drm_i915_gem_object *obj,
struct drm_i915_gem_request *to);
void i915_vma_move_to_active(struct i915_vma *vma,
struct drm_i915_gem_request *req,
unsigned int flags);
......
......@@ -2818,97 +2818,6 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
return ret;
}
static int
__i915_gem_object_sync(struct drm_i915_gem_request *to,
struct drm_i915_gem_request *from)
{
int ret;
if (to->engine == from->engine)
return 0;
if (!i915.semaphores) {
ret = i915_wait_request(from,
from->i915->mm.interruptible |
I915_WAIT_LOCKED,
NULL,
NO_WAITBOOST);
if (ret)
return ret;
} else {
int idx = intel_engine_sync_index(from->engine, to->engine);
if (from->fence.seqno <= from->engine->semaphore.sync_seqno[idx])
return 0;
trace_i915_gem_ring_sync_to(to, from);
ret = to->engine->semaphore.sync_to(to, from);
if (ret)
return ret;
from->engine->semaphore.sync_seqno[idx] = from->fence.seqno;
}
return 0;
}
/**
* i915_gem_object_sync - sync an object to a ring.
*
* @obj: object which may be in use on another ring.
* @to: request we are wishing to use
*
* This code is meant to abstract object synchronization with the GPU.
* Conceptually we serialise writes between engines inside the GPU.
* We only allow one engine to write into a buffer at any time, but
* multiple readers. To ensure each has a coherent view of memory, we must:
*
* - If there is an outstanding write request to the object, the new
* request must wait for it to complete (either CPU or in hw, requests
* on the same ring will be naturally ordered).
*
* - If we are a write request (pending_write_domain is set), the new
* request must wait for outstanding read requests to complete.
*
* Returns 0 if successful, else propagates up the lower layer error.
*/
int
i915_gem_object_sync(struct drm_i915_gem_object *obj,
struct drm_i915_gem_request *to)
{
struct i915_gem_active *active;
unsigned long active_mask;
int idx;
lockdep_assert_held(&obj->base.dev->struct_mutex);
active_mask = i915_gem_object_get_active(obj);
if (!active_mask)
return 0;
if (obj->base.pending_write_domain) {
active = obj->last_read;
} else {
active_mask = 1;
active = &obj->last_write;
}
for_each_active(active_mask, idx) {
struct drm_i915_gem_request *request;
int ret;
request = i915_gem_active_peek(&active[idx],
&obj->base.dev->struct_mutex);
if (!request)
continue;
ret = __i915_gem_object_sync(to, request);
if (ret)
return ret;
}
return 0;
}
static void __i915_vma_iounmap(struct i915_vma *vma)
{
GEM_BUG_ON(i915_vma_is_pinned(vma));
......
......@@ -1133,7 +1133,8 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
struct drm_i915_gem_object *obj = vma->obj;
if (obj->flags & other_rings) {
ret = i915_gem_object_sync(obj, req);
ret = i915_gem_request_await_object
(req, obj, obj->base.pending_write_domain);
if (ret)
return ret;
}
......
......@@ -460,6 +460,93 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
return ERR_PTR(ret);
}
static int
i915_gem_request_await_request(struct drm_i915_gem_request *to,
struct drm_i915_gem_request *from)
{
int idx, ret;
GEM_BUG_ON(to == from);
if (to->engine == from->engine)
return 0;
idx = intel_engine_sync_index(from->engine, to->engine);
if (from->fence.seqno <= from->engine->semaphore.sync_seqno[idx])
return 0;
trace_i915_gem_ring_sync_to(to, from);
if (!i915.semaphores) {
ret = i915_wait_request(from,
I915_WAIT_INTERRUPTIBLE |
I915_WAIT_LOCKED,
NULL, NO_WAITBOOST);
if (ret)
return ret;
} else {
ret = to->engine->semaphore.sync_to(to, from);
if (ret)
return ret;
}
from->engine->semaphore.sync_seqno[idx] = from->fence.seqno;
return 0;
}
/**
* i915_gem_request_await_object - set this request to (async) wait upon a bo
*
* @to: request we are wishing to use
* @obj: object which may be in use on another ring.
*
* This code is meant to abstract object synchronization with the GPU.
* Conceptually we serialise writes between engines inside the GPU.
* We only allow one engine to write into a buffer at any time, but
* multiple readers. To ensure each has a coherent view of memory, we must:
*
* - If there is an outstanding write request to the object, the new
* request must wait for it to complete (either CPU or in hw, requests
* on the same ring will be naturally ordered).
*
* - If we are a write request (pending_write_domain is set), the new
* request must wait for outstanding read requests to complete.
*
* Returns 0 if successful, else propagates up the lower layer error.
*/
int
i915_gem_request_await_object(struct drm_i915_gem_request *to,
struct drm_i915_gem_object *obj,
bool write)
{
struct i915_gem_active *active;
unsigned long active_mask;
int idx;
if (write) {
active_mask = i915_gem_object_get_active(obj);
active = obj->last_read;
} else {
active_mask = 1;
active = &obj->last_write;
}
for_each_active(active_mask, idx) {
struct drm_i915_gem_request *request;
int ret;
request = i915_gem_active_peek(&active[idx],
&obj->base.dev->struct_mutex);
if (!request)
continue;
ret = i915_gem_request_await_request(to, request);
if (ret)
return ret;
}
return 0;
}
static void i915_gem_mark_busy(const struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
......
......@@ -209,6 +209,11 @@ static inline void i915_gem_request_assign(struct drm_i915_gem_request **pdst,
*pdst = src;
}
int
i915_gem_request_await_object(struct drm_i915_gem_request *to,
struct drm_i915_gem_object *obj,
bool write);
void __i915_add_request(struct drm_i915_gem_request *req, bool flush_caches);
#define i915_add_request(req) \
__i915_add_request(req, true)
......
......@@ -12273,7 +12273,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
goto cleanup_unpin;
}
ret = i915_gem_object_sync(obj, request);
ret = i915_gem_request_await_object(request, obj, false);
if (ret)
goto cleanup_request;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部