* [PATCH 01/53] drm/i915: Rename 'flags' to 'dispatch_flags' for better code reading
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 13:21 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 02/53] drm/i915: Add missing trace point to LRC execbuff code path John.C.Harrison
` (53 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
There is a flags word that is passed through the execbuffer code path all the
way from initial decoding of the user parameters down to the very final dispatch
buffer call. It is simply called 'flags'. Unfortuantely, there are many other
flags words floating around in the same blocks of code. Even more once the GPU
scheduler arrives.
This patch makes it more obvious exactly which flags word is which by renaming
'flags' to 'dispatch_flags'. Note that the bit definitions for this flags word
already have an 'I915_DISPATCH_' prefix on them and so are not quite so
ambiguous.
For: VIZ-1587
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 25 ++++++++++----------
drivers/gpu/drm/i915/intel_lrc.c | 10 ++++----
drivers/gpu/drm/i915/intel_lrc.h | 2 +-
drivers/gpu/drm/i915/intel_ringbuffer.c | 35 ++++++++++++++++------------
drivers/gpu/drm/i915/intel_ringbuffer.h | 4 ++--
5 files changed, 41 insertions(+), 35 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index b773368..ec9ea45 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1138,7 +1138,7 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
struct drm_i915_gem_execbuffer2 *args,
struct list_head *vmas,
struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 flags)
+ u64 exec_start, u32 dispatch_flags)
{
struct drm_clip_rect *cliprects = NULL;
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1266,19 +1266,19 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
ret = ring->dispatch_execbuffer(ring,
exec_start, exec_len,
- flags);
+ dispatch_flags);
if (ret)
goto error;
}
} else {
ret = ring->dispatch_execbuffer(ring,
exec_start, exec_len,
- flags);
+ dispatch_flags);
if (ret)
return ret;
}
- trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), flags);
+ trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
i915_gem_execbuffer_move_to_active(vmas, ring);
i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
@@ -1353,7 +1353,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
struct i915_address_space *vm;
const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
u64 exec_start = args->batch_start_offset;
- u32 flags;
+ u32 dispatch_flags;
int ret;
bool need_relocs;
@@ -1364,15 +1364,15 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
if (ret)
return ret;
- flags = 0;
+ dispatch_flags = 0;
if (args->flags & I915_EXEC_SECURE) {
if (!file->is_master || !capable(CAP_SYS_ADMIN))
return -EPERM;
- flags |= I915_DISPATCH_SECURE;
+ dispatch_flags |= I915_DISPATCH_SECURE;
}
if (args->flags & I915_EXEC_IS_PINNED)
- flags |= I915_DISPATCH_PINNED;
+ dispatch_flags |= I915_DISPATCH_PINNED;
if ((args->flags & I915_EXEC_RING_MASK) > LAST_USER_RING) {
DRM_DEBUG("execbuf with unknown ring: %d\n",
@@ -1495,7 +1495,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
args->batch_start_offset,
args->batch_len,
file->is_master,
- &flags);
+ &dispatch_flags);
if (IS_ERR(batch_obj)) {
ret = PTR_ERR(batch_obj);
goto err;
@@ -1507,7 +1507,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
/* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
* batch" bit. Hence we need to pin secure batches into the global gtt.
* hsw should have this fixed, but bdw mucks it up again. */
- if (flags & I915_DISPATCH_SECURE) {
+ if (dispatch_flags & I915_DISPATCH_SECURE) {
/*
* So on first glance it looks freaky that we pin the batch here
* outside of the reservation loop. But:
@@ -1527,7 +1527,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
exec_start += i915_gem_obj_offset(batch_obj, vm);
ret = dev_priv->gt.do_execbuf(dev, file, ring, ctx, args,
- &eb->vmas, batch_obj, exec_start, flags);
+ &eb->vmas, batch_obj, exec_start,
+ dispatch_flags);
/*
* FIXME: We crucially rely upon the active tracking for the (ppgtt)
@@ -1535,7 +1536,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
* needs to be adjusted to also track the ggtt batch vma properly as
* active.
*/
- if (flags & I915_DISPATCH_SECURE)
+ if (dispatch_flags & I915_DISPATCH_SECURE)
i915_gem_object_ggtt_unpin(batch_obj);
err:
/* the request owns the ref now */
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index aafcef3..f30a8e3 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -620,7 +620,7 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
* @vmas: list of vmas.
* @batch_obj: the batchbuffer to submit.
* @exec_start: batchbuffer start virtual address pointer.
- * @flags: translated execbuffer call flags.
+ * @dispatch_flags: translated execbuffer call flags.
*
* This is the evil twin version of i915_gem_ringbuffer_submission. It abstracts
* away the submission details of the execbuffer ioctl call.
@@ -633,7 +633,7 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
struct drm_i915_gem_execbuffer2 *args,
struct list_head *vmas,
struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 flags)
+ u64 exec_start, u32 dispatch_flags)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
@@ -706,7 +706,7 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
dev_priv->relative_constants_mode = instp_mode;
}
- ret = ring->emit_bb_start(ringbuf, ctx, exec_start, flags);
+ ret = ring->emit_bb_start(ringbuf, ctx, exec_start, dispatch_flags);
if (ret)
return ret;
@@ -1163,9 +1163,9 @@ static int gen9_init_render_ring(struct intel_engine_cs *ring)
static int gen8_emit_bb_start(struct intel_ringbuffer *ringbuf,
struct intel_context *ctx,
- u64 offset, unsigned flags)
+ u64 offset, unsigned dispatch_flags)
{
- bool ppgtt = !(flags & I915_DISPATCH_SECURE);
+ bool ppgtt = !(dispatch_flags & I915_DISPATCH_SECURE);
int ret;
ret = intel_logical_ring_begin(ringbuf, ctx, 4);
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index f635735..b66fc4d 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -82,7 +82,7 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
struct drm_i915_gem_execbuffer2 *args,
struct list_head *vmas,
struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 flags);
+ u64 exec_start, u32 dispatch_flags);
u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj);
void intel_lrc_irq_handler(struct intel_engine_cs *ring);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index d17e76d..ca7de3d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1690,7 +1690,7 @@ gen8_ring_put_irq(struct intel_engine_cs *ring)
static int
i965_dispatch_execbuffer(struct intel_engine_cs *ring,
u64 offset, u32 length,
- unsigned flags)
+ unsigned dispatch_flags)
{
int ret;
@@ -1701,7 +1701,8 @@ i965_dispatch_execbuffer(struct intel_engine_cs *ring,
intel_ring_emit(ring,
MI_BATCH_BUFFER_START |
MI_BATCH_GTT |
- (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE_I965));
+ (dispatch_flags & I915_DISPATCH_SECURE ?
+ 0 : MI_BATCH_NON_SECURE_I965));
intel_ring_emit(ring, offset);
intel_ring_advance(ring);
@@ -1714,8 +1715,8 @@ i965_dispatch_execbuffer(struct intel_engine_cs *ring,
#define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT)
static int
i830_dispatch_execbuffer(struct intel_engine_cs *ring,
- u64 offset, u32 len,
- unsigned flags)
+ u64 offset, u32 len,
+ unsigned dispatch_flags)
{
u32 cs_offset = ring->scratch.gtt_offset;
int ret;
@@ -1733,7 +1734,7 @@ i830_dispatch_execbuffer(struct intel_engine_cs *ring,
intel_ring_emit(ring, MI_NOOP);
intel_ring_advance(ring);
- if ((flags & I915_DISPATCH_PINNED) == 0) {
+ if ((dispatch_flags & I915_DISPATCH_PINNED) == 0) {
if (len > I830_BATCH_LIMIT)
return -ENOSPC;
@@ -1765,7 +1766,8 @@ i830_dispatch_execbuffer(struct intel_engine_cs *ring,
return ret;
intel_ring_emit(ring, MI_BATCH_BUFFER);
- intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
+ intel_ring_emit(ring, offset | (dispatch_flags & I915_DISPATCH_SECURE ?
+ 0 : MI_BATCH_NON_SECURE));
intel_ring_emit(ring, offset + len - 8);
intel_ring_emit(ring, MI_NOOP);
intel_ring_advance(ring);
@@ -1776,7 +1778,7 @@ i830_dispatch_execbuffer(struct intel_engine_cs *ring,
static int
i915_dispatch_execbuffer(struct intel_engine_cs *ring,
u64 offset, u32 len,
- unsigned flags)
+ unsigned dispatch_flags)
{
int ret;
@@ -1785,7 +1787,8 @@ i915_dispatch_execbuffer(struct intel_engine_cs *ring,
return ret;
intel_ring_emit(ring, MI_BATCH_BUFFER_START | MI_BATCH_GTT);
- intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
+ intel_ring_emit(ring, offset | (dispatch_flags & I915_DISPATCH_SECURE ?
+ 0 : MI_BATCH_NON_SECURE));
intel_ring_advance(ring);
return 0;
@@ -2352,9 +2355,10 @@ static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
static int
gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
u64 offset, u32 len,
- unsigned flags)
+ unsigned dispatch_flags)
{
- bool ppgtt = USES_PPGTT(ring->dev) && !(flags & I915_DISPATCH_SECURE);
+ bool ppgtt = USES_PPGTT(ring->dev) &&
+ !(dispatch_flags & I915_DISPATCH_SECURE);
int ret;
ret = intel_ring_begin(ring, 4);
@@ -2373,8 +2377,8 @@ gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
static int
hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
- u64 offset, u32 len,
- unsigned flags)
+ u64 offset, u32 len,
+ unsigned dispatch_flags)
{
int ret;
@@ -2384,7 +2388,7 @@ hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
intel_ring_emit(ring,
MI_BATCH_BUFFER_START |
- (flags & I915_DISPATCH_SECURE ?
+ (dispatch_flags & I915_DISPATCH_SECURE ?
0 : MI_BATCH_PPGTT_HSW | MI_BATCH_NON_SECURE_HSW));
/* bit0-7 is the length on GEN6+ */
intel_ring_emit(ring, offset);
@@ -2396,7 +2400,7 @@ hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
static int
gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
u64 offset, u32 len,
- unsigned flags)
+ unsigned dispatch_flags)
{
int ret;
@@ -2406,7 +2410,8 @@ gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
intel_ring_emit(ring,
MI_BATCH_BUFFER_START |
- (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE_I965));
+ (dispatch_flags & I915_DISPATCH_SECURE ?
+ 0 : MI_BATCH_NON_SECURE_I965));
/* bit0-7 is the length on GEN6+ */
intel_ring_emit(ring, offset);
intel_ring_advance(ring);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index b6c484f..ffa3724 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -164,7 +164,7 @@ struct intel_engine_cs {
u32 seqno);
int (*dispatch_execbuffer)(struct intel_engine_cs *ring,
u64 offset, u32 length,
- unsigned flags);
+ unsigned dispatch_flags);
#define I915_DISPATCH_SECURE 0x1
#define I915_DISPATCH_PINNED 0x2
void (*cleanup)(struct intel_engine_cs *ring);
@@ -242,7 +242,7 @@ struct intel_engine_cs {
u32 flush_domains);
int (*emit_bb_start)(struct intel_ringbuffer *ringbuf,
struct intel_context *ctx,
- u64 offset, unsigned flags);
+ u64 offset, unsigned dispatch_flags);
/**
* List of objects currently involved in rendering from the
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 01/53] drm/i915: Rename 'flags' to 'dispatch_flags' for better code reading
2015-02-19 17:17 ` [PATCH 01/53] drm/i915: Rename 'flags' to 'dispatch_flags' for better code reading John.C.Harrison
@ 2015-03-05 13:21 ` Tomas Elf
2015-03-06 12:30 ` John Harrison
0 siblings, 1 reply; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 13:21 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> There is a flags word that is passed through the execbuffer code path all the
> way from initial decoding of the user parameters down to the very final dispatch
> buffer call. It is simply called 'flags'. Unfortuantely, there are many other
> flags words floating around in the same blocks of code. Even more once the GPU
> scheduler arrives.
>
> This patch makes it more obvious exactly which flags word is which by renaming
> 'flags' to 'dispatch_flags'. Note that the bit definitions for this flags word
> already have an 'I915_DISPATCH_' prefix on them and so are not quite so
> ambiguous.
>
> For: VIZ-1587
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 25 ++++++++++----------
> drivers/gpu/drm/i915/intel_lrc.c | 10 ++++----
> drivers/gpu/drm/i915/intel_lrc.h | 2 +-
> drivers/gpu/drm/i915/intel_ringbuffer.c | 35 ++++++++++++++++------------
> drivers/gpu/drm/i915/intel_ringbuffer.h | 4 ++--
> 5 files changed, 41 insertions(+), 35 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index b773368..ec9ea45 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1138,7 +1138,7 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
> struct drm_i915_gem_execbuffer2 *args,
> struct list_head *vmas,
> struct drm_i915_gem_object *batch_obj,
> - u64 exec_start, u32 flags)
> + u64 exec_start, u32 dispatch_flags)
You didn't change the parameter name in the prototype declaration in
i915_drv.h .
Thanks,
Tomas
> {
> struct drm_clip_rect *cliprects = NULL;
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -1266,19 +1266,19 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
>
> ret = ring->dispatch_execbuffer(ring,
> exec_start, exec_len,
> - flags);
> + dispatch_flags);
> if (ret)
> goto error;
> }
> } else {
> ret = ring->dispatch_execbuffer(ring,
> exec_start, exec_len,
> - flags);
> + dispatch_flags);
> if (ret)
> return ret;
> }
>
> - trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), flags);
> + trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
>
> i915_gem_execbuffer_move_to_active(vmas, ring);
> i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
> @@ -1353,7 +1353,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> struct i915_address_space *vm;
> const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
> u64 exec_start = args->batch_start_offset;
> - u32 flags;
> + u32 dispatch_flags;
> int ret;
> bool need_relocs;
>
> @@ -1364,15 +1364,15 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> if (ret)
> return ret;
>
> - flags = 0;
> + dispatch_flags = 0;
> if (args->flags & I915_EXEC_SECURE) {
> if (!file->is_master || !capable(CAP_SYS_ADMIN))
> return -EPERM;
>
> - flags |= I915_DISPATCH_SECURE;
> + dispatch_flags |= I915_DISPATCH_SECURE;
> }
> if (args->flags & I915_EXEC_IS_PINNED)
> - flags |= I915_DISPATCH_PINNED;
> + dispatch_flags |= I915_DISPATCH_PINNED;
>
> if ((args->flags & I915_EXEC_RING_MASK) > LAST_USER_RING) {
> DRM_DEBUG("execbuf with unknown ring: %d\n",
> @@ -1495,7 +1495,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> args->batch_start_offset,
> args->batch_len,
> file->is_master,
> - &flags);
> + &dispatch_flags);
> if (IS_ERR(batch_obj)) {
> ret = PTR_ERR(batch_obj);
> goto err;
> @@ -1507,7 +1507,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> /* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
> * batch" bit. Hence we need to pin secure batches into the global gtt.
> * hsw should have this fixed, but bdw mucks it up again. */
> - if (flags & I915_DISPATCH_SECURE) {
> + if (dispatch_flags & I915_DISPATCH_SECURE) {
> /*
> * So on first glance it looks freaky that we pin the batch here
> * outside of the reservation loop. But:
> @@ -1527,7 +1527,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> exec_start += i915_gem_obj_offset(batch_obj, vm);
>
> ret = dev_priv->gt.do_execbuf(dev, file, ring, ctx, args,
> - &eb->vmas, batch_obj, exec_start, flags);
> + &eb->vmas, batch_obj, exec_start,
> + dispatch_flags);
>
> /*
> * FIXME: We crucially rely upon the active tracking for the (ppgtt)
> @@ -1535,7 +1536,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> * needs to be adjusted to also track the ggtt batch vma properly as
> * active.
> */
> - if (flags & I915_DISPATCH_SECURE)
> + if (dispatch_flags & I915_DISPATCH_SECURE)
> i915_gem_object_ggtt_unpin(batch_obj);
> err:
> /* the request owns the ref now */
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index aafcef3..f30a8e3 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -620,7 +620,7 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
> * @vmas: list of vmas.
> * @batch_obj: the batchbuffer to submit.
> * @exec_start: batchbuffer start virtual address pointer.
> - * @flags: translated execbuffer call flags.
> + * @dispatch_flags: translated execbuffer call flags.
> *
> * This is the evil twin version of i915_gem_ringbuffer_submission. It abstracts
> * away the submission details of the execbuffer ioctl call.
> @@ -633,7 +633,7 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
> struct drm_i915_gem_execbuffer2 *args,
> struct list_head *vmas,
> struct drm_i915_gem_object *batch_obj,
> - u64 exec_start, u32 flags)
> + u64 exec_start, u32 dispatch_flags)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
> @@ -706,7 +706,7 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
> dev_priv->relative_constants_mode = instp_mode;
> }
>
> - ret = ring->emit_bb_start(ringbuf, ctx, exec_start, flags);
> + ret = ring->emit_bb_start(ringbuf, ctx, exec_start, dispatch_flags);
> if (ret)
> return ret;
>
> @@ -1163,9 +1163,9 @@ static int gen9_init_render_ring(struct intel_engine_cs *ring)
>
> static int gen8_emit_bb_start(struct intel_ringbuffer *ringbuf,
> struct intel_context *ctx,
> - u64 offset, unsigned flags)
> + u64 offset, unsigned dispatch_flags)
> {
> - bool ppgtt = !(flags & I915_DISPATCH_SECURE);
> + bool ppgtt = !(dispatch_flags & I915_DISPATCH_SECURE);
> int ret;
>
> ret = intel_logical_ring_begin(ringbuf, ctx, 4);
> diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
> index f635735..b66fc4d 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.h
> +++ b/drivers/gpu/drm/i915/intel_lrc.h
> @@ -82,7 +82,7 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
> struct drm_i915_gem_execbuffer2 *args,
> struct list_head *vmas,
> struct drm_i915_gem_object *batch_obj,
> - u64 exec_start, u32 flags);
> + u64 exec_start, u32 dispatch_flags);
> u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj);
>
> void intel_lrc_irq_handler(struct intel_engine_cs *ring);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index d17e76d..ca7de3d 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -1690,7 +1690,7 @@ gen8_ring_put_irq(struct intel_engine_cs *ring)
> static int
> i965_dispatch_execbuffer(struct intel_engine_cs *ring,
> u64 offset, u32 length,
> - unsigned flags)
> + unsigned dispatch_flags)
> {
> int ret;
>
> @@ -1701,7 +1701,8 @@ i965_dispatch_execbuffer(struct intel_engine_cs *ring,
> intel_ring_emit(ring,
> MI_BATCH_BUFFER_START |
> MI_BATCH_GTT |
> - (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE_I965));
> + (dispatch_flags & I915_DISPATCH_SECURE ?
> + 0 : MI_BATCH_NON_SECURE_I965));
> intel_ring_emit(ring, offset);
> intel_ring_advance(ring);
>
> @@ -1714,8 +1715,8 @@ i965_dispatch_execbuffer(struct intel_engine_cs *ring,
> #define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT)
> static int
> i830_dispatch_execbuffer(struct intel_engine_cs *ring,
> - u64 offset, u32 len,
> - unsigned flags)
> + u64 offset, u32 len,
> + unsigned dispatch_flags)
> {
> u32 cs_offset = ring->scratch.gtt_offset;
> int ret;
> @@ -1733,7 +1734,7 @@ i830_dispatch_execbuffer(struct intel_engine_cs *ring,
> intel_ring_emit(ring, MI_NOOP);
> intel_ring_advance(ring);
>
> - if ((flags & I915_DISPATCH_PINNED) == 0) {
> + if ((dispatch_flags & I915_DISPATCH_PINNED) == 0) {
> if (len > I830_BATCH_LIMIT)
> return -ENOSPC;
>
> @@ -1765,7 +1766,8 @@ i830_dispatch_execbuffer(struct intel_engine_cs *ring,
> return ret;
>
> intel_ring_emit(ring, MI_BATCH_BUFFER);
> - intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
> + intel_ring_emit(ring, offset | (dispatch_flags & I915_DISPATCH_SECURE ?
> + 0 : MI_BATCH_NON_SECURE));
> intel_ring_emit(ring, offset + len - 8);
> intel_ring_emit(ring, MI_NOOP);
> intel_ring_advance(ring);
> @@ -1776,7 +1778,7 @@ i830_dispatch_execbuffer(struct intel_engine_cs *ring,
> static int
> i915_dispatch_execbuffer(struct intel_engine_cs *ring,
> u64 offset, u32 len,
> - unsigned flags)
> + unsigned dispatch_flags)
> {
> int ret;
>
> @@ -1785,7 +1787,8 @@ i915_dispatch_execbuffer(struct intel_engine_cs *ring,
> return ret;
>
> intel_ring_emit(ring, MI_BATCH_BUFFER_START | MI_BATCH_GTT);
> - intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
> + intel_ring_emit(ring, offset | (dispatch_flags & I915_DISPATCH_SECURE ?
> + 0 : MI_BATCH_NON_SECURE));
> intel_ring_advance(ring);
>
> return 0;
> @@ -2352,9 +2355,10 @@ static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
> static int
> gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> u64 offset, u32 len,
> - unsigned flags)
> + unsigned dispatch_flags)
> {
> - bool ppgtt = USES_PPGTT(ring->dev) && !(flags & I915_DISPATCH_SECURE);
> + bool ppgtt = USES_PPGTT(ring->dev) &&
> + !(dispatch_flags & I915_DISPATCH_SECURE);
> int ret;
>
> ret = intel_ring_begin(ring, 4);
> @@ -2373,8 +2377,8 @@ gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
>
> static int
> hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> - u64 offset, u32 len,
> - unsigned flags)
> + u64 offset, u32 len,
> + unsigned dispatch_flags)
> {
> int ret;
>
> @@ -2384,7 +2388,7 @@ hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
>
> intel_ring_emit(ring,
> MI_BATCH_BUFFER_START |
> - (flags & I915_DISPATCH_SECURE ?
> + (dispatch_flags & I915_DISPATCH_SECURE ?
> 0 : MI_BATCH_PPGTT_HSW | MI_BATCH_NON_SECURE_HSW));
> /* bit0-7 is the length on GEN6+ */
> intel_ring_emit(ring, offset);
> @@ -2396,7 +2400,7 @@ hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> static int
> gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> u64 offset, u32 len,
> - unsigned flags)
> + unsigned dispatch_flags)
> {
> int ret;
>
> @@ -2406,7 +2410,8 @@ gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
>
> intel_ring_emit(ring,
> MI_BATCH_BUFFER_START |
> - (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE_I965));
> + (dispatch_flags & I915_DISPATCH_SECURE ?
> + 0 : MI_BATCH_NON_SECURE_I965));
> /* bit0-7 is the length on GEN6+ */
> intel_ring_emit(ring, offset);
> intel_ring_advance(ring);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index b6c484f..ffa3724 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -164,7 +164,7 @@ struct intel_engine_cs {
> u32 seqno);
> int (*dispatch_execbuffer)(struct intel_engine_cs *ring,
> u64 offset, u32 length,
> - unsigned flags);
> + unsigned dispatch_flags);
> #define I915_DISPATCH_SECURE 0x1
> #define I915_DISPATCH_PINNED 0x2
> void (*cleanup)(struct intel_engine_cs *ring);
> @@ -242,7 +242,7 @@ struct intel_engine_cs {
> u32 flush_domains);
> int (*emit_bb_start)(struct intel_ringbuffer *ringbuf,
> struct intel_context *ctx,
> - u64 offset, unsigned flags);
> + u64 offset, unsigned dispatch_flags);
>
> /**
> * List of objects currently involved in rendering from the
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 01/53] drm/i915: Rename 'flags' to 'dispatch_flags' for better code reading
2015-03-05 13:21 ` Tomas Elf
@ 2015-03-06 12:30 ` John Harrison
0 siblings, 0 replies; 234+ messages in thread
From: John Harrison @ 2015-03-06 12:30 UTC (permalink / raw)
To: Tomas Elf, Intel-GFX
On 05/03/2015 13:21, Tomas Elf wrote:
> On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
>> From: John Harrison <John.C.Harrison@Intel.com>
>>
>> There is a flags word that is passed through the execbuffer code path
>> all the
>> way from initial decoding of the user parameters down to the very
>> final dispatch
>> buffer call. It is simply called 'flags'. Unfortuantely, there are
>> many other
>> flags words floating around in the same blocks of code. Even more
>> once the GPU
>> scheduler arrives.
>>
>> This patch makes it more obvious exactly which flags word is which by
>> renaming
>> 'flags' to 'dispatch_flags'. Note that the bit definitions for this
>> flags word
>> already have an 'I915_DISPATCH_' prefix on them and so are not quite so
>> ambiguous.
>>
>> For: VIZ-1587
>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
>> ---
>> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 25 ++++++++++----------
>> drivers/gpu/drm/i915/intel_lrc.c | 10 ++++----
>> drivers/gpu/drm/i915/intel_lrc.h | 2 +-
>> drivers/gpu/drm/i915/intel_ringbuffer.c | 35
>> ++++++++++++++++------------
>> drivers/gpu/drm/i915/intel_ringbuffer.h | 4 ++--
>> 5 files changed, 41 insertions(+), 35 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>> b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>> index b773368..ec9ea45 100644
>> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>> @@ -1138,7 +1138,7 @@ i915_gem_ringbuffer_submission(struct
>> drm_device *dev, struct drm_file *file,
>> struct drm_i915_gem_execbuffer2 *args,
>> struct list_head *vmas,
>> struct drm_i915_gem_object *batch_obj,
>> - u64 exec_start, u32 flags)
>> + u64 exec_start, u32 dispatch_flags)
>
> You didn't change the parameter name in the prototype declaration in
> i915_drv.h .
Bit late now, this patch has already been merged. Also, it isn't really
worth following up with an extra fix patch as those parameters get
removed in a later patch in this series anyway (albeit one that is being
discussed as contentious).
>
> Thanks,
> Tomas
>
>> {
>> struct drm_clip_rect *cliprects = NULL;
>> struct drm_i915_private *dev_priv = dev->dev_private;
>> @@ -1266,19 +1266,19 @@ i915_gem_ringbuffer_submission(struct
>> drm_device *dev, struct drm_file *file,
>>
>> ret = ring->dispatch_execbuffer(ring,
>> exec_start, exec_len,
>> - flags);
>> + dispatch_flags);
>> if (ret)
>> goto error;
>> }
>> } else {
>> ret = ring->dispatch_execbuffer(ring,
>> exec_start, exec_len,
>> - flags);
>> + dispatch_flags);
>> if (ret)
>> return ret;
>> }
>>
>> - trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), flags);
>> + trace_i915_gem_ring_dispatch(intel_ring_get_request(ring),
>> dispatch_flags);
>>
>> i915_gem_execbuffer_move_to_active(vmas, ring);
>> i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
>> @@ -1353,7 +1353,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>> void *data,
>> struct i915_address_space *vm;
>> const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
>> u64 exec_start = args->batch_start_offset;
>> - u32 flags;
>> + u32 dispatch_flags;
>> int ret;
>> bool need_relocs;
>>
>> @@ -1364,15 +1364,15 @@ i915_gem_do_execbuffer(struct drm_device
>> *dev, void *data,
>> if (ret)
>> return ret;
>>
>> - flags = 0;
>> + dispatch_flags = 0;
>> if (args->flags & I915_EXEC_SECURE) {
>> if (!file->is_master || !capable(CAP_SYS_ADMIN))
>> return -EPERM;
>>
>> - flags |= I915_DISPATCH_SECURE;
>> + dispatch_flags |= I915_DISPATCH_SECURE;
>> }
>> if (args->flags & I915_EXEC_IS_PINNED)
>> - flags |= I915_DISPATCH_PINNED;
>> + dispatch_flags |= I915_DISPATCH_PINNED;
>>
>> if ((args->flags & I915_EXEC_RING_MASK) > LAST_USER_RING) {
>> DRM_DEBUG("execbuf with unknown ring: %d\n",
>> @@ -1495,7 +1495,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>> void *data,
>> args->batch_start_offset,
>> args->batch_len,
>> file->is_master,
>> - &flags);
>> + &dispatch_flags);
>> if (IS_ERR(batch_obj)) {
>> ret = PTR_ERR(batch_obj);
>> goto err;
>> @@ -1507,7 +1507,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>> void *data,
>> /* snb/ivb/vlv conflate the "batch in ppgtt" bit with the
>> "non-secure
>> * batch" bit. Hence we need to pin secure batches into the
>> global gtt.
>> * hsw should have this fixed, but bdw mucks it up again. */
>> - if (flags & I915_DISPATCH_SECURE) {
>> + if (dispatch_flags & I915_DISPATCH_SECURE) {
>> /*
>> * So on first glance it looks freaky that we pin the batch
>> here
>> * outside of the reservation loop. But:
>> @@ -1527,7 +1527,8 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>> void *data,
>> exec_start += i915_gem_obj_offset(batch_obj, vm);
>>
>> ret = dev_priv->gt.do_execbuf(dev, file, ring, ctx, args,
>> - &eb->vmas, batch_obj, exec_start, flags);
>> + &eb->vmas, batch_obj, exec_start,
>> + dispatch_flags);
>>
>> /*
>> * FIXME: We crucially rely upon the active tracking for the
>> (ppgtt)
>> @@ -1535,7 +1536,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>> void *data,
>> * needs to be adjusted to also track the ggtt batch vma
>> properly as
>> * active.
>> */
>> - if (flags & I915_DISPATCH_SECURE)
>> + if (dispatch_flags & I915_DISPATCH_SECURE)
>> i915_gem_object_ggtt_unpin(batch_obj);
>> err:
>> /* the request owns the ref now */
>> diff --git a/drivers/gpu/drm/i915/intel_lrc.c
>> b/drivers/gpu/drm/i915/intel_lrc.c
>> index aafcef3..f30a8e3 100644
>> --- a/drivers/gpu/drm/i915/intel_lrc.c
>> +++ b/drivers/gpu/drm/i915/intel_lrc.c
>> @@ -620,7 +620,7 @@ static int execlists_move_to_gpu(struct
>> intel_ringbuffer *ringbuf,
>> * @vmas: list of vmas.
>> * @batch_obj: the batchbuffer to submit.
>> * @exec_start: batchbuffer start virtual address pointer.
>> - * @flags: translated execbuffer call flags.
>> + * @dispatch_flags: translated execbuffer call flags.
>> *
>> * This is the evil twin version of i915_gem_ringbuffer_submission.
>> It abstracts
>> * away the submission details of the execbuffer ioctl call.
>> @@ -633,7 +633,7 @@ int intel_execlists_submission(struct drm_device
>> *dev, struct drm_file *file,
>> struct drm_i915_gem_execbuffer2 *args,
>> struct list_head *vmas,
>> struct drm_i915_gem_object *batch_obj,
>> - u64 exec_start, u32 flags)
>> + u64 exec_start, u32 dispatch_flags)
>> {
>> struct drm_i915_private *dev_priv = dev->dev_private;
>> struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
>> @@ -706,7 +706,7 @@ int intel_execlists_submission(struct drm_device
>> *dev, struct drm_file *file,
>> dev_priv->relative_constants_mode = instp_mode;
>> }
>>
>> - ret = ring->emit_bb_start(ringbuf, ctx, exec_start, flags);
>> + ret = ring->emit_bb_start(ringbuf, ctx, exec_start,
>> dispatch_flags);
>> if (ret)
>> return ret;
>>
>> @@ -1163,9 +1163,9 @@ static int gen9_init_render_ring(struct
>> intel_engine_cs *ring)
>>
>> static int gen8_emit_bb_start(struct intel_ringbuffer *ringbuf,
>> struct intel_context *ctx,
>> - u64 offset, unsigned flags)
>> + u64 offset, unsigned dispatch_flags)
>> {
>> - bool ppgtt = !(flags & I915_DISPATCH_SECURE);
>> + bool ppgtt = !(dispatch_flags & I915_DISPATCH_SECURE);
>> int ret;
>>
>> ret = intel_logical_ring_begin(ringbuf, ctx, 4);
>> diff --git a/drivers/gpu/drm/i915/intel_lrc.h
>> b/drivers/gpu/drm/i915/intel_lrc.h
>> index f635735..b66fc4d 100644
>> --- a/drivers/gpu/drm/i915/intel_lrc.h
>> +++ b/drivers/gpu/drm/i915/intel_lrc.h
>> @@ -82,7 +82,7 @@ int intel_execlists_submission(struct drm_device
>> *dev, struct drm_file *file,
>> struct drm_i915_gem_execbuffer2 *args,
>> struct list_head *vmas,
>> struct drm_i915_gem_object *batch_obj,
>> - u64 exec_start, u32 flags);
>> + u64 exec_start, u32 dispatch_flags);
>> u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj);
>>
>> void intel_lrc_irq_handler(struct intel_engine_cs *ring);
>> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c
>> b/drivers/gpu/drm/i915/intel_ringbuffer.c
>> index d17e76d..ca7de3d 100644
>> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
>> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
>> @@ -1690,7 +1690,7 @@ gen8_ring_put_irq(struct intel_engine_cs *ring)
>> static int
>> i965_dispatch_execbuffer(struct intel_engine_cs *ring,
>> u64 offset, u32 length,
>> - unsigned flags)
>> + unsigned dispatch_flags)
>> {
>> int ret;
>>
>> @@ -1701,7 +1701,8 @@ i965_dispatch_execbuffer(struct intel_engine_cs
>> *ring,
>> intel_ring_emit(ring,
>> MI_BATCH_BUFFER_START |
>> MI_BATCH_GTT |
>> - (flags & I915_DISPATCH_SECURE ? 0 :
>> MI_BATCH_NON_SECURE_I965));
>> + (dispatch_flags & I915_DISPATCH_SECURE ?
>> + 0 : MI_BATCH_NON_SECURE_I965));
>> intel_ring_emit(ring, offset);
>> intel_ring_advance(ring);
>>
>> @@ -1714,8 +1715,8 @@ i965_dispatch_execbuffer(struct intel_engine_cs
>> *ring,
>> #define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT)
>> static int
>> i830_dispatch_execbuffer(struct intel_engine_cs *ring,
>> - u64 offset, u32 len,
>> - unsigned flags)
>> + u64 offset, u32 len,
>> + unsigned dispatch_flags)
>> {
>> u32 cs_offset = ring->scratch.gtt_offset;
>> int ret;
>> @@ -1733,7 +1734,7 @@ i830_dispatch_execbuffer(struct intel_engine_cs
>> *ring,
>> intel_ring_emit(ring, MI_NOOP);
>> intel_ring_advance(ring);
>>
>> - if ((flags & I915_DISPATCH_PINNED) == 0) {
>> + if ((dispatch_flags & I915_DISPATCH_PINNED) == 0) {
>> if (len > I830_BATCH_LIMIT)
>> return -ENOSPC;
>>
>> @@ -1765,7 +1766,8 @@ i830_dispatch_execbuffer(struct intel_engine_cs
>> *ring,
>> return ret;
>>
>> intel_ring_emit(ring, MI_BATCH_BUFFER);
>> - intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0
>> : MI_BATCH_NON_SECURE));
>> + intel_ring_emit(ring, offset | (dispatch_flags &
>> I915_DISPATCH_SECURE ?
>> + 0 : MI_BATCH_NON_SECURE));
>> intel_ring_emit(ring, offset + len - 8);
>> intel_ring_emit(ring, MI_NOOP);
>> intel_ring_advance(ring);
>> @@ -1776,7 +1778,7 @@ i830_dispatch_execbuffer(struct intel_engine_cs
>> *ring,
>> static int
>> i915_dispatch_execbuffer(struct intel_engine_cs *ring,
>> u64 offset, u32 len,
>> - unsigned flags)
>> + unsigned dispatch_flags)
>> {
>> int ret;
>>
>> @@ -1785,7 +1787,8 @@ i915_dispatch_execbuffer(struct intel_engine_cs
>> *ring,
>> return ret;
>>
>> intel_ring_emit(ring, MI_BATCH_BUFFER_START | MI_BATCH_GTT);
>> - intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0
>> : MI_BATCH_NON_SECURE));
>> + intel_ring_emit(ring, offset | (dispatch_flags &
>> I915_DISPATCH_SECURE ?
>> + 0 : MI_BATCH_NON_SECURE));
>> intel_ring_advance(ring);
>>
>> return 0;
>> @@ -2352,9 +2355,10 @@ static int gen6_bsd_ring_flush(struct
>> intel_engine_cs *ring,
>> static int
>> gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
>> u64 offset, u32 len,
>> - unsigned flags)
>> + unsigned dispatch_flags)
>> {
>> - bool ppgtt = USES_PPGTT(ring->dev) && !(flags &
>> I915_DISPATCH_SECURE);
>> + bool ppgtt = USES_PPGTT(ring->dev) &&
>> + !(dispatch_flags & I915_DISPATCH_SECURE);
>> int ret;
>>
>> ret = intel_ring_begin(ring, 4);
>> @@ -2373,8 +2377,8 @@ gen8_ring_dispatch_execbuffer(struct
>> intel_engine_cs *ring,
>>
>> static int
>> hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
>> - u64 offset, u32 len,
>> - unsigned flags)
>> + u64 offset, u32 len,
>> + unsigned dispatch_flags)
>> {
>> int ret;
>>
>> @@ -2384,7 +2388,7 @@ hsw_ring_dispatch_execbuffer(struct
>> intel_engine_cs *ring,
>>
>> intel_ring_emit(ring,
>> MI_BATCH_BUFFER_START |
>> - (flags & I915_DISPATCH_SECURE ?
>> + (dispatch_flags & I915_DISPATCH_SECURE ?
>> 0 : MI_BATCH_PPGTT_HSW | MI_BATCH_NON_SECURE_HSW));
>> /* bit0-7 is the length on GEN6+ */
>> intel_ring_emit(ring, offset);
>> @@ -2396,7 +2400,7 @@ hsw_ring_dispatch_execbuffer(struct
>> intel_engine_cs *ring,
>> static int
>> gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
>> u64 offset, u32 len,
>> - unsigned flags)
>> + unsigned dispatch_flags)
>> {
>> int ret;
>>
>> @@ -2406,7 +2410,8 @@ gen6_ring_dispatch_execbuffer(struct
>> intel_engine_cs *ring,
>>
>> intel_ring_emit(ring,
>> MI_BATCH_BUFFER_START |
>> - (flags & I915_DISPATCH_SECURE ? 0 :
>> MI_BATCH_NON_SECURE_I965));
>> + (dispatch_flags & I915_DISPATCH_SECURE ?
>> + 0 : MI_BATCH_NON_SECURE_I965));
>> /* bit0-7 is the length on GEN6+ */
>> intel_ring_emit(ring, offset);
>> intel_ring_advance(ring);
>> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h
>> b/drivers/gpu/drm/i915/intel_ringbuffer.h
>> index b6c484f..ffa3724 100644
>> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
>> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
>> @@ -164,7 +164,7 @@ struct intel_engine_cs {
>> u32 seqno);
>> int (*dispatch_execbuffer)(struct intel_engine_cs *ring,
>> u64 offset, u32 length,
>> - unsigned flags);
>> + unsigned dispatch_flags);
>> #define I915_DISPATCH_SECURE 0x1
>> #define I915_DISPATCH_PINNED 0x2
>> void (*cleanup)(struct intel_engine_cs *ring);
>> @@ -242,7 +242,7 @@ struct intel_engine_cs {
>> u32 flush_domains);
>> int (*emit_bb_start)(struct intel_ringbuffer *ringbuf,
>> struct intel_context *ctx,
>> - u64 offset, unsigned flags);
>> + u64 offset, unsigned dispatch_flags);
>>
>> /**
>> * List of objects currently involved in rendering from the
>>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 02/53] drm/i915: Add missing trace point to LRC execbuff code path
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
2015-02-19 17:17 ` [PATCH 01/53] drm/i915: Rename 'flags' to 'dispatch_flags' for better code reading John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 13:26 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 03/53] drm/i915: Cache ringbuf pointer in request structure John.C.Harrison
` (52 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
There is a trace point in the legacy execbuffer execution path that is missing
from the execlist path. Trace points are extremely useful for debugging and are
used by various automated validation tests. Hence, this patch adds the missing
trace point back in.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_lrc.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index f30a8e3..637cbb7 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -710,6 +710,8 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
if (ret)
return ret;
+ trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
+
i915_gem_execbuffer_move_to_active(vmas, ring);
i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 02/53] drm/i915: Add missing trace point to LRC execbuff code path
2015-02-19 17:17 ` [PATCH 02/53] drm/i915: Add missing trace point to LRC execbuff code path John.C.Harrison
@ 2015-03-05 13:26 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 13:26 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> There is a trace point in the legacy execbuffer execution path that is missing
> from the execlist path. Trace points are extremely useful for debugging and are
> used by various automated validation tests. Hence, this patch adds the missing
> trace point back in.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_lrc.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index f30a8e3..637cbb7 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -710,6 +710,8 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
> if (ret)
> return ret;
>
> + trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
> +
> i915_gem_execbuffer_move_to_active(vmas, ring);
> i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
>
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 03/53] drm/i915: Cache ringbuf pointer in request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
2015-02-19 17:17 ` [PATCH 01/53] drm/i915: Rename 'flags' to 'dispatch_flags' for better code reading John.C.Harrison
2015-02-19 17:17 ` [PATCH 02/53] drm/i915: Add missing trace point to LRC execbuff code path John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 13:56 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 04/53] drm/i915: Merged the many do_execbuf() parameters into a structure John.C.Harrison
` (51 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
In execlist mode, the ringbuf is a function of the ring and context whereas in
legacy mode, it is derived from the ring alone. Thus the calculation required to
determine the ringbuf pointer from the ring (and context) also needs to test
execlist mode or not. This is messy.
Further, the request structure holds a pointer to both the ring and the context
for which it was created. Thus, given a request, it is possible to derive the
ringbuf in either legacy or execlist mode. Hence it is necessary to pass just
the request in to all the low level functions rather than some combination of
request, ring, context and ringbuf. However, rather than recalculating it each
time, it is much simpler to just cache the ringbuf pointer in the request
structure itself.
Caching the pointer means the calculation is done one at request creation time
and all further code and simply read it directly from the request structure.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 3 ++-
drivers/gpu/drm/i915/i915_gem.c | 14 +-------------
drivers/gpu/drm/i915/intel_lrc.c | 6 ++++--
drivers/gpu/drm/i915/intel_ringbuffer.c | 1 +
4 files changed, 8 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2dedd43..ba09137 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2144,8 +2144,9 @@ struct drm_i915_gem_request {
/** Position in the ringbuffer of the end of the whole request */
u32 tail;
- /** Context related to this request */
+ /** Context and ring buffer related to this request */
struct intel_context *ctx;
+ struct intel_ringbuffer *ringbuf;
/** Batch buffer related to this request if any */
struct drm_i915_gem_object *batch_obj;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 61134ab..7a0dc7c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2763,7 +2763,6 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
while (!list_empty(&ring->request_list)) {
struct drm_i915_gem_request *request;
- struct intel_ringbuffer *ringbuf;
request = list_first_entry(&ring->request_list,
struct drm_i915_gem_request,
@@ -2774,23 +2773,12 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
trace_i915_gem_request_retire(request);
- /* This is one of the few common intersection points
- * between legacy ringbuffer submission and execlists:
- * we need to tell them apart in order to find the correct
- * ringbuffer to which the request belongs to.
- */
- if (i915.enable_execlists) {
- struct intel_context *ctx = request->ctx;
- ringbuf = ctx->engine[ring->id].ringbuf;
- } else
- ringbuf = ring->buffer;
-
/* We know the GPU must have read the request to have
* sent us the seqno + interrupt, so use the position
* of tail of the request to update the last known position
* of the GPU head.
*/
- ringbuf->last_retired_head = request->postfix;
+ request->ringbuf->last_retired_head = request->postfix;
i915_gem_free_request(request);
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 637cbb7..f14b517 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -888,12 +888,14 @@ static int logical_ring_alloc_request(struct intel_engine_cs *ring,
return ret;
}
- /* Hold a reference to the context this request belongs to
+ /*
+ * Hold a reference to the context this request belongs to
* (we will need it when the time comes to emit/retire the
- * request).
+ * request). Likewise, the ringbuff is useful to keep track of.
*/
request->ctx = ctx;
i915_gem_context_reference(request->ctx);
+ request->ringbuf = ctx->engine[ring->id].ringbuf;
ring->outstanding_lazy_request = request;
return 0;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index ca7de3d..7fd89e5 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2179,6 +2179,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring)
kref_init(&request->ref);
request->ring = ring;
+ request->ringbuf = ring->buffer;
request->uniq = dev_private->request_uniq++;
ret = i915_gem_get_seqno(ring->dev, &request->seqno);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 03/53] drm/i915: Cache ringbuf pointer in request structure
2015-02-19 17:17 ` [PATCH 03/53] drm/i915: Cache ringbuf pointer in request structure John.C.Harrison
@ 2015-03-05 13:56 ` Tomas Elf
2015-03-06 12:28 ` John Harrison
0 siblings, 1 reply; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 13:56 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> In execlist mode, the ringbuf is a function of the ring and context whereas in
> legacy mode, it is derived from the ring alone. Thus the calculation required to
> determine the ringbuf pointer from the ring (and context) also needs to test
> execlist mode or not. This is messy.
>
> Further, the request structure holds a pointer to both the ring and the context
> for which it was created. Thus, given a request, it is possible to derive the
> ringbuf in either legacy or execlist mode. Hence it is necessary to pass just
> the request in to all the low level functions rather than some combination of
> request, ring, context and ringbuf. However, rather than recalculating it each
> time, it is much simpler to just cache the ringbuf pointer in the request
> structure itself.
>
> Caching the pointer means the calculation is done one at request creation time
> and all further code and simply read it directly from the request structure.
>
"Caching the pointer means the calculation is done one at request
creation time and all further code and simply read it directly from the
request structure"
Nitpick: Broken sentence, you might want to fix that. Aside from that,
no major problems with this patch.
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 3 ++-
> drivers/gpu/drm/i915/i915_gem.c | 14 +-------------
> drivers/gpu/drm/i915/intel_lrc.c | 6 ++++--
> drivers/gpu/drm/i915/intel_ringbuffer.c | 1 +
> 4 files changed, 8 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 2dedd43..ba09137 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2144,8 +2144,9 @@ struct drm_i915_gem_request {
> /** Position in the ringbuffer of the end of the whole request */
> u32 tail;
>
> - /** Context related to this request */
> + /** Context and ring buffer related to this request */
> struct intel_context *ctx;
> + struct intel_ringbuffer *ringbuf;
>
> /** Batch buffer related to this request if any */
> struct drm_i915_gem_object *batch_obj;
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 61134ab..7a0dc7c 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2763,7 +2763,6 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
>
> while (!list_empty(&ring->request_list)) {
> struct drm_i915_gem_request *request;
> - struct intel_ringbuffer *ringbuf;
>
> request = list_first_entry(&ring->request_list,
> struct drm_i915_gem_request,
> @@ -2774,23 +2773,12 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
>
> trace_i915_gem_request_retire(request);
>
> - /* This is one of the few common intersection points
> - * between legacy ringbuffer submission and execlists:
> - * we need to tell them apart in order to find the correct
> - * ringbuffer to which the request belongs to.
> - */
> - if (i915.enable_execlists) {
> - struct intel_context *ctx = request->ctx;
> - ringbuf = ctx->engine[ring->id].ringbuf;
> - } else
> - ringbuf = ring->buffer;
> -
> /* We know the GPU must have read the request to have
> * sent us the seqno + interrupt, so use the position
> * of tail of the request to update the last known position
> * of the GPU head.
> */
> - ringbuf->last_retired_head = request->postfix;
> + request->ringbuf->last_retired_head = request->postfix;
>
> i915_gem_free_request(request);
> }
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 637cbb7..f14b517 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -888,12 +888,14 @@ static int logical_ring_alloc_request(struct intel_engine_cs *ring,
> return ret;
> }
>
> - /* Hold a reference to the context this request belongs to
> + /*
> + * Hold a reference to the context this request belongs to
> * (we will need it when the time comes to emit/retire the
> - * request).
> + * request). Likewise, the ringbuff is useful to keep track of.
> */
> request->ctx = ctx;
> i915_gem_context_reference(request->ctx);
> + request->ringbuf = ctx->engine[ring->id].ringbuf;
>
> ring->outstanding_lazy_request = request;
> return 0;
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index ca7de3d..7fd89e5 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -2179,6 +2179,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring)
>
> kref_init(&request->ref);
> request->ring = ring;
> + request->ringbuf = ring->buffer;
> request->uniq = dev_private->request_uniq++;
>
> ret = i915_gem_get_seqno(ring->dev, &request->seqno);
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 03/53] drm/i915: Cache ringbuf pointer in request structure
2015-03-05 13:56 ` Tomas Elf
@ 2015-03-06 12:28 ` John Harrison
0 siblings, 0 replies; 234+ messages in thread
From: John Harrison @ 2015-03-06 12:28 UTC (permalink / raw)
To: Tomas Elf, Intel-GFX
On 05/03/2015 13:56, Tomas Elf wrote:
> On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
>> From: John Harrison <John.C.Harrison@Intel.com>
>>
>> In execlist mode, the ringbuf is a function of the ring and context
>> whereas in
>> legacy mode, it is derived from the ring alone. Thus the calculation
>> required to
>> determine the ringbuf pointer from the ring (and context) also needs
>> to test
>> execlist mode or not. This is messy.
>>
>> Further, the request structure holds a pointer to both the ring and
>> the context
>> for which it was created. Thus, given a request, it is possible to
>> derive the
>> ringbuf in either legacy or execlist mode. Hence it is necessary to
>> pass just
>> the request in to all the low level functions rather than some
>> combination of
>> request, ring, context and ringbuf. However, rather than
>> recalculating it each
>> time, it is much simpler to just cache the ringbuf pointer in the
>> request
>> structure itself.
>>
>> Caching the pointer means the calculation is done one at request
>> creation time
>> and all further code and simply read it directly from the request
>> structure.
>>
>
> "Caching the pointer means the calculation is done one at request
> creation time and all further code and simply read it directly from
> the request structure"
>
> Nitpick: Broken sentence, you might want to fix that. Aside from that,
> no major problems with this patch.
Bit late now, it has already been merged as is.
>
> Reviewed-by: Tomas Elf <tomas.elf@intel.com>
>
> Thanks,
> Tomas
>
>> For: VIZ-5115
>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
>> ---
>> drivers/gpu/drm/i915/i915_drv.h | 3 ++-
>> drivers/gpu/drm/i915/i915_gem.c | 14 +-------------
>> drivers/gpu/drm/i915/intel_lrc.c | 6 ++++--
>> drivers/gpu/drm/i915/intel_ringbuffer.c | 1 +
>> 4 files changed, 8 insertions(+), 16 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/i915_drv.h
>> b/drivers/gpu/drm/i915/i915_drv.h
>> index 2dedd43..ba09137 100644
>> --- a/drivers/gpu/drm/i915/i915_drv.h
>> +++ b/drivers/gpu/drm/i915/i915_drv.h
>> @@ -2144,8 +2144,9 @@ struct drm_i915_gem_request {
>> /** Position in the ringbuffer of the end of the whole request */
>> u32 tail;
>>
>> - /** Context related to this request */
>> + /** Context and ring buffer related to this request */
>> struct intel_context *ctx;
>> + struct intel_ringbuffer *ringbuf;
>>
>> /** Batch buffer related to this request if any */
>> struct drm_i915_gem_object *batch_obj;
>> diff --git a/drivers/gpu/drm/i915/i915_gem.c
>> b/drivers/gpu/drm/i915/i915_gem.c
>> index 61134ab..7a0dc7c 100644
>> --- a/drivers/gpu/drm/i915/i915_gem.c
>> +++ b/drivers/gpu/drm/i915/i915_gem.c
>> @@ -2763,7 +2763,6 @@ i915_gem_retire_requests_ring(struct
>> intel_engine_cs *ring)
>>
>> while (!list_empty(&ring->request_list)) {
>> struct drm_i915_gem_request *request;
>> - struct intel_ringbuffer *ringbuf;
>>
>> request = list_first_entry(&ring->request_list,
>> struct drm_i915_gem_request,
>> @@ -2774,23 +2773,12 @@ i915_gem_retire_requests_ring(struct
>> intel_engine_cs *ring)
>>
>> trace_i915_gem_request_retire(request);
>>
>> - /* This is one of the few common intersection points
>> - * between legacy ringbuffer submission and execlists:
>> - * we need to tell them apart in order to find the correct
>> - * ringbuffer to which the request belongs to.
>> - */
>> - if (i915.enable_execlists) {
>> - struct intel_context *ctx = request->ctx;
>> - ringbuf = ctx->engine[ring->id].ringbuf;
>> - } else
>> - ringbuf = ring->buffer;
>> -
>> /* We know the GPU must have read the request to have
>> * sent us the seqno + interrupt, so use the position
>> * of tail of the request to update the last known position
>> * of the GPU head.
>> */
>> - ringbuf->last_retired_head = request->postfix;
>> + request->ringbuf->last_retired_head = request->postfix;
>>
>> i915_gem_free_request(request);
>> }
>> diff --git a/drivers/gpu/drm/i915/intel_lrc.c
>> b/drivers/gpu/drm/i915/intel_lrc.c
>> index 637cbb7..f14b517 100644
>> --- a/drivers/gpu/drm/i915/intel_lrc.c
>> +++ b/drivers/gpu/drm/i915/intel_lrc.c
>> @@ -888,12 +888,14 @@ static int logical_ring_alloc_request(struct
>> intel_engine_cs *ring,
>> return ret;
>> }
>>
>> - /* Hold a reference to the context this request belongs to
>> + /*
>> + * Hold a reference to the context this request belongs to
>> * (we will need it when the time comes to emit/retire the
>> - * request).
>> + * request). Likewise, the ringbuff is useful to keep track of.
>> */
>> request->ctx = ctx;
>> i915_gem_context_reference(request->ctx);
>> + request->ringbuf = ctx->engine[ring->id].ringbuf;
>>
>> ring->outstanding_lazy_request = request;
>> return 0;
>> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c
>> b/drivers/gpu/drm/i915/intel_ringbuffer.c
>> index ca7de3d..7fd89e5 100644
>> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
>> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
>> @@ -2179,6 +2179,7 @@ intel_ring_alloc_request(struct intel_engine_cs
>> *ring)
>>
>> kref_init(&request->ref);
>> request->ring = ring;
>> + request->ringbuf = ring->buffer;
>> request->uniq = dev_private->request_uniq++;
>>
>> ret = i915_gem_get_seqno(ring->dev, &request->seqno);
>>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 04/53] drm/i915: Merged the many do_execbuf() parameters into a structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (2 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 03/53] drm/i915: Cache ringbuf pointer in request structure John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 13:37 ` John.C.Harrison
2015-03-05 14:30 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 05/53] drm/i915: Add return code check to i915_gem_execbuffer_retire_commands() John.C.Harrison
` (50 subsequent siblings)
54 siblings, 2 replies; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The do_execbuf() function takes quite a few parameters. The actual set of
parameters is going to change with the conversion to passing requests around.
Further, it is due to grow massively with the arrival of the GPU scheduler.
