From: John Harrison <john.c.harri...@intel.com>
There is a construct in the linux kernel called 'struct fence' that is intended
to keep track of work that is executed on hardware. I.e. it solves the basic
problem that the drivers 'struct drm_i915_gem_request' is trying to address. The
request structure does quite a lot more than simply track the execution progress
so is very definitely still required. However, the basic completion status side
could be updated to use the ready made fence implementation and gain all the
advantages that provides.
This patch makes the first step of integrating a struct fence into the request.
It replaces the explicit reference count with that of the fence. It also
replaces the 'is completed' test with the fence's equivalent. Currently, that
simply chains on to the original request implementation. A future patch will
improve this.
For: VIZ-5190
Signed-off-by: John Harrison <john.c.harri...@intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 45 +++++++++++++-------------
drivers/gpu/drm/i915/i915_gem.c | 56 ++++++++++++++++++++++++++++++---
drivers/gpu/drm/i915/intel_lrc.c | 1 +
drivers/gpu/drm/i915/intel_ringbuffer.c | 1 +
drivers/gpu/drm/i915/intel_ringbuffer.h | 3 ++
5 files changed, 78 insertions(+), 28 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index afcca15..fe2c1af 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -50,6 +50,7 @@
#include <linux/intel-iommu.h>
#include <linux/kref.h>
#include <linux/pm_qos.h>
+#include <linux/fence.h>
/* General customization:
*/
@@ -2134,7 +2135,17 @@ void i915_gem_track_fb(struct drm_i915_gem_object *old,
* initial reference taken using kref_init
*/
struct drm_i915_gem_request {
- struct kref ref;
+ /*
+ * Underlying object for implementing the signal/wait stuff.
+ * NB: Never call fence_later() or return this fence object to user
+ * land! Due to lazy allocation, scheduler re-ordering, pre-emption,
+ * etc., there is no guarantee at all about the validity or
+ * sequentiality of the fence's seqno! It is also unsafe to let
+ * anything outside of the i915 driver get hold of the fence object
+ * as the clean up when decrementing the reference count requires
+ * holding the driver mutex lock.
+ */
+ struct fence fence;
/** On Which ring this request was generated */
struct drm_i915_private *i915;
@@ -2211,7 +2222,13 @@ int i915_gem_request_alloc(struct intel_engine_cs *ring,
struct intel_context *ctx,
struct drm_i915_gem_request **req_out);
void i915_gem_request_cancel(struct drm_i915_gem_request *req);
-void i915_gem_request_free(struct kref *req_ref);
+
+static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req,
+ bool lazy_coherency)
+{
+ return fence_is_signaled(&req->fence);
+}
+
int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
struct drm_file *file);
@@ -2231,7 +2248,7 @@ static inline struct drm_i915_gem_request *
i915_gem_request_reference(struct drm_i915_gem_request *req)
{
if (req)
- kref_get(&req->ref);
+ fence_get(&req->fence);
return req;
}
@@ -2239,7 +2256,7 @@ static inline void
i915_gem_request_unreference(struct drm_i915_gem_request *req)
{
WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
- kref_put(&req->ref, i915_gem_request_free);
+ fence_put(&req->fence);
}
static inline void
@@ -2251,7 +2268,7 @@ i915_gem_request_unreference__unlocked(struct
drm_i915_gem_request *req)
return;
dev = req->ring->dev;
- if (kref_put_mutex(&req->ref, i915_gem_request_free,
&dev->struct_mutex))
+ if (kref_put_mutex(&req->fence.refcount, fence_release,
&dev->struct_mutex))
mutex_unlock(&dev->struct_mutex);
}
@@ -2268,12 +2285,6 @@ static inline void i915_gem_request_assign(struct
drm_i915_gem_request **pdst,
}
/*
- * XXX: i915_gem_request_completed should be here but currently needs the
- * definition of i915_seqno_passed() which is below. It will be moved in
- * a later patch when the call to i915_seqno_passed() is obsoleted...
- */
-
-/*
* A command that requires special handling by the command parser.