This patch simplies the prototype by passing a parameter structure instead.
Changing the parameter set in the future is then simply a matter of
adding/removing items to the structure.
Note that the structure does not contain absolutely everything that is passed
in. This is because the intention is to use this structure more extensively
later in this patch series and more especially in the GPU scheduler that is
coming soon. The latter requires hanging on to the structure as the final
hardware submission can be delayed until long after the execbuf IOCTL has
returned to user land. Thus it is unsafe to put anything in the structure that
is local to the IOCTL call itself - such as the 'args' parameter. All entries
must be copies of data or pointers to structures that are reference counted in
someway and guaranteed to exist for the duration of the batch buffer's life.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 27 +++++++-------
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 56 ++++++++++++++++++----------
drivers/gpu/drm/i915/intel_lrc.c | 26 +++++++------
drivers/gpu/drm/i915/intel_lrc.h | 9 ++---
4 files changed, 67 insertions(+), 51 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ba09137..fdd63ab 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1645,6 +1645,16 @@ struct i915_virtual_gpu {
bool active;
};
+struct i915_execbuffer_params {
+ struct drm_device *dev;
+ struct drm_file *file;
+ uint32_t dispatch_flags;
+ uint32_t batch_obj_vm_offset;
+ struct intel_engine_cs *ring;
+ struct drm_i915_gem_object *batch_obj;
+ struct intel_context *ctx;
+};
+
struct drm_i915_private {
struct drm_device *dev;
struct kmem_cache *slab;
@@ -1898,13 +1908,9 @@ struct drm_i915_private {
/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
struct {
- int (*do_execbuf)(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+ int (*do_execbuf)(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 flags);
+ struct list_head *vmas);
int (*init_rings)(struct drm_device *dev);
void (*cleanup_ring)(struct intel_engine_cs *ring);
void (*stop_ring)(struct intel_engine_cs *ring);
@@ -2638,14 +2644,9 @@ void i915_gem_execbuffer_retire_commands(struct drm_device *dev,
struct drm_file *file,
struct intel_engine_cs *ring,
struct drm_i915_gem_object *obj);
-int i915_gem_ringbuffer_submission(struct drm_device *dev,
- struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+int i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 flags);
+ struct list_head *vmas);
int i915_gem_execbuffer(struct drm_device *dev, void *data,
struct drm_file *file_priv);
int i915_gem_execbuffer2(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index ec9ea45..93b0ef0 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1132,17 +1132,15 @@ i915_gem_execbuffer_parse(struct intel_engine_cs *ring,
}
int
-i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 dispatch_flags)
+ struct list_head *vmas)
{
struct drm_clip_rect *cliprects = NULL;
+ struct drm_device *dev = params->dev;
+ struct intel_engine_cs *ring = params->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
- u64 exec_len;
+ u64 exec_start, exec_len;
int instp_mode;
u32 instp_mask;
int i, ret = 0;
@@ -1194,7 +1192,7 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
if (ret)
goto error;
- ret = i915_switch_context(ring, ctx);
+ ret = i915_switch_context(ring, params->ctx);
if (ret)
goto error;
@@ -1251,12 +1249,15 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
}
if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
- ret = i915_reset_gen7_sol_offsets(dev, ring);
+ ret = i915_reset_gen7_sol_offsets(params->dev, ring);
if (ret)
goto error;
}
- exec_len = args->batch_len;
+ exec_len = args->batch_len;
+ exec_start = params->batch_obj_vm_offset +
+ args->batch_start_offset;
+
if (cliprects) {
for (i = 0; i < args->num_cliprects; i++) {
ret = i915_emit_box(ring, &cliprects[i],
@@ -1266,22 +1267,23 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
ret = ring->dispatch_execbuffer(ring,
exec_start, exec_len,
- dispatch_flags);
+ params->dispatch_flags);
if (ret)
goto error;
}
} else {
ret = ring->dispatch_execbuffer(ring,
exec_start, exec_len,
- dispatch_flags);
+ params->dispatch_flags);
if (ret)
return ret;
}
- trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
+ trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
i915_gem_execbuffer_move_to_active(vmas, ring);
- i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
+ i915_gem_execbuffer_retire_commands(params->dev, params->file, ring,
+ params->batch_obj);
error:
kfree(cliprects);
@@ -1351,8 +1353,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
struct intel_engine_cs *ring;
struct intel_context *ctx;
struct i915_address_space *vm;
+ struct i915_execbuffer_params params_master; /* XXX: will be removed later */
+ struct i915_execbuffer_params *params = ¶ms_master;
const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
- u64 exec_start = args->batch_start_offset;
u32 dispatch_flags;
int ret;
bool need_relocs;
@@ -1445,6 +1448,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
else
vm = &dev_priv->gtt.base;
+ memset(¶ms_master, 0x00, sizeof(params_master));
+
eb = eb_create(args);
if (eb == NULL) {
i915_gem_context_unreference(ctx);
@@ -1522,13 +1527,24 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
if (ret)
goto err;
- exec_start += i915_gem_obj_ggtt_offset(batch_obj);
+ params->batch_obj_vm_offset = i915_gem_obj_ggtt_offset(batch_obj);
} else
- exec_start += i915_gem_obj_offset(batch_obj, vm);
+ params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
- ret = dev_priv->gt.do_execbuf(dev, file, ring, ctx, args,
- &eb->vmas, batch_obj, exec_start,
- dispatch_flags);
+ /*
+ * Save assorted stuff away to pass through to *_submission().
+ * NB: This data should be 'persistent' and not local as it will
+ * kept around beyond the duration of the IOCTL once the GPU
+ * scheduler arrives.
+ */
+ params->dev = dev;
+ params->file = file;
+ params->ring = ring;
+ params->dispatch_flags = dispatch_flags;
+ params->batch_obj = batch_obj;
+ params->ctx = ctx;
+
+ ret = dev_priv->gt.do_execbuf(params, args, &eb->vmas);
/*
* FIXME: We crucially rely upon the active tracking for the (ppgtt)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index f14b517..f6a24e8a2 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -627,16 +627,15 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
*
* Return: non-zero if the submission fails.
*/
-int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+int intel_execlists_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 dispatch_flags)
+ struct list_head *vmas)
{
+ struct drm_device *dev = params->dev;
+ struct intel_engine_cs *ring = params->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+ struct intel_ringbuffer *ringbuf = params->ctx->engine[ring->id].ringbuf;
+ u64 exec_start;
int instp_mode;
u32 instp_mask;
int ret;
@@ -687,13 +686,13 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
return -EINVAL;
}
- ret = execlists_move_to_gpu(ringbuf, ctx, vmas);
+ ret = execlists_move_to_gpu(ringbuf, params->ctx, vmas);
if (ret)
return ret;
if (ring == &dev_priv->ring[RCS] &&
instp_mode != dev_priv->relative_constants_mode) {
- ret = intel_logical_ring_begin(ringbuf, ctx, 4);
+ ret = intel_logical_ring_begin(ringbuf, params->ctx, 4);
if (ret)
return ret;
@@ -706,14 +705,17 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
dev_priv->relative_constants_mode = instp_mode;
}
- ret = ring->emit_bb_start(ringbuf, ctx, exec_start, dispatch_flags);
+ exec_start = params->batch_obj_vm_offset +
+ args->batch_start_offset;
+
+ ret = ring->emit_bb_start(ringbuf, params->ctx, exec_start, params->dispatch_flags);
if (ret)
return ret;
- trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
+ trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
i915_gem_execbuffer_move_to_active(vmas, ring);
- i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
+ i915_gem_execbuffer_retire_commands(params->dev, params->file, ring, params->batch_obj);
return 0;
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index b66fc4d..3a6abce 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -76,13 +76,10 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring,
/* Execlists */
int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists);
-int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+struct i915_execbuffer_params;
+int intel_execlists_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 dispatch_flags);
+ struct list_head *vmas);
u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj);
void intel_lrc_irq_handler(struct intel_engine_cs *ring);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* [PATCH 04/53] drm/i915: Merged the many do_execbuf() parameters into a structure
2015-02-19 17:17 ` [PATCH 04/53] drm/i915: Merged the many do_execbuf() parameters into a structure John.C.Harrison
@ 2015-03-05 13:37 ` John.C.Harrison
2015-03-05 14:30 ` Tomas Elf
1 sibling, 0 replies; 234+ messages in thread
From: John.C.Harrison @ 2015-03-05 13:37 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The do_execbuf() function takes quite a few parameters. The actual set of
parameters is going to change with the conversion to passing requests around.
Further, it is due to grow massively with the arrival of the GPU scheduler.
This patch simplies the prototype by passing a parameter structure instead.
Changing the parameter set in the future is then simply a matter of
adding/removing items to the structure.
Note that the structure does not contain absolutely everything that is passed
in. This is because the intention is to use this structure more extensively
later in this patch series and more especially in the GPU scheduler that is
coming soon. The latter requires hanging on to the structure as the final
hardware submission can be delayed until long after the execbuf IOCTL has
returned to user land. Thus it is unsafe to put anything in the structure that
is local to the IOCTL call itself - such as the 'args' parameter. All entries
must be copies of data or pointers to structures that are reference counted in
someway and guaranteed to exist for the duration of the batch buffer's life.
v2: Rebased to newer tree and updated for changes to the command parser.
Specifically, a code shuffle has required saving the batch start address in the
params structure.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 28 +++++++------
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 61 ++++++++++++++++++----------
drivers/gpu/drm/i915/intel_lrc.c | 26 ++++++------
drivers/gpu/drm/i915/intel_lrc.h | 9 ++--
4 files changed, 71 insertions(+), 53 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 05f106d..8dc08bc 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1525,6 +1525,17 @@ struct i915_virtual_gpu {
bool active;
};
+struct i915_execbuffer_params {
+ struct drm_device *dev;
+ struct drm_file *file;
+ uint32_t dispatch_flags;
+ uint32_t args_batch_start_offset;
+ uint32_t batch_obj_vm_offset;
+ struct intel_engine_cs *ring;
+ struct drm_i915_gem_object *batch_obj;
+ struct intel_context *ctx;
+};
+
struct drm_i915_private {
struct drm_device *dev;
struct kmem_cache *slab;
@@ -1778,13 +1789,9 @@ struct drm_i915_private {
/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
struct {
- int (*do_execbuf)(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+ int (*do_execbuf)(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 flags);
+ struct list_head *vmas);
int (*init_rings)(struct drm_device *dev);
void (*cleanup_ring)(struct intel_engine_cs *ring);
void (*stop_ring)(struct intel_engine_cs *ring);
@@ -2531,14 +2538,9 @@ void i915_gem_execbuffer_retire_commands(struct drm_device *dev,
struct drm_file *file,
struct intel_engine_cs *ring,
struct drm_i915_gem_object *obj);
-int i915_gem_ringbuffer_submission(struct drm_device *dev,
- struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+int i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 flags);
+ struct list_head *vmas);
int i915_gem_execbuffer(struct drm_device *dev, void *data,
struct drm_file *file_priv);
int i915_gem_execbuffer2(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 61fd8fa..2c4176f 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1121,17 +1121,15 @@ err:
}
int
-i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 dispatch_flags)
+ struct list_head *vmas)
{
struct drm_clip_rect *cliprects = NULL;
+ struct drm_device *dev = params->dev;
+ struct intel_engine_cs *ring = params->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
- u64 exec_len;
+ u64 exec_start, exec_len;
int instp_mode;
u32 instp_mask;
int i, ret = 0;
@@ -1183,7 +1181,7 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
if (ret)
goto error;
- ret = i915_switch_context(ring, ctx);
+ ret = i915_switch_context(ring, params->ctx);
if (ret)
goto error;
@@ -1240,12 +1238,15 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
}
if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
- ret = i915_reset_gen7_sol_offsets(dev, ring);
+ ret = i915_reset_gen7_sol_offsets(params->dev, ring);
if (ret)
goto error;
}
- exec_len = args->batch_len;
+ exec_len = args->batch_len;
+ exec_start = params->batch_obj_vm_offset +
+ params->args_batch_start_offset;
+
if (cliprects) {
for (i = 0; i < args->num_cliprects; i++) {
ret = i915_emit_box(ring, &cliprects[i],
@@ -1255,22 +1256,23 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
ret = ring->dispatch_execbuffer(ring,
exec_start, exec_len,
- dispatch_flags);
+ params->dispatch_flags);
if (ret)
goto error;
}
} else {
ret = ring->dispatch_execbuffer(ring,
exec_start, exec_len,
- dispatch_flags);
+ params->dispatch_flags);
if (ret)
return ret;
}
- trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
+ trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
i915_gem_execbuffer_move_to_active(vmas, ring);
- i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
+ i915_gem_execbuffer_retire_commands(params->dev, params->file, ring,
+ params->batch_obj);
error:
kfree(cliprects);
@@ -1340,8 +1342,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
struct intel_engine_cs *ring;
struct intel_context *ctx;
struct i915_address_space *vm;
+ struct i915_execbuffer_params params_master; /* XXX: will be removed later */
+ struct i915_execbuffer_params *params = ¶ms_master;
const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
- u64 exec_start = args->batch_start_offset;
u32 dispatch_flags;
int ret;
bool need_relocs;
@@ -1434,6 +1437,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
else
vm = &dev_priv->gtt.base;
+ memset(¶ms_master, 0x00, sizeof(params_master));
+
eb = eb_create(args);
if (eb == NULL) {
i915_gem_context_unreference(ctx);
@@ -1503,8 +1508,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
if (USES_FULL_PPGTT(dev))
dispatch_flags |= I915_DISPATCH_SECURE;
- exec_start = 0;
- }
+ params->args_batch_start_offset = 0;
+ } else
+ params->args_batch_start_offset = args->batch_start_offset;
batch_obj->base.pending_read_domains |= I915_GEM_DOMAIN_COMMAND;
@@ -1526,13 +1532,24 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
if (ret)
goto err;
- exec_start += i915_gem_obj_ggtt_offset(batch_obj);
+ params->batch_obj_vm_offset = i915_gem_obj_ggtt_offset(batch_obj);
} else
- exec_start += i915_gem_obj_offset(batch_obj, vm);
+ params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
- ret = dev_priv->gt.do_execbuf(dev, file, ring, ctx, args,
- &eb->vmas, batch_obj, exec_start,
- dispatch_flags);
+ /*
+ * Save assorted stuff away to pass through to *_submission().
+ * NB: This data should be 'persistent' and not local as it will
+ * kept around beyond the duration of the IOCTL once the GPU
+ * scheduler arrives.
+ */
+ params->dev = dev;
+ params->file = file;
+ params->ring = ring;
+ params->dispatch_flags = dispatch_flags;
+ params->batch_obj = batch_obj;
+ params->ctx = ctx;
+
+ ret = dev_priv->gt.do_execbuf(params, args, &eb->vmas);
/*
* FIXME: We crucially rely upon the active tracking for the (ppgtt)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index fcb074b..32fabbc 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -628,16 +628,15 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
*
* Return: non-zero if the submission fails.
*/
-int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+int intel_execlists_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 dispatch_flags)
+ struct list_head *vmas)
{
+ struct drm_device *dev = params->dev;
+ struct intel_engine_cs *ring = params->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+ struct intel_ringbuffer *ringbuf = params->ctx->engine[ring->id].ringbuf;
+ u64 exec_start;
int instp_mode;
u32 instp_mask;
int ret;
@@ -688,13 +687,13 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
return -EINVAL;
}
- ret = execlists_move_to_gpu(ringbuf, ctx, vmas);
+ ret = execlists_move_to_gpu(ringbuf, params->ctx, vmas);
if (ret)
return ret;
if (ring == &dev_priv->ring[RCS] &&
instp_mode != dev_priv->relative_constants_mode) {
- ret = intel_logical_ring_begin(ringbuf, ctx, 4);
+ ret = intel_logical_ring_begin(ringbuf, params->ctx, 4);
if (ret)
return ret;
@@ -707,14 +706,17 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
dev_priv->relative_constants_mode = instp_mode;
}
- ret = ring->emit_bb_start(ringbuf, ctx, exec_start, dispatch_flags);
+ exec_start = params->batch_obj_vm_offset +
+ args->batch_start_offset;
+
+ ret = ring->emit_bb_start(ringbuf, params->ctx, exec_start, params->dispatch_flags);
if (ret)
return ret;
- trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
+ trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
i915_gem_execbuffer_move_to_active(vmas, ring);
- i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
+ i915_gem_execbuffer_retire_commands(params->dev, params->file, ring, params->batch_obj);
return 0;
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index adb731e4..a64e344 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -78,13 +78,10 @@ void intel_lr_context_reset(struct drm_device *dev,
/* Execlists */
int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists);
-int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
- struct intel_engine_cs *ring,
- struct intel_context *ctx,
+struct i915_execbuffer_params;
+int intel_execlists_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas,
- struct drm_i915_gem_object *batch_obj,
- u64 exec_start, u32 dispatch_flags);
+ struct list_head *vmas);
u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj);
void intel_lrc_irq_handler(struct intel_engine_cs *ring);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 04/53] drm/i915: Merged the many do_execbuf() parameters into a structure
2015-02-19 17:17 ` [PATCH 04/53] drm/i915: Merged the many do_execbuf() parameters into a structure John.C.Harrison
2015-03-05 13:37 ` John.C.Harrison
@ 2015-03-05 14:30 ` Tomas Elf
1 sibling, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 14:30 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The do_execbuf() function takes quite a few parameters. The actual set of
> parameters is going to change with the conversion to passing requests around.
> Further, it is due to grow massively with the arrival of the GPU scheduler.
>
> This patch simplies the prototype by passing a parameter structure instead.
Nitpick: simplies -> simplifies.
> Changing the parameter set in the future is then simply a matter of
> adding/removing items to the structure.
>
> Note that the structure does not contain absolutely everything that is passed
> in. This is because the intention is to use this structure more extensively
> later in this patch series and more especially in the GPU scheduler that is
> coming soon. The latter requires hanging on to the structure as the final
> hardware submission can be delayed until long after the execbuf IOCTL has
> returned to user land. Thus it is unsafe to put anything in the structure that
> is local to the IOCTL call itself - such as the 'args' parameter. All entries
> must be copies of data or pointers to structures that are reference counted in
> someway and guaranteed to exist for the duration of the batch buffer's life.
Nitpick: someway -> some way
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 27 +++++++-------
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 56 ++++++++++++++++++----------
> drivers/gpu/drm/i915/intel_lrc.c | 26 +++++++------
> drivers/gpu/drm/i915/intel_lrc.h | 9 ++---
> 4 files changed, 67 insertions(+), 51 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index ba09137..fdd63ab 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -1645,6 +1645,16 @@ struct i915_virtual_gpu {
> bool active;
> };
>
> +struct i915_execbuffer_params {
> + struct drm_device *dev;
> + struct drm_file *file;
> + uint32_t dispatch_flags;
> + uint32_t batch_obj_vm_offset;
> + struct intel_engine_cs *ring;
> + struct drm_i915_gem_object *batch_obj;
> + struct intel_context *ctx;
> +};
> +
> struct drm_i915_private {
> struct drm_device *dev;
> struct kmem_cache *slab;
> @@ -1898,13 +1908,9 @@ struct drm_i915_private {
>
> /* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
> struct {
> - int (*do_execbuf)(struct drm_device *dev, struct drm_file *file,
> - struct intel_engine_cs *ring,
> - struct intel_context *ctx,
> + int (*do_execbuf)(struct i915_execbuffer_params *params,
> struct drm_i915_gem_execbuffer2 *args,
> - struct list_head *vmas,
> - struct drm_i915_gem_object *batch_obj,
> - u64 exec_start, u32 flags);
> + struct list_head *vmas);
> int (*init_rings)(struct drm_device *dev);
> void (*cleanup_ring)(struct intel_engine_cs *ring);
> void (*stop_ring)(struct intel_engine_cs *ring);
> @@ -2638,14 +2644,9 @@ void i915_gem_execbuffer_retire_commands(struct drm_device *dev,
> struct drm_file *file,
> struct intel_engine_cs *ring,
> struct drm_i915_gem_object *obj);
> -int i915_gem_ringbuffer_submission(struct drm_device *dev,
> - struct drm_file *file,
> - struct intel_engine_cs *ring,
> - struct intel_context *ctx,
> +int i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> struct drm_i915_gem_execbuffer2 *args,
> - struct list_head *vmas,
> - struct drm_i915_gem_object *batch_obj,
> - u64 exec_start, u32 flags);
> + struct list_head *vmas);
> int i915_gem_execbuffer(struct drm_device *dev, void *data,
> struct drm_file *file_priv);
> int i915_gem_execbuffer2(struct drm_device *dev, void *data,
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index ec9ea45..93b0ef0 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1132,17 +1132,15 @@ i915_gem_execbuffer_parse(struct intel_engine_cs *ring,
> }
>
> int
> -i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
> - struct intel_engine_cs *ring,
> - struct intel_context *ctx,
> +i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> struct drm_i915_gem_execbuffer2 *args,
> - struct list_head *vmas,
> - struct drm_i915_gem_object *batch_obj,
> - u64 exec_start, u32 dispatch_flags)
> + struct list_head *vmas)
> {
> struct drm_clip_rect *cliprects = NULL;
> + struct drm_device *dev = params->dev;
> + struct intel_engine_cs *ring = params->ring;
> struct drm_i915_private *dev_priv = dev->dev_private;
> - u64 exec_len;
> + u64 exec_start, exec_len;
> int instp_mode;
> u32 instp_mask;
> int i, ret = 0;
> @@ -1194,7 +1192,7 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
> if (ret)
> goto error;
>
> - ret = i915_switch_context(ring, ctx);
> + ret = i915_switch_context(ring, params->ctx);
> if (ret)
> goto error;
>
> @@ -1251,12 +1249,15 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
> }
>
> if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
> - ret = i915_reset_gen7_sol_offsets(dev, ring);
> + ret = i915_reset_gen7_sol_offsets(params->dev, ring);
> if (ret)
> goto error;
> }
>
> - exec_len = args->batch_len;
> + exec_len = args->batch_len;
> + exec_start = params->batch_obj_vm_offset +
> + args->batch_start_offset;
> +
> if (cliprects) {
> for (i = 0; i < args->num_cliprects; i++) {
> ret = i915_emit_box(ring, &cliprects[i],
> @@ -1266,22 +1267,23 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
>
> ret = ring->dispatch_execbuffer(ring,
> exec_start, exec_len,
> - dispatch_flags);
> + params->dispatch_flags);
> if (ret)
> goto error;
> }
> } else {
> ret = ring->dispatch_execbuffer(ring,
> exec_start, exec_len,
> - dispatch_flags);
> + params->dispatch_flags);
> if (ret)
> return ret;
> }
>
> - trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
> + trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
>
> i915_gem_execbuffer_move_to_active(vmas, ring);
> - i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
> + i915_gem_execbuffer_retire_commands(params->dev, params->file, ring,
> + params->batch_obj);
>
> error:
> kfree(cliprects);
> @@ -1351,8 +1353,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> struct intel_engine_cs *ring;
> struct intel_context *ctx;
> struct i915_address_space *vm;
> + struct i915_execbuffer_params params_master; /* XXX: will be removed later */
params_master is not removed anywhere in this patch series. What is the
plan for this variable?
(Update: John has in later discussions said that it will be dropped once
the scheduler lands, also it is explained further in comment below where
the params variable is populated. Still, the comment above could say
"will be removed once the scheduler lands" or something. Not a big deal,
though.)
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
> + struct i915_execbuffer_params *params = ¶ms_master;
> const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
> - u64 exec_start = args->batch_start_offset;
> u32 dispatch_flags;
> int ret;
> bool need_relocs;
> @@ -1445,6 +1448,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> else
> vm = &dev_priv->gtt.base;
>
> + memset(¶ms_master, 0x00, sizeof(params_master));
> +
> eb = eb_create(args);
> if (eb == NULL) {
> i915_gem_context_unreference(ctx);
> @@ -1522,13 +1527,24 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> if (ret)
> goto err;
>
> - exec_start += i915_gem_obj_ggtt_offset(batch_obj);
> + params->batch_obj_vm_offset = i915_gem_obj_ggtt_offset(batch_obj);
> } else
> - exec_start += i915_gem_obj_offset(batch_obj, vm);
> + params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
>
> - ret = dev_priv->gt.do_execbuf(dev, file, ring, ctx, args,
> - &eb->vmas, batch_obj, exec_start,
> - dispatch_flags);
> + /*
> + * Save assorted stuff away to pass through to *_submission().
> + * NB: This data should be 'persistent' and not local as it will
> + * kept around beyond the duration of the IOCTL once the GPU
> + * scheduler arrives.
> + */
> + params->dev = dev;
> + params->file = file;
> + params->ring = ring;
> + params->dispatch_flags = dispatch_flags;
> + params->batch_obj = batch_obj;
> + params->ctx = ctx;
> +
> + ret = dev_priv->gt.do_execbuf(params, args, &eb->vmas);
>
> /*
> * FIXME: We crucially rely upon the active tracking for the (ppgtt)
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index f14b517..f6a24e8a2 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -627,16 +627,15 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
> *
> * Return: non-zero if the submission fails.
> */
> -int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
> - struct intel_engine_cs *ring,
> - struct intel_context *ctx,
> +int intel_execlists_submission(struct i915_execbuffer_params *params,
> struct drm_i915_gem_execbuffer2 *args,
> - struct list_head *vmas,
> - struct drm_i915_gem_object *batch_obj,
> - u64 exec_start, u32 dispatch_flags)
> + struct list_head *vmas)
> {
> + struct drm_device *dev = params->dev;
> + struct intel_engine_cs *ring = params->ring;
> struct drm_i915_private *dev_priv = dev->dev_private;
> - struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
> + struct intel_ringbuffer *ringbuf = params->ctx->engine[ring->id].ringbuf;
> + u64 exec_start;
> int instp_mode;
> u32 instp_mask;
> int ret;
> @@ -687,13 +686,13 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
> return -EINVAL;
> }
>
> - ret = execlists_move_to_gpu(ringbuf, ctx, vmas);
> + ret = execlists_move_to_gpu(ringbuf, params->ctx, vmas);
> if (ret)
> return ret;
>
> if (ring == &dev_priv->ring[RCS] &&
> instp_mode != dev_priv->relative_constants_mode) {
> - ret = intel_logical_ring_begin(ringbuf, ctx, 4);
> + ret = intel_logical_ring_begin(ringbuf, params->ctx, 4);
> if (ret)
> return ret;
>
> @@ -706,14 +705,17 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
> dev_priv->relative_constants_mode = instp_mode;
> }
>
> - ret = ring->emit_bb_start(ringbuf, ctx, exec_start, dispatch_flags);
> + exec_start = params->batch_obj_vm_offset +
> + args->batch_start_offset;
> +
> + ret = ring->emit_bb_start(ringbuf, params->ctx, exec_start, params->dispatch_flags);
> if (ret)
> return ret;
>
> - trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
> + trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
>
> i915_gem_execbuffer_move_to_active(vmas, ring);
> - i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
> + i915_gem_execbuffer_retire_commands(params->dev, params->file, ring, params->batch_obj);
>
> return 0;
> }
> diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
> index b66fc4d..3a6abce 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.h
> +++ b/drivers/gpu/drm/i915/intel_lrc.h
> @@ -76,13 +76,10 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring,
>
> /* Execlists */
> int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists);
> -int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
> - struct intel_engine_cs *ring,
> - struct intel_context *ctx,
> +struct i915_execbuffer_params;
> +int intel_execlists_submission(struct i915_execbuffer_params *params,
> struct drm_i915_gem_execbuffer2 *args,
> - struct list_head *vmas,
> - struct drm_i915_gem_object *batch_obj,
> - u64 exec_start, u32 dispatch_flags);
> + struct list_head *vmas);
> u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj);
>
> void intel_lrc_irq_handler(struct intel_engine_cs *ring);
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 05/53] drm/i915: Add return code check to i915_gem_execbuffer_retire_commands()
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (3 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 04/53] drm/i915: Merged the many do_execbuf() parameters into a structure John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 14:45 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 06/53] drm/i915: Wrap request allocation with a function pointer John.C.Harrison
` (49 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
For some reason, the i915_add_request() call in
i915_gem_execbuffer_retire_commands() was explicitly having its return code
ignored. The _retire_commands() function itself was 'void'. Given that
_add_request() can fail without dispatching the batch buffer, this seems odd.
Also shrunk the parameter list to a single structure as everything it requires
is available in the execbuff_params object.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 5 +----
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 16 +++++++---------
drivers/gpu/drm/i915/intel_lrc.c | 3 +--
3 files changed, 9 insertions(+), 15 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index fdd63ab..b350910 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2640,10 +2640,7 @@ int i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv);
void i915_gem_execbuffer_move_to_active(struct list_head *vmas,
struct intel_engine_cs *ring);
-void i915_gem_execbuffer_retire_commands(struct drm_device *dev,
- struct drm_file *file,
- struct intel_engine_cs *ring,
- struct drm_i915_gem_object *obj);
+int i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params);
int i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
struct list_head *vmas);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 93b0ef0..ca85803 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -989,17 +989,15 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
}
}
-void
-i915_gem_execbuffer_retire_commands(struct drm_device *dev,
- struct drm_file *file,
- struct intel_engine_cs *ring,
- struct drm_i915_gem_object *obj)
+int
+i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
{
/* Unconditionally force add_request to emit a full flush. */
- ring->gpu_caches_dirty = true;
+ params->ring->gpu_caches_dirty = true;
/* Add a breadcrumb for the completion of the batch buffer */
- (void)__i915_add_request(ring, file, obj);
+ return __i915_add_request(params->ring, params->file,
+ params->batch_obj);
}
static int
@@ -1282,8 +1280,8 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
i915_gem_execbuffer_move_to_active(vmas, ring);
- i915_gem_execbuffer_retire_commands(params->dev, params->file, ring,
- params->batch_obj);
+
+ ret = i915_gem_execbuffer_retire_commands(params);
error:
kfree(cliprects);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index f6a24e8a2..dc474b4 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -715,9 +715,8 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
i915_gem_execbuffer_move_to_active(vmas, ring);
- i915_gem_execbuffer_retire_commands(params->dev, params->file, ring, params->batch_obj);
- return 0;
+ return i915_gem_execbuffer_retire_commands(params);
}
void intel_execlists_retire_requests(struct intel_engine_cs *ring)
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 05/53] drm/i915: Add return code check to i915_gem_execbuffer_retire_commands()
2015-02-19 17:17 ` [PATCH 05/53] drm/i915: Add return code check to i915_gem_execbuffer_retire_commands() John.C.Harrison
@ 2015-03-05 14:45 ` Tomas Elf
2015-03-06 16:15 ` Daniel Vetter
0 siblings, 1 reply; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 14:45 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> For some reason, the i915_add_request() call in
> i915_gem_execbuffer_retire_commands() was explicitly having its return code
> ignored. The _retire_commands() function itself was 'void'. Given that
> _add_request() can fail without dispatching the batch buffer, this seems odd.
>
> Also shrunk the parameter list to a single structure as everything it requires
> is available in the execbuff_params object.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 5 +----
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 16 +++++++---------
> drivers/gpu/drm/i915/intel_lrc.c | 3 +--
> 3 files changed, 9 insertions(+), 15 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index fdd63ab..b350910 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2640,10 +2640,7 @@ int i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
> struct drm_file *file_priv);
> void i915_gem_execbuffer_move_to_active(struct list_head *vmas,
> struct intel_engine_cs *ring);
> -void i915_gem_execbuffer_retire_commands(struct drm_device *dev,
> - struct drm_file *file,
> - struct intel_engine_cs *ring,
> - struct drm_i915_gem_object *obj);
> +int i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params);
> int i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> struct drm_i915_gem_execbuffer2 *args,
> struct list_head *vmas);
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 93b0ef0..ca85803 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -989,17 +989,15 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
> }
> }
>
> -void
> -i915_gem_execbuffer_retire_commands(struct drm_device *dev,
> - struct drm_file *file,
> - struct intel_engine_cs *ring,
> - struct drm_i915_gem_object *obj)
> +int
> +i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
> {
> /* Unconditionally force add_request to emit a full flush. */
> - ring->gpu_caches_dirty = true;
> + params->ring->gpu_caches_dirty = true;
>
> /* Add a breadcrumb for the completion of the batch buffer */
> - (void)__i915_add_request(ring, file, obj);
> + return __i915_add_request(params->ring, params->file,
> + params->batch_obj);
> }
>
> static int
> @@ -1282,8 +1280,8 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
>
> i915_gem_execbuffer_move_to_active(vmas, ring);
> - i915_gem_execbuffer_retire_commands(params->dev, params->file, ring,
> - params->batch_obj);
> +
> + ret = i915_gem_execbuffer_retire_commands(params);
>
> error:
> kfree(cliprects);
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index f6a24e8a2..dc474b4 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -715,9 +715,8 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
> trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
>
> i915_gem_execbuffer_move_to_active(vmas, ring);
> - i915_gem_execbuffer_retire_commands(params->dev, params->file, ring, params->batch_obj);
>
> - return 0;
> + return i915_gem_execbuffer_retire_commands(params);
> }
>
> void intel_execlists_retire_requests(struct intel_engine_cs *ring)
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 05/53] drm/i915: Add return code check to i915_gem_execbuffer_retire_commands()
2015-03-05 14:45 ` Tomas Elf
@ 2015-03-06 16:15 ` Daniel Vetter
0 siblings, 0 replies; 234+ messages in thread
From: Daniel Vetter @ 2015-03-06 16:15 UTC (permalink / raw)
To: Tomas Elf; +Cc: Intel-GFX
On Thu, Mar 05, 2015 at 02:45:11PM +0000, Tomas Elf wrote:
> On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> >From: John Harrison <John.C.Harrison@Intel.com>
> >
> >For some reason, the i915_add_request() call in
> >i915_gem_execbuffer_retire_commands() was explicitly having its return code
> >ignored. The _retire_commands() function itself was 'void'. Given that
> >_add_request() can fail without dispatching the batch buffer, this seems odd.
> >
> >Also shrunk the parameter list to a single structure as everything it requires
> >is available in the execbuff_params object.
> >
> >For: VIZ-5115
> >Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> >---
> > drivers/gpu/drm/i915/i915_drv.h | 5 +----
> > drivers/gpu/drm/i915/i915_gem_execbuffer.c | 16 +++++++---------
> > drivers/gpu/drm/i915/intel_lrc.c | 3 +--
> > 3 files changed, 9 insertions(+), 15 deletions(-)
> >
> >diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> >index fdd63ab..b350910 100644
> >--- a/drivers/gpu/drm/i915/i915_drv.h
> >+++ b/drivers/gpu/drm/i915/i915_drv.h
> >@@ -2640,10 +2640,7 @@ int i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
> > struct drm_file *file_priv);
> > void i915_gem_execbuffer_move_to_active(struct list_head *vmas,
> > struct intel_engine_cs *ring);
> >-void i915_gem_execbuffer_retire_commands(struct drm_device *dev,
> >- struct drm_file *file,
> >- struct intel_engine_cs *ring,
> >- struct drm_i915_gem_object *obj);
> >+int i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params);
> > int i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> > struct drm_i915_gem_execbuffer2 *args,
> > struct list_head *vmas);
> >diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> >index 93b0ef0..ca85803 100644
> >--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> >+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> >@@ -989,17 +989,15 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
> > }
> > }
> >
> >-void
> >-i915_gem_execbuffer_retire_commands(struct drm_device *dev,
> >- struct drm_file *file,
> >- struct intel_engine_cs *ring,
> >- struct drm_i915_gem_object *obj)
> >+int
> >+i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
> > {
> > /* Unconditionally force add_request to emit a full flush. */
> >- ring->gpu_caches_dirty = true;
> >+ params->ring->gpu_caches_dirty = true;
> >
> > /* Add a breadcrumb for the completion of the batch buffer */
> >- (void)__i915_add_request(ring, file, obj);
> >+ return __i915_add_request(params->ring, params->file,
> >+ params->batch_obj);
> > }
> >
> > static int
> >@@ -1282,8 +1280,8 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> > trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
> >
> > i915_gem_execbuffer_move_to_active(vmas, ring);
> >- i915_gem_execbuffer_retire_commands(params->dev, params->file, ring,
> >- params->batch_obj);
> >+
> >+ ret = i915_gem_execbuffer_retire_commands(params);
> >
> > error:
> > kfree(cliprects);
> >diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> >index f6a24e8a2..dc474b4 100644
> >--- a/drivers/gpu/drm/i915/intel_lrc.c
> >+++ b/drivers/gpu/drm/i915/intel_lrc.c
> >@@ -715,9 +715,8 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
> > trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
> >
> > i915_gem_execbuffer_move_to_active(vmas, ring);
> >- i915_gem_execbuffer_retire_commands(params->dev, params->file, ring, params->batch_obj);
> >
> >- return 0;
> >+ return i915_gem_execbuffer_retire_commands(params);
> > }
> >
> > void intel_execlists_retire_requests(struct intel_engine_cs *ring)
> >
>
> Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Patch discussion unfortunately split since I've made all my comments on
the earlier iteration. Anyway there's a big discussion there, you might
want to look into that and reconsder your r-b ;-)
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 06/53] drm/i915: Wrap request allocation with a function pointer
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (4 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 05/53] drm/i915: Add return code check to i915_gem_execbuffer_retire_commands() John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 15:01 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 07/53] drm/i915: Early alloc request in execbuff John.C.Harrison
` (48 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
In order to explicitly manage requests from creation to submission, it is
necessary to be able to explicitly create them in the first place. This patch
adds an indirection wrapper to the request creation function so that it can be
called from generic code without having to worry about execlist vs legacy mode.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 2 ++
drivers/gpu/drm/i915/i915_gem.c | 2 ++
drivers/gpu/drm/i915/intel_lrc.c | 6 +++---
drivers/gpu/drm/i915/intel_lrc.h | 2 ++
drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 ++
6 files changed, 14 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b350910..87a4a2e 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1908,6 +1908,8 @@ struct drm_i915_private {
/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
struct {
+ int (*alloc_request)(struct intel_engine_cs *ring,
+ struct intel_context *ctx);
int (*do_execbuf)(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
struct list_head *vmas);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 7a0dc7c..cf959e3 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4860,11 +4860,13 @@ int i915_gem_init(struct drm_device *dev)
}
if (!i915.enable_execlists) {
+ dev_priv->gt.alloc_request = intel_ring_alloc_request;
dev_priv->gt.do_execbuf = i915_gem_ringbuffer_submission;
dev_priv->gt.init_rings = i915_gem_init_rings;
dev_priv->gt.cleanup_ring = intel_cleanup_ring_buffer;
dev_priv->gt.stop_ring = intel_stop_ring_buffer;
} else {
+ dev_priv->gt.alloc_request = intel_logical_ring_alloc_request;
dev_priv->gt.do_execbuf = intel_execlists_submission;
dev_priv->gt.init_rings = intel_logical_rings_init;
dev_priv->gt.cleanup_ring = intel_logical_ring_cleanup;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index dc474b4..8628abf 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -856,8 +856,8 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring,
}
}
-static int logical_ring_alloc_request(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
+ struct intel_context *ctx)
{
struct drm_i915_gem_request *request;
struct drm_i915_private *dev_private = ring->dev->dev_private;
@@ -1066,7 +1066,7 @@ int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
return ret;
/* Preallocate the olr before touching the ring */
- ret = logical_ring_alloc_request(ring, ctx);
+ ret = intel_logical_ring_alloc_request(ring, ctx);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 3a6abce..3cc38bd 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -36,6 +36,8 @@
#define RING_CONTEXT_STATUS_PTR(ring) ((ring)->mmio_base+0x3a0)
/* Logical Rings */
+int __must_check intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
+ struct intel_context *ctx);
void intel_logical_ring_stop(struct intel_engine_cs *ring);
void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
int intel_logical_rings_init(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 7fd89e5..635707a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2163,8 +2163,8 @@ int intel_ring_idle(struct intel_engine_cs *ring)
return i915_wait_request(req);
}
-static int
-intel_ring_alloc_request(struct intel_engine_cs *ring)
+int
+intel_ring_alloc_request(struct intel_engine_cs *ring, struct intel_context *ctx)
{
int ret;
struct drm_i915_gem_request *request;
@@ -2229,7 +2229,7 @@ int intel_ring_begin(struct intel_engine_cs *ring,
return ret;
/* Preallocate the olr before touching the ring */
- ret = intel_ring_alloc_request(ring);
+ ret = intel_ring_alloc_request(ring, NULL);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index ffa3724..2fd960a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -392,6 +392,8 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
+int __must_check intel_ring_alloc_request(struct intel_engine_cs *ring,
+ struct intel_context *ctx);
static inline void intel_ring_emit(struct intel_engine_cs *ring,
u32 data)
{
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 06/53] drm/i915: Wrap request allocation with a function pointer
2015-02-19 17:17 ` [PATCH 06/53] drm/i915: Wrap request allocation with a function pointer John.C.Harrison
@ 2015-03-05 15:01 ` Tomas Elf
2015-03-05 16:20 ` Daniel Vetter
0 siblings, 1 reply; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 15:01 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> In order to explicitly manage requests from creation to submission, it is
> necessary to be able to explicitly create them in the first place. This patch
> adds an indirection wrapper to the request creation function so that it can be
> called from generic code without having to worry about execlist vs legacy mode.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 2 ++
> drivers/gpu/drm/i915/i915_gem.c | 2 ++
> drivers/gpu/drm/i915/intel_lrc.c | 6 +++---
> drivers/gpu/drm/i915/intel_lrc.h | 2 ++
> drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
> drivers/gpu/drm/i915/intel_ringbuffer.h | 2 ++
> 6 files changed, 14 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index b350910..87a4a2e 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -1908,6 +1908,8 @@ struct drm_i915_private {
>
> /* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
> struct {
> + int (*alloc_request)(struct intel_engine_cs *ring,
> + struct intel_context *ctx);
> int (*do_execbuf)(struct i915_execbuffer_params *params,
> struct drm_i915_gem_execbuffer2 *args,
> struct list_head *vmas);
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 7a0dc7c..cf959e3 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -4860,11 +4860,13 @@ int i915_gem_init(struct drm_device *dev)
> }
>
> if (!i915.enable_execlists) {
> + dev_priv->gt.alloc_request = intel_ring_alloc_request;
> dev_priv->gt.do_execbuf = i915_gem_ringbuffer_submission;
> dev_priv->gt.init_rings = i915_gem_init_rings;
> dev_priv->gt.cleanup_ring = intel_cleanup_ring_buffer;
> dev_priv->gt.stop_ring = intel_stop_ring_buffer;
> } else {
> + dev_priv->gt.alloc_request = intel_logical_ring_alloc_request;
> dev_priv->gt.do_execbuf = intel_execlists_submission;
> dev_priv->gt.init_rings = intel_logical_rings_init;
> dev_priv->gt.cleanup_ring = intel_logical_ring_cleanup;
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index dc474b4..8628abf 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -856,8 +856,8 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring,
> }
> }
>
> -static int logical_ring_alloc_request(struct intel_engine_cs *ring,
> - struct intel_context *ctx)
> +int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> + struct intel_context *ctx)
> {
> struct drm_i915_gem_request *request;
> struct drm_i915_private *dev_private = ring->dev->dev_private;
> @@ -1066,7 +1066,7 @@ int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
> return ret;
>
> /* Preallocate the olr before touching the ring */
> - ret = logical_ring_alloc_request(ring, ctx);
> + ret = intel_logical_ring_alloc_request(ring, ctx);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
> index 3a6abce..3cc38bd 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.h
> +++ b/drivers/gpu/drm/i915/intel_lrc.h
> @@ -36,6 +36,8 @@
> #define RING_CONTEXT_STATUS_PTR(ring) ((ring)->mmio_base+0x3a0)
>
> /* Logical Rings */
> +int __must_check intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> + struct intel_context *ctx);
> void intel_logical_ring_stop(struct intel_engine_cs *ring);
> void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
> int intel_logical_rings_init(struct drm_device *dev);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 7fd89e5..635707a 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -2163,8 +2163,8 @@ int intel_ring_idle(struct intel_engine_cs *ring)
> return i915_wait_request(req);
> }
>
> -static int
> -intel_ring_alloc_request(struct intel_engine_cs *ring)
> +int
> +intel_ring_alloc_request(struct intel_engine_cs *ring, struct intel_context *ctx)
> {
> int ret;
> struct drm_i915_gem_request *request;
> @@ -2229,7 +2229,7 @@ int intel_ring_begin(struct intel_engine_cs *ring,
> return ret;
>
> /* Preallocate the olr before touching the ring */
> - ret = intel_ring_alloc_request(ring);
> + ret = intel_ring_alloc_request(ring, NULL);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index ffa3724..2fd960a 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -392,6 +392,8 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
>
> int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
> int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
> +int __must_check intel_ring_alloc_request(struct intel_engine_cs *ring,
> + struct intel_context *ctx);
> static inline void intel_ring_emit(struct intel_engine_cs *ring,
> u32 data)
> {
>
I find the whole idea of having virtual functions pointing to public
functions kind of strange since it allows for two ways of accessing the
function. If you look at the way we set up the virtual ring buffer
functions those virtual functions are static and the set up is done in
intel_ringbuffer.c without exposing the functions to the outside world.
Having the set up take place in i915_gem.c forces the virtual functions
to be public, which is not very nice. It would've been a better idea to
pass the virtual function struct for initialization inside intel_lrc.c
and intel_ringbuffer.c, which would have avoided making those functions
public.
I'd like to hear some input from someone else on this on this, like e.g.
Daniel Vetter (since he was a strong proponent of the legacy/execlist
split, which was the underlying reason for this construct in the first
place - not saying that it couldn't have been done in some other way,
though).
Obviously, this is not the fault of the patch at hand and you're just
following the already established pattern of setting up these virtual
functions so I can't fault you for that.
Therefore I'm ok with this change (but not the construct as a whole):
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 06/53] drm/i915: Wrap request allocation with a function pointer
2015-03-05 15:01 ` Tomas Elf
@ 2015-03-05 16:20 ` Daniel Vetter
0 siblings, 0 replies; 234+ messages in thread
From: Daniel Vetter @ 2015-03-05 16:20 UTC (permalink / raw)
To: Tomas Elf; +Cc: Intel-GFX
On Thu, Mar 05, 2015 at 03:01:21PM +0000, Tomas Elf wrote:
> On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> >From: John Harrison <John.C.Harrison@Intel.com>
> >
> >In order to explicitly manage requests from creation to submission, it is
> >necessary to be able to explicitly create them in the first place. This patch
> >adds an indirection wrapper to the request creation function so that it can be
> >called from generic code without having to worry about execlist vs legacy mode.
> >
> >For: VIZ-5115
> >Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> >---
> > drivers/gpu/drm/i915/i915_drv.h | 2 ++
> > drivers/gpu/drm/i915/i915_gem.c | 2 ++
> > drivers/gpu/drm/i915/intel_lrc.c | 6 +++---
> > drivers/gpu/drm/i915/intel_lrc.h | 2 ++
> > drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
> > drivers/gpu/drm/i915/intel_ringbuffer.h | 2 ++
> > 6 files changed, 14 insertions(+), 6 deletions(-)
> >
> >diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> >index b350910..87a4a2e 100644
> >--- a/drivers/gpu/drm/i915/i915_drv.h
> >+++ b/drivers/gpu/drm/i915/i915_drv.h
> >@@ -1908,6 +1908,8 @@ struct drm_i915_private {
> >
> > /* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
> > struct {
> >+ int (*alloc_request)(struct intel_engine_cs *ring,
> >+ struct intel_context *ctx);
> > int (*do_execbuf)(struct i915_execbuffer_params *params,
> > struct drm_i915_gem_execbuffer2 *args,
> > struct list_head *vmas);
> >diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> >index 7a0dc7c..cf959e3 100644
> >--- a/drivers/gpu/drm/i915/i915_gem.c
> >+++ b/drivers/gpu/drm/i915/i915_gem.c
> >@@ -4860,11 +4860,13 @@ int i915_gem_init(struct drm_device *dev)
> > }
> >
> > if (!i915.enable_execlists) {
> >+ dev_priv->gt.alloc_request = intel_ring_alloc_request;
> > dev_priv->gt.do_execbuf = i915_gem_ringbuffer_submission;
> > dev_priv->gt.init_rings = i915_gem_init_rings;
> > dev_priv->gt.cleanup_ring = intel_cleanup_ring_buffer;
> > dev_priv->gt.stop_ring = intel_stop_ring_buffer;
> > } else {
> >+ dev_priv->gt.alloc_request = intel_logical_ring_alloc_request;
> > dev_priv->gt.do_execbuf = intel_execlists_submission;
> > dev_priv->gt.init_rings = intel_logical_rings_init;
> > dev_priv->gt.cleanup_ring = intel_logical_ring_cleanup;
> >diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> >index dc474b4..8628abf 100644
> >--- a/drivers/gpu/drm/i915/intel_lrc.c
> >+++ b/drivers/gpu/drm/i915/intel_lrc.c
> >@@ -856,8 +856,8 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring,
> > }
> > }
> >
> >-static int logical_ring_alloc_request(struct intel_engine_cs *ring,
> >- struct intel_context *ctx)
> >+int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> >+ struct intel_context *ctx)
> > {
> > struct drm_i915_gem_request *request;
> > struct drm_i915_private *dev_private = ring->dev->dev_private;
> >@@ -1066,7 +1066,7 @@ int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
> > return ret;
> >
> > /* Preallocate the olr before touching the ring */
> >- ret = logical_ring_alloc_request(ring, ctx);
> >+ ret = intel_logical_ring_alloc_request(ring, ctx);
> > if (ret)
> > return ret;
> >
> >diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
> >index 3a6abce..3cc38bd 100644
> >--- a/drivers/gpu/drm/i915/intel_lrc.h
> >+++ b/drivers/gpu/drm/i915/intel_lrc.h
> >@@ -36,6 +36,8 @@
> > #define RING_CONTEXT_STATUS_PTR(ring) ((ring)->mmio_base+0x3a0)
> >
> > /* Logical Rings */
> >+int __must_check intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> >+ struct intel_context *ctx);
> > void intel_logical_ring_stop(struct intel_engine_cs *ring);
> > void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
> > int intel_logical_rings_init(struct drm_device *dev);
> >diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> >index 7fd89e5..635707a 100644
> >--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> >+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> >@@ -2163,8 +2163,8 @@ int intel_ring_idle(struct intel_engine_cs *ring)
> > return i915_wait_request(req);
> > }
> >
> >-static int
> >-intel_ring_alloc_request(struct intel_engine_cs *ring)
> >+int
> >+intel_ring_alloc_request(struct intel_engine_cs *ring, struct intel_context *ctx)
> > {
> > int ret;
> > struct drm_i915_gem_request *request;
> >@@ -2229,7 +2229,7 @@ int intel_ring_begin(struct intel_engine_cs *ring,
> > return ret;
> >
> > /* Preallocate the olr before touching the ring */
> >- ret = intel_ring_alloc_request(ring);
> >+ ret = intel_ring_alloc_request(ring, NULL);
> > if (ret)
> > return ret;
> >
> >diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> >index ffa3724..2fd960a 100644
> >--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> >+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> >@@ -392,6 +392,8 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
> >
> > int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
> > int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
> >+int __must_check intel_ring_alloc_request(struct intel_engine_cs *ring,
> >+ struct intel_context *ctx);
> > static inline void intel_ring_emit(struct intel_engine_cs *ring,
> > u32 data)
> > {
> >
>
> I find the whole idea of having virtual functions pointing to public
> functions kind of strange since it allows for two ways of accessing the
> function. If you look at the way we set up the virtual ring buffer functions
> those virtual functions are static and the set up is done in
> intel_ringbuffer.c without exposing the functions to the outside world.
> Having the set up take place in i915_gem.c forces the virtual functions to
> be public, which is not very nice. It would've been a better idea to pass
> the virtual function struct for initialization inside intel_lrc.c and
> intel_ringbuffer.c, which would have avoided making those functions public.
>
> I'd like to hear some input from someone else on this on this, like e.g.
> Daniel Vetter (since he was a strong proponent of the legacy/execlist split,
> which was the underlying reason for this construct in the first place - not
> saying that it couldn't have been done in some other way, though).
Yeah generally the pattern is to have one public _init function per file
which sets up the vfunc tables as needed. Follow-up patches would be
really nice though indeed.
-Daniel
>
> Obviously, this is not the fault of the patch at hand and you're just
> following the already established pattern of setting up these virtual
> functions so I can't fault you for that.
>
> Therefore I'm ok with this change (but not the construct as a whole):
>
> Reviewed-by: Tomas Elf <tomas.elf@intel.com>
>
> Thanks,
> Tomas
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 07/53] drm/i915: Early alloc request in execbuff
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (5 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 06/53] drm/i915: Wrap request allocation with a function pointer John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 15:11 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 08/53] drm/i915: Update alloc_request to return the allocated request John.C.Harrison
` (47 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Start of explicit request management in the execbuffer code path. This patch
adds a call to allocate a request structure before all the actual hardware work
is done. Thus guaranteeing that all that work is tagged by a known request. At
present, nothing further is done with the request, the rest comes later in the
series.
The only noticable change is that failure to get a request (e.g. due to lack of
memory) will be caught earlier in the sequence. It now occurs right at the start
before any un-undoable work has been done.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index ca85803..61471e9 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1356,7 +1356,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
u32 dispatch_flags;
int ret;
- bool need_relocs;
+ bool need_relocs, batch_pinned = false;
if (!i915_gem_check_execbuffer(args))
return -EINVAL;
@@ -1525,10 +1525,16 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
if (ret)
goto err;
+ batch_pinned = true;
params->batch_obj_vm_offset = i915_gem_obj_ggtt_offset(batch_obj);
} else
params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
+ /* Allocate a request for this batch buffer nice and early. */
+ ret = dev_priv->gt.alloc_request(ring, ctx);
+ if (ret)
+ goto err;
+
/*
* Save assorted stuff away to pass through to *_submission().
* NB: This data should be 'persistent' and not local as it will
@@ -1544,15 +1550,16 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
ret = dev_priv->gt.do_execbuf(params, args, &eb->vmas);
+err:
/*
* FIXME: We crucially rely upon the active tracking for the (ppgtt)
* batch vma for correctness. For less ugly and less fragility this
* needs to be adjusted to also track the ggtt batch vma properly as
* active.
*/
- if (dispatch_flags & I915_DISPATCH_SECURE)
+ if (batch_pinned)
i915_gem_object_ggtt_unpin(batch_obj);
-err:
+
/* the request owns the ref now */
i915_gem_context_unreference(ctx);
eb_destroy(eb);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 07/53] drm/i915: Early alloc request in execbuff
2015-02-19 17:17 ` [PATCH 07/53] drm/i915: Early alloc request in execbuff John.C.Harrison
@ 2015-03-05 15:11 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 15:11 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Start of explicit request management in the execbuffer code path. This patch
> adds a call to allocate a request structure before all the actual hardware work
> is done. Thus guaranteeing that all that work is tagged by a known request. At
> present, nothing further is done with the request, the rest comes later in the
> series.
>
> The only noticable change is that failure to get a request (e.g. due to lack of
> memory) will be caught earlier in the sequence. It now occurs right at the start
> before any un-undoable work has been done.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 13 ++++++++++---
> 1 file changed, 10 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index ca85803..61471e9 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1356,7 +1356,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
> u32 dispatch_flags;
> int ret;
> - bool need_relocs;
> + bool need_relocs, batch_pinned = false;
>
> if (!i915_gem_check_execbuffer(args))
> return -EINVAL;
> @@ -1525,10 +1525,16 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> if (ret)
> goto err;
>
> + batch_pinned = true;
> params->batch_obj_vm_offset = i915_gem_obj_ggtt_offset(batch_obj);
> } else
> params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
>
> + /* Allocate a request for this batch buffer nice and early. */
> + ret = dev_priv->gt.alloc_request(ring, ctx);
> + if (ret)
> + goto err;
> +
> /*
> * Save assorted stuff away to pass through to *_submission().
> * NB: This data should be 'persistent' and not local as it will
> @@ -1544,15 +1550,16 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
>
> ret = dev_priv->gt.do_execbuf(params, args, &eb->vmas);
>
> +err:
> /*
> * FIXME: We crucially rely upon the active tracking for the (ppgtt)
> * batch vma for correctness. For less ugly and less fragility this
> * needs to be adjusted to also track the ggtt batch vma properly as
> * active.
> */
> - if (dispatch_flags & I915_DISPATCH_SECURE)
> + if (batch_pinned)
> i915_gem_object_ggtt_unpin(batch_obj);
> -err:
> +
> /* the request owns the ref now */
> i915_gem_context_unreference(ctx);
> eb_destroy(eb);
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 08/53] drm/i915: Update alloc_request to return the allocated request
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (6 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 07/53] drm/i915: Early alloc request in execbuff John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 15:27 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 09/53] drm/i915: Add request to execbuf params and add explicit cleanup John.C.Harrison
` (46 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The alloc_request() function does not actually return the newly allocated
request. Instead, it must be pulled from ring->outstanding_lazy_request. This
patch fixes this so that code can create a request and start using it knowing
exactly which request it actually owns.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 3 ++-
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 ++-
drivers/gpu/drm/i915/intel_lrc.c | 13 +++++++++----
drivers/gpu/drm/i915/intel_lrc.h | 3 ++-
drivers/gpu/drm/i915/intel_ringbuffer.c | 14 ++++++++++----
drivers/gpu/drm/i915/intel_ringbuffer.h | 3 ++-
6 files changed, 27 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 87a4a2e..90223f208 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1909,7 +1909,8 @@ struct drm_i915_private {
/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
struct {
int (*alloc_request)(struct intel_engine_cs *ring,
- struct intel_context *ctx);
+ struct intel_context *ctx,
+ struct drm_i915_gem_request **req_out);
int (*do_execbuf)(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
struct list_head *vmas);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 61471e9..37dcc6f 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1353,6 +1353,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
struct i915_address_space *vm;
struct i915_execbuffer_params params_master; /* XXX: will be removed later */
struct i915_execbuffer_params *params = ¶ms_master;
+ struct drm_i915_gem_request *request;
const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
u32 dispatch_flags;
int ret;
@@ -1531,7 +1532,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
/* Allocate a request for this batch buffer nice and early. */
- ret = dev_priv->gt.alloc_request(ring, ctx);
+ ret = dev_priv->gt.alloc_request(ring, ctx, &request);
if (ret)
goto err;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 8628abf..c3c783f 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -857,13 +857,17 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring,
}
int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+ struct intel_context *ctx,
+ struct drm_i915_gem_request **req_out)
{
struct drm_i915_gem_request *request;
struct drm_i915_private *dev_private = ring->dev->dev_private;
int ret;
- if (ring->outstanding_lazy_request)
+ if (!req_out)
+ return -EINVAL;
+
+ if ((*req_out = ring->outstanding_lazy_request) != NULL)
return 0;
request = kzalloc(sizeof(*request), GFP_KERNEL);
@@ -898,7 +902,7 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
i915_gem_context_reference(request->ctx);
request->ringbuf = ctx->engine[ring->id].ringbuf;
- ring->outstanding_lazy_request = request;
+ *req_out = ring->outstanding_lazy_request = request;
return 0;
}
@@ -1051,6 +1055,7 @@ static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
struct intel_context *ctx, int num_dwords)
{
+ struct drm_i915_gem_request *req;
struct intel_engine_cs *ring = ringbuf->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1066,7 +1071,7 @@ int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
return ret;
/* Preallocate the olr before touching the ring */
- ret = intel_logical_ring_alloc_request(ring, ctx);
+ ret = intel_logical_ring_alloc_request(ring, ctx, &req);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 3cc38bd..77de8ac 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -37,7 +37,8 @@
/* Logical Rings */
int __must_check intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
- struct intel_context *ctx);
+ struct intel_context *ctx,
+ struct drm_i915_gem_request **req_out);
void intel_logical_ring_stop(struct intel_engine_cs *ring);
void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
int intel_logical_rings_init(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 635707a..1a9f884 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2164,13 +2164,18 @@ int intel_ring_idle(struct intel_engine_cs *ring)
}
int
-intel_ring_alloc_request(struct intel_engine_cs *ring, struct intel_context *ctx)
+intel_ring_alloc_request(struct intel_engine_cs *ring,
+ struct intel_context *ctx,
+ struct drm_i915_gem_request **req_out)
{
int ret;
struct drm_i915_gem_request *request;
struct drm_i915_private *dev_private = ring->dev->dev_private;
- if (ring->outstanding_lazy_request)
+ if (!req_out)
+ return -EINVAL;
+
+ if ((*req_out = ring->outstanding_lazy_request) != NULL)
return 0;
request = kzalloc(sizeof(*request), GFP_KERNEL);
@@ -2188,7 +2193,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring, struct intel_context *ctx
return ret;
}
- ring->outstanding_lazy_request = request;
+ *req_out = ring->outstanding_lazy_request = request;
return 0;
}
@@ -2216,6 +2221,7 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring,
int intel_ring_begin(struct intel_engine_cs *ring,
int num_dwords)
{
+ struct drm_i915_gem_request *req;
struct drm_i915_private *dev_priv = ring->dev->dev_private;
int ret;
@@ -2229,7 +2235,7 @@ int intel_ring_begin(struct intel_engine_cs *ring,
return ret;
/* Preallocate the olr before touching the ring */
- ret = intel_ring_alloc_request(ring, NULL);
+ ret = intel_ring_alloc_request(ring, NULL, &req);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 2fd960a..4f8a14a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -393,7 +393,8 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
int __must_check intel_ring_alloc_request(struct intel_engine_cs *ring,
- struct intel_context *ctx);
+ struct intel_context *ctx,
+ struct drm_i915_gem_request **req_out);
static inline void intel_ring_emit(struct intel_engine_cs *ring,
u32 data)
{
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 08/53] drm/i915: Update alloc_request to return the allocated request
2015-02-19 17:17 ` [PATCH 08/53] drm/i915: Update alloc_request to return the allocated request John.C.Harrison
@ 2015-03-05 15:27 ` Tomas Elf
2015-03-05 15:46 ` John Harrison
0 siblings, 1 reply; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 15:27 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The alloc_request() function does not actually return the newly allocated
> request. Instead, it must be pulled from ring->outstanding_lazy_request. This
> patch fixes this so that code can create a request and start using it knowing
> exactly which request it actually owns.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 3 ++-
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 ++-
> drivers/gpu/drm/i915/intel_lrc.c | 13 +++++++++----
> drivers/gpu/drm/i915/intel_lrc.h | 3 ++-
> drivers/gpu/drm/i915/intel_ringbuffer.c | 14 ++++++++++----
> drivers/gpu/drm/i915/intel_ringbuffer.h | 3 ++-
> 6 files changed, 27 insertions(+), 12 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 87a4a2e..90223f208 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -1909,7 +1909,8 @@ struct drm_i915_private {
> /* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
> struct {
> int (*alloc_request)(struct intel_engine_cs *ring,
> - struct intel_context *ctx);
> + struct intel_context *ctx,
> + struct drm_i915_gem_request **req_out);
> int (*do_execbuf)(struct i915_execbuffer_params *params,
> struct drm_i915_gem_execbuffer2 *args,
> struct list_head *vmas);
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 61471e9..37dcc6f 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1353,6 +1353,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> struct i915_address_space *vm;
> struct i915_execbuffer_params params_master; /* XXX: will be removed later */
> struct i915_execbuffer_params *params = ¶ms_master;
> + struct drm_i915_gem_request *request;
Please initialize request to NULL. If you accidentally dereference it
before it is allocated (seeing as the allocation is several pages down
from here) you get a null pointer exception, which is a clear indication
that you did something stupid. Otherwise it's not clear what will happen
(sure, page fault, but null pointer exception is a better failure
indication).
Thanks,
Tomas
> const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
> u32 dispatch_flags;
> int ret;
> @@ -1531,7 +1532,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
>
> /* Allocate a request for this batch buffer nice and early. */
> - ret = dev_priv->gt.alloc_request(ring, ctx);
> + ret = dev_priv->gt.alloc_request(ring, ctx, &request);
> if (ret)
> goto err;
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 8628abf..c3c783f 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -857,13 +857,17 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring,
> }
>
> int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> - struct intel_context *ctx)
> + struct intel_context *ctx,
> + struct drm_i915_gem_request **req_out)
> {
> struct drm_i915_gem_request *request;
> struct drm_i915_private *dev_private = ring->dev->dev_private;
> int ret;
>
> - if (ring->outstanding_lazy_request)
> + if (!req_out)
> + return -EINVAL;
> +
> + if ((*req_out = ring->outstanding_lazy_request) != NULL)
> return 0;
>
> request = kzalloc(sizeof(*request), GFP_KERNEL);
> @@ -898,7 +902,7 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> i915_gem_context_reference(request->ctx);
> request->ringbuf = ctx->engine[ring->id].ringbuf;
>
> - ring->outstanding_lazy_request = request;
> + *req_out = ring->outstanding_lazy_request = request;
> return 0;
> }
>
> @@ -1051,6 +1055,7 @@ static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
> int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
> struct intel_context *ctx, int num_dwords)
> {
> + struct drm_i915_gem_request *req;
> struct intel_engine_cs *ring = ringbuf->ring;
> struct drm_device *dev = ring->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -1066,7 +1071,7 @@ int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
> return ret;
>
> /* Preallocate the olr before touching the ring */
> - ret = intel_logical_ring_alloc_request(ring, ctx);
> + ret = intel_logical_ring_alloc_request(ring, ctx, &req);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
> index 3cc38bd..77de8ac 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.h
> +++ b/drivers/gpu/drm/i915/intel_lrc.h
> @@ -37,7 +37,8 @@
>
> /* Logical Rings */
> int __must_check intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> - struct intel_context *ctx);
> + struct intel_context *ctx,
> + struct drm_i915_gem_request **req_out);
> void intel_logical_ring_stop(struct intel_engine_cs *ring);
> void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
> int intel_logical_rings_init(struct drm_device *dev);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 635707a..1a9f884 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -2164,13 +2164,18 @@ int intel_ring_idle(struct intel_engine_cs *ring)
> }
>
> int
> -intel_ring_alloc_request(struct intel_engine_cs *ring, struct intel_context *ctx)
> +intel_ring_alloc_request(struct intel_engine_cs *ring,
> + struct intel_context *ctx,
> + struct drm_i915_gem_request **req_out)
> {
> int ret;
> struct drm_i915_gem_request *request;
> struct drm_i915_private *dev_private = ring->dev->dev_private;
>
> - if (ring->outstanding_lazy_request)
> + if (!req_out)
> + return -EINVAL;
> +
> + if ((*req_out = ring->outstanding_lazy_request) != NULL)
> return 0;
>
> request = kzalloc(sizeof(*request), GFP_KERNEL);
> @@ -2188,7 +2193,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring, struct intel_context *ctx
> return ret;
> }
>
> - ring->outstanding_lazy_request = request;
> + *req_out = ring->outstanding_lazy_request = request;
> return 0;
> }
>
> @@ -2216,6 +2221,7 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring,
> int intel_ring_begin(struct intel_engine_cs *ring,
> int num_dwords)
> {
> + struct drm_i915_gem_request *req;
> struct drm_i915_private *dev_priv = ring->dev->dev_private;
> int ret;
>
> @@ -2229,7 +2235,7 @@ int intel_ring_begin(struct intel_engine_cs *ring,
> return ret;
>
> /* Preallocate the olr before touching the ring */
> - ret = intel_ring_alloc_request(ring, NULL);
> + ret = intel_ring_alloc_request(ring, NULL, &req);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 2fd960a..4f8a14a 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -393,7 +393,8 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
> int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
> int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
> int __must_check intel_ring_alloc_request(struct intel_engine_cs *ring,
> - struct intel_context *ctx);
> + struct intel_context *ctx,
> + struct drm_i915_gem_request **req_out);
> static inline void intel_ring_emit(struct intel_engine_cs *ring,
> u32 data)
> {
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 08/53] drm/i915: Update alloc_request to return the allocated request
2015-03-05 15:27 ` Tomas Elf
@ 2015-03-05 15:46 ` John Harrison
2015-03-05 20:13 ` Tomas Elf
0 siblings, 1 reply; 234+ messages in thread
From: John Harrison @ 2015-03-05 15:46 UTC (permalink / raw)
To: Tomas Elf, Intel-GFX
On 05/03/2015 15:27, Tomas Elf wrote:
> On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
>> From: John Harrison <John.C.Harrison@Intel.com>
>>
>> The alloc_request() function does not actually return the newly
>> allocated
>> request. Instead, it must be pulled from
>> ring->outstanding_lazy_request. This
>> patch fixes this so that code can create a request and start using it
>> knowing
>> exactly which request it actually owns.
>>
>> For: VIZ-5115
>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
>> ---
>> drivers/gpu/drm/i915/i915_drv.h | 3 ++-
>> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 ++-
>> drivers/gpu/drm/i915/intel_lrc.c | 13 +++++++++----
>> drivers/gpu/drm/i915/intel_lrc.h | 3 ++-
>> drivers/gpu/drm/i915/intel_ringbuffer.c | 14 ++++++++++----
>> drivers/gpu/drm/i915/intel_ringbuffer.h | 3 ++-
>> 6 files changed, 27 insertions(+), 12 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/i915_drv.h
>> b/drivers/gpu/drm/i915/i915_drv.h
>> index 87a4a2e..90223f208 100644
>> --- a/drivers/gpu/drm/i915/i915_drv.h
>> +++ b/drivers/gpu/drm/i915/i915_drv.h
>> @@ -1909,7 +1909,8 @@ struct drm_i915_private {
>> /* Abstract the submission mechanism (legacy ringbuffer or
>> execlists) away */
>> struct {
>> int (*alloc_request)(struct intel_engine_cs *ring,
>> - struct intel_context *ctx);
>> + struct intel_context *ctx,
>> + struct drm_i915_gem_request **req_out);
>> int (*do_execbuf)(struct i915_execbuffer_params *params,
>> struct drm_i915_gem_execbuffer2 *args,
>> struct list_head *vmas);
>> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>> b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>> index 61471e9..37dcc6f 100644
>> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>> @@ -1353,6 +1353,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>> void *data,
>> struct i915_address_space *vm;
>> struct i915_execbuffer_params params_master; /* XXX: will be
>> removed later */
>> struct i915_execbuffer_params *params = ¶ms_master;
>> + struct drm_i915_gem_request *request;
>
> Please initialize request to NULL. If you accidentally dereference it
> before it is allocated (seeing as the allocation is several pages down
> from here) you get a null pointer exception, which is a clear
> indication that you did something stupid. Otherwise it's not clear
> what will happen (sure, page fault, but null pointer exception is a
> better failure indication).
That should generate a 'use before assignment' compiler warning.
>
> Thanks,
> Tomas
>
>> const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
>> u32 dispatch_flags;
>> int ret;
>> @@ -1531,7 +1532,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>> void *data,
>> params->batch_obj_vm_offset =
>> i915_gem_obj_offset(batch_obj, vm);
>>
>> /* Allocate a request for this batch buffer nice and early. */
>> - ret = dev_priv->gt.alloc_request(ring, ctx);
>> + ret = dev_priv->gt.alloc_request(ring, ctx, &request);
>> if (ret)
>> goto err;
>>
>> diff --git a/drivers/gpu/drm/i915/intel_lrc.c
>> b/drivers/gpu/drm/i915/intel_lrc.c
>> index 8628abf..c3c783f 100644
>> --- a/drivers/gpu/drm/i915/intel_lrc.c
>> +++ b/drivers/gpu/drm/i915/intel_lrc.c
>> @@ -857,13 +857,17 @@ void intel_lr_context_unpin(struct
>> intel_engine_cs *ring,
>> }
>>
>> int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
>> - struct intel_context *ctx)
>> + struct intel_context *ctx,
>> + struct drm_i915_gem_request **req_out)
>> {
>> struct drm_i915_gem_request *request;
>> struct drm_i915_private *dev_private = ring->dev->dev_private;
>> int ret;
>>
>> - if (ring->outstanding_lazy_request)
>> + if (!req_out)
>> + return -EINVAL;
>> +
>> + if ((*req_out = ring->outstanding_lazy_request) != NULL)
>> return 0;
>>
>> request = kzalloc(sizeof(*request), GFP_KERNEL);
>> @@ -898,7 +902,7 @@ int intel_logical_ring_alloc_request(struct
>> intel_engine_cs *ring,
>> i915_gem_context_reference(request->ctx);
>> request->ringbuf = ctx->engine[ring->id].ringbuf;
>>
>> - ring->outstanding_lazy_request = request;
>> + *req_out = ring->outstanding_lazy_request = request;
>> return 0;
>> }
>>
>> @@ -1051,6 +1055,7 @@ static int logical_ring_prepare(struct
>> intel_ringbuffer *ringbuf,
>> int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
>> struct intel_context *ctx, int num_dwords)
>> {
>> + struct drm_i915_gem_request *req;
>> struct intel_engine_cs *ring = ringbuf->ring;
>> struct drm_device *dev = ring->dev;
>> struct drm_i915_private *dev_priv = dev->dev_private;
>> @@ -1066,7 +1071,7 @@ int intel_logical_ring_begin(struct
>> intel_ringbuffer *ringbuf,
>> return ret;
>>
>> /* Preallocate the olr before touching the ring */
>> - ret = intel_logical_ring_alloc_request(ring, ctx);
>> + ret = intel_logical_ring_alloc_request(ring, ctx, &req);
>> if (ret)
>> return ret;
>>
>> diff --git a/drivers/gpu/drm/i915/intel_lrc.h
>> b/drivers/gpu/drm/i915/intel_lrc.h
>> index 3cc38bd..77de8ac 100644
>> --- a/drivers/gpu/drm/i915/intel_lrc.h
>> +++ b/drivers/gpu/drm/i915/intel_lrc.h
>> @@ -37,7 +37,8 @@
>>
>> /* Logical Rings */
>> int __must_check intel_logical_ring_alloc_request(struct
>> intel_engine_cs *ring,
>> - struct intel_context *ctx);
>> + struct intel_context *ctx,
>> + struct drm_i915_gem_request **req_out);
>> void intel_logical_ring_stop(struct intel_engine_cs *ring);
>> void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
>> int intel_logical_rings_init(struct drm_device *dev);
>> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c
>> b/drivers/gpu/drm/i915/intel_ringbuffer.c
>> index 635707a..1a9f884 100644
>> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
>> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
>> @@ -2164,13 +2164,18 @@ int intel_ring_idle(struct intel_engine_cs
>> *ring)
>> }
>>
>> int
>> -intel_ring_alloc_request(struct intel_engine_cs *ring, struct
>> intel_context *ctx)
>> +intel_ring_alloc_request(struct intel_engine_cs *ring,
>> + struct intel_context *ctx,
>> + struct drm_i915_gem_request **req_out)
>> {
>> int ret;
>> struct drm_i915_gem_request *request;
>> struct drm_i915_private *dev_private = ring->dev->dev_private;
>>
>> - if (ring->outstanding_lazy_request)
>> + if (!req_out)
>> + return -EINVAL;
>> +
>> + if ((*req_out = ring->outstanding_lazy_request) != NULL)
>> return 0;
>>
>> request = kzalloc(sizeof(*request), GFP_KERNEL);
>> @@ -2188,7 +2193,7 @@ intel_ring_alloc_request(struct intel_engine_cs
>> *ring, struct intel_context *ctx
>> return ret;
>> }
>>
>> - ring->outstanding_lazy_request = request;
>> + *req_out = ring->outstanding_lazy_request = request;
>> return 0;
>> }
>>
>> @@ -2216,6 +2221,7 @@ static int __intel_ring_prepare(struct
>> intel_engine_cs *ring,
>> int intel_ring_begin(struct intel_engine_cs *ring,
>> int num_dwords)
>> {
>> + struct drm_i915_gem_request *req;
>> struct drm_i915_private *dev_priv = ring->dev->dev_private;
>> int ret;
>>
>> @@ -2229,7 +2235,7 @@ int intel_ring_begin(struct intel_engine_cs *ring,
>> return ret;
>>
>> /* Preallocate the olr before touching the ring */
>> - ret = intel_ring_alloc_request(ring, NULL);
>> + ret = intel_ring_alloc_request(ring, NULL, &req);
>> if (ret)
>> return ret;
>>
>> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h
>> b/drivers/gpu/drm/i915/intel_ringbuffer.h
>> index 2fd960a..4f8a14a 100644
>> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
>> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
>> @@ -393,7 +393,8 @@ void intel_cleanup_ring_buffer(struct
>> intel_engine_cs *ring);
>> int __must_check intel_ring_begin(struct intel_engine_cs *ring, int
>> n);
>> int __must_check intel_ring_cacheline_align(struct intel_engine_cs
>> *ring);
>> int __must_check intel_ring_alloc_request(struct intel_engine_cs
>> *ring,
>> - struct intel_context *ctx);
>> + struct intel_context *ctx,
>> + struct drm_i915_gem_request **req_out);
>> static inline void intel_ring_emit(struct intel_engine_cs *ring,
>> u32 data)
>> {
>>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 08/53] drm/i915: Update alloc_request to return the allocated request
2015-03-05 15:46 ` John Harrison
@ 2015-03-05 20:13 ` Tomas Elf
2015-03-06 16:18 ` Daniel Vetter
0 siblings, 1 reply; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 20:13 UTC (permalink / raw)
To: John Harrison, Intel-GFX
On 05/03/2015 15:46, John Harrison wrote:
> On 05/03/2015 15:27, Tomas Elf wrote:
>> On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
>>> From: John Harrison <John.C.Harrison@Intel.com>
>>>
>>> The alloc_request() function does not actually return the newly
>>> allocated
>>> request. Instead, it must be pulled from
>>> ring->outstanding_lazy_request. This
>>> patch fixes this so that code can create a request and start using it
>>> knowing
>>> exactly which request it actually owns.
>>>
>>> For: VIZ-5115
>>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
>>> ---
>>> drivers/gpu/drm/i915/i915_drv.h | 3 ++-
>>> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 ++-
>>> drivers/gpu/drm/i915/intel_lrc.c | 13 +++++++++----
>>> drivers/gpu/drm/i915/intel_lrc.h | 3 ++-
>>> drivers/gpu/drm/i915/intel_ringbuffer.c | 14 ++++++++++----
>>> drivers/gpu/drm/i915/intel_ringbuffer.h | 3 ++-
>>> 6 files changed, 27 insertions(+), 12 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/i915/i915_drv.h
>>> b/drivers/gpu/drm/i915/i915_drv.h
>>> index 87a4a2e..90223f208 100644
>>> --- a/drivers/gpu/drm/i915/i915_drv.h
>>> +++ b/drivers/gpu/drm/i915/i915_drv.h
>>> @@ -1909,7 +1909,8 @@ struct drm_i915_private {
>>> /* Abstract the submission mechanism (legacy ringbuffer or
>>> execlists) away */
>>> struct {
>>> int (*alloc_request)(struct intel_engine_cs *ring,
>>> - struct intel_context *ctx);
>>> + struct intel_context *ctx,
>>> + struct drm_i915_gem_request **req_out);
>>> int (*do_execbuf)(struct i915_execbuffer_params *params,
>>> struct drm_i915_gem_execbuffer2 *args,
>>> struct list_head *vmas);
>>> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>> b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>> index 61471e9..37dcc6f 100644
>>> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>> @@ -1353,6 +1353,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>>> void *data,
>>> struct i915_address_space *vm;
>>> struct i915_execbuffer_params params_master; /* XXX: will be
>>> removed later */
>>> struct i915_execbuffer_params *params = ¶ms_master;
>>> + struct drm_i915_gem_request *request;
>>
>> Please initialize request to NULL. If you accidentally dereference it
>> before it is allocated (seeing as the allocation is several pages down
>> from here) you get a null pointer exception, which is a clear
>> indication that you did something stupid. Otherwise it's not clear
>> what will happen (sure, page fault, but null pointer exception is a
>> better failure indication).
>
> That should generate a 'use before assignment' compiler warning.
That assumes that the developer in question isn't too busy hacking to
check for warnings (in all honesty that developer probably would've been
me ;)). Sure, you should always check for warnings but if we can save
this developer some time by giving them a clear run-time indication
aside from the compile-time warning then that would not be a bad thing.
I've been there myself a few times and I know times in the past where
this would've saved me the time it takes to rebuild and redeploy the
kernel once.
Thanks,
Tomas
>
>>
>> Thanks,
>> Tomas
>>
>>> const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
>>> u32 dispatch_flags;
>>> int ret;
>>> @@ -1531,7 +1532,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>>> void *data,
>>> params->batch_obj_vm_offset =
>>> i915_gem_obj_offset(batch_obj, vm);
>>>
>>> /* Allocate a request for this batch buffer nice and early. */
>>> - ret = dev_priv->gt.alloc_request(ring, ctx);
>>> + ret = dev_priv->gt.alloc_request(ring, ctx, &request);
>>> if (ret)
>>> goto err;
>>>
>>> diff --git a/drivers/gpu/drm/i915/intel_lrc.c
>>> b/drivers/gpu/drm/i915/intel_lrc.c
>>> index 8628abf..c3c783f 100644
>>> --- a/drivers/gpu/drm/i915/intel_lrc.c
>>> +++ b/drivers/gpu/drm/i915/intel_lrc.c
>>> @@ -857,13 +857,17 @@ void intel_lr_context_unpin(struct
>>> intel_engine_cs *ring,
>>> }
>>>
>>> int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
>>> - struct intel_context *ctx)
>>> + struct intel_context *ctx,
>>> + struct drm_i915_gem_request **req_out)
>>> {
>>> struct drm_i915_gem_request *request;
>>> struct drm_i915_private *dev_private = ring->dev->dev_private;
>>> int ret;
>>>
>>> - if (ring->outstanding_lazy_request)
>>> + if (!req_out)
>>> + return -EINVAL;
>>> +
>>> + if ((*req_out = ring->outstanding_lazy_request) != NULL)
>>> return 0;
>>>
>>> request = kzalloc(sizeof(*request), GFP_KERNEL);
>>> @@ -898,7 +902,7 @@ int intel_logical_ring_alloc_request(struct
>>> intel_engine_cs *ring,
>>> i915_gem_context_reference(request->ctx);
>>> request->ringbuf = ctx->engine[ring->id].ringbuf;
>>>
>>> - ring->outstanding_lazy_request = request;
>>> + *req_out = ring->outstanding_lazy_request = request;
>>> return 0;
>>> }
>>>
>>> @@ -1051,6 +1055,7 @@ static int logical_ring_prepare(struct
>>> intel_ringbuffer *ringbuf,
>>> int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
>>> struct intel_context *ctx, int num_dwords)
>>> {
>>> + struct drm_i915_gem_request *req;
>>> struct intel_engine_cs *ring = ringbuf->ring;
>>> struct drm_device *dev = ring->dev;
>>> struct drm_i915_private *dev_priv = dev->dev_private;
>>> @@ -1066,7 +1071,7 @@ int intel_logical_ring_begin(struct
>>> intel_ringbuffer *ringbuf,
>>> return ret;
>>>
>>> /* Preallocate the olr before touching the ring */
>>> - ret = intel_logical_ring_alloc_request(ring, ctx);
>>> + ret = intel_logical_ring_alloc_request(ring, ctx, &req);
>>> if (ret)
>>> return ret;
>>>
>>> diff --git a/drivers/gpu/drm/i915/intel_lrc.h
>>> b/drivers/gpu/drm/i915/intel_lrc.h
>>> index 3cc38bd..77de8ac 100644
>>> --- a/drivers/gpu/drm/i915/intel_lrc.h
>>> +++ b/drivers/gpu/drm/i915/intel_lrc.h
>>> @@ -37,7 +37,8 @@
>>>
>>> /* Logical Rings */
>>> int __must_check intel_logical_ring_alloc_request(struct
>>> intel_engine_cs *ring,
>>> - struct intel_context *ctx);
>>> + struct intel_context *ctx,
>>> + struct drm_i915_gem_request **req_out);
>>> void intel_logical_ring_stop(struct intel_engine_cs *ring);
>>> void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
>>> int intel_logical_rings_init(struct drm_device *dev);
>>> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c
>>> b/drivers/gpu/drm/i915/intel_ringbuffer.c
>>> index 635707a..1a9f884 100644
>>> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
>>> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
>>> @@ -2164,13 +2164,18 @@ int intel_ring_idle(struct intel_engine_cs
>>> *ring)
>>> }
>>>
>>> int
>>> -intel_ring_alloc_request(struct intel_engine_cs *ring, struct
>>> intel_context *ctx)
>>> +intel_ring_alloc_request(struct intel_engine_cs *ring,
>>> + struct intel_context *ctx,
>>> + struct drm_i915_gem_request **req_out)
>>> {
>>> int ret;
>>> struct drm_i915_gem_request *request;
>>> struct drm_i915_private *dev_private = ring->dev->dev_private;
>>>
>>> - if (ring->outstanding_lazy_request)
>>> + if (!req_out)
>>> + return -EINVAL;
>>> +
>>> + if ((*req_out = ring->outstanding_lazy_request) != NULL)
>>> return 0;
>>>
>>> request = kzalloc(sizeof(*request), GFP_KERNEL);
>>> @@ -2188,7 +2193,7 @@ intel_ring_alloc_request(struct intel_engine_cs
>>> *ring, struct intel_context *ctx
>>> return ret;
>>> }
>>>
>>> - ring->outstanding_lazy_request = request;
>>> + *req_out = ring->outstanding_lazy_request = request;
>>> return 0;
>>> }
>>>
>>> @@ -2216,6 +2221,7 @@ static int __intel_ring_prepare(struct
>>> intel_engine_cs *ring,
>>> int intel_ring_begin(struct intel_engine_cs *ring,
>>> int num_dwords)
>>> {
>>> + struct drm_i915_gem_request *req;
>>> struct drm_i915_private *dev_priv = ring->dev->dev_private;
>>> int ret;
>>>
>>> @@ -2229,7 +2235,7 @@ int intel_ring_begin(struct intel_engine_cs *ring,
>>> return ret;
>>>
>>> /* Preallocate the olr before touching the ring */
>>> - ret = intel_ring_alloc_request(ring, NULL);
>>> + ret = intel_ring_alloc_request(ring, NULL, &req);
>>> if (ret)
>>> return ret;
>>>
>>> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h
>>> b/drivers/gpu/drm/i915/intel_ringbuffer.h
>>> index 2fd960a..4f8a14a 100644
>>> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
>>> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
>>> @@ -393,7 +393,8 @@ void intel_cleanup_ring_buffer(struct
>>> intel_engine_cs *ring);
>>> int __must_check intel_ring_begin(struct intel_engine_cs *ring, int
>>> n);
>>> int __must_check intel_ring_cacheline_align(struct intel_engine_cs
>>> *ring);
>>> int __must_check intel_ring_alloc_request(struct intel_engine_cs
>>> *ring,
>>> - struct intel_context *ctx);
>>> + struct intel_context *ctx,
>>> + struct drm_i915_gem_request **req_out);
>>> static inline void intel_ring_emit(struct intel_engine_cs *ring,
>>> u32 data)
>>> {
>>>
>>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 08/53] drm/i915: Update alloc_request to return the allocated request
2015-03-05 20:13 ` Tomas Elf
@ 2015-03-06 16:18 ` Daniel Vetter
2015-03-06 17:36 ` John Harrison
0 siblings, 1 reply; 234+ messages in thread
From: Daniel Vetter @ 2015-03-06 16:18 UTC (permalink / raw)
To: Tomas Elf; +Cc: Intel-GFX
On Thu, Mar 05, 2015 at 08:13:07PM +0000, Tomas Elf wrote:
> On 05/03/2015 15:46, John Harrison wrote:
> >On 05/03/2015 15:27, Tomas Elf wrote:
> >>On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> >>>From: John Harrison <John.C.Harrison@Intel.com>
> >>>
> >>>The alloc_request() function does not actually return the newly
> >>>allocated
> >>>request. Instead, it must be pulled from
> >>>ring->outstanding_lazy_request. This
> >>>patch fixes this so that code can create a request and start using it
> >>>knowing
> >>>exactly which request it actually owns.
> >>>
> >>>For: VIZ-5115
> >>>Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> >>>---
> >>> drivers/gpu/drm/i915/i915_drv.h | 3 ++-
> >>> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 ++-
> >>> drivers/gpu/drm/i915/intel_lrc.c | 13 +++++++++----
> >>> drivers/gpu/drm/i915/intel_lrc.h | 3 ++-
> >>> drivers/gpu/drm/i915/intel_ringbuffer.c | 14 ++++++++++----
> >>> drivers/gpu/drm/i915/intel_ringbuffer.h | 3 ++-
> >>> 6 files changed, 27 insertions(+), 12 deletions(-)
> >>>
> >>>diff --git a/drivers/gpu/drm/i915/i915_drv.h
> >>>b/drivers/gpu/drm/i915/i915_drv.h
> >>>index 87a4a2e..90223f208 100644
> >>>--- a/drivers/gpu/drm/i915/i915_drv.h
> >>>+++ b/drivers/gpu/drm/i915/i915_drv.h
> >>>@@ -1909,7 +1909,8 @@ struct drm_i915_private {
> >>> /* Abstract the submission mechanism (legacy ringbuffer or
> >>>execlists) away */
> >>> struct {
> >>> int (*alloc_request)(struct intel_engine_cs *ring,
> >>>- struct intel_context *ctx);
> >>>+ struct intel_context *ctx,
> >>>+ struct drm_i915_gem_request **req_out);
> >>> int (*do_execbuf)(struct i915_execbuffer_params *params,
> >>> struct drm_i915_gem_execbuffer2 *args,
> >>> struct list_head *vmas);
> >>>diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> >>>b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> >>>index 61471e9..37dcc6f 100644
> >>>--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> >>>+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> >>>@@ -1353,6 +1353,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
> >>>void *data,
> >>> struct i915_address_space *vm;
> >>> struct i915_execbuffer_params params_master; /* XXX: will be
> >>>removed later */
> >>> struct i915_execbuffer_params *params = ¶ms_master;
> >>>+ struct drm_i915_gem_request *request;
> >>
> >>Please initialize request to NULL. If you accidentally dereference it
> >>before it is allocated (seeing as the allocation is several pages down
> >>from here) you get a null pointer exception, which is a clear
> >>indication that you did something stupid. Otherwise it's not clear
> >>what will happen (sure, page fault, but null pointer exception is a
> >>better failure indication).
> >
> >That should generate a 'use before assignment' compiler warning.
>
> That assumes that the developer in question isn't too busy hacking to check
> for warnings (in all honesty that developer probably would've been me ;)).
> Sure, you should always check for warnings but if we can save this developer
> some time by giving them a clear run-time indication aside from the
> compile-time warning then that would not be a bad thing. I've been there
> myself a few times and I know times in the past where this would've saved me
> the time it takes to rebuild and redeploy the kernel once.
kbuild is _very_ good at catching and reporting these. And the linux
kernel generally has a 0 warnings rule, which means even when it slips
through a lot of developers will get mad at me for not spotting it.
I think relying upon gcc to do its job here is safe enough. We only
initialize stack variables if it's really needed, or if gcc is too dense
to figure it out itself.
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 08/53] drm/i915: Update alloc_request to return the allocated request
2015-03-06 16:18 ` Daniel Vetter
@ 2015-03-06 17:36 ` John Harrison
2015-03-06 20:17 ` Tomas Elf
0 siblings, 1 reply; 234+ messages in thread
From: John Harrison @ 2015-03-06 17:36 UTC (permalink / raw)
To: Daniel Vetter, Tomas Elf; +Cc: Intel-GFX
On 06/03/2015 16:18, Daniel Vetter wrote:
> On Thu, Mar 05, 2015 at 08:13:07PM +0000, Tomas Elf wrote:
>> On 05/03/2015 15:46, John Harrison wrote:
>>> On 05/03/2015 15:27, Tomas Elf wrote:
>>>> On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
>>>>> From: John Harrison <John.C.Harrison@Intel.com>
>>>>>
>>>>> The alloc_request() function does not actually return the newly
>>>>> allocated
>>>>> request. Instead, it must be pulled from
>>>>> ring->outstanding_lazy_request. This
>>>>> patch fixes this so that code can create a request and start using it
>>>>> knowing
>>>>> exactly which request it actually owns.
>>>>>
>>>>> For: VIZ-5115
>>>>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
>>>>> ---
>>>>> drivers/gpu/drm/i915/i915_drv.h | 3 ++-
>>>>> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 ++-
>>>>> drivers/gpu/drm/i915/intel_lrc.c | 13 +++++++++----
>>>>> drivers/gpu/drm/i915/intel_lrc.h | 3 ++-
>>>>> drivers/gpu/drm/i915/intel_ringbuffer.c | 14 ++++++++++----
>>>>> drivers/gpu/drm/i915/intel_ringbuffer.h | 3 ++-
>>>>> 6 files changed, 27 insertions(+), 12 deletions(-)
>>>>>
>>>>> diff --git a/drivers/gpu/drm/i915/i915_drv.h
>>>>> b/drivers/gpu/drm/i915/i915_drv.h
>>>>> index 87a4a2e..90223f208 100644
>>>>> --- a/drivers/gpu/drm/i915/i915_drv.h
>>>>> +++ b/drivers/gpu/drm/i915/i915_drv.h
>>>>> @@ -1909,7 +1909,8 @@ struct drm_i915_private {
>>>>> /* Abstract the submission mechanism (legacy ringbuffer or
>>>>> execlists) away */
>>>>> struct {
>>>>> int (*alloc_request)(struct intel_engine_cs *ring,
>>>>> - struct intel_context *ctx);
>>>>> + struct intel_context *ctx,
>>>>> + struct drm_i915_gem_request **req_out);
>>>>> int (*do_execbuf)(struct i915_execbuffer_params *params,
>>>>> struct drm_i915_gem_execbuffer2 *args,
>>>>> struct list_head *vmas);
>>>>> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>>>> b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>>>> index 61471e9..37dcc6f 100644
>>>>> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>>>> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>>>> @@ -1353,6 +1353,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>>>>> void *data,
>>>>> struct i915_address_space *vm;
>>>>> struct i915_execbuffer_params params_master; /* XXX: will be
>>>>> removed later */
>>>>> struct i915_execbuffer_params *params = ¶ms_master;
>>>>> + struct drm_i915_gem_request *request;
>>>> Please initialize request to NULL. If you accidentally dereference it
>>>> before it is allocated (seeing as the allocation is several pages down
>>> >from here) you get a null pointer exception, which is a clear
>>>> indication that you did something stupid. Otherwise it's not clear
>>>> what will happen (sure, page fault, but null pointer exception is a
>>>> better failure indication).
>>> That should generate a 'use before assignment' compiler warning.
>> That assumes that the developer in question isn't too busy hacking to check
>> for warnings (in all honesty that developer probably would've been me ;)).
>> Sure, you should always check for warnings but if we can save this developer
>> some time by giving them a clear run-time indication aside from the
>> compile-time warning then that would not be a bad thing. I've been there
>> myself a few times and I know times in the past where this would've saved me
>> the time it takes to rebuild and redeploy the kernel once.
> kbuild is _very_ good at catching and reporting these. And the linux
> kernel generally has a 0 warnings rule, which means even when it slips
> through a lot of developers will get mad at me for not spotting it.
>
> I think relying upon gcc to do its job here is safe enough. We only
> initialize stack variables if it's really needed, or if gcc is too dense
> to figure it out itself.
> -Daniel
I agree with Daniel. If you ignore warnings in your own test builds, you
get what you deserve. If you check warnings into the tree then you
should be shot. Or worse.
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 08/53] drm/i915: Update alloc_request to return the allocated request
2015-03-06 17:36 ` John Harrison
@ 2015-03-06 20:17 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-06 20:17 UTC (permalink / raw)
To: John Harrison, Daniel Vetter; +Cc: Intel-GFX
On 06/03/2015 17:36, John Harrison wrote:
> On 06/03/2015 16:18, Daniel Vetter wrote:
>> On Thu, Mar 05, 2015 at 08:13:07PM +0000, Tomas Elf wrote:
>>> On 05/03/2015 15:46, John Harrison wrote:
>>>> On 05/03/2015 15:27, Tomas Elf wrote:
>>>>> On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
>>>>>> From: John Harrison <John.C.Harrison@Intel.com>
>>>>>>
>>>>>> The alloc_request() function does not actually return the newly
>>>>>> allocated
>>>>>> request. Instead, it must be pulled from
>>>>>> ring->outstanding_lazy_request. This
>>>>>> patch fixes this so that code can create a request and start using it
>>>>>> knowing
>>>>>> exactly which request it actually owns.
>>>>>>
>>>>>> For: VIZ-5115
>>>>>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
>>>>>> ---
>>>>>> drivers/gpu/drm/i915/i915_drv.h | 3 ++-
>>>>>> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 ++-
>>>>>> drivers/gpu/drm/i915/intel_lrc.c | 13 +++++++++----
>>>>>> drivers/gpu/drm/i915/intel_lrc.h | 3 ++-
>>>>>> drivers/gpu/drm/i915/intel_ringbuffer.c | 14 ++++++++++----
>>>>>> drivers/gpu/drm/i915/intel_ringbuffer.h | 3 ++-
>>>>>> 6 files changed, 27 insertions(+), 12 deletions(-)
>>>>>>
>>>>>> diff --git a/drivers/gpu/drm/i915/i915_drv.h
>>>>>> b/drivers/gpu/drm/i915/i915_drv.h
>>>>>> index 87a4a2e..90223f208 100644
>>>>>> --- a/drivers/gpu/drm/i915/i915_drv.h
>>>>>> +++ b/drivers/gpu/drm/i915/i915_drv.h
>>>>>> @@ -1909,7 +1909,8 @@ struct drm_i915_private {
>>>>>> /* Abstract the submission mechanism (legacy ringbuffer or
>>>>>> execlists) away */
>>>>>> struct {
>>>>>> int (*alloc_request)(struct intel_engine_cs *ring,
>>>>>> - struct intel_context *ctx);
>>>>>> + struct intel_context *ctx,
>>>>>> + struct drm_i915_gem_request **req_out);
>>>>>> int (*do_execbuf)(struct i915_execbuffer_params *params,
>>>>>> struct drm_i915_gem_execbuffer2 *args,
>>>>>> struct list_head *vmas);
>>>>>> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>>>>> b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>>>>> index 61471e9..37dcc6f 100644
>>>>>> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>>>>> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>>>>> @@ -1353,6 +1353,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>>>>>> void *data,
>>>>>> struct i915_address_space *vm;
>>>>>> struct i915_execbuffer_params params_master; /* XXX: will be
>>>>>> removed later */
>>>>>> struct i915_execbuffer_params *params = ¶ms_master;
>>>>>> + struct drm_i915_gem_request *request;
>>>>> Please initialize request to NULL. If you accidentally dereference it
>>>>> before it is allocated (seeing as the allocation is several pages down
>>>> >from here) you get a null pointer exception, which is a clear
>>>>> indication that you did something stupid. Otherwise it's not clear
>>>>> what will happen (sure, page fault, but null pointer exception is a
>>>>> better failure indication).
>>>> That should generate a 'use before assignment' compiler warning.
>>> That assumes that the developer in question isn't too busy hacking to
>>> check
>>> for warnings (in all honesty that developer probably would've been me
>>> ;)).
>>> Sure, you should always check for warnings but if we can save this
>>> developer
>>> some time by giving them a clear run-time indication aside from the
>>> compile-time warning then that would not be a bad thing. I've been there
>>> myself a few times and I know times in the past where this would've
>>> saved me
>>> the time it takes to rebuild and redeploy the kernel once.
>> kbuild is _very_ good at catching and reporting these. And the linux
>> kernel generally has a 0 warnings rule, which means even when it slips
>> through a lot of developers will get mad at me for not spotting it.
>>
>> I think relying upon gcc to do its job here is safe enough. We only
>> initialize stack variables if it's really needed, or if gcc is too dense
>> to figure it out itself.
>> -Daniel
>
> I agree with Daniel. If you ignore warnings in your own test builds, you
> get what you deserve. If you check warnings into the tree then you
> should be shot. Or worse.
>
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 09/53] drm/i915: Add request to execbuf params and add explicit cleanup
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (7 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 08/53] drm/i915: Update alloc_request to return the allocated request John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 15:37 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 10/53] drm/i915: Update the dispatch tracepoint to use params->request John.C.Harrison
` (45 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Rather than just having a local request variable in the execbuff code, the
request pointer is now stored in the execbuff params structure. Also added
explicit cleanup of the request (plus wiping the OLR to match) in the error
case. This means that the execbuff code is no longer dependent upon the OLR
keeping track of the request so as to not leak it when things do go wrong. Note
that in the success case, the i915_add_request() at the end of the submission
function will tidy up the request and clear the OLR.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 1 +
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 13 +++++++++++--
2 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 90223f208..678b190 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1653,6 +1653,7 @@ struct i915_execbuffer_params {
struct intel_engine_cs *ring;
struct drm_i915_gem_object *batch_obj;
struct intel_context *ctx;
+ struct drm_i915_gem_request *request;
};
struct drm_i915_private {
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 37dcc6f..10462f6 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1353,7 +1353,6 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
struct i915_address_space *vm;
struct i915_execbuffer_params params_master; /* XXX: will be removed later */
struct i915_execbuffer_params *params = ¶ms_master;
- struct drm_i915_gem_request *request;
const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
u32 dispatch_flags;
int ret;
@@ -1532,7 +1531,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
/* Allocate a request for this batch buffer nice and early. */
- ret = dev_priv->gt.alloc_request(ring, ctx, &request);
+ ret = dev_priv->gt.alloc_request(ring, ctx, ¶ms->request);
if (ret)
goto err;
@@ -1565,6 +1564,16 @@ err:
i915_gem_context_unreference(ctx);
eb_destroy(eb);
+ /*
+ * If the request was created but not successfully submitted then it
+ * must be freed again. If it was submitted then it is being tracked
+ * on the active request list and no clean up is required here.
+ */
+ if (ret && params->request) {
+ i915_gem_request_unreference(params->request);
+ ring->outstanding_lazy_request = NULL;
+ }
+
mutex_unlock(&dev->struct_mutex);
pre_mutex_err:
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 09/53] drm/i915: Add request to execbuf params and add explicit cleanup
2015-02-19 17:17 ` [PATCH 09/53] drm/i915: Add request to execbuf params and add explicit cleanup John.C.Harrison
@ 2015-03-05 15:37 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 15:37 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Rather than just having a local request variable in the execbuff code, the
> request pointer is now stored in the execbuff params structure. Also added
> explicit cleanup of the request (plus wiping the OLR to match) in the error
> case. This means that the execbuff code is no longer dependent upon the OLR
> keeping track of the request so as to not leak it when things do go wrong. Note
> that in the success case, the i915_add_request() at the end of the submission
> function will tidy up the request and clear the OLR.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 1 +
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 13 +++++++++++--
> 2 files changed, 12 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 90223f208..678b190 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -1653,6 +1653,7 @@ struct i915_execbuffer_params {
> struct intel_engine_cs *ring;
> struct drm_i915_gem_object *batch_obj;
> struct intel_context *ctx;
> + struct drm_i915_gem_request *request;
> };
>
> struct drm_i915_private {
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 37dcc6f..10462f6 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1353,7 +1353,6 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> struct i915_address_space *vm;
> struct i915_execbuffer_params params_master; /* XXX: will be removed later */
> struct i915_execbuffer_params *params = ¶ms_master;
> - struct drm_i915_gem_request *request;
> const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
> u32 dispatch_flags;
> int ret;
> @@ -1532,7 +1531,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
>
> /* Allocate a request for this batch buffer nice and early. */
> - ret = dev_priv->gt.alloc_request(ring, ctx, &request);
> + ret = dev_priv->gt.alloc_request(ring, ctx, ¶ms->request);
> if (ret)
> goto err;
>
> @@ -1565,6 +1564,16 @@ err:
> i915_gem_context_unreference(ctx);
> eb_destroy(eb);
>
> + /*
> + * If the request was created but not successfully submitted then it
> + * must be freed again. If it was submitted then it is being tracked
> + * on the active request list and no clean up is required here.
> + */
> + if (ret && params->request) {
> + i915_gem_request_unreference(params->request);
> + ring->outstanding_lazy_request = NULL;
> + }
> +
> mutex_unlock(&dev->struct_mutex);
>
> pre_mutex_err:
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 10/53] drm/i915: Update the dispatch tracepoint to use params->request
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (8 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 09/53] drm/i915: Add request to execbuf params and add explicit cleanup John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 15:43 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 11/53] drm/i915: Update move_to_gpu() to take a request structure John.C.Harrison
` (44 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated a couple of trace points to use the now cached request pointer rather
than extracting it from the ring.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
drivers/gpu/drm/i915/intel_lrc.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 10462f6..883cabd 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1277,7 +1277,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
return ret;
}
- trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
+ trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
i915_gem_execbuffer_move_to_active(vmas, ring);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index c3c783f..c42af08 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -712,7 +712,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
if (ret)
return ret;
- trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
+ trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
i915_gem_execbuffer_move_to_active(vmas, ring);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 10/53] drm/i915: Update the dispatch tracepoint to use params->request
2015-02-19 17:17 ` [PATCH 10/53] drm/i915: Update the dispatch tracepoint to use params->request John.C.Harrison
@ 2015-03-05 15:43 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 15:43 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated a couple of trace points to use the now cached request pointer rather
> than extracting it from the ring.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
> drivers/gpu/drm/i915/intel_lrc.c | 2 +-
> 2 files changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 10462f6..883cabd 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1277,7 +1277,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> return ret;
> }
>
> - trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
> + trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
>
> i915_gem_execbuffer_move_to_active(vmas, ring);
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index c3c783f..c42af08 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -712,7 +712,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
> if (ret)
> return ret;
>
> - trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
> + trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
>
> i915_gem_execbuffer_move_to_active(vmas, ring);
>
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 11/53] drm/i915: Update move_to_gpu() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (9 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 10/53] drm/i915: Update the dispatch tracepoint to use params->request John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 15:54 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 12/53] drm/i915: Update execbuffer_move_to_active() " John.C.Harrison
` (43 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The plan is to pass requests around as the basic submission tracking structure
rather than rings and contexts. This patch updates the move_to_gpu() code paths.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 10 +++++-----
drivers/gpu/drm/i915/intel_lrc.c | 10 ++++------
2 files changed, 9 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 883cabd..da1e232 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -828,7 +828,7 @@ err:
}
static int
-i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
+i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
struct list_head *vmas)
{
struct i915_vma *vma;
@@ -838,7 +838,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
list_for_each_entry(vma, vmas, exec_list) {
struct drm_i915_gem_object *obj = vma->obj;
- ret = i915_gem_object_sync(obj, ring);
+ ret = i915_gem_object_sync(obj, req->ring);
if (ret)
return ret;
@@ -849,7 +849,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
}
if (flush_chipset)
- i915_gem_chipset_flush(ring->dev);
+ i915_gem_chipset_flush(req->ring->dev);
if (flush_domains & I915_GEM_DOMAIN_GTT)
wmb();
@@ -857,7 +857,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
/* Unconditionally invalidate gpu caches and ensure that we do flush
* any residual writes from the previous batch.
*/
- return intel_ring_invalidate_all_caches(ring);
+ return intel_ring_invalidate_all_caches(req->ring);
}
static bool
@@ -1186,7 +1186,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
}
}
- ret = i915_gem_execbuffer_move_to_gpu(ring, vmas);
+ ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas);
if (ret)
goto error;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index c42af08..efe970f 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -578,11 +578,9 @@ static int logical_ring_invalidate_all_caches(struct intel_ringbuffer *ringbuf,
return 0;
}
-static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+static int execlists_move_to_gpu(struct drm_i915_gem_request *req,
struct list_head *vmas)
{
- struct intel_engine_cs *ring = ringbuf->ring;
struct i915_vma *vma;
uint32_t flush_domains = 0;
bool flush_chipset = false;
@@ -591,7 +589,7 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
list_for_each_entry(vma, vmas, exec_list) {
struct drm_i915_gem_object *obj = vma->obj;
- ret = i915_gem_object_sync(obj, ring);
+ ret = i915_gem_object_sync(obj, req->ring);
if (ret)
return ret;
@@ -607,7 +605,7 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
/* Unconditionally invalidate gpu caches and ensure that we do flush
* any residual writes from the previous batch.
*/
- return logical_ring_invalidate_all_caches(ringbuf, ctx);
+ return logical_ring_invalidate_all_caches(req->ringbuf, req->ctx);
}
/**
@@ -686,7 +684,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
return -EINVAL;
}
- ret = execlists_move_to_gpu(ringbuf, params->ctx, vmas);
+ ret = execlists_move_to_gpu(params->request, vmas);
if (ret)
return ret;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 11/53] drm/i915: Update move_to_gpu() to take a request structure
2015-02-19 17:17 ` [PATCH 11/53] drm/i915: Update move_to_gpu() to take a request structure John.C.Harrison
@ 2015-03-05 15:54 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 15:54 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The plan is to pass requests around as the basic submission tracking structure
> rather than rings and contexts. This patch updates the move_to_gpu() code paths.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 10 +++++-----
> drivers/gpu/drm/i915/intel_lrc.c | 10 ++++------
> 2 files changed, 9 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 883cabd..da1e232 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -828,7 +828,7 @@ err:
> }
>
> static int
> -i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
> +i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
> struct list_head *vmas)
> {
> struct i915_vma *vma;
> @@ -838,7 +838,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
>
> list_for_each_entry(vma, vmas, exec_list) {
> struct drm_i915_gem_object *obj = vma->obj;
> - ret = i915_gem_object_sync(obj, ring);
> + ret = i915_gem_object_sync(obj, req->ring);
> if (ret)
> return ret;
>
> @@ -849,7 +849,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
> }
>
> if (flush_chipset)
> - i915_gem_chipset_flush(ring->dev);
> + i915_gem_chipset_flush(req->ring->dev);
>
> if (flush_domains & I915_GEM_DOMAIN_GTT)
> wmb();
> @@ -857,7 +857,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
> /* Unconditionally invalidate gpu caches and ensure that we do flush
> * any residual writes from the previous batch.