*/
struct drm_i915_cmd_descriptor {
@@ -2830,18 +2841,6 @@ i915_seqno_passed(uint32_t seq1, uint32_t seq2)
return (int32_t)(seq1 - seq2) >= 0;
}
-static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req,
- bool lazy_coherency)
-{
- u32 seqno;
-
- BUG_ON(req == NULL);
-
- seqno = req->ring->get_seqno(req->ring, lazy_coherency);
-
- return i915_seqno_passed(seqno, req->seqno);
-}
-
int __must_check i915_gem_get_seqno(struct drm_device *dev, u32 *seqno);
int __must_check i915_gem_set_seqno(struct drm_device *dev, u32 seqno);
int __must_check i915_gem_object_get_fence(struct drm_i915_gem_object *obj);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 45f0460..5fc44bf 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2610,10 +2610,10 @@ static void i915_set_reset_status(struct
drm_i915_private *dev_priv,
}
}
-void i915_gem_request_free(struct kref *req_ref)
+static void i915_gem_request_free(struct fence *req_fence)
{
- struct drm_i915_gem_request *req = container_of(req_ref,
- typeof(*req), ref);
+ struct drm_i915_gem_request *req = container_of(req_fence,
+ typeof(*req), fence);
struct intel_context *ctx = req->ctx;
if (req->file_priv)
@@ -2633,6 +2633,47 @@ void i915_gem_request_free(struct kref *req_ref)
kmem_cache_free(req->i915->requests, req);
}
+static const char *i915_gem_request_get_driver_name(struct fence *req_fence)
+{
+ return "i915_request";
+}
+
+static const char *i915_gem_request_get_timeline_name(struct fence *req_fence)
+{
+ struct drm_i915_gem_request *req = container_of(req_fence,
+ typeof(*req), fence);
+ return req->ring->name;
+}
+
+static bool i915_gem_request_enable_signaling(struct fence *req_fence)
+{
+ /* Interrupt driven fences are not implemented yet.*/
+ WARN(true, "This should not be called!");
+ return true;
+}
+
+static bool i915_gem_request_is_completed(struct fence *req_fence)
+{
+ struct drm_i915_gem_request *req = container_of(req_fence,
+ typeof(*req), fence);
+ u32 seqno;
+
+ BUG_ON(req == NULL);
+
+ seqno = req->ring->get_seqno(req->ring, false/*lazy_coherency*/);
+
+ return i915_seqno_passed(seqno, req->seqno);
+}
+
+static const struct fence_ops i915_gem_request_fops = {
+ .get_driver_name = i915_gem_request_get_driver_name,
+ .get_timeline_name = i915_gem_request_get_timeline_name,
+ .enable_signaling = i915_gem_request_enable_signaling,
+ .signaled = i915_gem_request_is_completed,
+ .wait = fence_default_wait,
+ .release = i915_gem_request_free,
+};
+
int i915_gem_request_alloc(struct intel_engine_cs *ring,
struct intel_context *ctx,
struct drm_i915_gem_request **req_out)
@@ -2654,7 +2695,6 @@ int i915_gem_request_alloc(struct intel_engine_cs *ring,
if (ret)
goto err;
- kref_init(&req->ref);
req->i915 = dev_priv;
req->ring = ring;
req->ctx = ctx;
@@ -2669,6 +2709,8 @@ int i915_gem_request_alloc(struct intel_engine_cs *ring,
goto err;
}
+ fence_init(&req->fence, &i915_gem_request_fops, &ring->fence_lock,
ring->fence_context, req->seqno);
+
/*
* Reserve space in the ring buffer for all the commands required to
* eventually emit this request. This is to guarantee that the
@@ -5031,7 +5073,7 @@ i915_gem_init_hw(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *ring;
- int ret, i, j;
+ int ret, i, j, fence_base;
if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
return -EIO;
@@ -5083,12 +5125,16 @@ i915_gem_init_hw(struct drm_device *dev)
goto out;
}
+ fence_base = fence_context_alloc(I915_NUM_RINGS);
+
/* Now it is safe to go back round and do everything else: */
for_each_ring(ring, dev_priv, i) {
struct drm_i915_gem_request *req;
WARN_ON(!ring->default_context);
+ ring->fence_context = fence_base + i;
+
ret = i915_gem_request_alloc(ring, ring->default_context, &req);
if (ret) {
i915_gem_cleanup_ringbuffer(dev);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index e998a54..3dc7e38 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1651,6 +1651,7 @@ static int logical_ring_init(struct drm_device *dev,
struct intel_engine_cs *rin
ring->dev = dev;
INIT_LIST_HEAD(&ring->active_list);
INIT_LIST_HEAD(&ring->request_list);
+ spin_lock_init(&ring->fence_lock);
i915_gem_batch_pool_init(dev, &ring->batch_pool);
init_waitqueue_head(&ring->irq_queue);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c
b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 7c5b4c2..cb63e2f 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2030,6 +2030,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
INIT_LIST_HEAD(&ring->active_list);
INIT_LIST_HEAD(&ring->request_list);
INIT_LIST_HEAD(&ring->execlist_queue);
+ spin_lock_init(&ring->fence_lock);
i915_gem_batch_pool_init(dev, &ring->batch_pool);
ringbuf->size = 32 * PAGE_SIZE;
ringbuf->ring = ring;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h
b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 304cac4..8ad25b0 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -338,6 +338,9 @@ struct intel_engine_cs {
* to encode the command length in the header).
*/
u32 (*get_cmd_length_mask)(u32 cmd_header);
+
+ unsigned fence_context;
+ spinlock_t fence_lock;
};
bool intel_ring_initialized(struct intel_engine_cs *ring);
--
1.9.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