> */
> - return intel_ring_invalidate_all_caches(ring);
> + return intel_ring_invalidate_all_caches(req->ring);
> }
>
> static bool
> @@ -1186,7 +1186,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> }
> }
>
> - ret = i915_gem_execbuffer_move_to_gpu(ring, vmas);
> + ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas);
> if (ret)
> goto error;
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index c42af08..efe970f 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -578,11 +578,9 @@ static int logical_ring_invalidate_all_caches(struct intel_ringbuffer *ringbuf,
> return 0;
> }
>
> -static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx,
> +static int execlists_move_to_gpu(struct drm_i915_gem_request *req,
> struct list_head *vmas)
> {
> - struct intel_engine_cs *ring = ringbuf->ring;
> struct i915_vma *vma;
> uint32_t flush_domains = 0;
> bool flush_chipset = false;
> @@ -591,7 +589,7 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
> list_for_each_entry(vma, vmas, exec_list) {
> struct drm_i915_gem_object *obj = vma->obj;
>
> - ret = i915_gem_object_sync(obj, ring);
> + ret = i915_gem_object_sync(obj, req->ring);
> if (ret)
> return ret;
>
> @@ -607,7 +605,7 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
> /* Unconditionally invalidate gpu caches and ensure that we do flush
> * any residual writes from the previous batch.
> */
> - return logical_ring_invalidate_all_caches(ringbuf, ctx);
> + return logical_ring_invalidate_all_caches(req->ringbuf, req->ctx);
> }
>
> /**
> @@ -686,7 +684,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
> return -EINVAL;
> }
>
> - ret = execlists_move_to_gpu(ringbuf, params->ctx, vmas);
> + ret = execlists_move_to_gpu(params->request, vmas);
> if (ret)
> return ret;
>
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 12/53] drm/i915: Update execbuffer_move_to_active() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (10 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 11/53] drm/i915: Update move_to_gpu() to take a request structure John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 16:03 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 13/53] drm/i915: Add flag to i915_add_request() to skip the cache flush John.C.Harrison
` (42 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The plan is to pass requests around as the basic submission tracking structure
rather than rings and contexts. This patch updates the
execbuffer_move_to_active() code path.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 2 +-
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 6 +++---
drivers/gpu/drm/i915/intel_lrc.c | 2 +-
3 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 678b190..68d6dec 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2643,7 +2643,7 @@ int i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
int i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv);
void i915_gem_execbuffer_move_to_active(struct list_head *vmas,
- struct intel_engine_cs *ring);
+ struct drm_i915_gem_request *req);
int i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params);
int i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index da1e232..f7c19bc 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -950,9 +950,9 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
void
i915_gem_execbuffer_move_to_active(struct list_head *vmas,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
- struct drm_i915_gem_request *req = intel_ring_get_request(ring);
+ struct intel_engine_cs *ring = i915_gem_request_get_ring(req);
struct i915_vma *vma;
list_for_each_entry(vma, vmas, exec_list) {
@@ -1279,7 +1279,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
- i915_gem_execbuffer_move_to_active(vmas, ring);
+ i915_gem_execbuffer_move_to_active(vmas, params->request);
ret = i915_gem_execbuffer_retire_commands(params);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index efe970f..bc3809e 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -712,7 +712,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
- i915_gem_execbuffer_move_to_active(vmas, ring);
+ i915_gem_execbuffer_move_to_active(vmas, params->request);
return i915_gem_execbuffer_retire_commands(params);
}
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 12/53] drm/i915: Update execbuffer_move_to_active() to take a request structure
2015-02-19 17:17 ` [PATCH 12/53] drm/i915: Update execbuffer_move_to_active() " John.C.Harrison
@ 2015-03-05 16:03 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 16:03 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The plan is to pass requests around as the basic submission tracking structure
> rather than rings and contexts. This patch updates the
> execbuffer_move_to_active() code path.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 2 +-
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 6 +++---
> drivers/gpu/drm/i915/intel_lrc.c | 2 +-
> 3 files changed, 5 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 678b190..68d6dec 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2643,7 +2643,7 @@ int i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
> int i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
> struct drm_file *file_priv);
> void i915_gem_execbuffer_move_to_active(struct list_head *vmas,
> - struct intel_engine_cs *ring);
> + struct drm_i915_gem_request *req);
> int i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params);
> int i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> struct drm_i915_gem_execbuffer2 *args,
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index da1e232..f7c19bc 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -950,9 +950,9 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
>
> void
> i915_gem_execbuffer_move_to_active(struct list_head *vmas,
> - struct intel_engine_cs *ring)
> + struct drm_i915_gem_request *req)
> {
> - struct drm_i915_gem_request *req = intel_ring_get_request(ring);
> + struct intel_engine_cs *ring = i915_gem_request_get_ring(req);
> struct i915_vma *vma;
>
> list_for_each_entry(vma, vmas, exec_list) {
> @@ -1279,7 +1279,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
>
> trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
>
> - i915_gem_execbuffer_move_to_active(vmas, ring);
> + i915_gem_execbuffer_move_to_active(vmas, params->request);
>
> ret = i915_gem_execbuffer_retire_commands(params);
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index efe970f..bc3809e 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -712,7 +712,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
>
> trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
>
> - i915_gem_execbuffer_move_to_active(vmas, ring);
> + i915_gem_execbuffer_move_to_active(vmas, params->request);
>
> return i915_gem_execbuffer_retire_commands(params);
> }
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 13/53] drm/i915: Add flag to i915_add_request() to skip the cache flush
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (11 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 12/53] drm/i915: Update execbuffer_move_to_active() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-02-19 17:17 ` [PATCH 14/53] drm/i915: Update pin_to_display_plane() to do explicit request management John.C.Harrison
` (41 subsequent siblings)
54 siblings, 0 replies; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
In order to explcitly track all GPU work (and completely remove the outstanding
lazy request), it is necessary to add extra i915_add_request() calls to various
places. Some of these do not need the implicit cache flush done as part of the
standard batch buffer submission process.
This patch adds a flag to _add_request() to specify whether the flush is
required or not.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 7 +++++--
drivers/gpu/drm/i915/i915_gem.c | 25 +++++++++++--------------
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
drivers/gpu/drm/i915/i915_gem_render_state.c | 2 +-
drivers/gpu/drm/i915/intel_lrc.c | 2 +-
5 files changed, 19 insertions(+), 19 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 68d6dec..375d4f9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2831,9 +2831,12 @@ int __must_check i915_gpu_idle(struct drm_device *dev);
int __must_check i915_gem_suspend(struct drm_device *dev);
int __i915_add_request(struct intel_engine_cs *ring,
struct drm_file *file,
- struct drm_i915_gem_object *batch_obj);
+ struct drm_i915_gem_object *batch_obj,
+ bool flush_caches);
#define i915_add_request(ring) \
- __i915_add_request(ring, NULL, NULL)
+ __i915_add_request(ring, NULL, NULL, true)
+#define i915_add_request_no_flush(ring) \
+ __i915_add_request(ring, NULL, NULL, false)
int __i915_wait_request(struct drm_i915_gem_request *req,
unsigned reset_counter,
bool interruptible,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index cf959e3..4c29177 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2409,7 +2409,8 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
int __i915_add_request(struct intel_engine_cs *ring,
struct drm_file *file,
- struct drm_i915_gem_object *obj)
+ struct drm_i915_gem_object *obj,
+ bool flush_caches)
{
struct drm_i915_private *dev_priv = ring->dev->dev_private;
struct drm_i915_gem_request *request;
@@ -2434,12 +2435,11 @@ int __i915_add_request(struct intel_engine_cs *ring,
* is that the flush _must_ happen before the next request, no matter
* what.
*/
- if (i915.enable_execlists) {
- ret = logical_ring_flush_all_caches(ringbuf, request->ctx);
- if (ret)
- return ret;
- } else {
- ret = intel_ring_flush_all_caches(ring);
+ if (flush_caches) {
+ if (i915.enable_execlists)
+ ret = logical_ring_flush_all_caches(ringbuf, request->ctx);
+ else
+ ret = intel_ring_flush_all_caches(ring);
if (ret)
return ret;
}
@@ -2451,15 +2451,12 @@ int __i915_add_request(struct intel_engine_cs *ring,
*/
request->postfix = intel_ring_get_tail(ringbuf);
- if (i915.enable_execlists) {
+ if (i915.enable_execlists)
ret = ring->emit_request(ringbuf, request);
- if (ret)
- return ret;
- } else {
+ else
ret = ring->add_request(ring);
- if (ret)
- return ret;
- }
+ if (ret)
+ return ret;
request->head = request_start;
request->tail = intel_ring_get_tail(ringbuf);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index f7c19bc..76f6dcf 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -997,7 +997,7 @@ i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
/* Add a breadcrumb for the completion of the batch buffer */
return __i915_add_request(params->ring, params->file,
- params->batch_obj);
+ params->batch_obj, true);
}
static int
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index 521548a..aba39c3 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -173,7 +173,7 @@ int i915_gem_render_state_init(struct intel_engine_cs *ring)
i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
- ret = __i915_add_request(ring, NULL, so.obj);
+ ret = __i915_add_request(ring, NULL, so.obj, true);
/* __i915_add_request moves object to inactive if it fails */
out:
i915_gem_render_state_fini(&so);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index bc3809e..4b42346 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1370,7 +1370,7 @@ static int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
- ret = __i915_add_request(ring, file, so.obj);
+ ret = __i915_add_request(ring, file, so.obj, true);
/* intel_logical_ring_add_request moves object to inactive if it
* fails */
out:
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* [PATCH 14/53] drm/i915: Update pin_to_display_plane() to do explicit request management
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (12 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 13/53] drm/i915: Add flag to i915_add_request() to skip the cache flush John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 16:21 ` Tomas Elf
2015-03-05 16:22 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 15/53] drm/i915: Update i915_gem_object_sync() to take a request structure John.C.Harrison
` (40 subsequent siblings)
54 siblings, 2 replies; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Added explicit creation creation and submission of the request structure to the
display object pinning code. This removes any reliance on the OLR keeping track
of the request and the unknown randomness that can ensue with other work
becoming part of the same request.
v2: Added semaphore enabled check to prevent allocating a pointless request
structure in the case where the sync just calls wait_rendering().
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 21 ++++++++++++++++++---
1 file changed, 18 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 4c29177..5897d54 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3943,9 +3943,24 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
int ret;
if (pipelined != i915_gem_request_get_ring(obj->last_read_req)) {
- ret = i915_gem_object_sync(obj, pipelined);
- if (ret)
- return ret;
+ if (!pipelined || !i915_semaphore_is_enabled(obj->base.dev)) {
+ ret = i915_gem_object_wait_rendering(obj, false);
+ } else {
+ struct drm_i915_private *dev_priv = pipelined->dev->dev_private;
+ struct drm_i915_gem_request *req;
+
+ ret = dev_priv->gt.alloc_request(pipelined, pipelined->default_context, &req);
+ if (ret)
+ return ret;
+
+ ret = i915_gem_object_sync(obj, req->ring);
+ if (ret)
+ return ret;
+
+ ret = i915_add_request_no_flush(req->ring);
+ if (ret)
+ return ret;
+ }
}
/* Mark the pin_display early so that we account for the
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 14/53] drm/i915: Update pin_to_display_plane() to do explicit request management
2015-02-19 17:17 ` [PATCH 14/53] drm/i915: Update pin_to_display_plane() to do explicit request management John.C.Harrison
@ 2015-03-05 16:21 ` Tomas Elf
2015-03-05 16:22 ` Tomas Elf
1 sibling, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 16:21 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Added explicit creation creation and submission of the request structure to the
Nitpick: "creation creation"
> display object pinning code. This removes any reliance on the OLR keeping track
> of the request and the unknown randomness that can ensue with other work
> becoming part of the same request.
>
> v2: Added semaphore enabled check to prevent allocating a pointless request
> structure in the case where the sync just calls wait_rendering().
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 21 ++++++++++++++++++---
> 1 file changed, 18 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 4c29177..5897d54 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -3943,9 +3943,24 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
> int ret;
>
> if (pipelined != i915_gem_request_get_ring(obj->last_read_req)) {
> - ret = i915_gem_object_sync(obj, pipelined);
> - if (ret)
> - return ret;
> + if (!pipelined || !i915_semaphore_is_enabled(obj->base.dev)) {
> + ret = i915_gem_object_wait_rendering(obj, false);
> + } else {
The call to i915_gem_object_wait_rendering() was taken from the
implementation of i915_gem_object_sync() below. Ripping out code from
the function you're calling just to do it in advance is not very nice.
Just imagine a scenario where the i915_gem_object_sync() implementation
were to change but the code outside the function would not. We need to
figure out a better way of doing this. In fact, allocating and managing
a request that never gets to be used inside the i915_gem_object_sync()
function could be a better way to go since it poses less potential
future problem even though it's more wasteful. But there are probably
better ways of doing this.
Thanks,
Tomas
> + struct drm_i915_private *dev_priv = pipelined->dev->dev_private;
> + struct drm_i915_gem_request *req;
> +
> + ret = dev_priv->gt.alloc_request(pipelined, pipelined->default_context, &req);
> + if (ret)
> + return ret;
> +
> + ret = i915_gem_object_sync(obj, req->ring);
> + if (ret)
> + return ret;
> +
> + ret = i915_add_request_no_flush(req->ring);
> + if (ret)
> + return ret;
> + }
> }
>
> /* Mark the pin_display early so that we account for the
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 14/53] drm/i915: Update pin_to_display_plane() to do explicit request management
2015-02-19 17:17 ` [PATCH 14/53] drm/i915: Update pin_to_display_plane() to do explicit request management John.C.Harrison
2015-03-05 16:21 ` Tomas Elf
@ 2015-03-05 16:22 ` Tomas Elf
1 sibling, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 16:22 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Added explicit creation creation and submission of the request structure to the
> display object pinning code. This removes any reliance on the OLR keeping track
> of the request and the unknown randomness that can ensue with other work
> becoming part of the same request.
>
> v2: Added semaphore enabled check to prevent allocating a pointless request
> structure in the case where the sync just calls wait_rendering().
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 21 ++++++++++++++++++---
> 1 file changed, 18 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 4c29177..5897d54 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -3943,9 +3943,24 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
> int ret;
>
> if (pipelined != i915_gem_request_get_ring(obj->last_read_req)) {
> - ret = i915_gem_object_sync(obj, pipelined);
> - if (ret)
> - return ret;
> + if (!pipelined || !i915_semaphore_is_enabled(obj->base.dev)) {
> + ret = i915_gem_object_wait_rendering(obj, false);
... Also, the ret value here is never checked and returned. It's
overwritten a few lines further down.
Thanks,
Tomas
> + } else {
> + struct drm_i915_private *dev_priv = pipelined->dev->dev_private;
> + struct drm_i915_gem_request *req;
> +
> + ret = dev_priv->gt.alloc_request(pipelined, pipelined->default_context, &req);
> + if (ret)
> + return ret;
> +
> + ret = i915_gem_object_sync(obj, req->ring);
> + if (ret)
> + return ret;
> +
> + ret = i915_add_request_no_flush(req->ring);
> + if (ret)
> + return ret;
> + }
> }
>
> /* Mark the pin_display early so that we account for the
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 15/53] drm/i915: Update i915_gem_object_sync() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (13 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 14/53] drm/i915: Update pin_to_display_plane() to do explicit request management John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 16:40 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 16/53] drm/i915: Update i915_gpu_idle() to manage its own request John.C.Harrison
` (39 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The plan is to pass requests around as the basic submission tracking structure
rather than rings and contexts. This patch updates the i915_gem_object_sync()
code path.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 2 +-
drivers/gpu/drm/i915/i915_gem.c | 7 ++++---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
drivers/gpu/drm/i915/intel_lrc.c | 2 +-
4 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 375d4f9..bfd7b47 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2744,7 +2744,7 @@ static inline void i915_gem_object_unpin_pages(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 intel_engine_cs *to);
+ struct drm_i915_gem_request *to_req);
void i915_vma_move_to_active(struct i915_vma *vma,
struct intel_engine_cs *ring);
int i915_gem_dumb_create(struct drm_file *file_priv,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5897d54..c5b9bc7 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2956,7 +2956,7 @@ out:
* i915_gem_object_sync - sync an object to a ring.
*
* @obj: object which may be in use on another ring.
- * @to: ring we wish to use the object on. May be NULL.
+ * @to_req: request we wish to use the object for. May be NULL.
*
* This code is meant to abstract object synchronization with the GPU.
* Calling with NULL implies synchronizing the object with the CPU
@@ -2966,8 +2966,9 @@ out:
*/
int
i915_gem_object_sync(struct drm_i915_gem_object *obj,
- struct intel_engine_cs *to)
+ struct drm_i915_gem_request *to_req)
{
+ struct intel_engine_cs *to = to_req ? to_req->ring : NULL;
struct intel_engine_cs *from;
u32 seqno;
int ret, idx;
@@ -3953,7 +3954,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
if (ret)
return ret;
- ret = i915_gem_object_sync(obj, req->ring);
+ ret = i915_gem_object_sync(obj, req);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 76f6dcf..2cd0579 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -838,7 +838,7 @@ 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;
- ret = i915_gem_object_sync(obj, req->ring);
+ ret = i915_gem_object_sync(obj, req);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 4b42346..0d88e9c 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -589,7 +589,7 @@ static int execlists_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;
- ret = i915_gem_object_sync(obj, req->ring);
+ ret = i915_gem_object_sync(obj, req);
if (ret)
return ret;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 15/53] drm/i915: Update i915_gem_object_sync() to take a request structure
2015-02-19 17:17 ` [PATCH 15/53] drm/i915: Update i915_gem_object_sync() to take a request structure John.C.Harrison
@ 2015-03-05 16:40 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 16:40 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The plan is to pass requests around as the basic submission tracking structure
> rather than rings and contexts. This patch updates the i915_gem_object_sync()
> code path.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 2 +-
> drivers/gpu/drm/i915/i915_gem.c | 7 ++++---
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
> drivers/gpu/drm/i915/intel_lrc.c | 2 +-
> 4 files changed, 7 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 375d4f9..bfd7b47 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2744,7 +2744,7 @@ static inline void i915_gem_object_unpin_pages(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 intel_engine_cs *to);
> + struct drm_i915_gem_request *to_req);
> void i915_vma_move_to_active(struct i915_vma *vma,
> struct intel_engine_cs *ring);
> int i915_gem_dumb_create(struct drm_file *file_priv,
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 5897d54..c5b9bc7 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2956,7 +2956,7 @@ out:
> * i915_gem_object_sync - sync an object to a ring.
> *
> * @obj: object which may be in use on another ring.
> - * @to: ring we wish to use the object on. May be NULL.
> + * @to_req: request we wish to use the object for. May be NULL.
> *
> * This code is meant to abstract object synchronization with the GPU.
> * Calling with NULL implies synchronizing the object with the CPU
> @@ -2966,8 +2966,9 @@ out:
> */
> int
> i915_gem_object_sync(struct drm_i915_gem_object *obj,
> - struct intel_engine_cs *to)
> + struct drm_i915_gem_request *to_req)
> {
> + struct intel_engine_cs *to = to_req ? to_req->ring : NULL;
> struct intel_engine_cs *from;
> u32 seqno;
> int ret, idx;
> @@ -3953,7 +3954,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
> if (ret)
> return ret;
>
> - ret = i915_gem_object_sync(obj, req->ring);
> + ret = i915_gem_object_sync(obj, req);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 76f6dcf..2cd0579 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -838,7 +838,7 @@ 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;
> - ret = i915_gem_object_sync(obj, req->ring);
> + ret = i915_gem_object_sync(obj, req);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 4b42346..0d88e9c 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -589,7 +589,7 @@ static int execlists_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;
>
> - ret = i915_gem_object_sync(obj, req->ring);
> + ret = i915_gem_object_sync(obj, req);
> if (ret)
> return ret;
>
>
This seems to be just fine but if the requests of any of the existing
i915_gem_object_sync() call sites were to be null they would cause local
null pointer exceptions in the calling functions even though
i915_gem_object_sync() itself supports an incoming null request. There
does not seem to be any call sites in the driver that actually passes or
supports passing null requests into i915_gem_object_sync(). Does the
driver do that anywhere today or how does that fit in?
Aside from that open question:
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 16/53] drm/i915: Update i915_gpu_idle() to manage its own request
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (14 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 15/53] drm/i915: Update i915_gem_object_sync() to take a request structure John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 16:45 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 17/53] drm/i915: Split i915_ppgtt_init_hw() in half - generic and per ring John.C.Harrison
` (38 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Added explicit request creation and submission to the GPU idle code path.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 18 +++++++++++++++++-
1 file changed, 17 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c5b9bc7..51f719c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3114,11 +3114,27 @@ int i915_gpu_idle(struct drm_device *dev)
/* Flush everything onto the inactive list. */
for_each_ring(ring, dev_priv, i) {
if (!i915.enable_execlists) {
- ret = i915_switch_context(ring, ring->default_context);
+ struct drm_i915_gem_request *req;
+
+ ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
if (ret)
return ret;
+
+ ret = i915_switch_context(req->ring, ring->default_context);
+ if (ret) {
+ i915_gem_request_unreference(req);
+ return ret;
+ }
+
+ ret = i915_add_request_no_flush(req->ring);
+ if (ret) {
+ i915_gem_request_unreference(req);
+ return ret;
+ }
}
+ WARN_ON(ring->outstanding_lazy_request);
+
ret = intel_ring_idle(ring);
if (ret)
return ret;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 16/53] drm/i915: Update i915_gpu_idle() to manage its own request
2015-02-19 17:17 ` [PATCH 16/53] drm/i915: Update i915_gpu_idle() to manage its own request John.C.Harrison
@ 2015-03-05 16:45 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 16:45 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Added explicit request creation and submission to the GPU idle code path.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 18 +++++++++++++++++-
> 1 file changed, 17 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index c5b9bc7..51f719c 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -3114,11 +3114,27 @@ int i915_gpu_idle(struct drm_device *dev)
> /* Flush everything onto the inactive list. */
> for_each_ring(ring, dev_priv, i) {
> if (!i915.enable_execlists) {
> - ret = i915_switch_context(ring, ring->default_context);
> + struct drm_i915_gem_request *req;
> +
> + ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
> if (ret)
> return ret;
> +
> + ret = i915_switch_context(req->ring, ring->default_context);
> + if (ret) {
> + i915_gem_request_unreference(req);
> + return ret;
> + }
> +
> + ret = i915_add_request_no_flush(req->ring);
> + if (ret) {
> + i915_gem_request_unreference(req);
> + return ret;
> + }
> }
>
> + WARN_ON(ring->outstanding_lazy_request);
> +
> ret = intel_ring_idle(ring);
> if (ret)
> return ret;
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 17/53] drm/i915: Split i915_ppgtt_init_hw() in half - generic and per ring
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (15 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 16/53] drm/i915: Update i915_gpu_idle() to manage its own request John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-02-24 13:55 ` Daniel, Thomas
2015-03-05 16:53 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 18/53] drm/i915: Moved the for_each_ring loop outside of i915_gem_context_enable() John.C.Harrison
` (37 subsequent siblings)
54 siblings, 2 replies; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The i915_gem_init_hw() function calls a bunch of smaller initialisation
functions. Multiple of which have generic sections and per ring sections. This
means multiple passes are done over the rings. Each pass writes data to the ring
which floats around in that ring's OLR until some random point in the future
when an add_request() is done by some random other piece of code.
This patch breaks i915_ppgtt_init_hw() in two with the per ring initialisation
now being done in i915_ppgtt_init_ring(). The ring looping is now done at the
top level in i915_gem_init_hw().
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 25 +++++++++++++++++++------
drivers/gpu/drm/i915/i915_gem_gtt.c | 25 ++++++++++++-------------
drivers/gpu/drm/i915/i915_gem_gtt.h | 1 +
3 files changed, 32 insertions(+), 19 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 51f719c..9bc60d7 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4844,19 +4844,32 @@ i915_gem_init_hw(struct drm_device *dev)
*/
init_unused_rings(dev);
+ ret = i915_ppgtt_init_hw(dev);
+ if (ret) {
+ DRM_ERROR("PPGTT enable HW failed %d\n", ret);
+ return ret;
+ }
+
+ /* Need to do basic initialisation of all rings first: */
for_each_ring(ring, dev_priv, i) {
ret = ring->init_hw(ring);
if (ret)
return ret;
}
- for (i = 0; i < NUM_L3_SLICES(dev); i++)
- i915_gem_l3_remap(&dev_priv->ring[RCS], i);
+ /* Now it is safe to go back round and do everything else: */
+ for_each_ring(ring, dev_priv, i) {
+ if (ring->id == RCS) {
+ for (i = 0; i < NUM_L3_SLICES(dev); i++)
+ i915_gem_l3_remap(ring, i);
+ }
- ret = i915_ppgtt_init_hw(dev);
- if (ret && ret != -EIO) {
- DRM_ERROR("PPGTT enable failed %d\n", ret);
- i915_gem_cleanup_ringbuffer(dev);
+ ret = i915_ppgtt_init_ring(ring);
+ if (ret && ret != -EIO) {
+ DRM_ERROR("PPGTT enable ring #%d failed %d\n", i, ret);
+ i915_gem_cleanup_ringbuffer(dev);
+ return ret;
+ }
}
ret = i915_gem_context_enable(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index e54b2a0..428d2f6 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1206,11 +1206,6 @@ int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
int i915_ppgtt_init_hw(struct drm_device *dev)
{
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_engine_cs *ring;
- struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
- int i, ret = 0;
-
/* In the case of execlists, PPGTT is enabled by the context descriptor
* and the PDPs are contained within the context itself. We don't
* need to do anything here. */
@@ -1229,16 +1224,20 @@ int i915_ppgtt_init_hw(struct drm_device *dev)
else
MISSING_CASE(INTEL_INFO(dev)->gen);
- if (ppgtt) {
- for_each_ring(ring, dev_priv, i) {
- ret = ppgtt->switch_mm(ppgtt, ring);
- if (ret != 0)
- return ret;
- }
- }
+ return 0;
+}
- return ret;
+int i915_ppgtt_init_ring(struct intel_engine_cs *ring)
+{
+ struct drm_i915_private *dev_priv = ring->dev->dev_private;
+ struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+
+ if (!ppgtt)
+ return 0;
+
+ return ppgtt->switch_mm(ppgtt, ring);
}
+
struct i915_hw_ppgtt *
i915_ppgtt_create(struct drm_device *dev, struct drm_i915_file_private *fpriv)
{
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 8f76990..5a6cef9 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -300,6 +300,7 @@ void i915_global_gtt_cleanup(struct drm_device *dev);
int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
int i915_ppgtt_init_hw(struct drm_device *dev);
+int i915_ppgtt_init_ring(struct intel_engine_cs *ring);
void i915_ppgtt_release(struct kref *kref);
struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_device *dev,
struct drm_i915_file_private *fpriv);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 17/53] drm/i915: Split i915_ppgtt_init_hw() in half - generic and per ring
2015-02-19 17:17 ` [PATCH 17/53] drm/i915: Split i915_ppgtt_init_hw() in half - generic and per ring John.C.Harrison
@ 2015-02-24 13:55 ` Daniel, Thomas
2015-03-05 16:53 ` Tomas Elf
1 sibling, 0 replies; 234+ messages in thread
From: Daniel, Thomas @ 2015-02-24 13:55 UTC (permalink / raw)
To: Harrison, John C, Intel-GFX
> -----Original Message-----
> From: Intel-gfx [mailto:intel-gfx-bounces@lists.freedesktop.org] On Behalf Of
> John.C.Harrison@Intel.com
> Sent: Thursday, February 19, 2015 5:17 PM
> To: Intel-GFX@Lists.FreeDesktop.Org
> Subject: [Intel-gfx] [PATCH 17/53] drm/i915: Split i915_ppgtt_init_hw() in half -
> generic and per ring
>
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The i915_gem_init_hw() function calls a bunch of smaller initialisation
> functions. Multiple of which have generic sections and per ring sections. This
> means multiple passes are done over the rings. Each pass writes data to the ring
> which floats around in that ring's OLR until some random point in the future
> when an add_request() is done by some random other piece of code.
>
> This patch breaks i915_ppgtt_init_hw() in two with the per ring initialisation
> now being done in i915_ppgtt_init_ring(). The ring looping is now done at the
> top level in i915_gem_init_hw().
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 25 +++++++++++++++++++------
> drivers/gpu/drm/i915/i915_gem_gtt.c | 25 ++++++++++++-------------
> drivers/gpu/drm/i915/i915_gem_gtt.h | 1 +
> 3 files changed, 32 insertions(+), 19 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c
> b/drivers/gpu/drm/i915/i915_gem.c
> index 51f719c..9bc60d7 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -4844,19 +4844,32 @@ i915_gem_init_hw(struct drm_device *dev)
> */
> init_unused_rings(dev);
>
> + ret = i915_ppgtt_init_hw(dev);
> + if (ret) {
> + DRM_ERROR("PPGTT enable HW failed %d\n", ret);
> + return ret;
> + }
> +
> + /* Need to do basic initialisation of all rings first: */
> for_each_ring(ring, dev_priv, i) {
> ret = ring->init_hw(ring);
> if (ret)
> return ret;
> }
>
> - for (i = 0; i < NUM_L3_SLICES(dev); i++)
> - i915_gem_l3_remap(&dev_priv->ring[RCS], i);
> + /* Now it is safe to go back round and do everything else: */
> + for_each_ring(ring, dev_priv, i) {
> + if (ring->id == RCS) {
> + for (i = 0; i < NUM_L3_SLICES(dev); i++)
> + i915_gem_l3_remap(ring, i);
> + }
>
> - ret = i915_ppgtt_init_hw(dev);
> - if (ret && ret != -EIO) {
> - DRM_ERROR("PPGTT enable failed %d\n", ret);
> - i915_gem_cleanup_ringbuffer(dev);
> + ret = i915_ppgtt_init_ring(ring);
> + if (ret && ret != -EIO) {
> + DRM_ERROR("PPGTT enable ring #%d failed %d\n", i,
> ret);
> + i915_gem_cleanup_ringbuffer(dev);
> + return ret;
> + }
> }
>
> ret = i915_gem_context_enable(dev_priv);
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c
> b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index e54b2a0..428d2f6 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -1206,11 +1206,6 @@ int i915_ppgtt_init(struct drm_device *dev, struct
> i915_hw_ppgtt *ppgtt)
>
> int i915_ppgtt_init_hw(struct drm_device *dev)
> {
> - struct drm_i915_private *dev_priv = dev->dev_private;
> - struct intel_engine_cs *ring;
> - struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
> - int i, ret = 0;
> -
> /* In the case of execlists, PPGTT is enabled by the context descriptor
> * and the PDPs are contained within the context itself. We don't
> * need to do anything here. */
> @@ -1229,16 +1224,20 @@ int i915_ppgtt_init_hw(struct drm_device *dev)
> else
> MISSING_CASE(INTEL_INFO(dev)->gen);
>
> - if (ppgtt) {
> - for_each_ring(ring, dev_priv, i) {
> - ret = ppgtt->switch_mm(ppgtt, ring);
> - if (ret != 0)
> - return ret;
> - }
> - }
> + return 0;
> +}
>
> - return ret;
> +int i915_ppgtt_init_ring(struct intel_engine_cs *ring)
> +{
> + struct drm_i915_private *dev_priv = ring->dev->dev_private;
> + struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
> +
> + if (!ppgtt)
> + return 0;
> +
> + return ppgtt->switch_mm(ppgtt, ring);
> }
This breaks alias PPGTT for execlists.
I915_ppgtt_init_hw() is a noop for execlists mode, but the new i915_ppgtt_init_ring() will try to do a switch_mm() which should not be done for execlists.
Thomas.
> +
> struct i915_hw_ppgtt *
> i915_ppgtt_create(struct drm_device *dev, struct drm_i915_file_private *fpriv)
> {
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h
> b/drivers/gpu/drm/i915/i915_gem_gtt.h
> index 8f76990..5a6cef9 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.h
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
> @@ -300,6 +300,7 @@ void i915_global_gtt_cleanup(struct drm_device *dev);
>
> int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
> int i915_ppgtt_init_hw(struct drm_device *dev);
> +int i915_ppgtt_init_ring(struct intel_engine_cs *ring);
> void i915_ppgtt_release(struct kref *kref);
> struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_device *dev,
> struct drm_i915_file_private *fpriv);
> --
> 1.7.9.5
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 17/53] drm/i915: Split i915_ppgtt_init_hw() in half - generic and per ring
2015-02-19 17:17 ` [PATCH 17/53] drm/i915: Split i915_ppgtt_init_hw() in half - generic and per ring John.C.Harrison
2015-02-24 13:55 ` Daniel, Thomas
@ 2015-03-05 16:53 ` Tomas Elf
1 sibling, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 16:53 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The i915_gem_init_hw() function calls a bunch of smaller initialisation
> functions. Multiple of which have generic sections and per ring sections. This
> means multiple passes are done over the rings. Each pass writes data to the ring
> which floats around in that ring's OLR until some random point in the future
> when an add_request() is done by some random other piece of code.
>
> This patch breaks i915_ppgtt_init_hw() in two with the per ring initialisation
> now being done in i915_ppgtt_init_ring(). The ring looping is now done at the
> top level in i915_gem_init_hw().
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 25 +++++++++++++++++++------
> drivers/gpu/drm/i915/i915_gem_gtt.c | 25 ++++++++++++-------------
> drivers/gpu/drm/i915/i915_gem_gtt.h | 1 +
> 3 files changed, 32 insertions(+), 19 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 51f719c..9bc60d7 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -4844,19 +4844,32 @@ i915_gem_init_hw(struct drm_device *dev)
> */
> init_unused_rings(dev);
>
> + ret = i915_ppgtt_init_hw(dev);
> + if (ret) {
> + DRM_ERROR("PPGTT enable HW failed %d\n", ret);
> + return ret;
> + }
> +
> + /* Need to do basic initialisation of all rings first: */
Nitpick: No need for trailing colon in comment
> for_each_ring(ring, dev_priv, i) {
> ret = ring->init_hw(ring);
> if (ret)
> return ret;
> }
>
> - for (i = 0; i < NUM_L3_SLICES(dev); i++)
> - i915_gem_l3_remap(&dev_priv->ring[RCS], i);
> + /* Now it is safe to go back round and do everything else: */
Nitpick: No need for trailing colon in comment
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
> + for_each_ring(ring, dev_priv, i) {
> + if (ring->id == RCS) {
> + for (i = 0; i < NUM_L3_SLICES(dev); i++)
> + i915_gem_l3_remap(ring, i);
> + }
>
> - ret = i915_ppgtt_init_hw(dev);
> - if (ret && ret != -EIO) {
> - DRM_ERROR("PPGTT enable failed %d\n", ret);
> - i915_gem_cleanup_ringbuffer(dev);
> + ret = i915_ppgtt_init_ring(ring);
> + if (ret && ret != -EIO) {
> + DRM_ERROR("PPGTT enable ring #%d failed %d\n", i, ret);
> + i915_gem_cleanup_ringbuffer(dev);
> + return ret;
> + }
> }
>
> ret = i915_gem_context_enable(dev_priv);
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index e54b2a0..428d2f6 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -1206,11 +1206,6 @@ int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
>
> int i915_ppgtt_init_hw(struct drm_device *dev)
> {
> - struct drm_i915_private *dev_priv = dev->dev_private;
> - struct intel_engine_cs *ring;
> - struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
> - int i, ret = 0;
> -
> /* In the case of execlists, PPGTT is enabled by the context descriptor
> * and the PDPs are contained within the context itself. We don't
> * need to do anything here. */
> @@ -1229,16 +1224,20 @@ int i915_ppgtt_init_hw(struct drm_device *dev)
> else
> MISSING_CASE(INTEL_INFO(dev)->gen);
>
> - if (ppgtt) {
> - for_each_ring(ring, dev_priv, i) {
> - ret = ppgtt->switch_mm(ppgtt, ring);
> - if (ret != 0)
> - return ret;
> - }
> - }
> + return 0;
> +}
>
> - return ret;
> +int i915_ppgtt_init_ring(struct intel_engine_cs *ring)
> +{
> + struct drm_i915_private *dev_priv = ring->dev->dev_private;
> + struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
> +
> + if (!ppgtt)
> + return 0;
> +
> + return ppgtt->switch_mm(ppgtt, ring);
> }
> +
> struct i915_hw_ppgtt *
> i915_ppgtt_create(struct drm_device *dev, struct drm_i915_file_private *fpriv)
> {
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
> index 8f76990..5a6cef9 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.h
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
> @@ -300,6 +300,7 @@ void i915_global_gtt_cleanup(struct drm_device *dev);
>
> int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
> int i915_ppgtt_init_hw(struct drm_device *dev);
> +int i915_ppgtt_init_ring(struct intel_engine_cs *ring);
> void i915_ppgtt_release(struct kref *kref);
> struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_device *dev,
> struct drm_i915_file_private *fpriv);
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 18/53] drm/i915: Moved the for_each_ring loop outside of i915_gem_context_enable()
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (16 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 17/53] drm/i915: Split i915_ppgtt_init_hw() in half - generic and per ring John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 17:04 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 19/53] drm/i915: Add explicit request management to i915_gem_init_hw() John.C.Harrison
` (36 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The start of day context initialisation code in i915_gem_context_enable() loops
over each ring and calls the legacy switch context or the execlist init context
code as appropriate.
This patch moves the ring looping out of that function in to the top level
caller i915_gem_init_hw(). This means the a single pass can be made over all
rings doing the PPGTT, L3 remap and context initialisation of each ring
altogether.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 2 +-
drivers/gpu/drm/i915/i915_gem.c | 18 ++++++++++-------
drivers/gpu/drm/i915/i915_gem_context.c | 32 +++++++++++--------------------
3 files changed, 23 insertions(+), 29 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index bfd7b47..653c82d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2989,7 +2989,7 @@ int __must_check i915_gem_context_init(struct drm_device *dev);
void i915_gem_context_fini(struct drm_device *dev);
void i915_gem_context_reset(struct drm_device *dev);
int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
-int i915_gem_context_enable(struct drm_i915_private *dev_priv);
+int i915_gem_context_enable(struct intel_engine_cs *ring);
void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
int i915_switch_context(struct intel_engine_cs *ring,
struct intel_context *to);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9bc60d7..5850991 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4844,6 +4844,8 @@ i915_gem_init_hw(struct drm_device *dev)
*/
init_unused_rings(dev);
+ BUG_ON(!dev_priv->ring[RCS].default_context);
+
ret = i915_ppgtt_init_hw(dev);
if (ret) {
DRM_ERROR("PPGTT enable HW failed %d\n", ret);
@@ -4859,6 +4861,8 @@ i915_gem_init_hw(struct drm_device *dev)
/* Now it is safe to go back round and do everything else: */
for_each_ring(ring, dev_priv, i) {
+ WARN_ON(!ring->default_context);
+
if (ring->id == RCS) {
for (i = 0; i < NUM_L3_SLICES(dev); i++)
i915_gem_l3_remap(ring, i);
@@ -4870,17 +4874,17 @@ i915_gem_init_hw(struct drm_device *dev)
i915_gem_cleanup_ringbuffer(dev);
return ret;
}
- }
- ret = i915_gem_context_enable(dev_priv);
- if (ret && ret != -EIO) {
- DRM_ERROR("Context enable failed %d\n", ret);
- i915_gem_cleanup_ringbuffer(dev);
+ ret = i915_gem_context_enable(ring);
+ if (ret && ret != -EIO) {
+ DRM_ERROR("Context enable ring #%d failed %d\n", i, ret);
+ i915_gem_cleanup_ringbuffer(dev);
- return ret;
+ return ret;
+ }
}
- return ret;
+ return 0;
}
int i915_gem_init(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 8603bf4..dd83d61 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -403,32 +403,22 @@ void i915_gem_context_fini(struct drm_device *dev)
i915_gem_context_unreference(dctx);
}
-int i915_gem_context_enable(struct drm_i915_private *dev_priv)
+int i915_gem_context_enable(struct intel_engine_cs *ring)
{
- struct intel_engine_cs *ring;
- int ret, i;
-
- BUG_ON(!dev_priv->ring[RCS].default_context);
+ int ret;
if (i915.enable_execlists) {
- for_each_ring(ring, dev_priv, i) {
- if (ring->init_context) {
- ret = ring->init_context(ring,
- ring->default_context);
- if (ret) {
- DRM_ERROR("ring init context: %d\n",
- ret);
- return ret;
- }
- }
- }
+ if (ring->init_context == NULL)
+ return 0;
+ ret = ring->init_context(ring, ring->default_context);
} else
- for_each_ring(ring, dev_priv, i) {
- ret = i915_switch_context(ring, ring->default_context);
- if (ret)
- return ret;
- }
+ ret = i915_switch_context(ring, ring->default_context);
+
+ if (ret) {
+ DRM_ERROR("ring init context: %d\n", ret);
+ return ret;
+ }
return 0;
}
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 18/53] drm/i915: Moved the for_each_ring loop outside of i915_gem_context_enable()
2015-02-19 17:17 ` [PATCH 18/53] drm/i915: Moved the for_each_ring loop outside of i915_gem_context_enable() John.C.Harrison
@ 2015-03-05 17:04 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 17:04 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The start of day context initialisation code in i915_gem_context_enable() loops
> over each ring and calls the legacy switch context or the execlist init context
> code as appropriate.
>
> This patch moves the ring looping out of that function in to the top level
> caller i915_gem_init_hw(). This means the a single pass can be made over all
> rings doing the PPGTT, L3 remap and context initialisation of each ring
> altogether.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 2 +-
> drivers/gpu/drm/i915/i915_gem.c | 18 ++++++++++-------
> drivers/gpu/drm/i915/i915_gem_context.c | 32 +++++++++++--------------------
> 3 files changed, 23 insertions(+), 29 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index bfd7b47..653c82d 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2989,7 +2989,7 @@ int __must_check i915_gem_context_init(struct drm_device *dev);
> void i915_gem_context_fini(struct drm_device *dev);
> void i915_gem_context_reset(struct drm_device *dev);
> int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
> -int i915_gem_context_enable(struct drm_i915_private *dev_priv);
> +int i915_gem_context_enable(struct intel_engine_cs *ring);
> void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
> int i915_switch_context(struct intel_engine_cs *ring,
> struct intel_context *to);
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 9bc60d7..5850991 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -4844,6 +4844,8 @@ i915_gem_init_hw(struct drm_device *dev)
> */
> init_unused_rings(dev);
>
> + BUG_ON(!dev_priv->ring[RCS].default_context);
> +
> ret = i915_ppgtt_init_hw(dev);
> if (ret) {
> DRM_ERROR("PPGTT enable HW failed %d\n", ret);
> @@ -4859,6 +4861,8 @@ i915_gem_init_hw(struct drm_device *dev)
>
> /* Now it is safe to go back round and do everything else: */
> for_each_ring(ring, dev_priv, i) {
> + WARN_ON(!ring->default_context);
> +
> if (ring->id == RCS) {
> for (i = 0; i < NUM_L3_SLICES(dev); i++)
> i915_gem_l3_remap(ring, i);
> @@ -4870,17 +4874,17 @@ i915_gem_init_hw(struct drm_device *dev)
> i915_gem_cleanup_ringbuffer(dev);
> return ret;
> }
> - }
>
> - ret = i915_gem_context_enable(dev_priv);
> - if (ret && ret != -EIO) {
> - DRM_ERROR("Context enable failed %d\n", ret);
> - i915_gem_cleanup_ringbuffer(dev);
> + ret = i915_gem_context_enable(ring);
> + if (ret && ret != -EIO) {
> + DRM_ERROR("Context enable ring #%d failed %d\n", i, ret);
> + i915_gem_cleanup_ringbuffer(dev);
>
> - return ret;
> + return ret;
> + }
> }
>
> - return ret;
> + return 0;
> }
>
> int i915_gem_init(struct drm_device *dev)
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index 8603bf4..dd83d61 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -403,32 +403,22 @@ void i915_gem_context_fini(struct drm_device *dev)
> i915_gem_context_unreference(dctx);
> }
>
> -int i915_gem_context_enable(struct drm_i915_private *dev_priv)
> +int i915_gem_context_enable(struct intel_engine_cs *ring)
> {
> - struct intel_engine_cs *ring;
> - int ret, i;
> -
> - BUG_ON(!dev_priv->ring[RCS].default_context);
> + int ret;
>
> if (i915.enable_execlists) {
> - for_each_ring(ring, dev_priv, i) {
> - if (ring->init_context) {
> - ret = ring->init_context(ring,
> - ring->default_context);
> - if (ret) {
> - DRM_ERROR("ring init context: %d\n",
> - ret);
> - return ret;
> - }
> - }
> - }
> + if (ring->init_context == NULL)
> + return 0;
>
> + ret = ring->init_context(ring, ring->default_context);
> } else
> - for_each_ring(ring, dev_priv, i) {
> - ret = i915_switch_context(ring, ring->default_context);
> - if (ret)
> - return ret;
> - }
> + ret = i915_switch_context(ring, ring->default_context);
> +
> + if (ret) {
> + DRM_ERROR("ring init context: %d\n", ret);
> + return ret;
> + }
>
> return 0;
> }
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 19/53] drm/i915: Add explicit request management to i915_gem_init_hw()
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (17 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 18/53] drm/i915: Moved the for_each_ring loop outside of i915_gem_context_enable() John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 17:13 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 20/53] drm/i915: Update ppgtt_init_ring() & context_enable() to take requests John.C.Harrison
` (35 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Now that a single per ring loop is being done for all the different
intialisation steps in i915_gem_init_hw(), it is possible to add proper request
management as well. The last remaining issue is that the context enable call
eventually ends up within *_render_state_init() and this does it's own private
_i915_add_request() call.
This patch adds explicit request creation and submission to the top level loop
and removes the add_request() from deep within the sub-functions. Note that the
old add_request() call was being passed a batch object. This is now explicitly
written to the request object instead. A warning has also been added to
i915_add_request() to ensure that there is never an attempt to add two batch
objects to a single request - e.g. because render_state_init() was called during
execbuffer processing.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 3 ++-
drivers/gpu/drm/i915/i915_gem.c | 18 ++++++++++++++++++
drivers/gpu/drm/i915/i915_gem_render_state.c | 3 ++-
drivers/gpu/drm/i915/intel_lrc.c | 8 +++-----
4 files changed, 25 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 653c82d..ea0da6b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2158,7 +2158,8 @@ struct drm_i915_gem_request {
struct intel_context *ctx;
struct intel_ringbuffer *ringbuf;
- /** Batch buffer related to this request if any */
+ /** Batch buffer related to this request if any (used for
+ error state dump only) */
struct drm_i915_gem_object *batch_obj;
/** Time at which this request was emitted, in jiffies. */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5850991..efed49a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2467,6 +2467,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
* inactive_list and lose its active reference. Hence we do not need
* to explicitly hold another reference here.
*/
+ WARN_ON(request->batch_obj && obj);
request->batch_obj = obj;
if (!i915.enable_execlists) {
@@ -4861,8 +4862,16 @@ i915_gem_init_hw(struct drm_device *dev)
/* 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);
+ ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
+ if (ret) {
+ i915_gem_cleanup_ringbuffer(dev);
+ return ret;
+ }
+
if (ring->id == RCS) {
for (i = 0; i < NUM_L3_SLICES(dev); i++)
i915_gem_l3_remap(ring, i);
@@ -4871,6 +4880,7 @@ i915_gem_init_hw(struct drm_device *dev)
ret = i915_ppgtt_init_ring(ring);
if (ret && ret != -EIO) {
DRM_ERROR("PPGTT enable ring #%d failed %d\n", i, ret);
+ i915_gem_request_unreference(req);
i915_gem_cleanup_ringbuffer(dev);
return ret;
}
@@ -4878,8 +4888,16 @@ i915_gem_init_hw(struct drm_device *dev)
ret = i915_gem_context_enable(ring);
if (ret && ret != -EIO) {
DRM_ERROR("Context enable ring #%d failed %d\n", i, ret);
+ i915_gem_request_unreference(req);
i915_gem_cleanup_ringbuffer(dev);
+ return ret;
+ }
+ ret = i915_add_request_no_flush(ring);
+ if (ret) {
+ DRM_ERROR("Add request ring #%d failed: %d\n", i, ret);
+ i915_gem_request_unreference(req);
+ i915_gem_cleanup_ringbuffer(dev);
return ret;
}
}
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index aba39c3..989476e 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -173,7 +173,8 @@ int i915_gem_render_state_init(struct intel_engine_cs *ring)
i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
- ret = __i915_add_request(ring, NULL, so.obj, true);
+ WARN_ON(ring->outstanding_lazy_request->batch_obj);
+ ring->outstanding_lazy_request->batch_obj = so.obj;
/* __i915_add_request moves object to inactive if it fails */
out:
i915_gem_render_state_fini(&so);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 0d88e9c..dff7829 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1350,8 +1350,6 @@ static int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
{
struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
struct render_state so;
- struct drm_i915_file_private *file_priv = ctx->file_priv;
- struct drm_file *file = file_priv ? file_priv->file : NULL;
int ret;
ret = i915_gem_render_state_prepare(ring, &so);
@@ -1370,9 +1368,9 @@ static int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
- ret = __i915_add_request(ring, file, so.obj, true);
- /* intel_logical_ring_add_request moves object to inactive if it
- * fails */
+ WARN_ON(ring->outstanding_lazy_request->batch_obj);
+ ring->outstanding_lazy_request->batch_obj = so.obj;
+ /* __i915_add_request moves object to inactive if it fails */
out:
i915_gem_render_state_fini(&so);
return ret;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 19/53] drm/i915: Add explicit request management to i915_gem_init_hw()
2015-02-19 17:17 ` [PATCH 19/53] drm/i915: Add explicit request management to i915_gem_init_hw() John.C.Harrison
@ 2015-03-05 17:13 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 17:13 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Now that a single per ring loop is being done for all the different
> intialisation steps in i915_gem_init_hw(), it is possible to add proper request
> management as well. The last remaining issue is that the context enable call
> eventually ends up within *_render_state_init() and this does it's own private
> _i915_add_request() call.
>
> This patch adds explicit request creation and submission to the top level loop
> and removes the add_request() from deep within the sub-functions. Note that the
> old add_request() call was being passed a batch object. This is now explicitly
> written to the request object instead. A warning has also been added to
> i915_add_request() to ensure that there is never an attempt to add two batch
> objects to a single request - e.g. because render_state_init() was called during
> execbuffer processing.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 3 ++-
> drivers/gpu/drm/i915/i915_gem.c | 18 ++++++++++++++++++
> drivers/gpu/drm/i915/i915_gem_render_state.c | 3 ++-
> drivers/gpu/drm/i915/intel_lrc.c | 8 +++-----
> 4 files changed, 25 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 653c82d..ea0da6b 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2158,7 +2158,8 @@ struct drm_i915_gem_request {
> struct intel_context *ctx;
> struct intel_ringbuffer *ringbuf;
>
> - /** Batch buffer related to this request if any */
> + /** Batch buffer related to this request if any (used for
> + error state dump only) */
> struct drm_i915_gem_object *batch_obj;
>
> /** Time at which this request was emitted, in jiffies. */
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 5850991..efed49a 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2467,6 +2467,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
> * inactive_list and lose its active reference. Hence we do not need
> * to explicitly hold another reference here.
> */
> + WARN_ON(request->batch_obj && obj);
> request->batch_obj = obj;
>
> if (!i915.enable_execlists) {
> @@ -4861,8 +4862,16 @@ i915_gem_init_hw(struct drm_device *dev)
>
> /* 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);
>
> + ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
> + if (ret) {
> + i915_gem_cleanup_ringbuffer(dev);
> + return ret;
> + }
> +
> if (ring->id == RCS) {
> for (i = 0; i < NUM_L3_SLICES(dev); i++)
> i915_gem_l3_remap(ring, i);
> @@ -4871,6 +4880,7 @@ i915_gem_init_hw(struct drm_device *dev)
> ret = i915_ppgtt_init_ring(ring);
> if (ret && ret != -EIO) {
> DRM_ERROR("PPGTT enable ring #%d failed %d\n", i, ret);
> + i915_gem_request_unreference(req);
> i915_gem_cleanup_ringbuffer(dev);
> return ret;
> }
> @@ -4878,8 +4888,16 @@ i915_gem_init_hw(struct drm_device *dev)
> ret = i915_gem_context_enable(ring);
> if (ret && ret != -EIO) {
> DRM_ERROR("Context enable ring #%d failed %d\n", i, ret);
> + i915_gem_request_unreference(req);
> i915_gem_cleanup_ringbuffer(dev);
> + return ret;
> + }
>
> + ret = i915_add_request_no_flush(ring);
> + if (ret) {
> + DRM_ERROR("Add request ring #%d failed: %d\n", i, ret);
> + i915_gem_request_unreference(req);
> + i915_gem_cleanup_ringbuffer(dev);
> return ret;
> }
> }
> diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
> index aba39c3..989476e 100644
> --- a/drivers/gpu/drm/i915/i915_gem_render_state.c
> +++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
> @@ -173,7 +173,8 @@ int i915_gem_render_state_init(struct intel_engine_cs *ring)
>
> i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
>
> - ret = __i915_add_request(ring, NULL, so.obj, true);
> + WARN_ON(ring->outstanding_lazy_request->batch_obj);
> + ring->outstanding_lazy_request->batch_obj = so.obj;
> /* __i915_add_request moves object to inactive if it fails */
> out:
> i915_gem_render_state_fini(&so);
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 0d88e9c..dff7829 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -1350,8 +1350,6 @@ static int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
> {
> struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
> struct render_state so;
> - struct drm_i915_file_private *file_priv = ctx->file_priv;
> - struct drm_file *file = file_priv ? file_priv->file : NULL;
> int ret;
>
> ret = i915_gem_render_state_prepare(ring, &so);
> @@ -1370,9 +1368,9 @@ static int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
>
> i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
>
> - ret = __i915_add_request(ring, file, so.obj, true);
> - /* intel_logical_ring_add_request moves object to inactive if it
> - * fails */
> + WARN_ON(ring->outstanding_lazy_request->batch_obj);
> + ring->outstanding_lazy_request->batch_obj = so.obj;
> + /* __i915_add_request moves object to inactive if it fails */
> out:
> i915_gem_render_state_fini(&so);
> return ret;
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 20/53] drm/i915: Update ppgtt_init_ring() & context_enable() to take requests
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (18 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 19/53] drm/i915: Add explicit request management to i915_gem_init_hw() John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 17:57 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 21/53] drm/i915: Set context in request from creation even in legacy mode John.C.Harrison
` (34 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The final step in removing the OLR from i915_gem_init_hw() is to pass the newly
allocated request structure in to each step rather than passing a ring
structure. This patch updates both i915_ppgtt_init_ring() and
i915_gem_context_enable() to take request pointers.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 2 +-
drivers/gpu/drm/i915/i915_gem.c | 4 ++--
drivers/gpu/drm/i915/i915_gem_context.c | 7 ++++---
drivers/gpu/drm/i915/i915_gem_gtt.c | 6 +++---
drivers/gpu/drm/i915/i915_gem_gtt.h | 2 +-
5 files changed, 11 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ea0da6b..618a841 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2990,7 +2990,7 @@ int __must_check i915_gem_context_init(struct drm_device *dev);
void i915_gem_context_fini(struct drm_device *dev);
void i915_gem_context_reset(struct drm_device *dev);
int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
-int i915_gem_context_enable(struct intel_engine_cs *ring);
+int i915_gem_context_enable(struct drm_i915_gem_request *req);
void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
int i915_switch_context(struct intel_engine_cs *ring,
struct intel_context *to);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index efed49a..379bf44 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4877,7 +4877,7 @@ i915_gem_init_hw(struct drm_device *dev)
i915_gem_l3_remap(ring, i);
}
- ret = i915_ppgtt_init_ring(ring);
+ ret = i915_ppgtt_init_ring(req);
if (ret && ret != -EIO) {
DRM_ERROR("PPGTT enable ring #%d failed %d\n", i, ret);
i915_gem_request_unreference(req);
@@ -4885,7 +4885,7 @@ i915_gem_init_hw(struct drm_device *dev)
return ret;
}
- ret = i915_gem_context_enable(ring);
+ ret = i915_gem_context_enable(req);
if (ret && ret != -EIO) {
DRM_ERROR("Context enable ring #%d failed %d\n", i, ret);
i915_gem_request_unreference(req);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index dd83d61..04d2a20 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -403,17 +403,18 @@ void i915_gem_context_fini(struct drm_device *dev)
i915_gem_context_unreference(dctx);
}
-int i915_gem_context_enable(struct intel_engine_cs *ring)
+int i915_gem_context_enable(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
if (i915.enable_execlists) {
if (ring->init_context == NULL)
return 0;
- ret = ring->init_context(ring, ring->default_context);
+ ret = ring->init_context(req->ring, ring->default_context);
} else
- ret = i915_switch_context(ring, ring->default_context);
+ ret = i915_switch_context(req->ring, ring->default_context);
if (ret) {
DRM_ERROR("ring init context: %d\n", ret);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 428d2f6..cd00080 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1227,15 +1227,15 @@ int i915_ppgtt_init_hw(struct drm_device *dev)
return 0;
}
-int i915_ppgtt_init_ring(struct intel_engine_cs *ring)
+int i915_ppgtt_init_ring(struct drm_i915_gem_request *req)
{
- struct drm_i915_private *dev_priv = ring->dev->dev_private;
+ struct drm_i915_private *dev_priv = req->ring->dev->dev_private;
struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
if (!ppgtt)
return 0;
- return ppgtt->switch_mm(ppgtt, ring);
+ return ppgtt->switch_mm(ppgtt, req->ring);
}
struct i915_hw_ppgtt *
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 5a6cef9..e7e202f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -300,7 +300,7 @@ void i915_global_gtt_cleanup(struct drm_device *dev);
int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
int i915_ppgtt_init_hw(struct drm_device *dev);
-int i915_ppgtt_init_ring(struct intel_engine_cs *ring);
+int i915_ppgtt_init_ring(struct drm_i915_gem_request *req);
void i915_ppgtt_release(struct kref *kref);
struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_device *dev,
struct drm_i915_file_private *fpriv);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 20/53] drm/i915: Update ppgtt_init_ring() & context_enable() to take requests
2015-02-19 17:17 ` [PATCH 20/53] drm/i915: Update ppgtt_init_ring() & context_enable() to take requests John.C.Harrison
@ 2015-03-05 17:57 ` Tomas Elf
[not found] ` <5502DC35.6020700@Intel.com>
0 siblings, 1 reply; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 17:57 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The final step in removing the OLR from i915_gem_init_hw() is to pass the newly
> allocated request structure in to each step rather than passing a ring
> structure. This patch updates both i915_ppgtt_init_ring() and
> i915_gem_context_enable() to take request pointers.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 2 +-
> drivers/gpu/drm/i915/i915_gem.c | 4 ++--
> drivers/gpu/drm/i915/i915_gem_context.c | 7 ++++---
> drivers/gpu/drm/i915/i915_gem_gtt.c | 6 +++---
> drivers/gpu/drm/i915/i915_gem_gtt.h | 2 +-
> 5 files changed, 11 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index ea0da6b..618a841 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2990,7 +2990,7 @@ int __must_check i915_gem_context_init(struct drm_device *dev);
> void i915_gem_context_fini(struct drm_device *dev);
> void i915_gem_context_reset(struct drm_device *dev);
> int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
> -int i915_gem_context_enable(struct intel_engine_cs *ring);
> +int i915_gem_context_enable(struct drm_i915_gem_request *req);
> void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
> int i915_switch_context(struct intel_engine_cs *ring,
> struct intel_context *to);
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index efed49a..379bf44 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -4877,7 +4877,7 @@ i915_gem_init_hw(struct drm_device *dev)
> i915_gem_l3_remap(ring, i);
> }
>
> - ret = i915_ppgtt_init_ring(ring);
> + ret = i915_ppgtt_init_ring(req);
> if (ret && ret != -EIO) {
> DRM_ERROR("PPGTT enable ring #%d failed %d\n", i, ret);
> i915_gem_request_unreference(req);
> @@ -4885,7 +4885,7 @@ i915_gem_init_hw(struct drm_device *dev)
> return ret;
> }
>
> - ret = i915_gem_context_enable(ring);
> + ret = i915_gem_context_enable(req);
> if (ret && ret != -EIO) {
> DRM_ERROR("Context enable ring #%d failed %d\n", i, ret);
> i915_gem_request_unreference(req);
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index dd83d61..04d2a20 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -403,17 +403,18 @@ void i915_gem_context_fini(struct drm_device *dev)
> i915_gem_context_unreference(dctx);
> }
>
> -int i915_gem_context_enable(struct intel_engine_cs *ring)
> +int i915_gem_context_enable(struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> if (i915.enable_execlists) {
> if (ring->init_context == NULL)
> return 0;
>
> - ret = ring->init_context(ring, ring->default_context);
> + ret = ring->init_context(req->ring, ring->default_context);
> } else
> - ret = i915_switch_context(ring, ring->default_context);
> + ret = i915_switch_context(req->ring, ring->default_context);
You don't have to make any more changes to this function aside from
setting up the ring variable at the top. ring = req->ring and if you
don't change these lines the will by default use ring like they always did.
>
> if (ret) {
> DRM_ERROR("ring init context: %d\n", ret);
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index 428d2f6..cd00080 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -1227,15 +1227,15 @@ int i915_ppgtt_init_hw(struct drm_device *dev)
> return 0;
> }
>
> -int i915_ppgtt_init_ring(struct intel_engine_cs *ring)
> +int i915_ppgtt_init_ring(struct drm_i915_gem_request *req)
> {
> - struct drm_i915_private *dev_priv = ring->dev->dev_private;
> + struct drm_i915_private *dev_priv = req->ring->dev->dev_private;
> struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
>
> if (!ppgtt)
> return 0;
>
> - return ppgtt->switch_mm(ppgtt, ring);
> + return ppgtt->switch_mm(ppgtt, req->ring);
> }
>
If you want to uphold a pattern that you've already established you
could just make a single change in the function above by setting up ring
= req->ring and then make no more changes to the function body. In this
case it's one new line vs. two changes of existing code so it's doesn't
make that much of a difference but it is nice to stick to patterns.
Also, you wouldn't have to make a 4-level indirection
(req->ring->dev->dev_private), only a 3-level one.
> struct i915_hw_ppgtt *
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
> index 5a6cef9..e7e202f 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.h
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
> @@ -300,7 +300,7 @@ void i915_global_gtt_cleanup(struct drm_device *dev);
>
> int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
> int i915_ppgtt_init_hw(struct drm_device *dev);
> -int i915_ppgtt_init_ring(struct intel_engine_cs *ring);
> +int i915_ppgtt_init_ring(struct drm_i915_gem_request *req);
> void i915_ppgtt_release(struct kref *kref);
> struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_device *dev,
> struct drm_i915_file_private *fpriv);
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 21/53] drm/i915: Set context in request from creation even in legacy mode
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (19 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 20/53] drm/i915: Update ppgtt_init_ring() & context_enable() to take requests John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 13:42 ` John.C.Harrison
2015-03-05 18:02 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 22/53] drm/i915: Update i915_switch_context() to take a request structure John.C.Harrison
` (33 subsequent siblings)
54 siblings, 2 replies; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
In execlist mode, the context object pointer is written in to the request
structure (and reference counted) at the point of request creation. In legacy
mode, this only happens inside i915_add_request().
This patch updates the legacy code path to match the execlist version. This
allows all the intermediate code between request creation and request submission
to get at the context object given only a request structure. Thus negating the
need to pass context pointers here, there and everywhere.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 9 +--------
drivers/gpu/drm/i915/intel_ringbuffer.c | 2 ++
2 files changed, 3 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 379bf44..64288e3 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2470,14 +2470,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
WARN_ON(request->batch_obj && obj);
request->batch_obj = obj;
- if (!i915.enable_execlists) {
- /* Hold a reference to the current context so that we can inspect
- * it later in case a hangcheck error event fires.
- */
- request->ctx = ring->last_context;
- if (request->ctx)
- i915_gem_context_reference(request->ctx);
- }
+ WARN_ON(request->ctx != ring->last_context);
request->emitted_jiffies = jiffies;
list_add_tail(&request->list, &ring->request_list);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 1a9f884..05a7e33 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2186,6 +2186,8 @@ intel_ring_alloc_request(struct intel_engine_cs *ring,
request->ring = ring;
request->ringbuf = ring->buffer;
request->uniq = dev_private->request_uniq++;
+ request->ctx = ctx;
+ i915_gem_context_reference(request->ctx);
ret = i915_gem_get_seqno(ring->dev, &request->seqno);
if (ret) {
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* [PATCH 21/53] drm/i915: Set context in request from creation even in legacy mode
2015-02-19 17:17 ` [PATCH 21/53] drm/i915: Set context in request from creation even in legacy mode John.C.Harrison
@ 2015-03-05 13:42 ` John.C.Harrison
2015-03-05 18:02 ` Tomas Elf
1 sibling, 0 replies; 234+ messages in thread
From: John.C.Harrison @ 2015-03-05 13:42 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
In execlist mode, the context object pointer is written in to the request
structure (and reference counted) at the point of request creation. In legacy
mode, this only happens inside i915_add_request().
This patch updates the legacy code path to match the execlist version. This
allows all the intermediate code between request creation and request submission
to get at the context object given only a request structure. Thus negating the
need to pass context pointers here, there and everywhere.
v2: Moved the context reference so it does not need to be undone if the
get_seqno() fails.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 9 +--------
drivers/gpu/drm/i915/intel_ringbuffer.c | 3 +++
2 files changed, 4 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 151ddb5..e237aa0 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2482,14 +2482,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
WARN_ON(request->batch_obj && obj);
request->batch_obj = obj;
- if (!i915.enable_execlists) {
- /* Hold a reference to the current context so that we can inspect
- * it later in case a hangcheck error event fires.
- */
- request->ctx = ring->last_context;
- if (request->ctx)
- i915_gem_context_reference(request->ctx);
- }
+ WARN_ON(request->ctx != ring->last_context);
request->emitted_jiffies = jiffies;
list_add_tail(&request->list, &ring->request_list);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index e7dd3cf..4550676 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2244,6 +2244,9 @@ intel_ring_alloc_request(struct intel_engine_cs *ring,
return ret;
}
+ request->ctx = ctx;
+ i915_gem_context_reference(request->ctx);
+
*req_out = ring->outstanding_lazy_request = request;
return 0;
}
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 21/53] drm/i915: Set context in request from creation even in legacy mode
2015-02-19 17:17 ` [PATCH 21/53] drm/i915: Set context in request from creation even in legacy mode John.C.Harrison
2015-03-05 13:42 ` John.C.Harrison
@ 2015-03-05 18:02 ` Tomas Elf
1 sibling, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 18:02 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> In execlist mode, the context object pointer is written in to the request
> structure (and reference counted) at the point of request creation. In legacy
> mode, this only happens inside i915_add_request().
>
> This patch updates the legacy code path to match the execlist version. This
> allows all the intermediate code between request creation and request submission
> to get at the context object given only a request structure. Thus negating the
> need to pass context pointers here, there and everywhere.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 9 +--------
> drivers/gpu/drm/i915/intel_ringbuffer.c | 2 ++
> 2 files changed, 3 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 379bf44..64288e3 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2470,14 +2470,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
> WARN_ON(request->batch_obj && obj);
> request->batch_obj = obj;
>
> - if (!i915.enable_execlists) {
> - /* Hold a reference to the current context so that we can inspect
> - * it later in case a hangcheck error event fires.
> - */
> - request->ctx = ring->last_context;
> - if (request->ctx)
> - i915_gem_context_reference(request->ctx);
> - }
> + WARN_ON(request->ctx != ring->last_context);
__i915_add_request is gen agnostic but ring->last_context is only used
in legacy mode. Maybe you want to check for !i915.enable_execlists just
like in the block you removed above?
>
> request->emitted_jiffies = jiffies;
> list_add_tail(&request->list, &ring->request_list);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 1a9f884..05a7e33 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -2186,6 +2186,8 @@ intel_ring_alloc_request(struct intel_engine_cs *ring,
> request->ring = ring;
> request->ringbuf = ring->buffer;
> request->uniq = dev_private->request_uniq++;
> + request->ctx = ctx;
> + i915_gem_context_reference(request->ctx);
>
> ret = i915_gem_get_seqno(ring->dev, &request->seqno);
> if (ret) {
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 22/53] drm/i915: Update i915_switch_context() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (20 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 21/53] drm/i915: Set context in request from creation even in legacy mode John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 18:08 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 23/53] drm/i915: Update do_switch() " John.C.Harrison
` (32 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Now that the request is guaranteed to specify the context, it is possible to
update the context switch code to use requests rather than ring and context
pairs. This patch updates i915_switch_context() accordingly.
Also removed the warning that the request's context must match the last context
switch's context. As the context switch now gets the context object from the
request structure, there is no longer any scope for the two to become out of
step.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 3 +--
drivers/gpu/drm/i915/i915_gem.c | 4 +---
drivers/gpu/drm/i915/i915_gem_context.c | 19 +++++++++----------
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
4 files changed, 12 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 618a841..e9cc343 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2992,8 +2992,7 @@ void i915_gem_context_reset(struct drm_device *dev);
int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
int i915_gem_context_enable(struct drm_i915_gem_request *req);
void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
-int i915_switch_context(struct intel_engine_cs *ring,
- struct intel_context *to);
+int i915_switch_context(struct drm_i915_gem_request *req);
struct intel_context *
i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id);
void i915_gem_context_free(struct kref *ctx_ref);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 64288e3..0c7e1bd 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2470,8 +2470,6 @@ int __i915_add_request(struct intel_engine_cs *ring,
WARN_ON(request->batch_obj && obj);
request->batch_obj = obj;
- WARN_ON(request->ctx != ring->last_context);
-
request->emitted_jiffies = jiffies;
list_add_tail(&request->list, &ring->request_list);
request->file_priv = NULL;
@@ -3114,7 +3112,7 @@ int i915_gpu_idle(struct drm_device *dev)
if (ret)
return ret;
- ret = i915_switch_context(req->ring, ring->default_context);
+ ret = i915_switch_context(req);
if (ret) {
i915_gem_request_unreference(req);
return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 04d2a20..b326f8d 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -414,7 +414,7 @@ int i915_gem_context_enable(struct drm_i915_gem_request *req)
ret = ring->init_context(req->ring, ring->default_context);
} else
- ret = i915_switch_context(req->ring, ring->default_context);
+ ret = i915_switch_context(req);
if (ret) {
DRM_ERROR("ring init context: %d\n", ret);
@@ -693,8 +693,7 @@ unpin_out:
/**
* i915_switch_context() - perform a GPU context switch.
- * @ring: ring for which we'll execute the context switch
- * @to: the context to switch to
+ * @req: request for which we'll execute the context switch
*
* The context life cycle is simple. The context refcount is incremented and
* decremented by 1 and create and destroy. If the context is in use by the GPU,
@@ -705,25 +704,25 @@ unpin_out:
* switched by writing to the ELSP and requests keep a reference to their
* context.
*/
-int i915_switch_context(struct intel_engine_cs *ring,
- struct intel_context *to)
+int i915_switch_context(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = ring->dev->dev_private;
WARN_ON(i915.enable_execlists);
WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
- if (to->legacy_hw_ctx.rcs_state == NULL) { /* We have the fake context */
- if (to != ring->last_context) {
- i915_gem_context_reference(to);
+ if (req->ctx->legacy_hw_ctx.rcs_state == NULL) { /* We have the fake context */
+ if (req->ctx != ring->last_context) {
+ i915_gem_context_reference(req->ctx);
if (ring->last_context)
i915_gem_context_unreference(ring->last_context);
- ring->last_context = to;
+ ring->last_context = req->ctx;
}
return 0;
}
- return do_switch(ring, to);
+ return do_switch(req->ring, req->ctx);
}
static bool contexts_enabled(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 2cd0579..1e2fc80 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1190,7 +1190,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
if (ret)
goto error;
- ret = i915_switch_context(ring, params->ctx);
+ ret = i915_switch_context(params->request);
if (ret)
goto error;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 22/53] drm/i915: Update i915_switch_context() to take a request structure
2015-02-19 17:17 ` [PATCH 22/53] drm/i915: Update i915_switch_context() to take a request structure John.C.Harrison
@ 2015-03-05 18:08 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 18:08 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Now that the request is guaranteed to specify the context, it is possible to
> update the context switch code to use requests rather than ring and context
> pairs. This patch updates i915_switch_context() accordingly.
>
> Also removed the warning that the request's context must match the last context
> switch's context. As the context switch now gets the context object from the
> request structure, there is no longer any scope for the two to become out of
> step.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 3 +--
> drivers/gpu/drm/i915/i915_gem.c | 4 +---
> drivers/gpu/drm/i915/i915_gem_context.c | 19 +++++++++----------
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
> 4 files changed, 12 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 618a841..e9cc343 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2992,8 +2992,7 @@ void i915_gem_context_reset(struct drm_device *dev);
> int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
> int i915_gem_context_enable(struct drm_i915_gem_request *req);
> void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
> -int i915_switch_context(struct intel_engine_cs *ring,
> - struct intel_context *to);
> +int i915_switch_context(struct drm_i915_gem_request *req);
> struct intel_context *
> i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id);
> void i915_gem_context_free(struct kref *ctx_ref);
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 64288e3..0c7e1bd 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2470,8 +2470,6 @@ int __i915_add_request(struct intel_engine_cs *ring,
> WARN_ON(request->batch_obj && obj);
> request->batch_obj = obj;
>
> - WARN_ON(request->ctx != ring->last_context);
> -
> request->emitted_jiffies = jiffies;
> list_add_tail(&request->list, &ring->request_list);
> request->file_priv = NULL;
> @@ -3114,7 +3112,7 @@ int i915_gpu_idle(struct drm_device *dev)
> if (ret)
> return ret;
>
> - ret = i915_switch_context(req->ring, ring->default_context);
> + ret = i915_switch_context(req);
> if (ret) {
> i915_gem_request_unreference(req);
> return ret;
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index 04d2a20..b326f8d 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -414,7 +414,7 @@ int i915_gem_context_enable(struct drm_i915_gem_request *req)
>
> ret = ring->init_context(req->ring, ring->default_context);
> } else
> - ret = i915_switch_context(req->ring, ring->default_context);
> + ret = i915_switch_context(req);
>
> if (ret) {
> DRM_ERROR("ring init context: %d\n", ret);
> @@ -693,8 +693,7 @@ unpin_out:
>
> /**
> * i915_switch_context() - perform a GPU context switch.
> - * @ring: ring for which we'll execute the context switch
> - * @to: the context to switch to
> + * @req: request for which we'll execute the context switch
> *
> * The context life cycle is simple. The context refcount is incremented and
> * decremented by 1 and create and destroy. If the context is in use by the GPU,
> @@ -705,25 +704,25 @@ unpin_out:
> * switched by writing to the ELSP and requests keep a reference to their
> * context.
> */
> -int i915_switch_context(struct intel_engine_cs *ring,
> - struct intel_context *to)
> +int i915_switch_context(struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct drm_i915_private *dev_priv = ring->dev->dev_private;
>
> WARN_ON(i915.enable_execlists);
> WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
>
> - if (to->legacy_hw_ctx.rcs_state == NULL) { /* We have the fake context */
> - if (to != ring->last_context) {
> - i915_gem_context_reference(to);
> + if (req->ctx->legacy_hw_ctx.rcs_state == NULL) { /* We have the fake context */
> + if (req->ctx != ring->last_context) {
> + i915_gem_context_reference(req->ctx);
> if (ring->last_context)
> i915_gem_context_unreference(ring->last_context);
> - ring->last_context = to;
> + ring->last_context = req->ctx;
> }
> return 0;
> }
>
> - return do_switch(ring, to);
> + return do_switch(req->ring, req->ctx);
> }
>
> static bool contexts_enabled(struct drm_device *dev)
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 2cd0579..1e2fc80 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1190,7 +1190,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> if (ret)
> goto error;
>
> - ret = i915_switch_context(ring, params->ctx);
> + ret = i915_switch_context(params->request);
> if (ret)
> goto error;
>
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 23/53] drm/i915: Update do_switch() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (21 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 22/53] drm/i915: Update i915_switch_context() to take a request structure John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 18:11 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 24/53] drm/i915: Update deferred context creation to do explicit request management John.C.Harrison
` (31 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated do_switch() to take a request pointer instead of a ring/context pair.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_context.c | 17 +++++++++--------
1 file changed, 9 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index b326f8d..eedb994 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -556,9 +556,10 @@ mi_set_context(struct intel_engine_cs *ring,
return ret;
}
-static int do_switch(struct intel_engine_cs *ring,
- struct intel_context *to)
+static int do_switch(struct drm_i915_gem_request *req)
{
+ struct intel_context *to = req->ctx;
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = ring->dev->dev_private;
struct intel_context *from = ring->last_context;
u32 hw_flags = 0;
@@ -591,7 +592,7 @@ static int do_switch(struct intel_engine_cs *ring,
if (to->ppgtt) {
trace_switch_mm(ring, to);
- ret = to->ppgtt->switch_mm(to->ppgtt, ring);
+ ret = to->ppgtt->switch_mm(to->ppgtt, req->ring);
if (ret)
goto unpin_out;
}
@@ -627,7 +628,7 @@ static int do_switch(struct intel_engine_cs *ring,
if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to))
hw_flags |= MI_RESTORE_INHIBIT;
- ret = mi_set_context(ring, to, hw_flags);
+ ret = mi_set_context(req->ring, to, hw_flags);
if (ret)
goto unpin_out;
@@ -635,7 +636,7 @@ static int do_switch(struct intel_engine_cs *ring,
if (!(to->remap_slice & (1<<i)))
continue;
- ret = i915_gem_l3_remap(ring, i);
+ ret = i915_gem_l3_remap(req->ring, i);
/* If it failed, try again next round */
if (ret)
DRM_DEBUG_DRIVER("L3 remapping failed\n");
@@ -651,7 +652,7 @@ static int do_switch(struct intel_engine_cs *ring,
*/
if (from != NULL) {
from->legacy_hw_ctx.rcs_state->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
- i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), ring);
+ i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), req->ring);
/* As long as MI_SET_CONTEXT is serializing, ie. it flushes the
* whole damn pipeline, we don't need to explicitly mark the
* object dirty. The only exception is that the context must be
@@ -677,7 +678,7 @@ done:
if (uninitialized) {
if (ring->init_context) {
- ret = ring->init_context(ring, to);
+ ret = ring->init_context(req->ring, to);
if (ret)
DRM_ERROR("ring init context: %d\n", ret);
}
@@ -722,7 +723,7 @@ int i915_switch_context(struct drm_i915_gem_request *req)
return 0;
}
- return do_switch(req->ring, req->ctx);
+ return do_switch(req);
}
static bool contexts_enabled(struct drm_device *dev)
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 23/53] drm/i915: Update do_switch() to take a request structure
2015-02-19 17:17 ` [PATCH 23/53] drm/i915: Update do_switch() " John.C.Harrison
@ 2015-03-05 18:11 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 18:11 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated do_switch() to take a request pointer instead of a ring/context pair.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_context.c | 17 +++++++++--------
> 1 file changed, 9 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index b326f8d..eedb994 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -556,9 +556,10 @@ mi_set_context(struct intel_engine_cs *ring,
> return ret;
> }
>
> -static int do_switch(struct intel_engine_cs *ring,
> - struct intel_context *to)
> +static int do_switch(struct drm_i915_gem_request *req)
> {
> + struct intel_context *to = req->ctx;
> + struct intel_engine_cs *ring = req->ring;
> struct drm_i915_private *dev_priv = ring->dev->dev_private;
> struct intel_context *from = ring->last_context;
> u32 hw_flags = 0;
> @@ -591,7 +592,7 @@ static int do_switch(struct intel_engine_cs *ring,
>
> if (to->ppgtt) {
> trace_switch_mm(ring, to);
> - ret = to->ppgtt->switch_mm(to->ppgtt, ring);
> + ret = to->ppgtt->switch_mm(to->ppgtt, req->ring);
No need for this change, ring = req->ring has already been set up. Just
leave the code as it was.
> if (ret)
> goto unpin_out;
> }
> @@ -627,7 +628,7 @@ static int do_switch(struct intel_engine_cs *ring,
> if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to))
> hw_flags |= MI_RESTORE_INHIBIT;
>
> - ret = mi_set_context(ring, to, hw_flags);
> + ret = mi_set_context(req->ring, to, hw_flags);
No need for this change, ring = req->ring has already been set up. Just
leave the code as it was.
> if (ret)
> goto unpin_out;
>
> @@ -635,7 +636,7 @@ static int do_switch(struct intel_engine_cs *ring,
> if (!(to->remap_slice & (1<<i)))
> continue;
>
> - ret = i915_gem_l3_remap(ring, i);
> + ret = i915_gem_l3_remap(req->ring, i);
No need for this change, ring = req->ring has already been set up. Just
leave the code as it was.
> /* If it failed, try again next round */
> if (ret)
> DRM_DEBUG_DRIVER("L3 remapping failed\n");
> @@ -651,7 +652,7 @@ static int do_switch(struct intel_engine_cs *ring,
> */
> if (from != NULL) {
> from->legacy_hw_ctx.rcs_state->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
> - i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), ring);
> + i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), req->ring);
No need for this change, ring = req->ring has already been set up. Just
leave the code as it was.
> /* As long as MI_SET_CONTEXT is serializing, ie. it flushes the
> * whole damn pipeline, we don't need to explicitly mark the
> * object dirty. The only exception is that the context must be
> @@ -677,7 +678,7 @@ done:
>
> if (uninitialized) {
> if (ring->init_context) {
> - ret = ring->init_context(ring, to);
> + ret = ring->init_context(req->ring, to);
No need for this change, ring = req->ring has already been set up. Just
leave the code as it was.
> if (ret)
> DRM_ERROR("ring init context: %d\n", ret);
> }
> @@ -722,7 +723,7 @@ int i915_switch_context(struct drm_i915_gem_request *req)
> return 0;
> }
>
> - return do_switch(req->ring, req->ctx);
> + return do_switch(req);
> }
>
> static bool contexts_enabled(struct drm_device *dev)
>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 24/53] drm/i915: Update deferred context creation to do explicit request management
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (22 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 23/53] drm/i915: Update do_switch() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 18:16 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 25/53] drm/i915: Update init_context() to take a request structure John.C.Harrison
` (30 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
In execlist mode, context initialisation is deferred until first use of the
given context. This is because execlist mode has many more contexts than legacy
mode and many are never actually used. Previously, the initialisation commands
were written to the ring and tagged with some random request structure via the
OLR. This seemed to be causing a null pointer deference bug under certain
circumstances (BZ:40112).
This patch adds explicit request creation and submission to the deferred
initialisation code path. Thus removing any reliance on or randomness caused by
the OLR.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_lrc.c | 17 ++++++++++++++++-
1 file changed, 16 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index dff7829..4bcb70e 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1849,6 +1849,7 @@ static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring,
int intel_lr_context_deferred_create(struct intel_context *ctx,
struct intel_engine_cs *ring)
{
+ struct drm_i915_private *dev_priv = ring->dev->dev_private;
const bool is_global_default_ctx = (ctx == ring->default_context);
struct drm_device *dev = ring->dev;
struct drm_i915_gem_object *ctx_obj;
@@ -1929,13 +1930,27 @@ int intel_lr_context_deferred_create(struct intel_context *ctx,
lrc_setup_hardware_status_page(ring, ctx_obj);
else if (ring->id == RCS && !ctx->rcs_initialized) {
if (ring->init_context) {
- ret = ring->init_context(ring, ctx);
+ struct drm_i915_gem_request *req;
+
+ ret = dev_priv->gt.alloc_request(ring, ctx, &req);
+ if (ret)
+ return ret;
+
+ ret = ring->init_context(req->ring, ctx);
if (ret) {
DRM_ERROR("ring init context: %d\n", ret);
+ i915_gem_request_unreference(req);
ctx->engine[ring->id].ringbuf = NULL;
ctx->engine[ring->id].state = NULL;
goto error;
}
+
+ ret = i915_add_request_no_flush(req->ring);
+ if (ret) {
+ DRM_ERROR("ring init context: %d\n", ret);
+ i915_gem_request_unreference(req);
+ goto error;
+ }
}
ctx->rcs_initialized = true;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 24/53] drm/i915: Update deferred context creation to do explicit request management
2015-02-19 17:17 ` [PATCH 24/53] drm/i915: Update deferred context creation to do explicit request management John.C.Harrison
@ 2015-03-05 18:16 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 18:16 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> In execlist mode, context initialisation is deferred until first use of the
> given context. This is because execlist mode has many more contexts than legacy
> mode and many are never actually used. Previously, the initialisation commands
> were written to the ring and tagged with some random request structure via the
> OLR. This seemed to be causing a null pointer deference bug under certain
> circumstances (BZ:40112).
>
> This patch adds explicit request creation and submission to the deferred
> initialisation code path. Thus removing any reliance on or randomness caused by
> the OLR.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_lrc.c | 17 ++++++++++++++++-
> 1 file changed, 16 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index dff7829..4bcb70e 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -1849,6 +1849,7 @@ static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring,
> int intel_lr_context_deferred_create(struct intel_context *ctx,
> struct intel_engine_cs *ring)
> {
> + struct drm_i915_private *dev_priv = ring->dev->dev_private;
> const bool is_global_default_ctx = (ctx == ring->default_context);
> struct drm_device *dev = ring->dev;
> struct drm_i915_gem_object *ctx_obj;
> @@ -1929,13 +1930,27 @@ int intel_lr_context_deferred_create(struct intel_context *ctx,
> lrc_setup_hardware_status_page(ring, ctx_obj);
> else if (ring->id == RCS && !ctx->rcs_initialized) {
> if (ring->init_context) {
> - ret = ring->init_context(ring, ctx);
> + struct drm_i915_gem_request *req;
> +
> + ret = dev_priv->gt.alloc_request(ring, ctx, &req);
> + if (ret)
> + return ret;
> +
> + ret = ring->init_context(req->ring, ctx);
> if (ret) {
> DRM_ERROR("ring init context: %d\n", ret);
> + i915_gem_request_unreference(req);
> ctx->engine[ring->id].ringbuf = NULL;
> ctx->engine[ring->id].state = NULL;
> goto error;
> }
> +
> + ret = i915_add_request_no_flush(req->ring);
> + if (ret) {
> + DRM_ERROR("ring init context: %d\n", ret);
> + i915_gem_request_unreference(req);
> + goto error;
> + }
> }
>
> ctx->rcs_initialized = true;
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 25/53] drm/i915: Update init_context() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (23 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 24/53] drm/i915: Update deferred context creation to do explicit request management John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 18:38 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 26/53] drm/i915: Update render_state_init() " John.C.Harrison
` (29 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Now that everything above has been converted to use requests, it is possible to
update init_context() to take a request pointer instead of a ring/context pair.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_context.c | 4 ++--
drivers/gpu/drm/i915/intel_lrc.c | 9 ++++-----
drivers/gpu/drm/i915/intel_ringbuffer.c | 7 +++----
drivers/gpu/drm/i915/intel_ringbuffer.h | 3 +--
4 files changed, 10 insertions(+), 13 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index eedb994..938cd26 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -412,7 +412,7 @@ int i915_gem_context_enable(struct drm_i915_gem_request *req)
if (ring->init_context == NULL)
return 0;
- ret = ring->init_context(req->ring, ring->default_context);
+ ret = ring->init_context(req);
} else
ret = i915_switch_context(req);
@@ -678,7 +678,7 @@ done:
if (uninitialized) {
if (ring->init_context) {
- ret = ring->init_context(req->ring, to);
+ ret = ring->init_context(req);
if (ret)
DRM_ERROR("ring init context: %d\n", ret);
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 4bcb70e..cbec056 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1376,16 +1376,15 @@ out:
return ret;
}
-static int gen8_init_rcs_context(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int gen8_init_rcs_context(struct drm_i915_gem_request *req)
{
int ret;
- ret = intel_logical_ring_workarounds_emit(ring, ctx);
+ ret = intel_logical_ring_workarounds_emit(req->ring, req->ctx);
if (ret)
return ret;
- return intel_lr_context_render_state_init(ring, ctx);
+ return intel_lr_context_render_state_init(req->ring, req->ctx);
}
/**
@@ -1936,7 +1935,7 @@ int intel_lr_context_deferred_create(struct intel_context *ctx,
if (ret)
return ret;
- ret = ring->init_context(req->ring, ctx);
+ ret = ring->init_context(req);
if (ret) {
DRM_ERROR("ring init context: %d\n", ret);
i915_gem_request_unreference(req);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 05a7e33..26964a2 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -775,16 +775,15 @@ static int intel_ring_workarounds_emit(struct intel_engine_cs *ring,
return 0;
}
-static int intel_rcs_ctx_init(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int intel_rcs_ctx_init(struct drm_i915_gem_request *req)
{
int ret;
- ret = intel_ring_workarounds_emit(ring, ctx);
+ ret = intel_ring_workarounds_emit(req->ring, req->ctx);
if (ret != 0)
return ret;
- ret = i915_gem_render_state_init(ring);
+ ret = i915_gem_render_state_init(req->ring);
if (ret)
DRM_ERROR("init render state: %d\n", ret);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 4f8a14a..c32f5a1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -143,8 +143,7 @@ struct intel_engine_cs {
int (*init_hw)(struct intel_engine_cs *ring);
- int (*init_context)(struct intel_engine_cs *ring,
- struct intel_context *ctx);
+ int (*init_context)(struct drm_i915_gem_request *req);
void (*write_tail)(struct intel_engine_cs *ring,
u32 value);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 25/53] drm/i915: Update init_context() to take a request structure
2015-02-19 17:17 ` [PATCH 25/53] drm/i915: Update init_context() to take a request structure John.C.Harrison
@ 2015-03-05 18:38 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 18:38 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Now that everything above has been converted to use requests, it is possible to
> update init_context() to take a request pointer instead of a ring/context pair.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_context.c | 4 ++--
> drivers/gpu/drm/i915/intel_lrc.c | 9 ++++-----
> drivers/gpu/drm/i915/intel_ringbuffer.c | 7 +++----
> drivers/gpu/drm/i915/intel_ringbuffer.h | 3 +--
> 4 files changed, 10 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index eedb994..938cd26 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -412,7 +412,7 @@ int i915_gem_context_enable(struct drm_i915_gem_request *req)
> if (ring->init_context == NULL)
> return 0;
>
> - ret = ring->init_context(req->ring, ring->default_context);
> + ret = ring->init_context(req);
> } else
> ret = i915_switch_context(req);
>
> @@ -678,7 +678,7 @@ done:
>
> if (uninitialized) {
> if (ring->init_context) {
> - ret = ring->init_context(req->ring, to);
> + ret = ring->init_context(req);
> if (ret)
> DRM_ERROR("ring init context: %d\n", ret);
> }
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 4bcb70e..cbec056 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -1376,16 +1376,15 @@ out:
> return ret;
> }
>
> -static int gen8_init_rcs_context(struct intel_engine_cs *ring,
> - struct intel_context *ctx)
> +static int gen8_init_rcs_context(struct drm_i915_gem_request *req)
> {
> int ret;
>
> - ret = intel_logical_ring_workarounds_emit(ring, ctx);
> + ret = intel_logical_ring_workarounds_emit(req->ring, req->ctx);
> if (ret)
> return ret;
>
> - return intel_lr_context_render_state_init(ring, ctx);
> + return intel_lr_context_render_state_init(req->ring, req->ctx);
> }
>
> /**
> @@ -1936,7 +1935,7 @@ int intel_lr_context_deferred_create(struct intel_context *ctx,
> if (ret)
> return ret;
>
> - ret = ring->init_context(req->ring, ctx);
> + ret = ring->init_context(req);
> if (ret) {
> DRM_ERROR("ring init context: %d\n", ret);
> i915_gem_request_unreference(req);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 05a7e33..26964a2 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -775,16 +775,15 @@ static int intel_ring_workarounds_emit(struct intel_engine_cs *ring,
> return 0;
> }
>
> -static int intel_rcs_ctx_init(struct intel_engine_cs *ring,
> - struct intel_context *ctx)
> +static int intel_rcs_ctx_init(struct drm_i915_gem_request *req)
> {
> int ret;
>
> - ret = intel_ring_workarounds_emit(ring, ctx);
> + ret = intel_ring_workarounds_emit(req->ring, req->ctx);
> if (ret != 0)
> return ret;
>
> - ret = i915_gem_render_state_init(ring);
> + ret = i915_gem_render_state_init(req->ring);
> if (ret)
> DRM_ERROR("init render state: %d\n", ret);
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 4f8a14a..c32f5a1 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -143,8 +143,7 @@ struct intel_engine_cs {
>
> int (*init_hw)(struct intel_engine_cs *ring);
>
> - int (*init_context)(struct intel_engine_cs *ring,
> - struct intel_context *ctx);
> + int (*init_context)(struct drm_i915_gem_request *req);
>
> void (*write_tail)(struct intel_engine_cs *ring,
> u32 value);
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 26/53] drm/i915: Update render_state_init() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (24 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 25/53] drm/i915: Update init_context() to take a request structure John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 18:43 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 27/53] drm/i915: Update overlay code to do explicit request management John.C.Harrison
` (28 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the two render_state_init() functions to take a request pointer instead
of a ring. This removes their reliance on the OLR.
v2: Rebased to newer tree.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_render_state.c | 18 +++++++++---------
drivers/gpu/drm/i915/i915_gem_render_state.h | 2 +-
drivers/gpu/drm/i915/intel_lrc.c | 22 ++++++++++------------
drivers/gpu/drm/i915/intel_ringbuffer.c | 2 +-
4 files changed, 21 insertions(+), 23 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index 989476e..85cc746 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -152,29 +152,29 @@ int i915_gem_render_state_prepare(struct intel_engine_cs *ring,
return 0;
}
-int i915_gem_render_state_init(struct intel_engine_cs *ring)
+int i915_gem_render_state_init(struct drm_i915_gem_request *req)
{
struct render_state so;
int ret;
- ret = i915_gem_render_state_prepare(ring, &so);
+ ret = i915_gem_render_state_prepare(req->ring, &so);
if (ret)
return ret;
if (so.rodata == NULL)
return 0;
- ret = ring->dispatch_execbuffer(ring,
- so.ggtt_offset,
- so.rodata->batch_items * 4,
- I915_DISPATCH_SECURE);
+ ret = req->ring->dispatch_execbuffer(req->ring,
+ so.ggtt_offset,
+ so.rodata->batch_items * 4,
+ I915_DISPATCH_SECURE);
if (ret)
goto out;
- i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
+ i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req->ring);
- WARN_ON(ring->outstanding_lazy_request->batch_obj);
- ring->outstanding_lazy_request->batch_obj = so.obj;
+ WARN_ON(req->batch_obj);
+ req->batch_obj = so.obj;
/* __i915_add_request moves object to inactive if it fails */
out:
i915_gem_render_state_fini(&so);
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.h b/drivers/gpu/drm/i915/i915_gem_render_state.h
index c44961e..7aa7372 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.h
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.h
@@ -39,7 +39,7 @@ struct render_state {
int gen;
};
-int i915_gem_render_state_init(struct intel_engine_cs *ring);
+int i915_gem_render_state_init(struct drm_i915_gem_request *req);
void i915_gem_render_state_fini(struct render_state *so);
int i915_gem_render_state_prepare(struct intel_engine_cs *ring,
struct render_state *so);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index cbec056..f0bb98a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1345,31 +1345,29 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf,
return 0;
}
-static int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req)
{
- struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
struct render_state so;
int ret;
- ret = i915_gem_render_state_prepare(ring, &so);
+ ret = i915_gem_render_state_prepare(req->ring, &so);
if (ret)
return ret;
if (so.rodata == NULL)
return 0;
- ret = ring->emit_bb_start(ringbuf,
- ctx,
- so.ggtt_offset,
- I915_DISPATCH_SECURE);
+ ret = req->ring->emit_bb_start(req->ringbuf,
+ req->ctx,
+ so.ggtt_offset,
+ I915_DISPATCH_SECURE);
if (ret)
goto out;
- i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
+ i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req->ring);
- WARN_ON(ring->outstanding_lazy_request->batch_obj);
- ring->outstanding_lazy_request->batch_obj = so.obj;
+ WARN_ON(req->batch_obj);
+ req->batch_obj = so.obj;
/* __i915_add_request moves object to inactive if it fails */
out:
i915_gem_render_state_fini(&so);
@@ -1384,7 +1382,7 @@ static int gen8_init_rcs_context(struct drm_i915_gem_request *req)
if (ret)
return ret;
- return intel_lr_context_render_state_init(req->ring, req->ctx);
+ return intel_lr_context_render_state_init(req);
}
/**
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 26964a2..efb1729 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -783,7 +783,7 @@ static int intel_rcs_ctx_init(struct drm_i915_gem_request *req)
if (ret != 0)
return ret;
- ret = i915_gem_render_state_init(req->ring);
+ ret = i915_gem_render_state_init(req);
if (ret)
DRM_ERROR("init render state: %d\n", ret);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 26/53] drm/i915: Update render_state_init() to take a request structure
2015-02-19 17:17 ` [PATCH 26/53] drm/i915: Update render_state_init() " John.C.Harrison
@ 2015-03-05 18:43 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 18:43 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the two render_state_init() functions to take a request pointer instead
> of a ring. This removes their reliance on the OLR.
>
> v2: Rebased to newer tree.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_render_state.c | 18 +++++++++---------
> drivers/gpu/drm/i915/i915_gem_render_state.h | 2 +-
> drivers/gpu/drm/i915/intel_lrc.c | 22 ++++++++++------------
> drivers/gpu/drm/i915/intel_ringbuffer.c | 2 +-
> 4 files changed, 21 insertions(+), 23 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
> index 989476e..85cc746 100644
> --- a/drivers/gpu/drm/i915/i915_gem_render_state.c
> +++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
> @@ -152,29 +152,29 @@ int i915_gem_render_state_prepare(struct intel_engine_cs *ring,
> return 0;
> }
>
> -int i915_gem_render_state_init(struct intel_engine_cs *ring)
> +int i915_gem_render_state_init(struct drm_i915_gem_request *req)
> {
> struct render_state so;
> int ret;
>
> - ret = i915_gem_render_state_prepare(ring, &so);
> + ret = i915_gem_render_state_prepare(req->ring, &so);
> if (ret)
> return ret;
>
> if (so.rodata == NULL)
> return 0;
>
> - ret = ring->dispatch_execbuffer(ring,
> - so.ggtt_offset,
> - so.rodata->batch_items * 4,
> - I915_DISPATCH_SECURE);
> + ret = req->ring->dispatch_execbuffer(req->ring,
> + so.ggtt_offset,
> + so.rodata->batch_items * 4,
> + I915_DISPATCH_SECURE);
> if (ret)
> goto out;
>
> - i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
> + i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req->ring);
>
> - WARN_ON(ring->outstanding_lazy_request->batch_obj);
> - ring->outstanding_lazy_request->batch_obj = so.obj;
> + WARN_ON(req->batch_obj);
> + req->batch_obj = so.obj;
> /* __i915_add_request moves object to inactive if it fails */
> out:
> i915_gem_render_state_fini(&so);
> diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.h b/drivers/gpu/drm/i915/i915_gem_render_state.h
> index c44961e..7aa7372 100644
> --- a/drivers/gpu/drm/i915/i915_gem_render_state.h
> +++ b/drivers/gpu/drm/i915/i915_gem_render_state.h
> @@ -39,7 +39,7 @@ struct render_state {
> int gen;
> };
>
> -int i915_gem_render_state_init(struct intel_engine_cs *ring);
> +int i915_gem_render_state_init(struct drm_i915_gem_request *req);
> void i915_gem_render_state_fini(struct render_state *so);
> int i915_gem_render_state_prepare(struct intel_engine_cs *ring,
> struct render_state *so);
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index cbec056..f0bb98a 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -1345,31 +1345,29 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf,
> return 0;
> }
>
> -static int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
> - struct intel_context *ctx)
> +static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req)
> {
> - struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
> struct render_state so;
> int ret;
>
> - ret = i915_gem_render_state_prepare(ring, &so);
> + ret = i915_gem_render_state_prepare(req->ring, &so);
> if (ret)
> return ret;
>
> if (so.rodata == NULL)
> return 0;
>
> - ret = ring->emit_bb_start(ringbuf,
> - ctx,
> - so.ggtt_offset,
> - I915_DISPATCH_SECURE);
> + ret = req->ring->emit_bb_start(req->ringbuf,
> + req->ctx,
> + so.ggtt_offset,
> + I915_DISPATCH_SECURE);
> if (ret)
> goto out;
>
> - i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
> + i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req->ring);
>
> - WARN_ON(ring->outstanding_lazy_request->batch_obj);
> - ring->outstanding_lazy_request->batch_obj = so.obj;
> + WARN_ON(req->batch_obj);
> + req->batch_obj = so.obj;
> /* __i915_add_request moves object to inactive if it fails */
> out:
> i915_gem_render_state_fini(&so);
> @@ -1384,7 +1382,7 @@ static int gen8_init_rcs_context(struct drm_i915_gem_request *req)
> if (ret)
> return ret;
>
> - return intel_lr_context_render_state_init(req->ring, req->ctx);
> + return intel_lr_context_render_state_init(req);
> }
>
> /**
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 26964a2..efb1729 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -783,7 +783,7 @@ static int intel_rcs_ctx_init(struct drm_i915_gem_request *req)
> if (ret != 0)
> return ret;
>
> - ret = i915_gem_render_state_init(req->ring);
> + ret = i915_gem_render_state_init(req);
> if (ret)
> DRM_ERROR("init render state: %d\n", ret);
>
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 27/53] drm/i915: Update overlay code to do explicit request management
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (25 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 26/53] drm/i915: Update render_state_init() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 18:51 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 28/53] drm/i915: Update queue_flip() " John.C.Harrison
` (27 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The overlay update code path to do explicit request creation and submission
rather than relying on the OLR to do the right thing.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_overlay.c | 64 +++++++++++++++++++++++++---------
1 file changed, 48 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index f93dfc1..dc209bf 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -209,19 +209,19 @@ static void intel_overlay_unmap_regs(struct intel_overlay *overlay,
}
static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
+ struct drm_i915_gem_request *req,
void (*tail)(struct intel_overlay *))
{
struct drm_device *dev = overlay->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_engine_cs *ring = &dev_priv->ring[RCS];
int ret;
BUG_ON(overlay->last_flip_req);
- i915_gem_request_assign(&overlay->last_flip_req,
- ring->outstanding_lazy_request);
- ret = i915_add_request(ring);
- if (ret)
+ i915_gem_request_assign(&overlay->last_flip_req, req);
+ ret = i915_add_request(req->ring);
+ if (ret) {
+ i915_gem_request_unreference(req);
return ret;
+ }
overlay->flip_tail = tail;
ret = i915_wait_request(overlay->last_flip_req);
@@ -239,6 +239,7 @@ static int intel_overlay_on(struct intel_overlay *overlay)
struct drm_device *dev = overlay->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *ring = &dev_priv->ring[RCS];
+ struct drm_i915_gem_request *req;
int ret;
BUG_ON(overlay->active);
@@ -246,17 +247,23 @@ static int intel_overlay_on(struct intel_overlay *overlay)
WARN_ON(IS_I830(dev) && !(dev_priv->quirks & QUIRK_PIPEA_FORCE));
- ret = intel_ring_begin(ring, 4);
+ ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
if (ret)
return ret;
+ ret = intel_ring_begin(ring, 4);
+ if (ret) {
+ i915_gem_request_unreference(req);
+ return ret;
+ }
+
intel_ring_emit(ring, MI_OVERLAY_FLIP | MI_OVERLAY_ON);
intel_ring_emit(ring, overlay->flip_addr | OFC_UPDATE);
intel_ring_emit(ring, MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
intel_ring_emit(ring, MI_NOOP);
intel_ring_advance(ring);
- return intel_overlay_do_wait_request(overlay, NULL);
+ return intel_overlay_do_wait_request(overlay, req, NULL);
}
/* overlay needs to be enabled in OCMD reg */
@@ -266,6 +273,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
struct drm_device *dev = overlay->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *ring = &dev_priv->ring[RCS];
+ struct drm_i915_gem_request *req;
u32 flip_addr = overlay->flip_addr;
u32 tmp;
int ret;
@@ -280,18 +288,27 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
if (tmp & (1 << 17))
DRM_DEBUG("overlay underrun, DOVSTA: %x\n", tmp);
- ret = intel_ring_begin(ring, 2);
+ ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
if (ret)
return ret;
+ ret = intel_ring_begin(ring, 2);
+ if (ret) {
+ i915_gem_request_unreference(req);
+ return ret;
+ }
+
intel_ring_emit(ring, MI_OVERLAY_FLIP | MI_OVERLAY_CONTINUE);
intel_ring_emit(ring, flip_addr);
intel_ring_advance(ring);
WARN_ON(overlay->last_flip_req);
- i915_gem_request_assign(&overlay->last_flip_req,
- ring->outstanding_lazy_request);
- return i915_add_request(ring);
+ i915_gem_request_assign(&overlay->last_flip_req, req);
+ ret = i915_add_request(req->ring);
+ if (ret)
+ i915_gem_request_unreference(req);
+
+ return ret;
}
static void intel_overlay_release_old_vid_tail(struct intel_overlay *overlay)
@@ -326,6 +343,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
struct drm_device *dev = overlay->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *ring = &dev_priv->ring[RCS];
+ struct drm_i915_gem_request *req;
u32 flip_addr = overlay->flip_addr;
int ret;
@@ -337,10 +355,16 @@ static int intel_overlay_off(struct intel_overlay *overlay)
* of the hw. Do it in both cases */
flip_addr |= OFC_UPDATE;
- ret = intel_ring_begin(ring, 6);
+ ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
if (ret)
return ret;
+ ret = intel_ring_begin(ring, 6);
+ if (ret) {
+ i915_gem_request_unreference(req);
+ return ret;
+ }
+
/* wait for overlay to go idle */
intel_ring_emit(ring, MI_OVERLAY_FLIP | MI_OVERLAY_CONTINUE);
intel_ring_emit(ring, flip_addr);
@@ -359,7 +383,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
}
intel_ring_advance(ring);
- return intel_overlay_do_wait_request(overlay, intel_overlay_off_tail);
+ return intel_overlay_do_wait_request(overlay, req, intel_overlay_off_tail);
}
/* recover from an interruption due to a signal
@@ -404,15 +428,23 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
if (I915_READ(ISR) & I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT) {
/* synchronous slowpath */
- ret = intel_ring_begin(ring, 2);
+ struct drm_i915_gem_request *req;
+
+ ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
if (ret)
return ret;
+ ret = intel_ring_begin(ring, 2);
+ if (ret) {
+ i915_gem_request_unreference(req);
+ return ret;
+ }
+
intel_ring_emit(ring, MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
intel_ring_emit(ring, MI_NOOP);
intel_ring_advance(ring);
- ret = intel_overlay_do_wait_request(overlay,
+ ret = intel_overlay_do_wait_request(overlay, req,
intel_overlay_release_old_vid_tail);
if (ret)
return ret;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 27/53] drm/i915: Update overlay code to do explicit request management
2015-02-19 17:17 ` [PATCH 27/53] drm/i915: Update overlay code to do explicit request management John.C.Harrison
@ 2015-03-05 18:51 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 18:51 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The overlay update code path to do explicit request creation and submission
> rather than relying on the OLR to do the right thing.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_overlay.c | 64 +++++++++++++++++++++++++---------
> 1 file changed, 48 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
> index f93dfc1..dc209bf 100644
> --- a/drivers/gpu/drm/i915/intel_overlay.c
> +++ b/drivers/gpu/drm/i915/intel_overlay.c
> @@ -209,19 +209,19 @@ static void intel_overlay_unmap_regs(struct intel_overlay *overlay,
> }
>
> static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
> + struct drm_i915_gem_request *req,
> void (*tail)(struct intel_overlay *))
> {
> struct drm_device *dev = overlay->dev;
> - struct drm_i915_private *dev_priv = dev->dev_private;
> - struct intel_engine_cs *ring = &dev_priv->ring[RCS];
> int ret;
>
> BUG_ON(overlay->last_flip_req);
> - i915_gem_request_assign(&overlay->last_flip_req,
> - ring->outstanding_lazy_request);
> - ret = i915_add_request(ring);
> - if (ret)
> + i915_gem_request_assign(&overlay->last_flip_req, req);
> + ret = i915_add_request(req->ring);
> + if (ret) {
> + i915_gem_request_unreference(req);
> return ret;
> + }
>
> overlay->flip_tail = tail;
> ret = i915_wait_request(overlay->last_flip_req);
> @@ -239,6 +239,7 @@ static int intel_overlay_on(struct intel_overlay *overlay)
> struct drm_device *dev = overlay->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> struct intel_engine_cs *ring = &dev_priv->ring[RCS];
> + struct drm_i915_gem_request *req;
> int ret;
>
> BUG_ON(overlay->active);
> @@ -246,17 +247,23 @@ static int intel_overlay_on(struct intel_overlay *overlay)
>
> WARN_ON(IS_I830(dev) && !(dev_priv->quirks & QUIRK_PIPEA_FORCE));
>
> - ret = intel_ring_begin(ring, 4);
> + ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
> if (ret)
> return ret;
>
> + ret = intel_ring_begin(ring, 4);
> + if (ret) {
> + i915_gem_request_unreference(req);
> + return ret;
> + }
> +
> intel_ring_emit(ring, MI_OVERLAY_FLIP | MI_OVERLAY_ON);
> intel_ring_emit(ring, overlay->flip_addr | OFC_UPDATE);
> intel_ring_emit(ring, MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
> intel_ring_emit(ring, MI_NOOP);
> intel_ring_advance(ring);
>
> - return intel_overlay_do_wait_request(overlay, NULL);
> + return intel_overlay_do_wait_request(overlay, req, NULL);
> }
>
> /* overlay needs to be enabled in OCMD reg */
> @@ -266,6 +273,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
> struct drm_device *dev = overlay->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> struct intel_engine_cs *ring = &dev_priv->ring[RCS];
> + struct drm_i915_gem_request *req;
> u32 flip_addr = overlay->flip_addr;
> u32 tmp;
> int ret;
> @@ -280,18 +288,27 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
> if (tmp & (1 << 17))
> DRM_DEBUG("overlay underrun, DOVSTA: %x\n", tmp);
>
> - ret = intel_ring_begin(ring, 2);
> + ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
> if (ret)
> return ret;
>
> + ret = intel_ring_begin(ring, 2);
> + if (ret) {
> + i915_gem_request_unreference(req);
> + return ret;
> + }
> +
> intel_ring_emit(ring, MI_OVERLAY_FLIP | MI_OVERLAY_CONTINUE);
> intel_ring_emit(ring, flip_addr);
> intel_ring_advance(ring);
>
> WARN_ON(overlay->last_flip_req);
> - i915_gem_request_assign(&overlay->last_flip_req,
> - ring->outstanding_lazy_request);
> - return i915_add_request(ring);
> + i915_gem_request_assign(&overlay->last_flip_req, req);
> + ret = i915_add_request(req->ring);
> + if (ret)
> + i915_gem_request_unreference(req);
> +
> + return ret;
> }
>
> static void intel_overlay_release_old_vid_tail(struct intel_overlay *overlay)
> @@ -326,6 +343,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
> struct drm_device *dev = overlay->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> struct intel_engine_cs *ring = &dev_priv->ring[RCS];
> + struct drm_i915_gem_request *req;
> u32 flip_addr = overlay->flip_addr;
> int ret;
>
> @@ -337,10 +355,16 @@ static int intel_overlay_off(struct intel_overlay *overlay)
> * of the hw. Do it in both cases */
> flip_addr |= OFC_UPDATE;
>
> - ret = intel_ring_begin(ring, 6);
> + ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
> if (ret)
> return ret;
>
> + ret = intel_ring_begin(ring, 6);
> + if (ret) {
> + i915_gem_request_unreference(req);
> + return ret;
> + }
> +
> /* wait for overlay to go idle */
> intel_ring_emit(ring, MI_OVERLAY_FLIP | MI_OVERLAY_CONTINUE);
> intel_ring_emit(ring, flip_addr);
> @@ -359,7 +383,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
> }
> intel_ring_advance(ring);
>
> - return intel_overlay_do_wait_request(overlay, intel_overlay_off_tail);
> + return intel_overlay_do_wait_request(overlay, req, intel_overlay_off_tail);
> }
>
> /* recover from an interruption due to a signal
> @@ -404,15 +428,23 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
>
> if (I915_READ(ISR) & I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT) {
> /* synchronous slowpath */
> - ret = intel_ring_begin(ring, 2);
> + struct drm_i915_gem_request *req;
> +
> + ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req)
> if (ret)
> return ret;
>
> + ret = intel_ring_begin(ring, 2);
> + if (ret) {
> + i915_gem_request_unreference(req);
> + return ret;
> + }
> +
> intel_ring_emit(ring, MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
> intel_ring_emit(ring, MI_NOOP);
> intel_ring_advance(ring);
>
> - ret = intel_overlay_do_wait_request(overlay,
> + ret = intel_overlay_do_wait_request(overlay, req,
> intel_overlay_release_old_vid_tail);
> if (ret)
> return ret;
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 28/53] drm/i915: Update queue_flip() to do explicit request management
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (26 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 27/53] drm/i915: Update overlay code to do explicit request management John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 19:29 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 29/53] drm/i915: Update add_request() to take a request structure John.C.Harrison
` (26 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the display page flip code to do explicit request creation and
submission rather than relying on the OLR and just hoping that the request
actually gets submitted at some random point.
The sequence is now to create a request, queue the work to the ring, assign the
known request to the flip queue work item then actually submit the work and post
the request.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 2 +-
drivers/gpu/drm/i915/intel_display.c | 43 ++++++++++++++++++++-----------
drivers/gpu/drm/i915/intel_ringbuffer.c | 2 +-
drivers/gpu/drm/i915/intel_ringbuffer.h | 1 -
4 files changed, 30 insertions(+), 18 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e9cc343..34fd338 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -560,7 +560,7 @@ struct drm_i915_display_funcs {
int (*queue_flip)(struct drm_device *dev, struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags);
void (*update_primary_plane)(struct drm_crtc *crtc,
struct drm_framebuffer *fb,
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3b0fe9f..c32bc0c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9251,9 +9251,10 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
+ struct intel_engine_cs *ring = req->ring;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
u32 flip_mask;
int ret;
@@ -9278,7 +9279,6 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
intel_ring_emit(ring, 0); /* aux display base address, unused */
intel_mark_page_flip_active(intel_crtc);
- __intel_ring_advance(ring);
return 0;
}
@@ -9286,9 +9286,10 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
+ struct intel_engine_cs *ring = req->ring;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
u32 flip_mask;
int ret;
@@ -9310,7 +9311,6 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
intel_ring_emit(ring, MI_NOOP);
intel_mark_page_flip_active(intel_crtc);
- __intel_ring_advance(ring);
return 0;
}
@@ -9318,9 +9318,10 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
uint32_t pf, pipesrc;
@@ -9349,7 +9350,6 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
intel_ring_emit(ring, pf | pipesrc);
intel_mark_page_flip_active(intel_crtc);
- __intel_ring_advance(ring);
return 0;
}
@@ -9357,9 +9357,10 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
uint32_t pf, pipesrc;
@@ -9385,7 +9386,6 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
intel_ring_emit(ring, pf | pipesrc);
intel_mark_page_flip_active(intel_crtc);
- __intel_ring_advance(ring);
return 0;
}
@@ -9393,9 +9393,10 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
+ struct intel_engine_cs *ring = req->ring;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
uint32_t plane_bit = 0;
int len, ret;
@@ -9480,7 +9481,6 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
intel_ring_emit(ring, (MI_NOOP));
intel_mark_page_flip_active(intel_crtc);
- __intel_ring_advance(ring);
return 0;
}
@@ -9636,7 +9636,7 @@ static int intel_default_queue_flip(struct drm_device *dev,
struct drm_crtc *crtc,
struct drm_framebuffer *fb,
struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring,
+ struct drm_i915_gem_request *req,
uint32_t flags)
{
return -ENODEV;
@@ -9715,6 +9715,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
enum pipe pipe = intel_crtc->pipe;
struct intel_unpin_work *work;
struct intel_engine_cs *ring;
+ struct drm_i915_gem_request *request;
int ret;
/*
@@ -9828,13 +9829,20 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
i915_gem_request_assign(&work->flip_queued_req,
obj->last_write_req);
} else {
- ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, ring,
- page_flip_flags);
+ ret = dev_priv->gt.alloc_request(ring, ring->default_context, &request);
if (ret)
goto cleanup_unpin;
- i915_gem_request_assign(&work->flip_queued_req,
- intel_ring_get_request(ring));
+ ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, request,
+ page_flip_flags);
+ if (ret)
+ goto cleanup_request;
+
+ i915_gem_request_assign(&work->flip_queued_req, request);
+
+ ret = i915_add_request_no_flush(request->ring);
+ if (ret)
+ goto cleanup_request_assign;
}
work->flip_queued_vblank = drm_vblank_count(dev, intel_crtc->pipe);
@@ -9851,6 +9859,11 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
return 0;
+cleanup_request_assign:
+ i915_gem_request_assign(&work->flip_queued_req, NULL);
+cleanup_request:
+ i915_gem_request_unreference(request);
+
cleanup_unpin:
intel_unpin_fb_obj(obj);
cleanup_pending:
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index efb1729..18d12a5 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -81,7 +81,7 @@ bool intel_ring_stopped(struct intel_engine_cs *ring)
return dev_priv->gpu_error.stop_rings & intel_ring_flag(ring);
}
-void __intel_ring_advance(struct intel_engine_cs *ring)
+static void __intel_ring_advance(struct intel_engine_cs *ring)
{
struct intel_ringbuffer *ringbuf = ring->buffer;
ringbuf->tail &= ringbuf->size - 1;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index c32f5a1..25d5ede 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -410,7 +410,6 @@ int __intel_ring_space(int head, int tail, int size);
void intel_ring_update_space(struct intel_ringbuffer *ringbuf);
int intel_ring_space(struct intel_ringbuffer *ringbuf);
bool intel_ring_stopped(struct intel_engine_cs *ring);
-void __intel_ring_advance(struct intel_engine_cs *ring);
int __must_check intel_ring_idle(struct intel_engine_cs *ring);
void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 28/53] drm/i915: Update queue_flip() to do explicit request management
2015-02-19 17:17 ` [PATCH 28/53] drm/i915: Update queue_flip() " John.C.Harrison
@ 2015-03-05 19:29 ` Tomas Elf
2015-03-06 16:30 ` Daniel Vetter
0 siblings, 1 reply; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 19:29 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the display page flip code to do explicit request creation and
> submission rather than relying on the OLR and just hoping that the request
> actually gets submitted at some random point.
>
> The sequence is now to create a request, queue the work to the ring, assign the
> known request to the flip queue work item then actually submit the work and post
> the request.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 2 +-
> drivers/gpu/drm/i915/intel_display.c | 43 ++++++++++++++++++++-----------
> drivers/gpu/drm/i915/intel_ringbuffer.c | 2 +-
> drivers/gpu/drm/i915/intel_ringbuffer.h | 1 -
> 4 files changed, 30 insertions(+), 18 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index e9cc343..34fd338 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -560,7 +560,7 @@ struct drm_i915_display_funcs {
> int (*queue_flip)(struct drm_device *dev, struct drm_crtc *crtc,
> struct drm_framebuffer *fb,
> struct drm_i915_gem_object *obj,
> - struct intel_engine_cs *ring,
> + struct drm_i915_gem_request *req,
> uint32_t flags);
> void (*update_primary_plane)(struct drm_crtc *crtc,
> struct drm_framebuffer *fb,
> diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> index 3b0fe9f..c32bc0c 100644
> --- a/drivers/gpu/drm/i915/intel_display.c
> +++ b/drivers/gpu/drm/i915/intel_display.c
> @@ -9251,9 +9251,10 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
> struct drm_crtc *crtc,
> struct drm_framebuffer *fb,
> struct drm_i915_gem_object *obj,
> - struct intel_engine_cs *ring,
> + struct drm_i915_gem_request *req,
> uint32_t flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> u32 flip_mask;
> int ret;
> @@ -9278,7 +9279,6 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
> intel_ring_emit(ring, 0); /* aux display base address, unused */
>
> intel_mark_page_flip_active(intel_crtc);
> - __intel_ring_advance(ring);
> return 0;
> }
>
> @@ -9286,9 +9286,10 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
> struct drm_crtc *crtc,
> struct drm_framebuffer *fb,
> struct drm_i915_gem_object *obj,
> - struct intel_engine_cs *ring,
> + struct drm_i915_gem_request *req,
> uint32_t flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> u32 flip_mask;
> int ret;
> @@ -9310,7 +9311,6 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
> intel_ring_emit(ring, MI_NOOP);
>
> intel_mark_page_flip_active(intel_crtc);
> - __intel_ring_advance(ring);
> return 0;
> }
>
> @@ -9318,9 +9318,10 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
> struct drm_crtc *crtc,
> struct drm_framebuffer *fb,
> struct drm_i915_gem_object *obj,
> - struct intel_engine_cs *ring,
> + struct drm_i915_gem_request *req,
> uint32_t flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct drm_i915_private *dev_priv = dev->dev_private;
> struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> uint32_t pf, pipesrc;
> @@ -9349,7 +9350,6 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
> intel_ring_emit(ring, pf | pipesrc);
>
> intel_mark_page_flip_active(intel_crtc);
> - __intel_ring_advance(ring);
> return 0;
> }
>
> @@ -9357,9 +9357,10 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
> struct drm_crtc *crtc,
> struct drm_framebuffer *fb,
> struct drm_i915_gem_object *obj,
> - struct intel_engine_cs *ring,
> + struct drm_i915_gem_request *req,
> uint32_t flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct drm_i915_private *dev_priv = dev->dev_private;
> struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> uint32_t pf, pipesrc;
> @@ -9385,7 +9386,6 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
> intel_ring_emit(ring, pf | pipesrc);
>
> intel_mark_page_flip_active(intel_crtc);
> - __intel_ring_advance(ring);
> return 0;
> }
>
> @@ -9393,9 +9393,10 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
> struct drm_crtc *crtc,
> struct drm_framebuffer *fb,
> struct drm_i915_gem_object *obj,
> - struct intel_engine_cs *ring,
> + struct drm_i915_gem_request *req,
> uint32_t flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> uint32_t plane_bit = 0;
> int len, ret;
> @@ -9480,7 +9481,6 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
> intel_ring_emit(ring, (MI_NOOP));
>
> intel_mark_page_flip_active(intel_crtc);
> - __intel_ring_advance(ring);
> return 0;
> }
>
> @@ -9636,7 +9636,7 @@ static int intel_default_queue_flip(struct drm_device *dev,
> struct drm_crtc *crtc,
> struct drm_framebuffer *fb,
> struct drm_i915_gem_object *obj,
> - struct intel_engine_cs *ring,
> + struct drm_i915_gem_request *req,
> uint32_t flags)
> {
> return -ENODEV;
> @@ -9715,6 +9715,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
> enum pipe pipe = intel_crtc->pipe;
> struct intel_unpin_work *work;
> struct intel_engine_cs *ring;
> + struct drm_i915_gem_request *request;
> int ret;
>
> /*
> @@ -9828,13 +9829,20 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
> i915_gem_request_assign(&work->flip_queued_req,
> obj->last_write_req);
> } else {
> - ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, ring,
> - page_flip_flags);
> + ret = dev_priv->gt.alloc_request(ring, ring->default_context, &request);
> if (ret)
> goto cleanup_unpin;
>
> - i915_gem_request_assign(&work->flip_queued_req,
> - intel_ring_get_request(ring));
> + ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, request,
> + page_flip_flags);
> + if (ret)
> + goto cleanup_request;
> +
> + i915_gem_request_assign(&work->flip_queued_req, request);
> +
> + ret = i915_add_request_no_flush(request->ring);
> + if (ret)
> + goto cleanup_request_assign;
> }
>
> work->flip_queued_vblank = drm_vblank_count(dev, intel_crtc->pipe);
> @@ -9851,6 +9859,11 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
>
> return 0;
>
> +cleanup_request_assign:
> + i915_gem_request_assign(&work->flip_queued_req, NULL);
> +cleanup_request:
> + i915_gem_request_unreference(request);
> +
> cleanup_unpin:
> intel_unpin_fb_obj(obj);
> cleanup_pending:
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index efb1729..18d12a5 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -81,7 +81,7 @@ bool intel_ring_stopped(struct intel_engine_cs *ring)
> return dev_priv->gpu_error.stop_rings & intel_ring_flag(ring);
> }
>
> -void __intel_ring_advance(struct intel_engine_cs *ring)
> +static void __intel_ring_advance(struct intel_engine_cs *ring)
> {
> struct intel_ringbuffer *ringbuf = ring->buffer;
> ringbuf->tail &= ringbuf->size - 1;
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index c32f5a1..25d5ede 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -410,7 +410,6 @@ int __intel_ring_space(int head, int tail, int size);
> void intel_ring_update_space(struct intel_ringbuffer *ringbuf);
> int intel_ring_space(struct intel_ringbuffer *ringbuf);
> bool intel_ring_stopped(struct intel_engine_cs *ring);
> -void __intel_ring_advance(struct intel_engine_cs *ring);
>
> int __must_check intel_ring_idle(struct intel_engine_cs *ring);
> void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
>
Could you perhaps make a small note in the commit message to clarify why
you remove __intel_ring_advance everywhere? After discussing it with you
I understood that it's because we already do the corresponding operation
in i915_add_request_no_flush that is added to intel_crtc_page_flip but
since these pieces of code are so far from each other it's not entirely
obvious from the start that they have something to do with each other.
Or am I the only one who thinks this is not trivial?
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 28/53] drm/i915: Update queue_flip() to do explicit request management
2015-03-05 19:29 ` Tomas Elf
@ 2015-03-06 16:30 ` Daniel Vetter
0 siblings, 0 replies; 234+ messages in thread
From: Daniel Vetter @ 2015-03-06 16:30 UTC (permalink / raw)
To: Tomas Elf; +Cc: Intel-GFX
On Thu, Mar 05, 2015 at 07:29:27PM +0000, Tomas Elf wrote:
> On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> >From: John Harrison <John.C.Harrison@Intel.com>
> >
> >Updated the display page flip code to do explicit request creation and
> >submission rather than relying on the OLR and just hoping that the request
> >actually gets submitted at some random point.
> >
> >The sequence is now to create a request, queue the work to the ring, assign the
> >known request to the flip queue work item then actually submit the work and post
> >the request.
> >
> >For: VIZ-5115
> >Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> >---
> > drivers/gpu/drm/i915/i915_drv.h | 2 +-
> > drivers/gpu/drm/i915/intel_display.c | 43 ++++++++++++++++++++-----------
> > drivers/gpu/drm/i915/intel_ringbuffer.c | 2 +-
> > drivers/gpu/drm/i915/intel_ringbuffer.h | 1 -
> > 4 files changed, 30 insertions(+), 18 deletions(-)
> >
> >diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> >index e9cc343..34fd338 100644
> >--- a/drivers/gpu/drm/i915/i915_drv.h
> >+++ b/drivers/gpu/drm/i915/i915_drv.h
> >@@ -560,7 +560,7 @@ struct drm_i915_display_funcs {
> > int (*queue_flip)(struct drm_device *dev, struct drm_crtc *crtc,
> > struct drm_framebuffer *fb,
> > struct drm_i915_gem_object *obj,
> >- struct intel_engine_cs *ring,
> >+ struct drm_i915_gem_request *req,
> > uint32_t flags);
> > void (*update_primary_plane)(struct drm_crtc *crtc,
> > struct drm_framebuffer *fb,
> >diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> >index 3b0fe9f..c32bc0c 100644
> >--- a/drivers/gpu/drm/i915/intel_display.c
> >+++ b/drivers/gpu/drm/i915/intel_display.c
> >@@ -9251,9 +9251,10 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
> > struct drm_crtc *crtc,
> > struct drm_framebuffer *fb,
> > struct drm_i915_gem_object *obj,
> >- struct intel_engine_cs *ring,
> >+ struct drm_i915_gem_request *req,
> > uint32_t flags)
> > {
> >+ struct intel_engine_cs *ring = req->ring;
> > struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> > u32 flip_mask;
> > int ret;
> >@@ -9278,7 +9279,6 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
> > intel_ring_emit(ring, 0); /* aux display base address, unused */
> >
> > intel_mark_page_flip_active(intel_crtc);
> >- __intel_ring_advance(ring);
> > return 0;
> > }
> >
> >@@ -9286,9 +9286,10 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
> > struct drm_crtc *crtc,
> > struct drm_framebuffer *fb,
> > struct drm_i915_gem_object *obj,
> >- struct intel_engine_cs *ring,
> >+ struct drm_i915_gem_request *req,
> > uint32_t flags)
> > {
> >+ struct intel_engine_cs *ring = req->ring;
> > struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> > u32 flip_mask;
> > int ret;
> >@@ -9310,7 +9311,6 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
> > intel_ring_emit(ring, MI_NOOP);
> >
> > intel_mark_page_flip_active(intel_crtc);
> >- __intel_ring_advance(ring);
> > return 0;
> > }
> >
> >@@ -9318,9 +9318,10 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
> > struct drm_crtc *crtc,
> > struct drm_framebuffer *fb,
> > struct drm_i915_gem_object *obj,
> >- struct intel_engine_cs *ring,
> >+ struct drm_i915_gem_request *req,
> > uint32_t flags)
> > {
> >+ struct intel_engine_cs *ring = req->ring;
> > struct drm_i915_private *dev_priv = dev->dev_private;
> > struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> > uint32_t pf, pipesrc;
> >@@ -9349,7 +9350,6 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
> > intel_ring_emit(ring, pf | pipesrc);
> >
> > intel_mark_page_flip_active(intel_crtc);
> >- __intel_ring_advance(ring);
> > return 0;
> > }
> >
> >@@ -9357,9 +9357,10 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
> > struct drm_crtc *crtc,
> > struct drm_framebuffer *fb,
> > struct drm_i915_gem_object *obj,
> >- struct intel_engine_cs *ring,
> >+ struct drm_i915_gem_request *req,
> > uint32_t flags)
> > {
> >+ struct intel_engine_cs *ring = req->ring;
> > struct drm_i915_private *dev_priv = dev->dev_private;
> > struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> > uint32_t pf, pipesrc;
> >@@ -9385,7 +9386,6 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
> > intel_ring_emit(ring, pf | pipesrc);
> >
> > intel_mark_page_flip_active(intel_crtc);
> >- __intel_ring_advance(ring);
> > return 0;
> > }
> >
> >@@ -9393,9 +9393,10 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
> > struct drm_crtc *crtc,
> > struct drm_framebuffer *fb,
> > struct drm_i915_gem_object *obj,
> >- struct intel_engine_cs *ring,
> >+ struct drm_i915_gem_request *req,
> > uint32_t flags)
> > {
> >+ struct intel_engine_cs *ring = req->ring;
> > struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
> > uint32_t plane_bit = 0;
> > int len, ret;
> >@@ -9480,7 +9481,6 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
> > intel_ring_emit(ring, (MI_NOOP));
> >
> > intel_mark_page_flip_active(intel_crtc);
> >- __intel_ring_advance(ring);
> > return 0;
> > }
> >
> >@@ -9636,7 +9636,7 @@ static int intel_default_queue_flip(struct drm_device *dev,
> > struct drm_crtc *crtc,
> > struct drm_framebuffer *fb,
> > struct drm_i915_gem_object *obj,
> >- struct intel_engine_cs *ring,
> >+ struct drm_i915_gem_request *req,
> > uint32_t flags)
> > {
> > return -ENODEV;
> >@@ -9715,6 +9715,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
> > enum pipe pipe = intel_crtc->pipe;
> > struct intel_unpin_work *work;
> > struct intel_engine_cs *ring;
> >+ struct drm_i915_gem_request *request;
> > int ret;
> >
> > /*
> >@@ -9828,13 +9829,20 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
> > i915_gem_request_assign(&work->flip_queued_req,
> > obj->last_write_req);
> > } else {
> >- ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, ring,
> >- page_flip_flags);
> >+ ret = dev_priv->gt.alloc_request(ring, ring->default_context, &request);
> > if (ret)
> > goto cleanup_unpin;
> >
> >- i915_gem_request_assign(&work->flip_queued_req,
> >- intel_ring_get_request(ring));
> >+ ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, request,
> >+ page_flip_flags);
> >+ if (ret)
> >+ goto cleanup_request;
> >+
> >+ i915_gem_request_assign(&work->flip_queued_req, request);
> >+
> >+ ret = i915_add_request_no_flush(request->ring);
> >+ if (ret)
> >+ goto cleanup_request_assign;
> > }
> >
> > work->flip_queued_vblank = drm_vblank_count(dev, intel_crtc->pipe);
> >@@ -9851,6 +9859,11 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
> >
> > return 0;
> >
> >+cleanup_request_assign:
> >+ i915_gem_request_assign(&work->flip_queued_req, NULL);
> >+cleanup_request:
> >+ i915_gem_request_unreference(request);
> >+
> > cleanup_unpin:
> > intel_unpin_fb_obj(obj);
> > cleanup_pending:
> >diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> >index efb1729..18d12a5 100644
> >--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> >+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> >@@ -81,7 +81,7 @@ bool intel_ring_stopped(struct intel_engine_cs *ring)
> > return dev_priv->gpu_error.stop_rings & intel_ring_flag(ring);
> > }
> >
> >-void __intel_ring_advance(struct intel_engine_cs *ring)
> >+static void __intel_ring_advance(struct intel_engine_cs *ring)
> > {
> > struct intel_ringbuffer *ringbuf = ring->buffer;
> > ringbuf->tail &= ringbuf->size - 1;
> >diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> >index c32f5a1..25d5ede 100644
> >--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> >+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> >@@ -410,7 +410,6 @@ int __intel_ring_space(int head, int tail, int size);
> > void intel_ring_update_space(struct intel_ringbuffer *ringbuf);
> > int intel_ring_space(struct intel_ringbuffer *ringbuf);
> > bool intel_ring_stopped(struct intel_engine_cs *ring);
> >-void __intel_ring_advance(struct intel_engine_cs *ring);
> >
> > int __must_check intel_ring_idle(struct intel_engine_cs *ring);
> > void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
> >
>
> Could you perhaps make a small note in the commit message to clarify why you
> remove __intel_ring_advance everywhere? After discussing it with you I
> understood that it's because we already do the corresponding operation in
> i915_add_request_no_flush that is added to intel_crtc_page_flip but since
> these pieces of code are so far from each other it's not entirely obvious
> from the start that they have something to do with each other.
>
> Or am I the only one who thinks this is not trivial?
I concur, the commit message should explain this.
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 29/53] drm/i915: Update add_request() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (27 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 28/53] drm/i915: Update queue_flip() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 19:35 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 30/53] drm/i915: Update [vma|object]_move_to_active() to take request structures John.C.Harrison
` (25 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Now that all callers of i915_add_request() have a request pointer to hand, it is
possible to update the add request function to take a request pointer rather
than pulling it out of the OLR.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 10 +++++-----
drivers/gpu/drm/i915/i915_gem.c | 24 ++++++++++++------------
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
drivers/gpu/drm/i915/intel_display.c | 2 +-
drivers/gpu/drm/i915/intel_lrc.c | 2 +-
drivers/gpu/drm/i915/intel_overlay.c | 4 ++--
drivers/gpu/drm/i915/intel_ringbuffer.c | 3 ++-
7 files changed, 24 insertions(+), 23 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 34fd338..9206328 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2830,14 +2830,14 @@ void i915_gem_init_swizzling(struct drm_device *dev);
void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
int __must_check i915_gpu_idle(struct drm_device *dev);
int __must_check i915_gem_suspend(struct drm_device *dev);
-int __i915_add_request(struct intel_engine_cs *ring,
+int __i915_add_request(struct drm_i915_gem_request *req,
struct drm_file *file,
struct drm_i915_gem_object *batch_obj,
bool flush_caches);
-#define i915_add_request(ring) \
- __i915_add_request(ring, NULL, NULL, true)
-#define i915_add_request_no_flush(ring) \
- __i915_add_request(ring, NULL, NULL, false)
+#define i915_add_request(req) \
+ __i915_add_request(req, NULL, NULL, true)
+#define i915_add_request_no_flush(req) \
+ __i915_add_request(req, NULL, NULL, false)
int __i915_wait_request(struct drm_i915_gem_request *req,
unsigned reset_counter,
bool interruptible,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0c7e1bd..24fb7b9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1162,7 +1162,7 @@ i915_gem_check_olr(struct drm_i915_gem_request *req)
ret = 0;
if (req == req->ring->outstanding_lazy_request)
- ret = i915_add_request(req->ring);
+ ret = i915_add_request(req);
return ret;
}
@@ -2407,25 +2407,25 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
return 0;
}
-int __i915_add_request(struct intel_engine_cs *ring,
+int __i915_add_request(struct drm_i915_gem_request *request,
struct drm_file *file,
struct drm_i915_gem_object *obj,
bool flush_caches)
{
- struct drm_i915_private *dev_priv = ring->dev->dev_private;
- struct drm_i915_gem_request *request;
+ struct intel_engine_cs *ring;
+ struct drm_i915_private *dev_priv;
struct intel_ringbuffer *ringbuf;
u32 request_start;
int ret;
- request = ring->outstanding_lazy_request;
if (WARN_ON(request == NULL))
return -ENOMEM;
- if (i915.enable_execlists) {
- ringbuf = request->ctx->engine[ring->id].ringbuf;
- } else
- ringbuf = ring->buffer;
+ ring = request->ring;
+ dev_priv = ring->dev->dev_private;
+ ringbuf = request->ringbuf;
+
+ WARN_ON(request != ring->outstanding_lazy_request);
request_start = intel_ring_get_tail(ringbuf);
/*
@@ -3118,7 +3118,7 @@ int i915_gpu_idle(struct drm_device *dev)
return ret;
}
- ret = i915_add_request_no_flush(req->ring);
+ ret = i915_add_request_no_flush(req);
if (ret) {
i915_gem_request_unreference(req);
return ret;
@@ -3966,7 +3966,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
if (ret)
return ret;
- ret = i915_add_request_no_flush(req->ring);
+ ret = i915_add_request_no_flush(req);
if (ret)
return ret;
}
@@ -4884,7 +4884,7 @@ i915_gem_init_hw(struct drm_device *dev)
return ret;
}
- ret = i915_add_request_no_flush(ring);
+ ret = i915_add_request_no_flush(req);
if (ret) {
DRM_ERROR("Add request ring #%d failed: %d\n", i, ret);
i915_gem_request_unreference(req);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 1e2fc80..15e33a9 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -996,7 +996,7 @@ i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
params->ring->gpu_caches_dirty = true;
/* Add a breadcrumb for the completion of the batch buffer */
- return __i915_add_request(params->ring, params->file,
+ return __i915_add_request(params->request, params->file,
params->batch_obj, true);
}
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index c32bc0c..9cbfb93 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9840,7 +9840,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
i915_gem_request_assign(&work->flip_queued_req, request);
- ret = i915_add_request_no_flush(request->ring);
+ ret = i915_add_request_no_flush(request);
if (ret)
goto cleanup_request_assign;
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index f0bb98a..3b4393c 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1942,7 +1942,7 @@ int intel_lr_context_deferred_create(struct intel_context *ctx,
goto error;
}
- ret = i915_add_request_no_flush(req->ring);
+ ret = i915_add_request_no_flush(req);
if (ret) {
DRM_ERROR("ring init context: %d\n", ret);
i915_gem_request_unreference(req);
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index dc209bf..228c9d1 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -217,7 +217,7 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
BUG_ON(overlay->last_flip_req);
i915_gem_request_assign(&overlay->last_flip_req, req);
- ret = i915_add_request(req->ring);
+ ret = i915_add_request(req);
if (ret) {
i915_gem_request_unreference(req);
return ret;
@@ -304,7 +304,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
WARN_ON(overlay->last_flip_req);
i915_gem_request_assign(&overlay->last_flip_req, req);
- ret = i915_add_request(req->ring);
+ ret = i915_add_request(req);
if (ret)
i915_gem_request_unreference(req);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 18d12a5..508d7d8 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2145,8 +2145,9 @@ int intel_ring_idle(struct intel_engine_cs *ring)
int ret;
/* We need to add any requests required to flush the objects and ring */
+ WARN_ON(ring->outstanding_lazy_request);
if (ring->outstanding_lazy_request) {
- ret = i915_add_request(ring);
+ ret = i915_add_request(ring->outstanding_lazy_request);
if (ret)
return ret;
}
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 29/53] drm/i915: Update add_request() to take a request structure
2015-02-19 17:17 ` [PATCH 29/53] drm/i915: Update add_request() to take a request structure John.C.Harrison
@ 2015-03-05 19:35 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 19:35 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Now that all callers of i915_add_request() have a request pointer to hand, it is
> possible to update the add request function to take a request pointer rather
> than pulling it out of the OLR.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 10 +++++-----
> drivers/gpu/drm/i915/i915_gem.c | 24 ++++++++++++------------
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
> drivers/gpu/drm/i915/intel_display.c | 2 +-
> drivers/gpu/drm/i915/intel_lrc.c | 2 +-
> drivers/gpu/drm/i915/intel_overlay.c | 4 ++--
> drivers/gpu/drm/i915/intel_ringbuffer.c | 3 ++-
> 7 files changed, 24 insertions(+), 23 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 34fd338..9206328 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2830,14 +2830,14 @@ void i915_gem_init_swizzling(struct drm_device *dev);
> void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
> int __must_check i915_gpu_idle(struct drm_device *dev);
> int __must_check i915_gem_suspend(struct drm_device *dev);
> -int __i915_add_request(struct intel_engine_cs *ring,
> +int __i915_add_request(struct drm_i915_gem_request *req,
> struct drm_file *file,
> struct drm_i915_gem_object *batch_obj,
> bool flush_caches);
> -#define i915_add_request(ring) \
> - __i915_add_request(ring, NULL, NULL, true)
> -#define i915_add_request_no_flush(ring) \
> - __i915_add_request(ring, NULL, NULL, false)
> +#define i915_add_request(req) \
> + __i915_add_request(req, NULL, NULL, true)
> +#define i915_add_request_no_flush(req) \
> + __i915_add_request(req, NULL, NULL, false)
> int __i915_wait_request(struct drm_i915_gem_request *req,
> unsigned reset_counter,
> bool interruptible,
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 0c7e1bd..24fb7b9 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -1162,7 +1162,7 @@ i915_gem_check_olr(struct drm_i915_gem_request *req)
>
> ret = 0;
> if (req == req->ring->outstanding_lazy_request)
> - ret = i915_add_request(req->ring);
> + ret = i915_add_request(req);
>
> return ret;
> }
> @@ -2407,25 +2407,25 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
> return 0;
> }
>
> -int __i915_add_request(struct intel_engine_cs *ring,
> +int __i915_add_request(struct drm_i915_gem_request *request,
> struct drm_file *file,
> struct drm_i915_gem_object *obj,
> bool flush_caches)
> {
> - struct drm_i915_private *dev_priv = ring->dev->dev_private;
> - struct drm_i915_gem_request *request;
> + struct intel_engine_cs *ring;
> + struct drm_i915_private *dev_priv;
> struct intel_ringbuffer *ringbuf;
> u32 request_start;
> int ret;
>
> - request = ring->outstanding_lazy_request;
> if (WARN_ON(request == NULL))
> return -ENOMEM;
>
> - if (i915.enable_execlists) {
> - ringbuf = request->ctx->engine[ring->id].ringbuf;
> - } else
> - ringbuf = ring->buffer;
> + ring = request->ring;
> + dev_priv = ring->dev->dev_private;
> + ringbuf = request->ringbuf;
> +
> + WARN_ON(request != ring->outstanding_lazy_request);
>
> request_start = intel_ring_get_tail(ringbuf);
> /*
> @@ -3118,7 +3118,7 @@ int i915_gpu_idle(struct drm_device *dev)
> return ret;
> }
>
> - ret = i915_add_request_no_flush(req->ring);
> + ret = i915_add_request_no_flush(req);
> if (ret) {
> i915_gem_request_unreference(req);
> return ret;
> @@ -3966,7 +3966,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
> if (ret)
> return ret;
>
> - ret = i915_add_request_no_flush(req->ring);
> + ret = i915_add_request_no_flush(req);
> if (ret)
> return ret;
> }
> @@ -4884,7 +4884,7 @@ i915_gem_init_hw(struct drm_device *dev)
> return ret;
> }
>
> - ret = i915_add_request_no_flush(ring);
> + ret = i915_add_request_no_flush(req);
> if (ret) {
> DRM_ERROR("Add request ring #%d failed: %d\n", i, ret);
> i915_gem_request_unreference(req);
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 1e2fc80..15e33a9 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -996,7 +996,7 @@ i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
> params->ring->gpu_caches_dirty = true;
>
> /* Add a breadcrumb for the completion of the batch buffer */
> - return __i915_add_request(params->ring, params->file,
> + return __i915_add_request(params->request, params->file,
> params->batch_obj, true);
> }
>
> diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> index c32bc0c..9cbfb93 100644
> --- a/drivers/gpu/drm/i915/intel_display.c
> +++ b/drivers/gpu/drm/i915/intel_display.c
> @@ -9840,7 +9840,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
>
> i915_gem_request_assign(&work->flip_queued_req, request);
>
> - ret = i915_add_request_no_flush(request->ring);
> + ret = i915_add_request_no_flush(request);
> if (ret)
> goto cleanup_request_assign;
> }
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index f0bb98a..3b4393c 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -1942,7 +1942,7 @@ int intel_lr_context_deferred_create(struct intel_context *ctx,
> goto error;
> }
>
> - ret = i915_add_request_no_flush(req->ring);
> + ret = i915_add_request_no_flush(req);
> if (ret) {
> DRM_ERROR("ring init context: %d\n", ret);
> i915_gem_request_unreference(req);
> diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
> index dc209bf..228c9d1 100644
> --- a/drivers/gpu/drm/i915/intel_overlay.c
> +++ b/drivers/gpu/drm/i915/intel_overlay.c
> @@ -217,7 +217,7 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
>
> BUG_ON(overlay->last_flip_req);
> i915_gem_request_assign(&overlay->last_flip_req, req);
> - ret = i915_add_request(req->ring);
> + ret = i915_add_request(req);
> if (ret) {
> i915_gem_request_unreference(req);
> return ret;
> @@ -304,7 +304,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
>
> WARN_ON(overlay->last_flip_req);
> i915_gem_request_assign(&overlay->last_flip_req, req);
> - ret = i915_add_request(req->ring);
> + ret = i915_add_request(req);
> if (ret)
> i915_gem_request_unreference(req);
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 18d12a5..508d7d8 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -2145,8 +2145,9 @@ int intel_ring_idle(struct intel_engine_cs *ring)
> int ret;
>
> /* We need to add any requests required to flush the objects and ring */
> + WARN_ON(ring->outstanding_lazy_request);
> if (ring->outstanding_lazy_request) {
> - ret = i915_add_request(ring);
> + ret = i915_add_request(ring->outstanding_lazy_request);
> if (ret)
> return ret;
> }
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 30/53] drm/i915: Update [vma|object]_move_to_active() to take request structures
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (28 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 29/53] drm/i915: Update add_request() to take a request structure John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 19:39 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 31/53] drm/i915: Update l3_remap to take a request structure John.C.Harrison
` (24 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Now that everything above has been converted to use request structures, it is
possible to update the lower level move_to_active() functions to be request
based as well.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 2 +-
drivers/gpu/drm/i915/i915_gem.c | 17 ++++++++---------
drivers/gpu/drm/i915/i915_gem_context.c | 2 +-
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
drivers/gpu/drm/i915/i915_gem_render_state.c | 2 +-
drivers/gpu/drm/i915/intel_lrc.c | 2 +-
6 files changed, 13 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 9206328..e9fef4c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2747,7 +2747,7 @@ 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_req);
void i915_vma_move_to_active(struct i915_vma *vma,
- struct intel_engine_cs *ring);
+ struct drm_i915_gem_request *req);
int i915_gem_dumb_create(struct drm_file *file_priv,
struct drm_device *dev,
struct drm_mode_create_dumb *args);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 24fb7b9..0ae9be2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2265,17 +2265,16 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
static void
i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
- struct drm_i915_gem_request *req;
- struct intel_engine_cs *old_ring;
+ struct intel_engine_cs *new_ring, *old_ring;
- BUG_ON(ring == NULL);
+ BUG_ON(req == NULL);
- req = intel_ring_get_request(ring);
+ new_ring = i915_gem_request_get_ring(req);
old_ring = i915_gem_request_get_ring(obj->last_read_req);
- if (old_ring != ring && obj->last_write_req) {
+ if (old_ring != new_ring && obj->last_write_req) {
/* Keep the request relative to the current ring */
i915_gem_request_assign(&obj->last_write_req, req);
}
@@ -2286,16 +2285,16 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
obj->active = 1;
}
- list_move_tail(&obj->ring_list, &ring->active_list);
+ list_move_tail(&obj->ring_list, &new_ring->active_list);
i915_gem_request_assign(&obj->last_read_req, req);
}
void i915_vma_move_to_active(struct i915_vma *vma,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
list_move_tail(&vma->mm_list, &vma->vm->active_list);
- return i915_gem_object_move_to_active(vma->obj, ring);
+ return i915_gem_object_move_to_active(vma->obj, req);
}
static void
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 938cd26..e4d75be 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -652,7 +652,7 @@ static int do_switch(struct drm_i915_gem_request *req)
*/
if (from != NULL) {
from->legacy_hw_ctx.rcs_state->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
- i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), req->ring);
+ i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), req);
/* As long as MI_SET_CONTEXT is serializing, ie. it flushes the
* whole damn pipeline, we don't need to explicitly mark the
* object dirty. The only exception is that the context must be
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 15e33a9..dc13751 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -966,7 +966,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
obj->base.pending_read_domains |= obj->base.read_domains;
obj->base.read_domains = obj->base.pending_read_domains;
- i915_vma_move_to_active(vma, ring);
+ i915_vma_move_to_active(vma, req);
if (obj->base.write_domain) {
obj->dirty = 1;
i915_gem_request_assign(&obj->last_write_req, req);
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index 85cc746..866274c 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -171,7 +171,7 @@ int i915_gem_render_state_init(struct drm_i915_gem_request *req)
if (ret)
goto out;
- i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req->ring);
+ i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req);
WARN_ON(req->batch_obj);
req->batch_obj = so.obj;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 3b4393c..479365e 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1364,7 +1364,7 @@ static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req)
if (ret)
goto out;
- i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req->ring);
+ i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req);
WARN_ON(req->batch_obj);
req->batch_obj = so.obj;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 30/53] drm/i915: Update [vma|object]_move_to_active() to take request structures
2015-02-19 17:17 ` [PATCH 30/53] drm/i915: Update [vma|object]_move_to_active() to take request structures John.C.Harrison
@ 2015-03-05 19:39 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 19:39 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Now that everything above has been converted to use request structures, it is
> possible to update the lower level move_to_active() functions to be request
> based as well.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 2 +-
> drivers/gpu/drm/i915/i915_gem.c | 17 ++++++++---------
> drivers/gpu/drm/i915/i915_gem_context.c | 2 +-
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
> drivers/gpu/drm/i915/i915_gem_render_state.c | 2 +-
> drivers/gpu/drm/i915/intel_lrc.c | 2 +-
> 6 files changed, 13 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 9206328..e9fef4c 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2747,7 +2747,7 @@ 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_req);
> void i915_vma_move_to_active(struct i915_vma *vma,
> - struct intel_engine_cs *ring);
> + struct drm_i915_gem_request *req);
> int i915_gem_dumb_create(struct drm_file *file_priv,
> struct drm_device *dev,
> struct drm_mode_create_dumb *args);
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 24fb7b9..0ae9be2 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2265,17 +2265,16 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
>
> static void
> i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
> - struct intel_engine_cs *ring)
> + struct drm_i915_gem_request *req)
> {
> - struct drm_i915_gem_request *req;
> - struct intel_engine_cs *old_ring;
> + struct intel_engine_cs *new_ring, *old_ring;
>
> - BUG_ON(ring == NULL);
> + BUG_ON(req == NULL);
>
> - req = intel_ring_get_request(ring);
> + new_ring = i915_gem_request_get_ring(req);
> old_ring = i915_gem_request_get_ring(obj->last_read_req);
>
> - if (old_ring != ring && obj->last_write_req) {
> + if (old_ring != new_ring && obj->last_write_req) {
> /* Keep the request relative to the current ring */
> i915_gem_request_assign(&obj->last_write_req, req);
> }
> @@ -2286,16 +2285,16 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
> obj->active = 1;
> }
>
> - list_move_tail(&obj->ring_list, &ring->active_list);
> + list_move_tail(&obj->ring_list, &new_ring->active_list);
>
> i915_gem_request_assign(&obj->last_read_req, req);
> }
>
> void i915_vma_move_to_active(struct i915_vma *vma,
> - struct intel_engine_cs *ring)
> + struct drm_i915_gem_request *req)
> {
> list_move_tail(&vma->mm_list, &vma->vm->active_list);
> - return i915_gem_object_move_to_active(vma->obj, ring);
> + return i915_gem_object_move_to_active(vma->obj, req);
> }
>
> static void
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index 938cd26..e4d75be 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -652,7 +652,7 @@ static int do_switch(struct drm_i915_gem_request *req)
> */
> if (from != NULL) {
> from->legacy_hw_ctx.rcs_state->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
> - i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), req->ring);
> + i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), req);
> /* As long as MI_SET_CONTEXT is serializing, ie. it flushes the
> * whole damn pipeline, we don't need to explicitly mark the
> * object dirty. The only exception is that the context must be
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 15e33a9..dc13751 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -966,7 +966,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
> obj->base.pending_read_domains |= obj->base.read_domains;
> obj->base.read_domains = obj->base.pending_read_domains;
>
> - i915_vma_move_to_active(vma, ring);
> + i915_vma_move_to_active(vma, req);
> if (obj->base.write_domain) {
> obj->dirty = 1;
> i915_gem_request_assign(&obj->last_write_req, req);
> diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
> index 85cc746..866274c 100644
> --- a/drivers/gpu/drm/i915/i915_gem_render_state.c
> +++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
> @@ -171,7 +171,7 @@ int i915_gem_render_state_init(struct drm_i915_gem_request *req)
> if (ret)
> goto out;
>
> - i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req->ring);
> + i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req);
>
> WARN_ON(req->batch_obj);
> req->batch_obj = so.obj;
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 3b4393c..479365e 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -1364,7 +1364,7 @@ static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req)
> if (ret)
> goto out;
>
> - i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req->ring);
> + i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req);
>
> WARN_ON(req->batch_obj);
> req->batch_obj = so.obj;
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 31/53] drm/i915: Update l3_remap to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (29 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 30/53] drm/i915: Update [vma|object]_move_to_active() to take request structures John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 19:44 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 32/53] drm/i915: Update mi_set_context() " John.C.Harrison
` (23 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Converted i915_gem_l3_remap() to take a request structure instead of a ring.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 2 +-
drivers/gpu/drm/i915/i915_gem.c | 5 +++--
drivers/gpu/drm/i915/i915_gem_context.c | 2 +-
3 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e9fef4c..3955bef 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2825,7 +2825,7 @@ int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
int __must_check i915_gem_init(struct drm_device *dev);
int i915_gem_init_rings(struct drm_device *dev);
int __must_check i915_gem_init_hw(struct drm_device *dev);
-int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice);
+int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice);
void i915_gem_init_swizzling(struct drm_device *dev);
void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
int __must_check i915_gpu_idle(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0ae9be2..043933b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4644,8 +4644,9 @@ err:
return ret;
}
-int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice)
+int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
@@ -4864,7 +4865,7 @@ i915_gem_init_hw(struct drm_device *dev)
if (ring->id == RCS) {
for (i = 0; i < NUM_L3_SLICES(dev); i++)
- i915_gem_l3_remap(ring, i);
+ i915_gem_l3_remap(req, i);
}
ret = i915_ppgtt_init_ring(req);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index e4d75be..475d1fd 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -636,7 +636,7 @@ static int do_switch(struct drm_i915_gem_request *req)
if (!(to->remap_slice & (1<<i)))
continue;
- ret = i915_gem_l3_remap(req->ring, i);
+ ret = i915_gem_l3_remap(req, i);
/* If it failed, try again next round */
if (ret)
DRM_DEBUG_DRIVER("L3 remapping failed\n");
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 31/53] drm/i915: Update l3_remap to take a request structure
2015-02-19 17:17 ` [PATCH 31/53] drm/i915: Update l3_remap to take a request structure John.C.Harrison
@ 2015-03-05 19:44 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 19:44 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Converted i915_gem_l3_remap() to take a request structure instead of a ring.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 2 +-
> drivers/gpu/drm/i915/i915_gem.c | 5 +++--
> drivers/gpu/drm/i915/i915_gem_context.c | 2 +-
> 3 files changed, 5 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index e9fef4c..3955bef 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2825,7 +2825,7 @@ int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
> int __must_check i915_gem_init(struct drm_device *dev);
> int i915_gem_init_rings(struct drm_device *dev);
> int __must_check i915_gem_init_hw(struct drm_device *dev);
> -int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice);
> +int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice);
> void i915_gem_init_swizzling(struct drm_device *dev);
> void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
> int __must_check i915_gpu_idle(struct drm_device *dev);
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 0ae9be2..043933b 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -4644,8 +4644,9 @@ err:
> return ret;
> }
>
> -int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice)
> +int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct drm_device *dev = ring->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
> @@ -4864,7 +4865,7 @@ i915_gem_init_hw(struct drm_device *dev)
>
> if (ring->id == RCS) {
> for (i = 0; i < NUM_L3_SLICES(dev); i++)
> - i915_gem_l3_remap(ring, i);
> + i915_gem_l3_remap(req, i);
> }
>
> ret = i915_ppgtt_init_ring(req);
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index e4d75be..475d1fd 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -636,7 +636,7 @@ static int do_switch(struct drm_i915_gem_request *req)
> if (!(to->remap_slice & (1<<i)))
> continue;
>
> - ret = i915_gem_l3_remap(req->ring, i);
> + ret = i915_gem_l3_remap(req, i);
> /* If it failed, try again next round */
> if (ret)
> DRM_DEBUG_DRIVER("L3 remapping failed\n");
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 32/53] drm/i915: Update mi_set_context() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (30 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 31/53] drm/i915: Update l3_remap to take a request structure John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 19:52 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 33/53] drm/i915: Update a bunch of execbuffer heplers to take request structures John.C.Harrison
` (22 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated mi_set_context() to take a request structure instead of a ring and
context pair.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_context.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 475d1fd..9e66fac 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -472,10 +472,9 @@ i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id)
}
static inline int
-mi_set_context(struct intel_engine_cs *ring,
- struct intel_context *new_context,
- u32 hw_flags)
+mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
{
+ struct intel_engine_cs *ring = req->ring;
u32 flags = hw_flags | MI_MM_SPACE_GTT;
const int num_rings =
/* Use an extended w/a on ivb+ if signalling from other rings */
@@ -527,7 +526,7 @@ mi_set_context(struct intel_engine_cs *ring,
intel_ring_emit(ring, MI_NOOP);
intel_ring_emit(ring, MI_SET_CONTEXT);
- intel_ring_emit(ring, i915_gem_obj_ggtt_offset(new_context->legacy_hw_ctx.rcs_state) |
+ intel_ring_emit(ring, i915_gem_obj_ggtt_offset(req->ctx->legacy_hw_ctx.rcs_state) |
flags);
/*
* w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
@@ -628,7 +627,7 @@ static int do_switch(struct drm_i915_gem_request *req)
if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to))
hw_flags |= MI_RESTORE_INHIBIT;
- ret = mi_set_context(req->ring, to, hw_flags);
+ ret = mi_set_context(req, hw_flags);
if (ret)
goto unpin_out;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 32/53] drm/i915: Update mi_set_context() to take a request structure
2015-02-19 17:17 ` [PATCH 32/53] drm/i915: Update mi_set_context() " John.C.Harrison
@ 2015-03-05 19:52 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 19:52 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated mi_set_context() to take a request structure instead of a ring and
> context pair.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_context.c | 9 ++++-----
> 1 file changed, 4 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index 475d1fd..9e66fac 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -472,10 +472,9 @@ i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id)
> }
>
> static inline int
> -mi_set_context(struct intel_engine_cs *ring,
> - struct intel_context *new_context,
> - u32 hw_flags)
> +mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> u32 flags = hw_flags | MI_MM_SPACE_GTT;
> const int num_rings =
> /* Use an extended w/a on ivb+ if signalling from other rings */
> @@ -527,7 +526,7 @@ mi_set_context(struct intel_engine_cs *ring,
>
> intel_ring_emit(ring, MI_NOOP);
> intel_ring_emit(ring, MI_SET_CONTEXT);
> - intel_ring_emit(ring, i915_gem_obj_ggtt_offset(new_context->legacy_hw_ctx.rcs_state) |
> + intel_ring_emit(ring, i915_gem_obj_ggtt_offset(req->ctx->legacy_hw_ctx.rcs_state) |
> flags);
> /*
> * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
> @@ -628,7 +627,7 @@ static int do_switch(struct drm_i915_gem_request *req)
> if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to))
> hw_flags |= MI_RESTORE_INHIBIT;
>
> - ret = mi_set_context(req->ring, to, hw_flags);
> + ret = mi_set_context(req, hw_flags);
> if (ret)
> goto unpin_out;
>
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 33/53] drm/i915: Update a bunch of execbuffer heplers to take request structures
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (31 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 32/53] drm/i915: Update mi_set_context() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-05 19:58 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 34/53] drm/i915: Update workarounds_emit() " John.C.Harrison
` (21 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated *_ring_invalidate_all_caches(), i915_reset_gen7_sol_offsets() and
i915_emit_box() to take request structures instead of ring or ringbuf/context
pairs.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 12 +++++++-----
drivers/gpu/drm/i915/intel_lrc.c | 9 ++++-----
drivers/gpu/drm/i915/intel_ringbuffer.c | 3 ++-
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
4 files changed, 14 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index dc13751..a79c893 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -857,7 +857,7 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
/* Unconditionally invalidate gpu caches and ensure that we do flush
* any residual writes from the previous batch.
*/
- return intel_ring_invalidate_all_caches(req->ring);
+ return intel_ring_invalidate_all_caches(req);
}
static bool
@@ -1002,8 +1002,9 @@ i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
static int
i915_reset_gen7_sol_offsets(struct drm_device *dev,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = dev->dev_private;
int ret, i;
@@ -1028,10 +1029,11 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
}
static int
-i915_emit_box(struct intel_engine_cs *ring,
+i915_emit_box(struct drm_i915_gem_request *req,
struct drm_clip_rect *box,
int DR1, int DR4)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
if (box->y2 <= box->y1 || box->x2 <= box->x1 ||
@@ -1247,7 +1249,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
}
if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
- ret = i915_reset_gen7_sol_offsets(params->dev, ring);
+ ret = i915_reset_gen7_sol_offsets(params->dev, params->request);
if (ret)
goto error;
}
@@ -1258,7 +1260,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
if (cliprects) {
for (i = 0; i < args->num_cliprects; i++) {
- ret = i915_emit_box(ring, &cliprects[i],
+ ret = i915_emit_box(params->request, &cliprects[i],
args->DR1, args->DR4);
if (ret)
goto error;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 479365e..fab9269 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -558,10 +558,9 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
return 0;
}
-static int logical_ring_invalidate_all_caches(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx)
+static int logical_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
{
- struct intel_engine_cs *ring = ringbuf->ring;
+ struct intel_engine_cs *ring = req->ring;
uint32_t flush_domains;
int ret;
@@ -569,7 +568,7 @@ static int logical_ring_invalidate_all_caches(struct intel_ringbuffer *ringbuf,
if (ring->gpu_caches_dirty)
flush_domains = I915_GEM_GPU_DOMAINS;
- ret = ring->emit_flush(ringbuf, ctx,
+ ret = ring->emit_flush(req->ringbuf, req->ctx,
I915_GEM_GPU_DOMAINS, flush_domains);
if (ret)
return ret;
@@ -605,7 +604,7 @@ static int execlists_move_to_gpu(struct drm_i915_gem_request *req,
/* Unconditionally invalidate gpu caches and ensure that we do flush
* any residual writes from the previous batch.
*/
- return logical_ring_invalidate_all_caches(req->ringbuf, req->ctx);
+ return logical_ring_invalidate_all_caches(req);
}
/**
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 508d7d8..efa44db 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2864,8 +2864,9 @@ intel_ring_flush_all_caches(struct intel_engine_cs *ring)
}
int
-intel_ring_invalidate_all_caches(struct intel_engine_cs *ring)
+intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
uint32_t flush_domains;
int ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 25d5ede..b817725 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -414,7 +414,7 @@ bool intel_ring_stopped(struct intel_engine_cs *ring);
int __must_check intel_ring_idle(struct intel_engine_cs *ring);
void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
int intel_ring_flush_all_caches(struct intel_engine_cs *ring);
-int intel_ring_invalidate_all_caches(struct intel_engine_cs *ring);
+int intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req);
void intel_fini_pipe_control(struct intel_engine_cs *ring);
int intel_init_pipe_control(struct intel_engine_cs *ring);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 33/53] drm/i915: Update a bunch of execbuffer heplers to take request structures
2015-02-19 17:17 ` [PATCH 33/53] drm/i915: Update a bunch of execbuffer heplers to take request structures John.C.Harrison
@ 2015-03-05 19:58 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-05 19:58 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated *_ring_invalidate_all_caches(), i915_reset_gen7_sol_offsets() and
> i915_emit_box() to take request structures instead of ring or ringbuf/context
> pairs.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 12 +++++++-----
> drivers/gpu/drm/i915/intel_lrc.c | 9 ++++-----
> drivers/gpu/drm/i915/intel_ringbuffer.c | 3 ++-
> drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
> 4 files changed, 14 insertions(+), 12 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index dc13751..a79c893 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -857,7 +857,7 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
> /* Unconditionally invalidate gpu caches and ensure that we do flush
> * any residual writes from the previous batch.
> */
> - return intel_ring_invalidate_all_caches(req->ring);
> + return intel_ring_invalidate_all_caches(req);
> }
>
> static bool
> @@ -1002,8 +1002,9 @@ i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
>
> static int
> i915_reset_gen7_sol_offsets(struct drm_device *dev,
> - struct intel_engine_cs *ring)
> + struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct drm_i915_private *dev_priv = dev->dev_private;
> int ret, i;
>
> @@ -1028,10 +1029,11 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
> }
>
> static int
> -i915_emit_box(struct intel_engine_cs *ring,
> +i915_emit_box(struct drm_i915_gem_request *req,
> struct drm_clip_rect *box,
> int DR1, int DR4)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> if (box->y2 <= box->y1 || box->x2 <= box->x1 ||
> @@ -1247,7 +1249,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> }
>
> if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
> - ret = i915_reset_gen7_sol_offsets(params->dev, ring);
> + ret = i915_reset_gen7_sol_offsets(params->dev, params->request);
> if (ret)
> goto error;
> }
> @@ -1258,7 +1260,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
>
> if (cliprects) {
> for (i = 0; i < args->num_cliprects; i++) {
> - ret = i915_emit_box(ring, &cliprects[i],
> + ret = i915_emit_box(params->request, &cliprects[i],
> args->DR1, args->DR4);
> if (ret)
> goto error;
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 479365e..fab9269 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -558,10 +558,9 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
> return 0;
> }
>
> -static int logical_ring_invalidate_all_caches(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx)
> +static int logical_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
> {
> - struct intel_engine_cs *ring = ringbuf->ring;
> + struct intel_engine_cs *ring = req->ring;
> uint32_t flush_domains;
> int ret;
>
> @@ -569,7 +568,7 @@ static int logical_ring_invalidate_all_caches(struct intel_ringbuffer *ringbuf,
> if (ring->gpu_caches_dirty)
> flush_domains = I915_GEM_GPU_DOMAINS;
>
> - ret = ring->emit_flush(ringbuf, ctx,
> + ret = ring->emit_flush(req->ringbuf, req->ctx,
> I915_GEM_GPU_DOMAINS, flush_domains);
> if (ret)
> return ret;
> @@ -605,7 +604,7 @@ static int execlists_move_to_gpu(struct drm_i915_gem_request *req,
> /* Unconditionally invalidate gpu caches and ensure that we do flush
> * any residual writes from the previous batch.
> */
> - return logical_ring_invalidate_all_caches(req->ringbuf, req->ctx);
> + return logical_ring_invalidate_all_caches(req);
> }
>
> /**
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 508d7d8..efa44db 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -2864,8 +2864,9 @@ intel_ring_flush_all_caches(struct intel_engine_cs *ring)
> }
>
> int
> -intel_ring_invalidate_all_caches(struct intel_engine_cs *ring)
> +intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> uint32_t flush_domains;
> int ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 25d5ede..b817725 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -414,7 +414,7 @@ bool intel_ring_stopped(struct intel_engine_cs *ring);
> int __must_check intel_ring_idle(struct intel_engine_cs *ring);
> void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
> int intel_ring_flush_all_caches(struct intel_engine_cs *ring);
> -int intel_ring_invalidate_all_caches(struct intel_engine_cs *ring);
> +int intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req);
>
> void intel_fini_pipe_control(struct intel_engine_cs *ring);
> int intel_init_pipe_control(struct intel_engine_cs *ring);
>
Nitpick: "Update a bunch of execbuffer >>> heplers <<< "
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 34/53] drm/i915: Update workarounds_emit() to take request structures
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (32 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 33/53] drm/i915: Update a bunch of execbuffer heplers to take request structures John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 20:17 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 35/53] drm/i915: Update flush_all_caches() " John.C.Harrison
` (20 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the *_ring_workarounds_emit() functions to take requests instead of
ring/context pairs.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_lrc.c | 14 +++++++-------
drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
2 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index fab9269..08ed800 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1076,11 +1076,11 @@ int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
return 0;
}
-static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
{
int ret, i;
- struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+ struct intel_engine_cs *ring = req->ring;
+ struct intel_ringbuffer *ringbuf = req->ringbuf;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_workarounds *w = &dev_priv->workarounds;
@@ -1089,11 +1089,11 @@ static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
return 0;
ring->gpu_caches_dirty = true;
- ret = logical_ring_flush_all_caches(ringbuf, ctx);
+ ret = logical_ring_flush_all_caches(ringbuf, req->ctx);
if (ret)
return ret;
- ret = intel_logical_ring_begin(ringbuf, ctx, w->count * 2 + 2);
+ ret = intel_logical_ring_begin(ringbuf, req->ctx, w->count * 2 + 2);
if (ret)
return ret;
@@ -1107,7 +1107,7 @@ static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
intel_logical_ring_advance(ringbuf);
ring->gpu_caches_dirty = true;
- ret = logical_ring_flush_all_caches(ringbuf, ctx);
+ ret = logical_ring_flush_all_caches(ringbuf, req->ctx);
if (ret)
return ret;
@@ -1377,7 +1377,7 @@ static int gen8_init_rcs_context(struct drm_i915_gem_request *req)
{
int ret;
- ret = intel_logical_ring_workarounds_emit(req->ring, req->ctx);
+ ret = intel_logical_ring_workarounds_emit(req);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index efa44db..d147ffa 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -736,10 +736,10 @@ err:
return ret;
}
-static int intel_ring_workarounds_emit(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
{
int ret, i;
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_workarounds *w = &dev_priv->workarounds;
@@ -779,7 +779,7 @@ static int intel_rcs_ctx_init(struct drm_i915_gem_request *req)
{
int ret;
- ret = intel_ring_workarounds_emit(req->ring, req->ctx);
+ ret = intel_ring_workarounds_emit(req);
if (ret != 0)
return ret;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 34/53] drm/i915: Update workarounds_emit() to take request structures
2015-02-19 17:17 ` [PATCH 34/53] drm/i915: Update workarounds_emit() " John.C.Harrison
@ 2015-03-09 20:17 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 20:17 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the *_ring_workarounds_emit() functions to take requests instead of
> ring/context pairs.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_lrc.c | 14 +++++++-------
> drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
> 2 files changed, 10 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index fab9269..08ed800 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -1076,11 +1076,11 @@ int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
> return 0;
> }
>
> -static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
> - struct intel_context *ctx)
> +static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
> {
> int ret, i;
> - struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
> + struct intel_engine_cs *ring = req->ring;
> + struct intel_ringbuffer *ringbuf = req->ringbuf;
> struct drm_device *dev = ring->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> struct i915_workarounds *w = &dev_priv->workarounds;
> @@ -1089,11 +1089,11 @@ static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
> return 0;
>
> ring->gpu_caches_dirty = true;
> - ret = logical_ring_flush_all_caches(ringbuf, ctx);
> + ret = logical_ring_flush_all_caches(ringbuf, req->ctx);
> if (ret)
> return ret;
>
> - ret = intel_logical_ring_begin(ringbuf, ctx, w->count * 2 + 2);
> + ret = intel_logical_ring_begin(ringbuf, req->ctx, w->count * 2 + 2);
> if (ret)
> return ret;
>
> @@ -1107,7 +1107,7 @@ static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
> intel_logical_ring_advance(ringbuf);
>
> ring->gpu_caches_dirty = true;
> - ret = logical_ring_flush_all_caches(ringbuf, ctx);
> + ret = logical_ring_flush_all_caches(ringbuf, req->ctx);
> if (ret)
> return ret;
>
> @@ -1377,7 +1377,7 @@ static int gen8_init_rcs_context(struct drm_i915_gem_request *req)
> {
> int ret;
>
> - ret = intel_logical_ring_workarounds_emit(req->ring, req->ctx);
> + ret = intel_logical_ring_workarounds_emit(req);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index efa44db..d147ffa 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -736,10 +736,10 @@ err:
> return ret;
> }
>
> -static int intel_ring_workarounds_emit(struct intel_engine_cs *ring,
> - struct intel_context *ctx)
> +static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
> {
> int ret, i;
> + struct intel_engine_cs *ring = req->ring;
> struct drm_device *dev = ring->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> struct i915_workarounds *w = &dev_priv->workarounds;
> @@ -779,7 +779,7 @@ static int intel_rcs_ctx_init(struct drm_i915_gem_request *req)
> {
> int ret;
>
> - ret = intel_ring_workarounds_emit(req->ring, req->ctx);
> + ret = intel_ring_workarounds_emit(req);
> if (ret != 0)
> return ret;
>
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 35/53] drm/i915: Update flush_all_caches() to take request structures
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (33 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 34/53] drm/i915: Update workarounds_emit() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 20:23 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 36/53] drm/i915: Update switch_mm() to take a request structure John.C.Harrison
` (19 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the *_ring_flush_all_caches() functions to take requests instead of
rings or ringbuf/context pairs.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 4 ++--
drivers/gpu/drm/i915/intel_lrc.c | 11 +++++------
drivers/gpu/drm/i915/intel_lrc.h | 3 +--
drivers/gpu/drm/i915/intel_ringbuffer.c | 7 ++++---
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
5 files changed, 13 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 043933b..e8577d7 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2436,9 +2436,9 @@ int __i915_add_request(struct drm_i915_gem_request *request,
*/
if (flush_caches) {
if (i915.enable_execlists)
- ret = logical_ring_flush_all_caches(ringbuf, request->ctx);
+ ret = logical_ring_flush_all_caches(request);
else
- ret = intel_ring_flush_all_caches(ring);
+ ret = intel_ring_flush_all_caches(request);
if (ret)
return ret;
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 08ed800..d8084a1 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -768,16 +768,15 @@ void intel_logical_ring_stop(struct intel_engine_cs *ring)
I915_WRITE_MODE(ring, _MASKED_BIT_DISABLE(STOP_RING));
}
-int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx)
+int logical_ring_flush_all_caches(struct drm_i915_gem_request *req)
{
- struct intel_engine_cs *ring = ringbuf->ring;
+ struct intel_engine_cs *ring = req->ring;
int ret;
if (!ring->gpu_caches_dirty)
return 0;
- ret = ring->emit_flush(ringbuf, ctx, 0, I915_GEM_GPU_DOMAINS);
+ ret = ring->emit_flush(req->ringbuf, req->ctx, 0, I915_GEM_GPU_DOMAINS);
if (ret)
return ret;
@@ -1089,7 +1088,7 @@ static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
return 0;
ring->gpu_caches_dirty = true;
- ret = logical_ring_flush_all_caches(ringbuf, req->ctx);
+ ret = logical_ring_flush_all_caches(req);
if (ret)
return ret;
@@ -1107,7 +1106,7 @@ static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
intel_logical_ring_advance(ringbuf);
ring->gpu_caches_dirty = true;
- ret = logical_ring_flush_all_caches(ringbuf, req->ctx);
+ ret = logical_ring_flush_all_caches(req);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 77de8ac..40848b0 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -43,8 +43,7 @@ void intel_logical_ring_stop(struct intel_engine_cs *ring);
void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
int intel_logical_rings_init(struct drm_device *dev);
-int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx);
+int logical_ring_flush_all_caches(struct drm_i915_gem_request *req);
/**
* intel_logical_ring_advance() - advance the ringbuffer tail
* @ringbuf: Ringbuffer to advance.
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index d147ffa..91a9131 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -748,7 +748,7 @@ static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
return 0;
ring->gpu_caches_dirty = true;
- ret = intel_ring_flush_all_caches(ring);
+ ret = intel_ring_flush_all_caches(req);
if (ret)
return ret;
@@ -766,7 +766,7 @@ static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
intel_ring_advance(ring);
ring->gpu_caches_dirty = true;
- ret = intel_ring_flush_all_caches(ring);
+ ret = intel_ring_flush_all_caches(req);
if (ret)
return ret;
@@ -2846,8 +2846,9 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
}
int
-intel_ring_flush_all_caches(struct intel_engine_cs *ring)
+intel_ring_flush_all_caches(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
if (!ring->gpu_caches_dirty)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index b817725..0ef29fb 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -413,7 +413,7 @@ bool intel_ring_stopped(struct intel_engine_cs *ring);
int __must_check intel_ring_idle(struct intel_engine_cs *ring);
void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
-int intel_ring_flush_all_caches(struct intel_engine_cs *ring);
+int intel_ring_flush_all_caches(struct drm_i915_gem_request *req);
int intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req);
void intel_fini_pipe_control(struct intel_engine_cs *ring);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 35/53] drm/i915: Update flush_all_caches() to take request structures
2015-02-19 17:17 ` [PATCH 35/53] drm/i915: Update flush_all_caches() " John.C.Harrison
@ 2015-03-09 20:23 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 20:23 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the *_ring_flush_all_caches() functions to take requests instead of
> rings or ringbuf/context pairs.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 4 ++--
> drivers/gpu/drm/i915/intel_lrc.c | 11 +++++------
> drivers/gpu/drm/i915/intel_lrc.h | 3 +--
> drivers/gpu/drm/i915/intel_ringbuffer.c | 7 ++++---
> drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
> 5 files changed, 13 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 043933b..e8577d7 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2436,9 +2436,9 @@ int __i915_add_request(struct drm_i915_gem_request *request,
> */
> if (flush_caches) {
> if (i915.enable_execlists)
> - ret = logical_ring_flush_all_caches(ringbuf, request->ctx);
> + ret = logical_ring_flush_all_caches(request);
> else
> - ret = intel_ring_flush_all_caches(ring);
> + ret = intel_ring_flush_all_caches(request);
> if (ret)
> return ret;
> }
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 08ed800..d8084a1 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -768,16 +768,15 @@ void intel_logical_ring_stop(struct intel_engine_cs *ring)
> I915_WRITE_MODE(ring, _MASKED_BIT_DISABLE(STOP_RING));
> }
>
> -int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx)
> +int logical_ring_flush_all_caches(struct drm_i915_gem_request *req)
> {
> - struct intel_engine_cs *ring = ringbuf->ring;
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> if (!ring->gpu_caches_dirty)
> return 0;
>
> - ret = ring->emit_flush(ringbuf, ctx, 0, I915_GEM_GPU_DOMAINS);
> + ret = ring->emit_flush(req->ringbuf, req->ctx, 0, I915_GEM_GPU_DOMAINS);
> if (ret)
> return ret;
>
> @@ -1089,7 +1088,7 @@ static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
> return 0;
>
> ring->gpu_caches_dirty = true;
> - ret = logical_ring_flush_all_caches(ringbuf, req->ctx);
> + ret = logical_ring_flush_all_caches(req);
> if (ret)
> return ret;
>
> @@ -1107,7 +1106,7 @@ static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
> intel_logical_ring_advance(ringbuf);
>
> ring->gpu_caches_dirty = true;
> - ret = logical_ring_flush_all_caches(ringbuf, req->ctx);
> + ret = logical_ring_flush_all_caches(req);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
> index 77de8ac..40848b0 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.h
> +++ b/drivers/gpu/drm/i915/intel_lrc.h
> @@ -43,8 +43,7 @@ void intel_logical_ring_stop(struct intel_engine_cs *ring);
> void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
> int intel_logical_rings_init(struct drm_device *dev);
>
> -int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx);
> +int logical_ring_flush_all_caches(struct drm_i915_gem_request *req);
> /**
> * intel_logical_ring_advance() - advance the ringbuffer tail
> * @ringbuf: Ringbuffer to advance.
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index d147ffa..91a9131 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -748,7 +748,7 @@ static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
> return 0;
>
> ring->gpu_caches_dirty = true;
> - ret = intel_ring_flush_all_caches(ring);
> + ret = intel_ring_flush_all_caches(req);
> if (ret)
> return ret;
>
> @@ -766,7 +766,7 @@ static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
> intel_ring_advance(ring);
>
> ring->gpu_caches_dirty = true;
> - ret = intel_ring_flush_all_caches(ring);
> + ret = intel_ring_flush_all_caches(req);
> if (ret)
> return ret;
>
> @@ -2846,8 +2846,9 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
> }
>
> int
> -intel_ring_flush_all_caches(struct intel_engine_cs *ring)
> +intel_ring_flush_all_caches(struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> if (!ring->gpu_caches_dirty)
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index b817725..0ef29fb 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -413,7 +413,7 @@ bool intel_ring_stopped(struct intel_engine_cs *ring);
>
> int __must_check intel_ring_idle(struct intel_engine_cs *ring);
> void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
> -int intel_ring_flush_all_caches(struct intel_engine_cs *ring);
> +int intel_ring_flush_all_caches(struct drm_i915_gem_request *req);
> int intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req);
>
> void intel_fini_pipe_control(struct intel_engine_cs *ring);
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 36/53] drm/i915: Update switch_mm() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (34 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 35/53] drm/i915: Update flush_all_caches() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 20:33 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 37/53] drm/i915: Update ring->flush() to take a requests structure John.C.Harrison
` (18 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the switch_mm() code paths to take a request instead of a ring.
v2: Rebased to newer tree.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_context.c | 2 +-
drivers/gpu/drm/i915/i915_gem_gtt.c | 23 ++++++++++++++---------
drivers/gpu/drm/i915/i915_gem_gtt.h | 2 +-
3 files changed, 16 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 9e66fac..816a442 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -591,7 +591,7 @@ static int do_switch(struct drm_i915_gem_request *req)
if (to->ppgtt) {
trace_switch_mm(ring, to);
- ret = to->ppgtt->switch_mm(to->ppgtt, req->ring);
+ ret = to->ppgtt->switch_mm(to->ppgtt, req);
if (ret)
goto unpin_out;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index cd00080..c3408f2 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -280,9 +280,10 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
}
/* Broadwell Page Directory Pointer Descriptors */
-static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
- uint64_t val)
+static int gen8_write_pdp(struct drm_i915_gem_request *req, unsigned entry,
+ uint64_t val)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
BUG_ON(entry >= 4);
@@ -303,7 +304,7 @@ static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
}
static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
int i, ret;
@@ -312,7 +313,7 @@ static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
for (i = used_pd - 1; i >= 0; i--) {
dma_addr_t addr = ppgtt->pd_dma_addr[i];
- ret = gen8_write_pdp(ring, i, addr);
+ ret = gen8_write_pdp(req, i, addr);
if (ret)
return ret;
}
@@ -777,8 +778,9 @@ static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt)
}
static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
/* NB: TLBs must be flushed and invalidated before a switch */
@@ -802,8 +804,9 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
}
static int vgpu_mm_switch(struct i915_hw_ppgtt *ppgtt,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = to_i915(ppgtt->base.dev);
I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
@@ -812,8 +815,9 @@ static int vgpu_mm_switch(struct i915_hw_ppgtt *ppgtt,
}
static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
/* NB: TLBs must be flushed and invalidated before a switch */
@@ -844,8 +848,9 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
}
static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
- struct intel_engine_cs *ring)
+ struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ppgtt->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1235,7 +1240,7 @@ int i915_ppgtt_init_ring(struct drm_i915_gem_request *req)
if (!ppgtt)
return 0;
- return ppgtt->switch_mm(ppgtt, req->ring);
+ return ppgtt->switch_mm(ppgtt, req);
}
struct i915_hw_ppgtt *
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index e7e202f..073be7f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -289,7 +289,7 @@ struct i915_hw_ppgtt {
int (*enable)(struct i915_hw_ppgtt *ppgtt);
int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
- struct intel_engine_cs *ring);
+ struct drm_i915_gem_request *req);
void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
};
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 36/53] drm/i915: Update switch_mm() to take a request structure
2015-02-19 17:17 ` [PATCH 36/53] drm/i915: Update switch_mm() to take a request structure John.C.Harrison
@ 2015-03-09 20:33 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 20:33 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the switch_mm() code paths to take a request instead of a ring.
>
This commit message could be slightly clearer by saying specifically
what you changed rather than using the blanket expression "paths". You
could e.g. say that you changed the mm_switch virtual function
implementations and the gen8_write_pdp helper function to take requests
rather than rings.
> v2: Rebased to newer tree.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_context.c | 2 +-
> drivers/gpu/drm/i915/i915_gem_gtt.c | 23 ++++++++++++++---------
> drivers/gpu/drm/i915/i915_gem_gtt.h | 2 +-
> 3 files changed, 16 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index 9e66fac..816a442 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -591,7 +591,7 @@ static int do_switch(struct drm_i915_gem_request *req)
>
> if (to->ppgtt) {
> trace_switch_mm(ring, to);
> - ret = to->ppgtt->switch_mm(to->ppgtt, req->ring);
> + ret = to->ppgtt->switch_mm(to->ppgtt, req);
> if (ret)
> goto unpin_out;
> }
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index cd00080..c3408f2 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -280,9 +280,10 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
> }
>
> /* Broadwell Page Directory Pointer Descriptors */
> -static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
> - uint64_t val)
> +static int gen8_write_pdp(struct drm_i915_gem_request *req, unsigned entry,
> + uint64_t val)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> BUG_ON(entry >= 4);
> @@ -303,7 +304,7 @@ static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
> }
>
> static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
> - struct intel_engine_cs *ring)
> + struct drm_i915_gem_request *req)
> {
> int i, ret;
>
> @@ -312,7 +313,7 @@ static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
>
> for (i = used_pd - 1; i >= 0; i--) {
> dma_addr_t addr = ppgtt->pd_dma_addr[i];
> - ret = gen8_write_pdp(ring, i, addr);
> + ret = gen8_write_pdp(req, i, addr);
> if (ret)
> return ret;
> }
> @@ -777,8 +778,9 @@ static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt)
> }
>
> static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
> - struct intel_engine_cs *ring)
> + struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> /* NB: TLBs must be flushed and invalidated before a switch */
> @@ -802,8 +804,9 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
> }
>
> static int vgpu_mm_switch(struct i915_hw_ppgtt *ppgtt,
> - struct intel_engine_cs *ring)
> + struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct drm_i915_private *dev_priv = to_i915(ppgtt->base.dev);
>
> I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
> @@ -812,8 +815,9 @@ static int vgpu_mm_switch(struct i915_hw_ppgtt *ppgtt,
> }
>
> static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
> - struct intel_engine_cs *ring)
> + struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> /* NB: TLBs must be flushed and invalidated before a switch */
> @@ -844,8 +848,9 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
> }
>
> static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
> - struct intel_engine_cs *ring)
> + struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct drm_device *dev = ppgtt->base.dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
>
> @@ -1235,7 +1240,7 @@ int i915_ppgtt_init_ring(struct drm_i915_gem_request *req)
> if (!ppgtt)
> return 0;
>
> - return ppgtt->switch_mm(ppgtt, req->ring);
> + return ppgtt->switch_mm(ppgtt, req);
> }
>
> struct i915_hw_ppgtt *
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
> index e7e202f..073be7f 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.h
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
> @@ -289,7 +289,7 @@ struct i915_hw_ppgtt {
>
> int (*enable)(struct i915_hw_ppgtt *ppgtt);
> int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
> - struct intel_engine_cs *ring);
> + struct drm_i915_gem_request *req);
> void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
> };
>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 37/53] drm/i915: Update ring->flush() to take a requests structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (35 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 36/53] drm/i915: Update switch_mm() to take a request structure John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 20:40 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 38/53] drm/i915: Update some flush helpers to take request structures John.C.Harrison
` (17 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Udpated the various ring->flush() functions to take a request instead of a ring.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_context.c | 2 +-
drivers/gpu/drm/i915/i915_gem_gtt.c | 6 +++---
drivers/gpu/drm/i915/intel_ringbuffer.c | 30 +++++++++++++++++++-----------
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
4 files changed, 24 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 816a442..384f481 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -489,7 +489,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
* itlb_before_ctx_switch.
*/
if (IS_GEN6(ring->dev)) {
- ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, 0);
+ ret = ring->flush(req, I915_GEM_GPU_DOMAINS, 0);
if (ret)
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index c3408f2..a1af644 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -784,7 +784,7 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
int ret;
/* NB: TLBs must be flushed and invalidated before a switch */
- ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
+ ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
if (ret)
return ret;
@@ -821,7 +821,7 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
int ret;
/* NB: TLBs must be flushed and invalidated before a switch */
- ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
+ ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
if (ret)
return ret;
@@ -839,7 +839,7 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
/* XXX: RCS is the only one to auto invalidate the TLBs? */
if (ring->id != RCS) {
- ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
+ ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
if (ret)
return ret;
}
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 91a9131..ca8f039 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -91,10 +91,11 @@ static void __intel_ring_advance(struct intel_engine_cs *ring)
}
static int
-gen2_render_ring_flush(struct intel_engine_cs *ring,
+gen2_render_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate_domains,
u32 flush_domains)
{
+ struct intel_engine_cs *ring = req->ring;
u32 cmd;
int ret;
@@ -117,10 +118,11 @@ gen2_render_ring_flush(struct intel_engine_cs *ring,
}
static int
-gen4_render_ring_flush(struct intel_engine_cs *ring,
+gen4_render_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate_domains,
u32 flush_domains)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
u32 cmd;
int ret;
@@ -247,9 +249,10 @@ intel_emit_post_sync_nonzero_flush(struct intel_engine_cs *ring)
}
static int
-gen6_render_ring_flush(struct intel_engine_cs *ring,
- u32 invalidate_domains, u32 flush_domains)
+gen6_render_ring_flush(struct drm_i915_gem_request *req,
+ u32 invalidate_domains, u32 flush_domains)
{
+ struct intel_engine_cs *ring = req->ring;
u32 flags = 0;
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
@@ -341,9 +344,10 @@ static int gen7_ring_fbc_flush(struct intel_engine_cs *ring, u32 value)
}
static int
-gen7_render_ring_flush(struct intel_engine_cs *ring,
+gen7_render_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate_domains, u32 flush_domains)
{
+ struct intel_engine_cs *ring = req->ring;
u32 flags = 0;
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
@@ -426,9 +430,10 @@ gen8_emit_pipe_control(struct intel_engine_cs *ring,
}
static int
-gen8_render_ring_flush(struct intel_engine_cs *ring,
+gen8_render_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate_domains, u32 flush_domains)
{
+ struct intel_engine_cs *ring = req->ring;
u32 flags = 0;
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
@@ -1527,10 +1532,11 @@ i8xx_ring_put_irq(struct intel_engine_cs *ring)
}
static int
-bsd_ring_flush(struct intel_engine_cs *ring,
+bsd_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate_domains,
u32 flush_domains)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
ret = intel_ring_begin(ring, 2);
@@ -2318,9 +2324,10 @@ static void gen6_bsd_ring_write_tail(struct intel_engine_cs *ring,
_MASKED_BIT_DISABLE(GEN6_BSD_SLEEP_MSG_DISABLE));
}
-static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
+static int gen6_bsd_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate, u32 flush)
{
+ struct intel_engine_cs *ring = req->ring;
uint32_t cmd;
int ret;
@@ -2430,9 +2437,10 @@ gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
/* Blitter support (SandyBridge+) */
-static int gen6_ring_flush(struct intel_engine_cs *ring,
+static int gen6_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate, u32 flush)
{
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t cmd;
@@ -2854,7 +2862,7 @@ intel_ring_flush_all_caches(struct drm_i915_gem_request *req)
if (!ring->gpu_caches_dirty)
return 0;
- ret = ring->flush(ring, 0, I915_GEM_GPU_DOMAINS);
+ ret = ring->flush(req, 0, I915_GEM_GPU_DOMAINS);
if (ret)
return ret;
@@ -2875,7 +2883,7 @@ intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
if (ring->gpu_caches_dirty)
flush_domains = I915_GEM_GPU_DOMAINS;
- ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, flush_domains);
+ ret = ring->flush(req, I915_GEM_GPU_DOMAINS, flush_domains);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 0ef29fb..c08e2dc 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -147,7 +147,7 @@ struct intel_engine_cs {
void (*write_tail)(struct intel_engine_cs *ring,
u32 value);
- int __must_check (*flush)(struct intel_engine_cs *ring,
+ int __must_check (*flush)(struct drm_i915_gem_request *req,
u32 invalidate_domains,
u32 flush_domains);
int (*add_request)(struct intel_engine_cs *ring);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 37/53] drm/i915: Update ring->flush() to take a requests structure
2015-02-19 17:17 ` [PATCH 37/53] drm/i915: Update ring->flush() to take a requests structure John.C.Harrison
@ 2015-03-09 20:40 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 20:40 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Udpated the various ring->flush() functions to take a request instead of a ring.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_context.c | 2 +-
> drivers/gpu/drm/i915/i915_gem_gtt.c | 6 +++---
> drivers/gpu/drm/i915/intel_ringbuffer.c | 30 +++++++++++++++++++-----------
> drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
> 4 files changed, 24 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index 816a442..384f481 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -489,7 +489,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
> * itlb_before_ctx_switch.
> */
> if (IS_GEN6(ring->dev)) {
> - ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, 0);
> + ret = ring->flush(req, I915_GEM_GPU_DOMAINS, 0);
> if (ret)
> return ret;
> }
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index c3408f2..a1af644 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -784,7 +784,7 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
> int ret;
>
> /* NB: TLBs must be flushed and invalidated before a switch */
> - ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
> + ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
> if (ret)
> return ret;
>
> @@ -821,7 +821,7 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
> int ret;
>
> /* NB: TLBs must be flushed and invalidated before a switch */
> - ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
> + ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
> if (ret)
> return ret;
>
> @@ -839,7 +839,7 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
>
> /* XXX: RCS is the only one to auto invalidate the TLBs? */
> if (ring->id != RCS) {
> - ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
> + ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
> if (ret)
> return ret;
> }
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 91a9131..ca8f039 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -91,10 +91,11 @@ static void __intel_ring_advance(struct intel_engine_cs *ring)
> }
>
> static int
> -gen2_render_ring_flush(struct intel_engine_cs *ring,
> +gen2_render_ring_flush(struct drm_i915_gem_request *req,
> u32 invalidate_domains,
> u32 flush_domains)
> {
> + struct intel_engine_cs *ring = req->ring;
> u32 cmd;
> int ret;
>
> @@ -117,10 +118,11 @@ gen2_render_ring_flush(struct intel_engine_cs *ring,
> }
>
> static int
> -gen4_render_ring_flush(struct intel_engine_cs *ring,
> +gen4_render_ring_flush(struct drm_i915_gem_request *req,
> u32 invalidate_domains,
> u32 flush_domains)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct drm_device *dev = ring->dev;
> u32 cmd;
> int ret;
> @@ -247,9 +249,10 @@ intel_emit_post_sync_nonzero_flush(struct intel_engine_cs *ring)
> }
>
> static int
> -gen6_render_ring_flush(struct intel_engine_cs *ring,
> - u32 invalidate_domains, u32 flush_domains)
> +gen6_render_ring_flush(struct drm_i915_gem_request *req,
> + u32 invalidate_domains, u32 flush_domains)
> {
> + struct intel_engine_cs *ring = req->ring;
> u32 flags = 0;
> u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
> int ret;
> @@ -341,9 +344,10 @@ static int gen7_ring_fbc_flush(struct intel_engine_cs *ring, u32 value)
> }
>
> static int
> -gen7_render_ring_flush(struct intel_engine_cs *ring,
> +gen7_render_ring_flush(struct drm_i915_gem_request *req,
> u32 invalidate_domains, u32 flush_domains)
> {
> + struct intel_engine_cs *ring = req->ring;
> u32 flags = 0;
> u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
> int ret;
> @@ -426,9 +430,10 @@ gen8_emit_pipe_control(struct intel_engine_cs *ring,
> }
>
> static int
> -gen8_render_ring_flush(struct intel_engine_cs *ring,
> +gen8_render_ring_flush(struct drm_i915_gem_request *req,
> u32 invalidate_domains, u32 flush_domains)
> {
> + struct intel_engine_cs *ring = req->ring;
> u32 flags = 0;
> u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
> int ret;
> @@ -1527,10 +1532,11 @@ i8xx_ring_put_irq(struct intel_engine_cs *ring)
> }
>
> static int
> -bsd_ring_flush(struct intel_engine_cs *ring,
> +bsd_ring_flush(struct drm_i915_gem_request *req,
> u32 invalidate_domains,
> u32 flush_domains)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> ret = intel_ring_begin(ring, 2);
> @@ -2318,9 +2324,10 @@ static void gen6_bsd_ring_write_tail(struct intel_engine_cs *ring,
> _MASKED_BIT_DISABLE(GEN6_BSD_SLEEP_MSG_DISABLE));
> }
>
> -static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
> +static int gen6_bsd_ring_flush(struct drm_i915_gem_request *req,
> u32 invalidate, u32 flush)
> {
> + struct intel_engine_cs *ring = req->ring;
> uint32_t cmd;
> int ret;
>
> @@ -2430,9 +2437,10 @@ gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
>
> /* Blitter support (SandyBridge+) */
>
> -static int gen6_ring_flush(struct intel_engine_cs *ring,
> +static int gen6_ring_flush(struct drm_i915_gem_request *req,
> u32 invalidate, u32 flush)
> {
> + struct intel_engine_cs *ring = req->ring;
> struct drm_device *dev = ring->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> uint32_t cmd;
> @@ -2854,7 +2862,7 @@ intel_ring_flush_all_caches(struct drm_i915_gem_request *req)
> if (!ring->gpu_caches_dirty)
> return 0;
>
> - ret = ring->flush(ring, 0, I915_GEM_GPU_DOMAINS);
> + ret = ring->flush(req, 0, I915_GEM_GPU_DOMAINS);
> if (ret)
> return ret;
>
> @@ -2875,7 +2883,7 @@ intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
> if (ring->gpu_caches_dirty)
> flush_domains = I915_GEM_GPU_DOMAINS;
>
> - ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, flush_domains);
> + ret = ring->flush(req, I915_GEM_GPU_DOMAINS, flush_domains);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 0ef29fb..c08e2dc 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -147,7 +147,7 @@ struct intel_engine_cs {
>
> void (*write_tail)(struct intel_engine_cs *ring,
> u32 value);
> - int __must_check (*flush)(struct intel_engine_cs *ring,
> + int __must_check (*flush)(struct drm_i915_gem_request *req,
> u32 invalidate_domains,
> u32 flush_domains);
> int (*add_request)(struct intel_engine_cs *ring);
>
trace_i915_gem_ring_flush still takes a ring as input argument. Do you
feel like updating it to reflect your changes?
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 38/53] drm/i915: Update some flush helpers to take request structures
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (36 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 37/53] drm/i915: Update ring->flush() to take a requests structure John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 20:46 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 39/53] drm/i915: Update ring->emit_flush() to take a request structure John.C.Harrison
` (16 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated intel_emit_post_sync_nonzero_flush(), gen7_render_ring_cs_stall_wa(),
gen7_ring_fbc_flush() and gen8_emit_pipe_control() to take requests instead of
rings.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_ringbuffer.c | 29 ++++++++++++++++-------------
1 file changed, 16 insertions(+), 13 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index ca8f039..470fa93 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -214,8 +214,9 @@ gen4_render_ring_flush(struct drm_i915_gem_request *req,
* really our business. That leaves only stall at scoreboard.
*/
static int
-intel_emit_post_sync_nonzero_flush(struct intel_engine_cs *ring)
+intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
@@ -258,7 +259,7 @@ gen6_render_ring_flush(struct drm_i915_gem_request *req,
int ret;
/* Force SNB workarounds for PIPE_CONTROL flushes */
- ret = intel_emit_post_sync_nonzero_flush(ring);
+ ret = intel_emit_post_sync_nonzero_flush(req);
if (ret)
return ret;
@@ -302,8 +303,9 @@ gen6_render_ring_flush(struct drm_i915_gem_request *req,
}
static int
-gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring)
+gen7_render_ring_cs_stall_wa(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
ret = intel_ring_begin(ring, 4);
@@ -320,8 +322,9 @@ gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring)
return 0;
}
-static int gen7_ring_fbc_flush(struct intel_engine_cs *ring, u32 value)
+static int gen7_ring_fbc_flush(struct drm_i915_gem_request *req, u32 value)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
if (!ring->fbc_dirty)
@@ -389,7 +392,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req,
/* Workaround: we must issue a pipe_control with CS-stall bit
* set before a pipe_control command that has the state cache
* invalidate bit set. */
- gen7_render_ring_cs_stall_wa(ring);
+ gen7_render_ring_cs_stall_wa(req);
}
ret = intel_ring_begin(ring, 4);
@@ -403,15 +406,16 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req,
intel_ring_advance(ring);
if (!invalidate_domains && flush_domains)
- return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
+ return gen7_ring_fbc_flush(req, FBC_REND_NUKE);
return 0;
}
static int
-gen8_emit_pipe_control(struct intel_engine_cs *ring,
+gen8_emit_pipe_control(struct drm_i915_gem_request *req,
u32 flags, u32 scratch_addr)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
ret = intel_ring_begin(ring, 6);
@@ -433,9 +437,8 @@ static int
gen8_render_ring_flush(struct drm_i915_gem_request *req,
u32 invalidate_domains, u32 flush_domains)
{
- struct intel_engine_cs *ring = req->ring;
u32 flags = 0;
- u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+ u32 scratch_addr = req->ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
flags |= PIPE_CONTROL_CS_STALL;
@@ -455,7 +458,7 @@ gen8_render_ring_flush(struct drm_i915_gem_request *req,
flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
/* WaCsStallBeforeStateCacheInvalidate:bdw,chv */
- ret = gen8_emit_pipe_control(ring,
+ ret = gen8_emit_pipe_control(req,
PIPE_CONTROL_CS_STALL |
PIPE_CONTROL_STALL_AT_SCOREBOARD,
0);
@@ -463,12 +466,12 @@ gen8_render_ring_flush(struct drm_i915_gem_request *req,
return ret;
}
- ret = gen8_emit_pipe_control(ring, flags, scratch_addr);
+ ret = gen8_emit_pipe_control(req, flags, scratch_addr);
if (ret)
return ret;
if (!invalidate_domains && flush_domains)
- return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
+ return gen7_ring_fbc_flush(req, FBC_REND_NUKE);
return 0;
}
@@ -2482,7 +2485,7 @@ static int gen6_ring_flush(struct drm_i915_gem_request *req,
if (!invalidate && flush) {
if (IS_GEN7(dev))
- return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN);
+ return gen7_ring_fbc_flush(req, FBC_REND_CACHE_CLEAN);
else if (IS_BROADWELL(dev))
dev_priv->fbc.need_sw_cache_clean = true;
}
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 38/53] drm/i915: Update some flush helpers to take request structures
2015-02-19 17:17 ` [PATCH 38/53] drm/i915: Update some flush helpers to take request structures John.C.Harrison
@ 2015-03-09 20:46 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 20:46 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated intel_emit_post_sync_nonzero_flush(), gen7_render_ring_cs_stall_wa(),
> gen7_ring_fbc_flush() and gen8_emit_pipe_control() to take requests instead of
> rings.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_ringbuffer.c | 29 ++++++++++++++++-------------
> 1 file changed, 16 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index ca8f039..470fa93 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -214,8 +214,9 @@ gen4_render_ring_flush(struct drm_i915_gem_request *req,
> * really our business. That leaves only stall at scoreboard.
> */
> static int
> -intel_emit_post_sync_nonzero_flush(struct intel_engine_cs *ring)
> +intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
> int ret;
>
> @@ -258,7 +259,7 @@ gen6_render_ring_flush(struct drm_i915_gem_request *req,
> int ret;
>
> /* Force SNB workarounds for PIPE_CONTROL flushes */
> - ret = intel_emit_post_sync_nonzero_flush(ring);
> + ret = intel_emit_post_sync_nonzero_flush(req);
> if (ret)
> return ret;
>
> @@ -302,8 +303,9 @@ gen6_render_ring_flush(struct drm_i915_gem_request *req,
> }
>
> static int
> -gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring)
> +gen7_render_ring_cs_stall_wa(struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> ret = intel_ring_begin(ring, 4);
> @@ -320,8 +322,9 @@ gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring)
> return 0;
> }
>
> -static int gen7_ring_fbc_flush(struct intel_engine_cs *ring, u32 value)
> +static int gen7_ring_fbc_flush(struct drm_i915_gem_request *req, u32 value)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> if (!ring->fbc_dirty)
> @@ -389,7 +392,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req,
> /* Workaround: we must issue a pipe_control with CS-stall bit
> * set before a pipe_control command that has the state cache
> * invalidate bit set. */
> - gen7_render_ring_cs_stall_wa(ring);
> + gen7_render_ring_cs_stall_wa(req);
> }
>
> ret = intel_ring_begin(ring, 4);
> @@ -403,15 +406,16 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req,
> intel_ring_advance(ring);
>
> if (!invalidate_domains && flush_domains)
> - return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
> + return gen7_ring_fbc_flush(req, FBC_REND_NUKE);
>
> return 0;
> }
>
> static int
> -gen8_emit_pipe_control(struct intel_engine_cs *ring,
> +gen8_emit_pipe_control(struct drm_i915_gem_request *req,
> u32 flags, u32 scratch_addr)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> ret = intel_ring_begin(ring, 6);
> @@ -433,9 +437,8 @@ static int
> gen8_render_ring_flush(struct drm_i915_gem_request *req,
> u32 invalidate_domains, u32 flush_domains)
> {
> - struct intel_engine_cs *ring = req->ring;
> u32 flags = 0;
> - u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
> + u32 scratch_addr = req->ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
> int ret;
>
> flags |= PIPE_CONTROL_CS_STALL;
> @@ -455,7 +458,7 @@ gen8_render_ring_flush(struct drm_i915_gem_request *req,
> flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
>
> /* WaCsStallBeforeStateCacheInvalidate:bdw,chv */
> - ret = gen8_emit_pipe_control(ring,
> + ret = gen8_emit_pipe_control(req,
> PIPE_CONTROL_CS_STALL |
> PIPE_CONTROL_STALL_AT_SCOREBOARD,
> 0);
> @@ -463,12 +466,12 @@ gen8_render_ring_flush(struct drm_i915_gem_request *req,
> return ret;
> }
>
> - ret = gen8_emit_pipe_control(ring, flags, scratch_addr);
> + ret = gen8_emit_pipe_control(req, flags, scratch_addr);
> if (ret)
> return ret;
>
> if (!invalidate_domains && flush_domains)
> - return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
> + return gen7_ring_fbc_flush(req, FBC_REND_NUKE);
>
> return 0;
> }
> @@ -2482,7 +2485,7 @@ static int gen6_ring_flush(struct drm_i915_gem_request *req,
>
> if (!invalidate && flush) {
> if (IS_GEN7(dev))
> - return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN);
> + return gen7_ring_fbc_flush(req, FBC_REND_CACHE_CLEAN);
> else if (IS_BROADWELL(dev))
> dev_priv->fbc.need_sw_cache_clean = true;
> }
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 39/53] drm/i915: Update ring->emit_flush() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (37 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 38/53] drm/i915: Update some flush helpers to take request structures John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 20:51 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 40/53] drm/i915: Update ring->add_request() " John.C.Harrison
` (15 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the various ring->emit_flush() implementations to take a request instead
of a ringbuf/context pair.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_lrc.c | 17 ++++++++---------
drivers/gpu/drm/i915/intel_ringbuffer.h | 3 +--
2 files changed, 9 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index d8084a1..f3bf2cc 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -568,8 +568,7 @@ static int logical_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
if (ring->gpu_caches_dirty)
flush_domains = I915_GEM_GPU_DOMAINS;
- ret = ring->emit_flush(req->ringbuf, req->ctx,
- I915_GEM_GPU_DOMAINS, flush_domains);
+ ret = ring->emit_flush(req, I915_GEM_GPU_DOMAINS, flush_domains);
if (ret)
return ret;
@@ -776,7 +775,7 @@ int logical_ring_flush_all_caches(struct drm_i915_gem_request *req)
if (!ring->gpu_caches_dirty)
return 0;
- ret = ring->emit_flush(req->ringbuf, req->ctx, 0, I915_GEM_GPU_DOMAINS);
+ ret = ring->emit_flush(req, 0, I915_GEM_GPU_DOMAINS);
if (ret)
return ret;
@@ -1221,18 +1220,18 @@ static void gen8_logical_ring_put_irq(struct intel_engine_cs *ring)
spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
}
-static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+static int gen8_emit_flush(struct drm_i915_gem_request *request,
u32 invalidate_domains,
u32 unused)
{
+ struct intel_ringbuffer *ringbuf = request->ringbuf;
struct intel_engine_cs *ring = ringbuf->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t cmd;
int ret;
- ret = intel_logical_ring_begin(ringbuf, ctx, 4);
+ ret = intel_logical_ring_begin(ringbuf, request->ctx, 4);
if (ret)
return ret;
@@ -1262,11 +1261,11 @@ static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
return 0;
}
-static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
u32 invalidate_domains,
u32 flush_domains)
{
+ struct intel_ringbuffer *ringbuf = request->ringbuf;
struct intel_engine_cs *ring = ringbuf->ring;
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
u32 flags = 0;
@@ -1290,7 +1289,7 @@ static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
}
- ret = intel_logical_ring_begin(ringbuf, ctx, 6);
+ ret = intel_logical_ring_begin(ringbuf, request->ctx, 6);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index c08e2dc..6f7c79c 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -235,8 +235,7 @@ struct intel_engine_cs {
u32 irq_keep_mask; /* bitmask for interrupts that should not be masked */
int (*emit_request)(struct intel_ringbuffer *ringbuf,
struct drm_i915_gem_request *request);
- int (*emit_flush)(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+ int (*emit_flush)(struct drm_i915_gem_request *request,
u32 invalidate_domains,
u32 flush_domains);
int (*emit_bb_start)(struct intel_ringbuffer *ringbuf,
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 39/53] drm/i915: Update ring->emit_flush() to take a request structure
2015-02-19 17:17 ` [PATCH 39/53] drm/i915: Update ring->emit_flush() to take a request structure John.C.Harrison
@ 2015-03-09 20:51 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 20:51 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the various ring->emit_flush() implementations to take a request instead
> of a ringbuf/context pair.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_lrc.c | 17 ++++++++---------
> drivers/gpu/drm/i915/intel_ringbuffer.h | 3 +--
> 2 files changed, 9 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index d8084a1..f3bf2cc 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -568,8 +568,7 @@ static int logical_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
> if (ring->gpu_caches_dirty)
> flush_domains = I915_GEM_GPU_DOMAINS;
>
> - ret = ring->emit_flush(req->ringbuf, req->ctx,
> - I915_GEM_GPU_DOMAINS, flush_domains);
> + ret = ring->emit_flush(req, I915_GEM_GPU_DOMAINS, flush_domains);
> if (ret)
> return ret;
>
> @@ -776,7 +775,7 @@ int logical_ring_flush_all_caches(struct drm_i915_gem_request *req)
> if (!ring->gpu_caches_dirty)
> return 0;
>
> - ret = ring->emit_flush(req->ringbuf, req->ctx, 0, I915_GEM_GPU_DOMAINS);
> + ret = ring->emit_flush(req, 0, I915_GEM_GPU_DOMAINS);
> if (ret)
> return ret;
>
> @@ -1221,18 +1220,18 @@ static void gen8_logical_ring_put_irq(struct intel_engine_cs *ring)
> spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
> }
>
> -static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx,
> +static int gen8_emit_flush(struct drm_i915_gem_request *request,
> u32 invalidate_domains,
> u32 unused)
> {
> + struct intel_ringbuffer *ringbuf = request->ringbuf;
> struct intel_engine_cs *ring = ringbuf->ring;
> struct drm_device *dev = ring->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> uint32_t cmd;
> int ret;
>
> - ret = intel_logical_ring_begin(ringbuf, ctx, 4);
> + ret = intel_logical_ring_begin(ringbuf, request->ctx, 4);
> if (ret)
> return ret;
>
> @@ -1262,11 +1261,11 @@ static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
> return 0;
> }
>
> -static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx,
> +static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
> u32 invalidate_domains,
> u32 flush_domains)
> {
> + struct intel_ringbuffer *ringbuf = request->ringbuf;
> struct intel_engine_cs *ring = ringbuf->ring;
> u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
> u32 flags = 0;
> @@ -1290,7 +1289,7 @@ static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
> flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
> }
>
> - ret = intel_logical_ring_begin(ringbuf, ctx, 6);
> + ret = intel_logical_ring_begin(ringbuf, request->ctx, 6);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index c08e2dc..6f7c79c 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -235,8 +235,7 @@ struct intel_engine_cs {
> u32 irq_keep_mask; /* bitmask for interrupts that should not be masked */
> int (*emit_request)(struct intel_ringbuffer *ringbuf,
> struct drm_i915_gem_request *request);
> - int (*emit_flush)(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx,
> + int (*emit_flush)(struct drm_i915_gem_request *request,
> u32 invalidate_domains,
> u32 flush_domains);
> int (*emit_bb_start)(struct intel_ringbuffer *ringbuf,
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 40/53] drm/i915: Update ring->add_request() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (38 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 39/53] drm/i915: Update ring->emit_flush() to take a request structure John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 21:02 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 41/53] drm/i915: Update ring->emit_request() " John.C.Harrison
` (14 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the various ring->add_request() implementations to take a request
instead of a ring. This removes their reliance on the OLR to obtain the seqno
value that the request should be tagged with.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 2 +-
drivers/gpu/drm/i915/intel_ringbuffer.c | 26 ++++++++++++--------------
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
3 files changed, 14 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index e8577d7..4357cd3 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2453,7 +2453,7 @@ int __i915_add_request(struct drm_i915_gem_request *request,
if (i915.enable_execlists)
ret = ring->emit_request(ringbuf, request);
else
- ret = ring->add_request(ring);
+ ret = ring->add_request(request);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 470fa93..99f0dd1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1222,16 +1222,16 @@ static int gen6_signal(struct intel_engine_cs *signaller,
/**
* gen6_add_request - Update the semaphore mailbox registers
- *
- * @ring - ring that is adding a request
- * @seqno - return seqno stuck into the ring
+ *
+ * @request - request to write to the ring
*
* Update the mailbox registers in the *other* rings with the current seqno.
* This acts like a signal in the canonical semaphore.
*/
static int
-gen6_add_request(struct intel_engine_cs *ring)
+gen6_add_request(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
if (ring->semaphore.signal)
@@ -1244,8 +1244,7 @@ gen6_add_request(struct intel_engine_cs *ring)
intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
- intel_ring_emit(ring,
- i915_gem_request_get_seqno(ring->outstanding_lazy_request));
+ intel_ring_emit(ring, i915_gem_request_get_seqno(req));
intel_ring_emit(ring, MI_USER_INTERRUPT);
__intel_ring_advance(ring);
@@ -1342,8 +1341,9 @@ do { \
} while (0)
static int
-pc_render_add_request(struct intel_engine_cs *ring)
+pc_render_add_request(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
@@ -1363,8 +1363,7 @@ pc_render_add_request(struct intel_engine_cs *ring)
PIPE_CONTROL_WRITE_FLUSH |
PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE);
intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
- intel_ring_emit(ring,
- i915_gem_request_get_seqno(ring->outstanding_lazy_request));
+ intel_ring_emit(ring, i915_gem_request_get_seqno(req));
intel_ring_emit(ring, 0);
PIPE_CONTROL_FLUSH(ring, scratch_addr);
scratch_addr += 2 * CACHELINE_BYTES; /* write to separate cachelines */
@@ -1383,8 +1382,7 @@ pc_render_add_request(struct intel_engine_cs *ring)
PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
PIPE_CONTROL_NOTIFY);
intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
- intel_ring_emit(ring,
- i915_gem_request_get_seqno(ring->outstanding_lazy_request));
+ intel_ring_emit(ring, i915_gem_request_get_seqno(req));
intel_ring_emit(ring, 0);
__intel_ring_advance(ring);
@@ -1553,8 +1551,9 @@ bsd_ring_flush(struct drm_i915_gem_request *req,
}
static int
-i9xx_add_request(struct intel_engine_cs *ring)
+i9xx_add_request(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
ret = intel_ring_begin(ring, 4);
@@ -1563,8 +1562,7 @@ i9xx_add_request(struct intel_engine_cs *ring)
intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
- intel_ring_emit(ring,
- i915_gem_request_get_seqno(ring->outstanding_lazy_request));
+ intel_ring_emit(ring, i915_gem_request_get_seqno(req));
intel_ring_emit(ring, MI_USER_INTERRUPT);
__intel_ring_advance(ring);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 6f7c79c..d2391a9 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -150,7 +150,7 @@ struct intel_engine_cs {
int __must_check (*flush)(struct drm_i915_gem_request *req,
u32 invalidate_domains,
u32 flush_domains);
- int (*add_request)(struct intel_engine_cs *ring);
+ int (*add_request)(struct drm_i915_gem_request *req);
/* Some chipsets are not quite as coherent as advertised and need
* an expensive kick to force a true read of the up-to-date seqno.
* However, the up-to-date seqno is not always required and the last
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 40/53] drm/i915: Update ring->add_request() to take a request structure
2015-02-19 17:17 ` [PATCH 40/53] drm/i915: Update ring->add_request() " John.C.Harrison
@ 2015-03-09 21:02 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 21:02 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the various ring->add_request() implementations to take a request
> instead of a ring. This removes their reliance on the OLR to obtain the seqno
> value that the request should be tagged with.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 2 +-
> drivers/gpu/drm/i915/intel_ringbuffer.c | 26 ++++++++++++--------------
> drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
> 3 files changed, 14 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index e8577d7..4357cd3 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2453,7 +2453,7 @@ int __i915_add_request(struct drm_i915_gem_request *request,
> if (i915.enable_execlists)
> ret = ring->emit_request(ringbuf, request);
> else
> - ret = ring->add_request(ring);
> + ret = ring->add_request(request);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 470fa93..99f0dd1 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -1222,16 +1222,16 @@ static int gen6_signal(struct intel_engine_cs *signaller,
>
> /**
> * gen6_add_request - Update the semaphore mailbox registers
> - *
> - * @ring - ring that is adding a request
> - * @seqno - return seqno stuck into the ring
> + *
> + * @request - request to write to the ring
> *
> * Update the mailbox registers in the *other* rings with the current seqno.
> * This acts like a signal in the canonical semaphore.
> */
> static int
> -gen6_add_request(struct intel_engine_cs *ring)
> +gen6_add_request(struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> if (ring->semaphore.signal)
> @@ -1244,8 +1244,7 @@ gen6_add_request(struct intel_engine_cs *ring)
>
> intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
> intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
> - intel_ring_emit(ring,
> - i915_gem_request_get_seqno(ring->outstanding_lazy_request));
> + intel_ring_emit(ring, i915_gem_request_get_seqno(req));
> intel_ring_emit(ring, MI_USER_INTERRUPT);
> __intel_ring_advance(ring);
>
> @@ -1342,8 +1341,9 @@ do { \
> } while (0)
>
> static int
> -pc_render_add_request(struct intel_engine_cs *ring)
> +pc_render_add_request(struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
> int ret;
>
> @@ -1363,8 +1363,7 @@ pc_render_add_request(struct intel_engine_cs *ring)
> PIPE_CONTROL_WRITE_FLUSH |
> PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE);
> intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
> - intel_ring_emit(ring,
> - i915_gem_request_get_seqno(ring->outstanding_lazy_request));
> + intel_ring_emit(ring, i915_gem_request_get_seqno(req));
> intel_ring_emit(ring, 0);
> PIPE_CONTROL_FLUSH(ring, scratch_addr);
> scratch_addr += 2 * CACHELINE_BYTES; /* write to separate cachelines */
> @@ -1383,8 +1382,7 @@ pc_render_add_request(struct intel_engine_cs *ring)
> PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
> PIPE_CONTROL_NOTIFY);
> intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
> - intel_ring_emit(ring,
> - i915_gem_request_get_seqno(ring->outstanding_lazy_request));
> + intel_ring_emit(ring, i915_gem_request_get_seqno(req));
> intel_ring_emit(ring, 0);
> __intel_ring_advance(ring);
>
> @@ -1553,8 +1551,9 @@ bsd_ring_flush(struct drm_i915_gem_request *req,
> }
>
> static int
> -i9xx_add_request(struct intel_engine_cs *ring)
> +i9xx_add_request(struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> ret = intel_ring_begin(ring, 4);
> @@ -1563,8 +1562,7 @@ i9xx_add_request(struct intel_engine_cs *ring)
>
> intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
> intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
> - intel_ring_emit(ring,
> - i915_gem_request_get_seqno(ring->outstanding_lazy_request));
> + intel_ring_emit(ring, i915_gem_request_get_seqno(req));
> intel_ring_emit(ring, MI_USER_INTERRUPT);
> __intel_ring_advance(ring);
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 6f7c79c..d2391a9 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -150,7 +150,7 @@ struct intel_engine_cs {
> int __must_check (*flush)(struct drm_i915_gem_request *req,
> u32 invalidate_domains,
> u32 flush_domains);
> - int (*add_request)(struct intel_engine_cs *ring);
> + int (*add_request)(struct drm_i915_gem_request *req);
> /* Some chipsets are not quite as coherent as advertised and need
> * an expensive kick to force a true read of the up-to-date seqno.
> * However, the up-to-date seqno is not always required and the last
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 41/53] drm/i915: Update ring->emit_request() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (39 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 40/53] drm/i915: Update ring->add_request() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 21:07 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 42/53] drm/i915: Update ring->dispatch_execbuffer() " John.C.Harrison
` (13 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the ring->emit_request() implementation to take a request instead of a
ringbuf/request pair. Also removed it's use of the OLR for obtaining the
request's seqno.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 2 +-
drivers/gpu/drm/i915/intel_lrc.c | 7 +++----
drivers/gpu/drm/i915/intel_ringbuffer.h | 3 +--
3 files changed, 5 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 4357cd3..4f6e9ad 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2451,7 +2451,7 @@ int __i915_add_request(struct drm_i915_gem_request *request,
request->postfix = intel_ring_get_tail(ringbuf);
if (i915.enable_execlists)
- ret = ring->emit_request(ringbuf, request);
+ ret = ring->emit_request(request);
else
ret = ring->add_request(request);
if (ret)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index f3bf2cc..f4661ec 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1314,9 +1314,9 @@ static void gen8_set_seqno(struct intel_engine_cs *ring, u32 seqno)
intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno);
}
-static int gen8_emit_request(struct intel_ringbuffer *ringbuf,
- struct drm_i915_gem_request *request)
+static int gen8_emit_request(struct drm_i915_gem_request *request)
{
+ struct intel_ringbuffer *ringbuf = request->ringbuf;
struct intel_engine_cs *ring = ringbuf->ring;
u32 cmd;
int ret;
@@ -1333,8 +1333,7 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf,
(ring->status_page.gfx_addr +
(I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT)));
intel_logical_ring_emit(ringbuf, 0);
- intel_logical_ring_emit(ringbuf,
- i915_gem_request_get_seqno(ring->outstanding_lazy_request));
+ intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
intel_logical_ring_emit(ringbuf, MI_NOOP);
intel_logical_ring_advance_and_submit(ringbuf, request->ctx, request);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index d2391a9..d8300f2 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -233,8 +233,7 @@ struct intel_engine_cs {
struct list_head execlist_retired_req_list;
u8 next_context_status_buffer;
u32 irq_keep_mask; /* bitmask for interrupts that should not be masked */
- int (*emit_request)(struct intel_ringbuffer *ringbuf,
- struct drm_i915_gem_request *request);
+ int (*emit_request)(struct drm_i915_gem_request *request);
int (*emit_flush)(struct drm_i915_gem_request *request,
u32 invalidate_domains,
u32 flush_domains);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 41/53] drm/i915: Update ring->emit_request() to take a request structure
2015-02-19 17:17 ` [PATCH 41/53] drm/i915: Update ring->emit_request() " John.C.Harrison
@ 2015-03-09 21:07 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 21:07 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the ring->emit_request() implementation to take a request instead of a
> ringbuf/request pair. Also removed it's use of the OLR for obtaining the
> request's seqno.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 2 +-
> drivers/gpu/drm/i915/intel_lrc.c | 7 +++----
> drivers/gpu/drm/i915/intel_ringbuffer.h | 3 +--
> 3 files changed, 5 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 4357cd3..4f6e9ad 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2451,7 +2451,7 @@ int __i915_add_request(struct drm_i915_gem_request *request,
> request->postfix = intel_ring_get_tail(ringbuf);
>
> if (i915.enable_execlists)
> - ret = ring->emit_request(ringbuf, request);
> + ret = ring->emit_request(request);
> else
> ret = ring->add_request(request);
> if (ret)
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index f3bf2cc..f4661ec 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -1314,9 +1314,9 @@ static void gen8_set_seqno(struct intel_engine_cs *ring, u32 seqno)
> intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno);
> }
>
> -static int gen8_emit_request(struct intel_ringbuffer *ringbuf,
> - struct drm_i915_gem_request *request)
> +static int gen8_emit_request(struct drm_i915_gem_request *request)
> {
> + struct intel_ringbuffer *ringbuf = request->ringbuf;
> struct intel_engine_cs *ring = ringbuf->ring;
> u32 cmd;
> int ret;
> @@ -1333,8 +1333,7 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf,
> (ring->status_page.gfx_addr +
> (I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT)));
> intel_logical_ring_emit(ringbuf, 0);
> - intel_logical_ring_emit(ringbuf,
> - i915_gem_request_get_seqno(ring->outstanding_lazy_request));
> + intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
> intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
> intel_logical_ring_emit(ringbuf, MI_NOOP);
> intel_logical_ring_advance_and_submit(ringbuf, request->ctx, request);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index d2391a9..d8300f2 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -233,8 +233,7 @@ struct intel_engine_cs {
> struct list_head execlist_retired_req_list;
> u8 next_context_status_buffer;
> u32 irq_keep_mask; /* bitmask for interrupts that should not be masked */
> - int (*emit_request)(struct intel_ringbuffer *ringbuf,
> - struct drm_i915_gem_request *request);
> + int (*emit_request)(struct drm_i915_gem_request *request);
> int (*emit_flush)(struct drm_i915_gem_request *request,
> u32 invalidate_domains,
> u32 flush_domains);
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 42/53] drm/i915: Update ring->dispatch_execbuffer() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (40 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 41/53] drm/i915: Update ring->emit_request() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 21:16 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 43/53] drm/i915: Update ring->emit_bb_start() " John.C.Harrison
` (12 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the various ring->dispatch_execbuffer() implementations to take a
request instead of a ring.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 4 ++--
drivers/gpu/drm/i915/i915_gem_render_state.c | 3 +--
drivers/gpu/drm/i915/intel_ringbuffer.c | 18 ++++++++++++------
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
4 files changed, 16 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index a79c893..8b4f8a9 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1265,14 +1265,14 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
if (ret)
goto error;
- ret = ring->dispatch_execbuffer(ring,
+ ret = ring->dispatch_execbuffer(params->request,
exec_start, exec_len,
params->dispatch_flags);
if (ret)
goto error;
}
} else {
- ret = ring->dispatch_execbuffer(ring,
+ ret = ring->dispatch_execbuffer(params->request,
exec_start, exec_len,
params->dispatch_flags);
if (ret)
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index 866274c..cdf2fee 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -164,8 +164,7 @@ int i915_gem_render_state_init(struct drm_i915_gem_request *req)
if (so.rodata == NULL)
return 0;
- ret = req->ring->dispatch_execbuffer(req->ring,
- so.ggtt_offset,
+ ret = req->ring->dispatch_execbuffer(req, so.ggtt_offset,
so.rodata->batch_items * 4,
I915_DISPATCH_SECURE);
if (ret)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 99f0dd1..87612f1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1694,10 +1694,11 @@ gen8_ring_put_irq(struct intel_engine_cs *ring)
}
static int
-i965_dispatch_execbuffer(struct intel_engine_cs *ring,
+i965_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 length,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
ret = intel_ring_begin(ring, 2);
@@ -1720,10 +1721,11 @@ i965_dispatch_execbuffer(struct intel_engine_cs *ring,
#define I830_TLB_ENTRIES (2)
#define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT)
static int
-i830_dispatch_execbuffer(struct intel_engine_cs *ring,
+i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 len,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
u32 cs_offset = ring->scratch.gtt_offset;
int ret;
@@ -1782,10 +1784,11 @@ i830_dispatch_execbuffer(struct intel_engine_cs *ring,
}
static int
-i915_dispatch_execbuffer(struct intel_engine_cs *ring,
+i915_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 len,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
ret = intel_ring_begin(ring, 2);
@@ -2370,10 +2373,11 @@ static int gen6_bsd_ring_flush(struct drm_i915_gem_request *req,
}
static int
-gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
+gen8_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 len,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
bool ppgtt = USES_PPGTT(ring->dev) &&
!(dispatch_flags & I915_DISPATCH_SECURE);
int ret;
@@ -2393,10 +2397,11 @@ gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
}
static int
-hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
+hsw_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 len,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
ret = intel_ring_begin(ring, 2);
@@ -2415,10 +2420,11 @@ hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
}
static int
-gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
+gen6_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
u64 offset, u32 len,
unsigned dispatch_flags)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
ret = intel_ring_begin(ring, 2);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index d8300f2..0b03b3a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -161,7 +161,7 @@ struct intel_engine_cs {
bool lazy_coherency);
void (*set_seqno)(struct intel_engine_cs *ring,
u32 seqno);
- int (*dispatch_execbuffer)(struct intel_engine_cs *ring,
+ int (*dispatch_execbuffer)(struct drm_i915_gem_request *req,
u64 offset, u32 length,
unsigned dispatch_flags);
#define I915_DISPATCH_SECURE 0x1
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 42/53] drm/i915: Update ring->dispatch_execbuffer() to take a request structure
2015-02-19 17:17 ` [PATCH 42/53] drm/i915: Update ring->dispatch_execbuffer() " John.C.Harrison
@ 2015-03-09 21:16 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 21:16 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the various ring->dispatch_execbuffer() implementations to take a
> request instead of a ring.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 4 ++--
> drivers/gpu/drm/i915/i915_gem_render_state.c | 3 +--
> drivers/gpu/drm/i915/intel_ringbuffer.c | 18 ++++++++++++------
> drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
> 4 files changed, 16 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index a79c893..8b4f8a9 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1265,14 +1265,14 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
> if (ret)
> goto error;
>
> - ret = ring->dispatch_execbuffer(ring,
> + ret = ring->dispatch_execbuffer(params->request,
> exec_start, exec_len,
> params->dispatch_flags);
> if (ret)
> goto error;
> }
> } else {
> - ret = ring->dispatch_execbuffer(ring,
> + ret = ring->dispatch_execbuffer(params->request,
> exec_start, exec_len,
> params->dispatch_flags);
> if (ret)
> diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
> index 866274c..cdf2fee 100644
> --- a/drivers/gpu/drm/i915/i915_gem_render_state.c
> +++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
> @@ -164,8 +164,7 @@ int i915_gem_render_state_init(struct drm_i915_gem_request *req)
> if (so.rodata == NULL)
> return 0;
>
> - ret = req->ring->dispatch_execbuffer(req->ring,
> - so.ggtt_offset,
> + ret = req->ring->dispatch_execbuffer(req, so.ggtt_offset,
> so.rodata->batch_items * 4,
> I915_DISPATCH_SECURE);
> if (ret)
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 99f0dd1..87612f1 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -1694,10 +1694,11 @@ gen8_ring_put_irq(struct intel_engine_cs *ring)
> }
>
> static int
> -i965_dispatch_execbuffer(struct intel_engine_cs *ring,
> +i965_dispatch_execbuffer(struct drm_i915_gem_request *req,
> u64 offset, u32 length,
> unsigned dispatch_flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> ret = intel_ring_begin(ring, 2);
> @@ -1720,10 +1721,11 @@ i965_dispatch_execbuffer(struct intel_engine_cs *ring,
> #define I830_TLB_ENTRIES (2)
> #define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT)
> static int
> -i830_dispatch_execbuffer(struct intel_engine_cs *ring,
> +i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
> u64 offset, u32 len,
> unsigned dispatch_flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> u32 cs_offset = ring->scratch.gtt_offset;
> int ret;
>
> @@ -1782,10 +1784,11 @@ i830_dispatch_execbuffer(struct intel_engine_cs *ring,
> }
>
> static int
> -i915_dispatch_execbuffer(struct intel_engine_cs *ring,
> +i915_dispatch_execbuffer(struct drm_i915_gem_request *req,
> u64 offset, u32 len,
> unsigned dispatch_flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> ret = intel_ring_begin(ring, 2);
> @@ -2370,10 +2373,11 @@ static int gen6_bsd_ring_flush(struct drm_i915_gem_request *req,
> }
>
> static int
> -gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> +gen8_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
> u64 offset, u32 len,
> unsigned dispatch_flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> bool ppgtt = USES_PPGTT(ring->dev) &&
> !(dispatch_flags & I915_DISPATCH_SECURE);
> int ret;
> @@ -2393,10 +2397,11 @@ gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> }
>
> static int
> -hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> +hsw_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
> u64 offset, u32 len,
> unsigned dispatch_flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> ret = intel_ring_begin(ring, 2);
> @@ -2415,10 +2420,11 @@ hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> }
>
> static int
> -gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> +gen6_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
> u64 offset, u32 len,
> unsigned dispatch_flags)
> {
> + struct intel_engine_cs *ring = req->ring;
> int ret;
>
> ret = intel_ring_begin(ring, 2);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index d8300f2..0b03b3a 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -161,7 +161,7 @@ struct intel_engine_cs {
> bool lazy_coherency);
> void (*set_seqno)(struct intel_engine_cs *ring,
> u32 seqno);
> - int (*dispatch_execbuffer)(struct intel_engine_cs *ring,
> + int (*dispatch_execbuffer)(struct drm_i915_gem_request *req,
> u64 offset, u32 length,
> unsigned dispatch_flags);
> #define I915_DISPATCH_SECURE 0x1
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 43/53] drm/i915: Update ring->emit_bb_start() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (41 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 42/53] drm/i915: Update ring->dispatch_execbuffer() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 21:29 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 44/53] drm/i915: Update ring->sync_to() " John.C.Harrison
` (11 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the ring->emit_bb_start() implementation to take a request instead of a
ringbuf/context pair.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_lrc.c | 12 +++++-------
drivers/gpu/drm/i915/intel_ringbuffer.h | 3 +--
2 files changed, 6 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index f4661ec..5212b54 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -704,7 +704,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
exec_start = params->batch_obj_vm_offset +
args->batch_start_offset;
- ret = ring->emit_bb_start(ringbuf, params->ctx, exec_start, params->dispatch_flags);
+ ret = ring->emit_bb_start(params->request, exec_start, params->dispatch_flags);
if (ret)
return ret;
@@ -1166,14 +1166,14 @@ static int gen9_init_render_ring(struct intel_engine_cs *ring)
return init_workarounds_ring(ring);
}
-static int gen8_emit_bb_start(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
u64 offset, unsigned dispatch_flags)
{
+ struct intel_ringbuffer *ringbuf = req->ringbuf;
bool ppgtt = !(dispatch_flags & I915_DISPATCH_SECURE);
int ret;
- ret = intel_logical_ring_begin(ringbuf, ctx, 4);
+ ret = intel_logical_ring_begin(ringbuf, req->ctx, 4);
if (ret)
return ret;
@@ -1353,9 +1353,7 @@ static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req)
if (so.rodata == NULL)
return 0;
- ret = req->ring->emit_bb_start(req->ringbuf,
- req->ctx,
- so.ggtt_offset,
+ ret = req->ring->emit_bb_start(req, so.ggtt_offset,
I915_DISPATCH_SECURE);
if (ret)
goto out;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 0b03b3a..1ff0ad1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -237,8 +237,7 @@ struct intel_engine_cs {
int (*emit_flush)(struct drm_i915_gem_request *request,
u32 invalidate_domains,
u32 flush_domains);
- int (*emit_bb_start)(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+ int (*emit_bb_start)(struct drm_i915_gem_request *req,
u64 offset, unsigned dispatch_flags);
/**
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 43/53] drm/i915: Update ring->emit_bb_start() to take a request structure
2015-02-19 17:17 ` [PATCH 43/53] drm/i915: Update ring->emit_bb_start() " John.C.Harrison
@ 2015-03-09 21:29 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 21:29 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the ring->emit_bb_start() implementation to take a request instead of a
> ringbuf/context pair.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_lrc.c | 12 +++++-------
> drivers/gpu/drm/i915/intel_ringbuffer.h | 3 +--
> 2 files changed, 6 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index f4661ec..5212b54 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -704,7 +704,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
> exec_start = params->batch_obj_vm_offset +
> args->batch_start_offset;
>
> - ret = ring->emit_bb_start(ringbuf, params->ctx, exec_start, params->dispatch_flags);
> + ret = ring->emit_bb_start(params->request, exec_start, params->dispatch_flags);
> if (ret)
> return ret;
>
> @@ -1166,14 +1166,14 @@ static int gen9_init_render_ring(struct intel_engine_cs *ring)
> return init_workarounds_ring(ring);
> }
>
> -static int gen8_emit_bb_start(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx,
> +static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
> u64 offset, unsigned dispatch_flags)
> {
> + struct intel_ringbuffer *ringbuf = req->ringbuf;
> bool ppgtt = !(dispatch_flags & I915_DISPATCH_SECURE);
> int ret;
>
> - ret = intel_logical_ring_begin(ringbuf, ctx, 4);
> + ret = intel_logical_ring_begin(ringbuf, req->ctx, 4);
> if (ret)
> return ret;
>
> @@ -1353,9 +1353,7 @@ static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req)
> if (so.rodata == NULL)
> return 0;
>
> - ret = req->ring->emit_bb_start(req->ringbuf,
> - req->ctx,
> - so.ggtt_offset,
> + ret = req->ring->emit_bb_start(req, so.ggtt_offset,
> I915_DISPATCH_SECURE);
> if (ret)
> goto out;
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 0b03b3a..1ff0ad1 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -237,8 +237,7 @@ struct intel_engine_cs {
> int (*emit_flush)(struct drm_i915_gem_request *request,
> u32 invalidate_domains,
> u32 flush_domains);
> - int (*emit_bb_start)(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx,
> + int (*emit_bb_start)(struct drm_i915_gem_request *req,
> u64 offset, unsigned dispatch_flags);
>
> /**
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 44/53] drm/i915: Update ring->sync_to() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (42 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 43/53] drm/i915: Update ring->emit_bb_start() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 21:49 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 45/53] drm/i915: Update ring->signal() " John.C.Harrison
` (10 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the ring->sync_to() implementations to take a request instead of a ring.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 2 +-
drivers/gpu/drm/i915/intel_ringbuffer.c | 6 ++++--
drivers/gpu/drm/i915/intel_ringbuffer.h | 4 ++--
3 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 4f6e9ad..b5613ff 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2985,7 +2985,7 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj,
return ret;
trace_i915_gem_ring_sync_to(from, to, obj->last_read_req);
- ret = to->semaphore.sync_to(to, from, seqno);
+ ret = to->semaphore.sync_to(to_req, from, seqno);
if (!ret)
/* We use last_read_req because sync_to()
* might have just caused seqno wrap under
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 87612f1..767bab1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1267,10 +1267,11 @@ static inline bool i915_gem_has_seqno_wrapped(struct drm_device *dev,
*/
static int
-gen8_ring_sync(struct intel_engine_cs *waiter,
+gen8_ring_sync(struct drm_i915_gem_request *waiter_req,
struct intel_engine_cs *signaller,
u32 seqno)
{
+ struct intel_engine_cs *waiter = waiter_req->ring;
struct drm_i915_private *dev_priv = waiter->dev->dev_private;
int ret;
@@ -1292,10 +1293,11 @@ gen8_ring_sync(struct intel_engine_cs *waiter,
}
static int
-gen6_ring_sync(struct intel_engine_cs *waiter,
+gen6_ring_sync(struct drm_i915_gem_request *waiter_req,
struct intel_engine_cs *signaller,
u32 seqno)
{
+ struct intel_engine_cs *waiter = waiter_req->ring;
u32 dw1 = MI_SEMAPHORE_MBOX |
MI_SEMAPHORE_COMPARE |
MI_SEMAPHORE_REGISTER;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 1ff0ad1..65fe151 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -219,8 +219,8 @@ struct intel_engine_cs {
};
/* AKA wait() */
- int (*sync_to)(struct intel_engine_cs *ring,
- struct intel_engine_cs *to,
+ int (*sync_to)(struct drm_i915_gem_request *to_req,
+ struct intel_engine_cs *from,
u32 seqno);
int (*signal)(struct intel_engine_cs *signaller,
/* num_dwords needed by caller */
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 44/53] drm/i915: Update ring->sync_to() to take a request structure
2015-02-19 17:17 ` [PATCH 44/53] drm/i915: Update ring->sync_to() " John.C.Harrison
@ 2015-03-09 21:49 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 21:49 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the ring->sync_to() implementations to take a request instead of a ring.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 2 +-
> drivers/gpu/drm/i915/intel_ringbuffer.c | 6 ++++--
> drivers/gpu/drm/i915/intel_ringbuffer.h | 4 ++--
> 3 files changed, 7 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 4f6e9ad..b5613ff 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2985,7 +2985,7 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj,
> return ret;
>
> trace_i915_gem_ring_sync_to(from, to, obj->last_read_req);
trace_i915_gem_ring_sync_to() still takes a ring as argument instead of
a request. Do you want to change the trace function to reflect your changes?
Thanks,
Tomas
> - ret = to->semaphore.sync_to(to, from, seqno);
> + ret = to->semaphore.sync_to(to_req, from, seqno);
> if (!ret)
> /* We use last_read_req because sync_to()
> * might have just caused seqno wrap under
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 87612f1..767bab1 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -1267,10 +1267,11 @@ static inline bool i915_gem_has_seqno_wrapped(struct drm_device *dev,
> */
>
> static int
> -gen8_ring_sync(struct intel_engine_cs *waiter,
> +gen8_ring_sync(struct drm_i915_gem_request *waiter_req,
> struct intel_engine_cs *signaller,
> u32 seqno)
> {
> + struct intel_engine_cs *waiter = waiter_req->ring;
> struct drm_i915_private *dev_priv = waiter->dev->dev_private;
> int ret;
>
> @@ -1292,10 +1293,11 @@ gen8_ring_sync(struct intel_engine_cs *waiter,
> }
>
> static int
> -gen6_ring_sync(struct intel_engine_cs *waiter,
> +gen6_ring_sync(struct drm_i915_gem_request *waiter_req,
> struct intel_engine_cs *signaller,
> u32 seqno)
> {
> + struct intel_engine_cs *waiter = waiter_req->ring;
> u32 dw1 = MI_SEMAPHORE_MBOX |
> MI_SEMAPHORE_COMPARE |
> MI_SEMAPHORE_REGISTER;
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 1ff0ad1..65fe151 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -219,8 +219,8 @@ struct intel_engine_cs {
> };
>
> /* AKA wait() */
> - int (*sync_to)(struct intel_engine_cs *ring,
> - struct intel_engine_cs *to,
> + int (*sync_to)(struct drm_i915_gem_request *to_req,
> + struct intel_engine_cs *from,
> u32 seqno);
> int (*signal)(struct intel_engine_cs *signaller,
> /* num_dwords needed by caller */
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 45/53] drm/i915: Update ring->signal() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (43 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 44/53] drm/i915: Update ring->sync_to() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 22:04 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 46/53] drm/i915: Update cacheline_align() " John.C.Harrison
` (9 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated the various ring->signal() implementations to take a request instead of
a ring. This removes their reliance on the OLR to obtain the seqno value that
should be used for the signal.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_ringbuffer.c | 20 ++++++++++----------
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
2 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 767bab1..440356d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1105,10 +1105,11 @@ static void render_ring_cleanup(struct intel_engine_cs *ring)
intel_fini_pipe_control(ring);
}
-static int gen8_rcs_signal(struct intel_engine_cs *signaller,
+static int gen8_rcs_signal(struct drm_i915_gem_request *signaller_req,
unsigned int num_dwords)
{
#define MBOX_UPDATE_DWORDS 8
+ struct intel_engine_cs *signaller = signaller_req->ring;
struct drm_device *dev = signaller->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *waiter;
@@ -1128,8 +1129,7 @@ static int gen8_rcs_signal(struct intel_engine_cs *signaller,
if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
continue;
- seqno = i915_gem_request_get_seqno(
- signaller->outstanding_lazy_request);
+ seqno = i915_gem_request_get_seqno(signaller_req);
intel_ring_emit(signaller, GFX_OP_PIPE_CONTROL(6));
intel_ring_emit(signaller, PIPE_CONTROL_GLOBAL_GTT_IVB |
PIPE_CONTROL_QW_WRITE |
@@ -1146,10 +1146,11 @@ static int gen8_rcs_signal(struct intel_engine_cs *signaller,
return 0;
}
-static int gen8_xcs_signal(struct intel_engine_cs *signaller,
+static int gen8_xcs_signal(struct drm_i915_gem_request *signaller_req,
unsigned int num_dwords)
{
#define MBOX_UPDATE_DWORDS 6
+ struct intel_engine_cs *signaller = signaller_req->ring;
struct drm_device *dev = signaller->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *waiter;
@@ -1169,8 +1170,7 @@ static int gen8_xcs_signal(struct intel_engine_cs *signaller,
if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
continue;
- seqno = i915_gem_request_get_seqno(
- signaller->outstanding_lazy_request);
+ seqno = i915_gem_request_get_seqno(signaller_req);
intel_ring_emit(signaller, (MI_FLUSH_DW + 1) |
MI_FLUSH_DW_OP_STOREDW);
intel_ring_emit(signaller, lower_32_bits(gtt_offset) |
@@ -1185,9 +1185,10 @@ static int gen8_xcs_signal(struct intel_engine_cs *signaller,
return 0;
}
-static int gen6_signal(struct intel_engine_cs *signaller,
+static int gen6_signal(struct drm_i915_gem_request *signaller_req,
unsigned int num_dwords)
{
+ struct intel_engine_cs *signaller = signaller_req->ring;
struct drm_device *dev = signaller->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *useless;
@@ -1205,8 +1206,7 @@ static int gen6_signal(struct intel_engine_cs *signaller,
for_each_ring(useless, dev_priv, i) {
u32 mbox_reg = signaller->semaphore.mbox.signal[i];
if (mbox_reg != GEN6_NOSYNC) {
- u32 seqno = i915_gem_request_get_seqno(
- signaller->outstanding_lazy_request);
+ u32 seqno = i915_gem_request_get_seqno(signaller_req);
intel_ring_emit(signaller, MI_LOAD_REGISTER_IMM(1));
intel_ring_emit(signaller, mbox_reg);
intel_ring_emit(signaller, seqno);
@@ -1235,7 +1235,7 @@ gen6_add_request(struct drm_i915_gem_request *req)
int ret;
if (ring->semaphore.signal)
- ret = ring->semaphore.signal(ring, 4);
+ ret = ring->semaphore.signal(req, 4);
else
ret = intel_ring_begin(ring, 4);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 65fe151..7c1e0f5 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -222,7 +222,7 @@ struct intel_engine_cs {
int (*sync_to)(struct drm_i915_gem_request *to_req,
struct intel_engine_cs *from,
u32 seqno);
- int (*signal)(struct intel_engine_cs *signaller,
+ int (*signal)(struct drm_i915_gem_request *signaller_req,
/* num_dwords needed by caller */
unsigned int num_dwords);
} semaphore;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 45/53] drm/i915: Update ring->signal() to take a request structure
2015-02-19 17:17 ` [PATCH 45/53] drm/i915: Update ring->signal() " John.C.Harrison
@ 2015-03-09 22:04 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 22:04 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated the various ring->signal() implementations to take a request instead of
> a ring. This removes their reliance on the OLR to obtain the seqno value that
> should be used for the signal.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_ringbuffer.c | 20 ++++++++++----------
> drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
> 2 files changed, 11 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 767bab1..440356d 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -1105,10 +1105,11 @@ static void render_ring_cleanup(struct intel_engine_cs *ring)
> intel_fini_pipe_control(ring);
> }
>
> -static int gen8_rcs_signal(struct intel_engine_cs *signaller,
> +static int gen8_rcs_signal(struct drm_i915_gem_request *signaller_req,
> unsigned int num_dwords)
> {
> #define MBOX_UPDATE_DWORDS 8
> + struct intel_engine_cs *signaller = signaller_req->ring;
> struct drm_device *dev = signaller->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> struct intel_engine_cs *waiter;
> @@ -1128,8 +1129,7 @@ static int gen8_rcs_signal(struct intel_engine_cs *signaller,
> if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
> continue;
>
> - seqno = i915_gem_request_get_seqno(
> - signaller->outstanding_lazy_request);
> + seqno = i915_gem_request_get_seqno(signaller_req);
> intel_ring_emit(signaller, GFX_OP_PIPE_CONTROL(6));
> intel_ring_emit(signaller, PIPE_CONTROL_GLOBAL_GTT_IVB |
> PIPE_CONTROL_QW_WRITE |
> @@ -1146,10 +1146,11 @@ static int gen8_rcs_signal(struct intel_engine_cs *signaller,
> return 0;
> }
>
> -static int gen8_xcs_signal(struct intel_engine_cs *signaller,
> +static int gen8_xcs_signal(struct drm_i915_gem_request *signaller_req,
> unsigned int num_dwords)
> {
> #define MBOX_UPDATE_DWORDS 6
> + struct intel_engine_cs *signaller = signaller_req->ring;
> struct drm_device *dev = signaller->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> struct intel_engine_cs *waiter;
> @@ -1169,8 +1170,7 @@ static int gen8_xcs_signal(struct intel_engine_cs *signaller,
> if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
> continue;
>
> - seqno = i915_gem_request_get_seqno(
> - signaller->outstanding_lazy_request);
> + seqno = i915_gem_request_get_seqno(signaller_req);
> intel_ring_emit(signaller, (MI_FLUSH_DW + 1) |
> MI_FLUSH_DW_OP_STOREDW);
> intel_ring_emit(signaller, lower_32_bits(gtt_offset) |
> @@ -1185,9 +1185,10 @@ static int gen8_xcs_signal(struct intel_engine_cs *signaller,
> return 0;
> }
>
> -static int gen6_signal(struct intel_engine_cs *signaller,
> +static int gen6_signal(struct drm_i915_gem_request *signaller_req,
> unsigned int num_dwords)
> {
> + struct intel_engine_cs *signaller = signaller_req->ring;
> struct drm_device *dev = signaller->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> struct intel_engine_cs *useless;
> @@ -1205,8 +1206,7 @@ static int gen6_signal(struct intel_engine_cs *signaller,
> for_each_ring(useless, dev_priv, i) {
> u32 mbox_reg = signaller->semaphore.mbox.signal[i];
> if (mbox_reg != GEN6_NOSYNC) {
> - u32 seqno = i915_gem_request_get_seqno(
> - signaller->outstanding_lazy_request);
> + u32 seqno = i915_gem_request_get_seqno(signaller_req);
> intel_ring_emit(signaller, MI_LOAD_REGISTER_IMM(1));
> intel_ring_emit(signaller, mbox_reg);
> intel_ring_emit(signaller, seqno);
> @@ -1235,7 +1235,7 @@ gen6_add_request(struct drm_i915_gem_request *req)
> int ret;
>
> if (ring->semaphore.signal)
> - ret = ring->semaphore.signal(ring, 4);
> + ret = ring->semaphore.signal(req, 4);
> else
> ret = intel_ring_begin(ring, 4);
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 65fe151..7c1e0f5 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -222,7 +222,7 @@ struct intel_engine_cs {
> int (*sync_to)(struct drm_i915_gem_request *to_req,
> struct intel_engine_cs *from,
> u32 seqno);
> - int (*signal)(struct intel_engine_cs *signaller,
> + int (*signal)(struct drm_i915_gem_request *signaller_req,
> /* num_dwords needed by caller */
> unsigned int num_dwords);
> } semaphore;
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 46/53] drm/i915: Update cacheline_align() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (44 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 45/53] drm/i915: Update ring->signal() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-03-09 22:16 ` Tomas Elf
2015-02-19 17:17 ` [PATCH 47/53] drm/i915: Update ironlake_enable_rc6() to do explicit request management John.C.Harrison
` (8 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated intel_ring_cacheline_align() to take a request instead of a ring.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_display.c | 2 +-
drivers/gpu/drm/i915/intel_ringbuffer.c | 3 ++-
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
3 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 9cbfb93..7962946 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9438,7 +9438,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
* then do the cacheline alignment, and finally emit the
* MI_DISPLAY_FLIP.
*/
- ret = intel_ring_cacheline_align(ring);
+ ret = intel_ring_cacheline_align(req);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 440356d..109f283 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2258,8 +2258,9 @@ int intel_ring_begin(struct intel_engine_cs *ring,
}
/* Align the ring tail to a cacheline boundary */
-int intel_ring_cacheline_align(struct intel_engine_cs *ring)
+int intel_ring_cacheline_align(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int num_dwords = (ring->buffer->tail & (CACHELINE_BYTES - 1)) / sizeof(uint32_t);
int ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 7c1e0f5..80eb399 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -387,7 +387,7 @@ void intel_stop_ring_buffer(struct intel_engine_cs *ring);
void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
-int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
+int __must_check intel_ring_cacheline_align(struct drm_i915_gem_request *req);
int __must_check intel_ring_alloc_request(struct intel_engine_cs *ring,
struct intel_context *ctx,
struct drm_i915_gem_request **req_out);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 46/53] drm/i915: Update cacheline_align() to take a request structure
2015-02-19 17:17 ` [PATCH 46/53] drm/i915: Update cacheline_align() " John.C.Harrison
@ 2015-03-09 22:16 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 22:16 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:17, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Updated intel_ring_cacheline_align() to take a request instead of a ring.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_display.c | 2 +-
> drivers/gpu/drm/i915/intel_ringbuffer.c | 3 ++-
> drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
> 3 files changed, 4 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> index 9cbfb93..7962946 100644
> --- a/drivers/gpu/drm/i915/intel_display.c
> +++ b/drivers/gpu/drm/i915/intel_display.c
> @@ -9438,7 +9438,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
> * then do the cacheline alignment, and finally emit the
> * MI_DISPLAY_FLIP.
> */
> - ret = intel_ring_cacheline_align(ring);
> + ret = intel_ring_cacheline_align(req);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 440356d..109f283 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -2258,8 +2258,9 @@ int intel_ring_begin(struct intel_engine_cs *ring,
> }
>
> /* Align the ring tail to a cacheline boundary */
> -int intel_ring_cacheline_align(struct intel_engine_cs *ring)
> +int intel_ring_cacheline_align(struct drm_i915_gem_request *req)
> {
> + struct intel_engine_cs *ring = req->ring;
> int num_dwords = (ring->buffer->tail & (CACHELINE_BYTES - 1)) / sizeof(uint32_t);
> int ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 7c1e0f5..80eb399 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -387,7 +387,7 @@ void intel_stop_ring_buffer(struct intel_engine_cs *ring);
> void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
>
> int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
> -int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
> +int __must_check intel_ring_cacheline_align(struct drm_i915_gem_request *req);
> int __must_check intel_ring_alloc_request(struct intel_engine_cs *ring,
> struct intel_context *ctx,
> struct drm_i915_gem_request **req_out);
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 47/53] drm/i915: Update ironlake_enable_rc6() to do explicit request management
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (45 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 46/53] drm/i915: Update cacheline_align() " John.C.Harrison
@ 2015-02-19 17:17 ` John.C.Harrison
2015-02-19 17:18 ` [PATCH 48/53] drm/i915: Update intel_ring_begin() to take a request structure John.C.Harrison
` (7 subsequent siblings)
54 siblings, 0 replies; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:17 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Updated ironlake_enable_rc6() to do explicit request creation and submission.
v2: Fixed null context bug.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_pm.c | 31 +++++++++++++++++++++----------
1 file changed, 21 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index f7c9938..6594a52 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4985,6 +4985,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *ring = &dev_priv->ring[RCS];
+ struct drm_i915_gem_request *req = NULL;
bool was_interruptible;
int ret;
@@ -5003,16 +5004,17 @@ static void ironlake_enable_rc6(struct drm_device *dev)
was_interruptible = dev_priv->mm.interruptible;
dev_priv->mm.interruptible = false;
+ ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
+ if (ret)
+ goto err;
+
/*
* GPU can automatically power down the render unit if given a page
* to save state.
*/
ret = intel_ring_begin(ring, 6);
- if (ret) {
- ironlake_teardown_rc6(dev);
- dev_priv->mm.interruptible = was_interruptible;
- return;
- }
+ if (ret)
+ goto err;
intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
intel_ring_emit(ring, MI_SET_CONTEXT);
@@ -5026,6 +5028,11 @@ static void ironlake_enable_rc6(struct drm_device *dev)
intel_ring_emit(ring, MI_FLUSH);
intel_ring_advance(ring);
+ ret = i915_add_request_no_flush(req);
+ if (ret)
+ goto err;
+ req = NULL;
+
/*
* Wait for the command parser to advance past MI_SET_CONTEXT. The HW
* does an implicit flush, combined with MI_FLUSH above, it should be
@@ -5033,16 +5040,20 @@ static void ironlake_enable_rc6(struct drm_device *dev)
*/
ret = intel_ring_idle(ring);
dev_priv->mm.interruptible = was_interruptible;
- if (ret) {
- DRM_ERROR("failed to enable ironlake power savings\n");
- ironlake_teardown_rc6(dev);
- return;
- }
+ if (ret)
+ goto err;
I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN);
I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
intel_print_rc6_info(dev, GEN6_RC_CTL_RC6_ENABLE);
+
+err:
+ DRM_ERROR("failed to enable ironlake power savings\n");
+ ironlake_teardown_rc6(dev);
+ dev_priv->mm.interruptible = was_interruptible;
+ if (req)
+ i915_gem_request_unreference(req);
}
static unsigned long intel_pxfreq(u32 vidfreq)
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* [PATCH 48/53] drm/i915: Update intel_ring_begin() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (46 preceding siblings ...)
2015-02-19 17:17 ` [PATCH 47/53] drm/i915: Update ironlake_enable_rc6() to do explicit request management John.C.Harrison
@ 2015-02-19 17:18 ` John.C.Harrison
2015-03-09 22:39 ` Tomas Elf
2015-02-19 17:18 ` [PATCH 49/53] drm/i915: Make intel_logical_ring_begin() static John.C.Harrison
` (6 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:18 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Now that everything above has been converted to use requests, intel_ring_begin()
can be updated to take a request instead of a ring. This also means that it no
longer needs to lazily allocate a request if no-one happens to have done it
earlier.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 2 +-
drivers/gpu/drm/i915/i915_gem_context.c | 2 +-
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 8 ++--
drivers/gpu/drm/i915/i915_gem_gtt.c | 6 +--
drivers/gpu/drm/i915/intel_display.c | 10 ++--
drivers/gpu/drm/i915/intel_overlay.c | 8 ++--
drivers/gpu/drm/i915/intel_pm.c | 2 +-
drivers/gpu/drm/i915/intel_ringbuffer.c | 72 +++++++++++++---------------
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
9 files changed, 54 insertions(+), 58 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b5613ff..60f6671 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4656,7 +4656,7 @@ int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
if (!HAS_L3_DPF(dev) || !remap_info)
return 0;
- ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
+ ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 384f481..e348424 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -503,7 +503,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
if (INTEL_INFO(ring->dev)->gen >= 7)
len += 2 + (num_rings ? 4*num_rings + 2 : 0);
- ret = intel_ring_begin(ring, len);
+ ret = intel_ring_begin(req, len);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 8b4f8a9..6a703e6 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1013,7 +1013,7 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
return -EINVAL;
}
- ret = intel_ring_begin(ring, 4 * 3);
+ ret = intel_ring_begin(req, 4 * 3);
if (ret)
return ret;
@@ -1044,7 +1044,7 @@ i915_emit_box(struct drm_i915_gem_request *req,
}
if (INTEL_INFO(ring->dev)->gen >= 4) {
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -1053,7 +1053,7 @@ i915_emit_box(struct drm_i915_gem_request *req,
intel_ring_emit(ring, ((box->x2 - 1) & 0xffff) | (box->y2 - 1) << 16);
intel_ring_emit(ring, DR4);
} else {
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
@@ -1235,7 +1235,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
if (ring == &dev_priv->ring[RCS] &&
instp_mode != dev_priv->relative_constants_mode) {
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(params->request, 4);
if (ret)
goto error;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index a1af644..0445278 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -288,7 +288,7 @@ static int gen8_write_pdp(struct drm_i915_gem_request *req, unsigned entry,
BUG_ON(entry >= 4);
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
@@ -788,7 +788,7 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
if (ret)
return ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
@@ -825,7 +825,7 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
if (ret)
return ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 7962946..6901e9a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9259,7 +9259,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
u32 flip_mask;
int ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
@@ -9294,7 +9294,7 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
u32 flip_mask;
int ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
@@ -9327,7 +9327,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
uint32_t pf, pipesrc;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -9366,7 +9366,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
uint32_t pf, pipesrc;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -9442,7 +9442,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
if (ret)
return ret;
- ret = intel_ring_begin(ring, len);
+ ret = intel_ring_begin(req, len);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 228c9d1..1fb7653 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -251,7 +251,7 @@ static int intel_overlay_on(struct intel_overlay *overlay)
if (ret)
return ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret) {
i915_gem_request_unreference(req);
return ret;
@@ -292,7 +292,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
if (ret)
return ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret) {
i915_gem_request_unreference(req);
return ret;
@@ -359,7 +359,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
if (ret)
return ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret) {
i915_gem_request_unreference(req);
return ret;
@@ -434,7 +434,7 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
if (ret)
return ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret) {
i915_gem_request_unreference(req);
return ret;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 6594a52..cc22536 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5012,7 +5012,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
* GPU can automatically power down the render unit if given a page
* to save state.
*/
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
goto err;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 109f283..5eef02e 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -106,7 +106,7 @@ gen2_render_ring_flush(struct drm_i915_gem_request *req,
if (invalidate_domains & I915_GEM_DOMAIN_SAMPLER)
cmd |= MI_READ_FLUSH;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
@@ -165,7 +165,7 @@ gen4_render_ring_flush(struct drm_i915_gem_request *req,
(IS_G4X(dev) || IS_GEN5(dev)))
cmd |= MI_INVALIDATE_ISP;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
@@ -220,8 +220,7 @@ intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
int ret;
-
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
@@ -234,7 +233,7 @@ intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
intel_ring_emit(ring, MI_NOOP);
intel_ring_advance(ring);
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
@@ -289,7 +288,7 @@ gen6_render_ring_flush(struct drm_i915_gem_request *req,
flags |= PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL;
}
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -308,7 +307,7 @@ gen7_render_ring_cs_stall_wa(struct drm_i915_gem_request *req)
struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -330,7 +329,7 @@ static int gen7_ring_fbc_flush(struct drm_i915_gem_request *req, u32 value)
if (!ring->fbc_dirty)
return 0;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
/* WaFbcNukeOn3DBlt:ivb/hsw */
@@ -395,7 +394,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req,
gen7_render_ring_cs_stall_wa(req);
}
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -418,7 +417,7 @@ gen8_emit_pipe_control(struct drm_i915_gem_request *req,
struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
@@ -760,7 +759,7 @@ static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
if (ret)
return ret;
- ret = intel_ring_begin(ring, (w->count * 2 + 2));
+ ret = intel_ring_begin(req, (w->count * 2 + 2));
if (ret)
return ret;
@@ -1119,7 +1118,7 @@ static int gen8_rcs_signal(struct drm_i915_gem_request *signaller_req,
num_dwords += (num_rings-1) * MBOX_UPDATE_DWORDS;
#undef MBOX_UPDATE_DWORDS
- ret = intel_ring_begin(signaller, num_dwords);
+ ret = intel_ring_begin(signaller_req, num_dwords);
if (ret)
return ret;
@@ -1160,7 +1159,7 @@ static int gen8_xcs_signal(struct drm_i915_gem_request *signaller_req,
num_dwords += (num_rings-1) * MBOX_UPDATE_DWORDS;
#undef MBOX_UPDATE_DWORDS
- ret = intel_ring_begin(signaller, num_dwords);
+ ret = intel_ring_begin(signaller_req, num_dwords);
if (ret)
return ret;
@@ -1199,7 +1198,7 @@ static int gen6_signal(struct drm_i915_gem_request *signaller_req,
num_dwords += round_up((num_rings-1) * MBOX_UPDATE_DWORDS, 2);
#undef MBOX_UPDATE_DWORDS
- ret = intel_ring_begin(signaller, num_dwords);
+ ret = intel_ring_begin(signaller_req, num_dwords);
if (ret)
return ret;
@@ -1237,7 +1236,7 @@ gen6_add_request(struct drm_i915_gem_request *req)
if (ring->semaphore.signal)
ret = ring->semaphore.signal(req, 4);
else
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -1275,7 +1274,7 @@ gen8_ring_sync(struct drm_i915_gem_request *waiter_req,
struct drm_i915_private *dev_priv = waiter->dev->dev_private;
int ret;
- ret = intel_ring_begin(waiter, 4);
+ ret = intel_ring_begin(waiter_req, 4);
if (ret)
return ret;
@@ -1312,7 +1311,7 @@ gen6_ring_sync(struct drm_i915_gem_request *waiter_req,
WARN_ON(wait_mbox == MI_SEMAPHORE_SYNC_INVALID);
- ret = intel_ring_begin(waiter, 4);
+ ret = intel_ring_begin(waiter_req, 4);
if (ret)
return ret;
@@ -1357,7 +1356,7 @@ pc_render_add_request(struct drm_i915_gem_request *req)
* incoherence by flushing the 6 PIPE_NOTIFY buffers out to
* memory before requesting an interrupt.
*/
- ret = intel_ring_begin(ring, 32);
+ ret = intel_ring_begin(req, 32);
if (ret)
return ret;
@@ -1542,7 +1541,7 @@ bsd_ring_flush(struct drm_i915_gem_request *req,
struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
@@ -1558,7 +1557,7 @@ i9xx_add_request(struct drm_i915_gem_request *req)
struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -1703,7 +1702,7 @@ i965_dispatch_execbuffer(struct drm_i915_gem_request *req,
struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
@@ -1731,7 +1730,7 @@ i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
u32 cs_offset = ring->scratch.gtt_offset;
int ret;
- ret = intel_ring_begin(ring, 6);
+ ret = intel_ring_begin(req, 6);
if (ret)
return ret;
@@ -1748,7 +1747,7 @@ i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
if (len > I830_BATCH_LIMIT)
return -ENOSPC;
- ret = intel_ring_begin(ring, 6 + 2);
+ ret = intel_ring_begin(req, 6 + 2);
if (ret)
return ret;
@@ -1771,7 +1770,7 @@ i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
offset = cs_offset;
}
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -1793,7 +1792,7 @@ i915_dispatch_execbuffer(struct drm_i915_gem_request *req,
struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
@@ -2232,13 +2231,15 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring,
return 0;
}
-int intel_ring_begin(struct intel_engine_cs *ring,
+int intel_ring_begin(struct drm_i915_gem_request *req,
int num_dwords)
{
- struct drm_i915_gem_request *req;
+ struct intel_engine_cs *ring = req->ring;
struct drm_i915_private *dev_priv = ring->dev->dev_private;
int ret;
+ WARN_ON(req == NULL);
+
ret = i915_gem_check_wedge(&dev_priv->gpu_error,
dev_priv->mm.interruptible);
if (ret)
@@ -2248,11 +2249,6 @@ int intel_ring_begin(struct intel_engine_cs *ring,
if (ret)
return ret;
- /* Preallocate the olr before touching the ring */
- ret = intel_ring_alloc_request(ring, NULL, &req);
- if (ret)
- return ret;
-
ring->buffer->space -= num_dwords * sizeof(uint32_t);
return 0;
}
@@ -2268,7 +2264,7 @@ int intel_ring_cacheline_align(struct drm_i915_gem_request *req)
return 0;
num_dwords = CACHELINE_BYTES / sizeof(uint32_t) - num_dwords;
- ret = intel_ring_begin(ring, num_dwords);
+ ret = intel_ring_begin(req, num_dwords);
if (ret)
return ret;
@@ -2338,7 +2334,7 @@ static int gen6_bsd_ring_flush(struct drm_i915_gem_request *req,
uint32_t cmd;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -2385,7 +2381,7 @@ gen8_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
!(dispatch_flags & I915_DISPATCH_SECURE);
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
@@ -2407,7 +2403,7 @@ hsw_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
@@ -2430,7 +2426,7 @@ gen6_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
struct intel_engine_cs *ring = req->ring;
int ret;
- ret = intel_ring_begin(ring, 2);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
@@ -2456,7 +2452,7 @@ static int gen6_ring_flush(struct drm_i915_gem_request *req,
uint32_t cmd;
int ret;
- ret = intel_ring_begin(ring, 4);
+ ret = intel_ring_begin(req, 4);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 80eb399..e83fbbb 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -386,7 +386,7 @@ int intel_alloc_ringbuffer_obj(struct drm_device *dev,
void intel_stop_ring_buffer(struct intel_engine_cs *ring);
void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
-int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
+int __must_check intel_ring_begin(struct drm_i915_gem_request *req, int n);
int __must_check intel_ring_cacheline_align(struct drm_i915_gem_request *req);
int __must_check intel_ring_alloc_request(struct intel_engine_cs *ring,
struct intel_context *ctx,
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 48/53] drm/i915: Update intel_ring_begin() to take a request structure
2015-02-19 17:18 ` [PATCH 48/53] drm/i915: Update intel_ring_begin() to take a request structure John.C.Harrison
@ 2015-03-09 22:39 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 22:39 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:18, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Now that everything above has been converted to use requests, intel_ring_begin()
> can be updated to take a request instead of a ring. This also means that it no
> longer needs to lazily allocate a request if no-one happens to have done it
> earlier.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 2 +-
> drivers/gpu/drm/i915/i915_gem_context.c | 2 +-
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 8 ++--
> drivers/gpu/drm/i915/i915_gem_gtt.c | 6 +--
> drivers/gpu/drm/i915/intel_display.c | 10 ++--
> drivers/gpu/drm/i915/intel_overlay.c | 8 ++--
> drivers/gpu/drm/i915/intel_pm.c | 2 +-
> drivers/gpu/drm/i915/intel_ringbuffer.c | 72 +++++++++++++---------------
> drivers/gpu/drm/i915/intel_ringbuffer.h | 2 +-
> 9 files changed, 54 insertions(+), 58 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index b5613ff..60f6671 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -4656,7 +4656,7 @@ int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
> if (!HAS_L3_DPF(dev) || !remap_info)
> return 0;
>
> - ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
> + ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index 384f481..e348424 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -503,7 +503,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
> if (INTEL_INFO(ring->dev)->gen >= 7)
> len += 2 + (num_rings ? 4*num_rings + 2 : 0);
>
> - ret = intel_ring_begin(ring, len);
> + ret = intel_ring_begin(req, len);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 8b4f8a9..6a703e6 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1013,7 +1013,7 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
> return -EINVAL;
> }
>
> - ret = intel_ring_begin(ring, 4 * 3);
> + ret = intel_ring_begin(req, 4 * 3);
> if (ret)
> return ret;
>
> @@ -1044,7 +1044,7 @@ i915_emit_box(struct drm_i915_gem_request *req,
> }
>
> if (INTEL_INFO(ring->dev)->gen >= 4) {
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret)
> return ret;
>
> @@ -1053,7 +1053,7 @@ i915_emit_box(struct drm_i915_gem_request *req,
> intel_ring_emit(ring, ((box->x2 - 1) & 0xffff) | (box->y2 - 1) << 16);
> intel_ring_emit(ring, DR4);
> } else {
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> return ret;
>
> @@ -1235,7 +1235,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
>
> if (ring == &dev_priv->ring[RCS] &&
> instp_mode != dev_priv->relative_constants_mode) {
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(params->request, 4);
> if (ret)
> goto error;
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index a1af644..0445278 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -288,7 +288,7 @@ static int gen8_write_pdp(struct drm_i915_gem_request *req, unsigned entry,
>
> BUG_ON(entry >= 4);
>
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> return ret;
>
> @@ -788,7 +788,7 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
> if (ret)
> return ret;
>
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> return ret;
>
> @@ -825,7 +825,7 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
> if (ret)
> return ret;
>
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> index 7962946..6901e9a 100644
> --- a/drivers/gpu/drm/i915/intel_display.c
> +++ b/drivers/gpu/drm/i915/intel_display.c
> @@ -9259,7 +9259,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
> u32 flip_mask;
> int ret;
>
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> return ret;
>
> @@ -9294,7 +9294,7 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
> u32 flip_mask;
> int ret;
>
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> return ret;
>
> @@ -9327,7 +9327,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
> uint32_t pf, pipesrc;
> int ret;
>
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret)
> return ret;
>
> @@ -9366,7 +9366,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
> uint32_t pf, pipesrc;
> int ret;
>
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret)
> return ret;
>
> @@ -9442,7 +9442,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
> if (ret)
> return ret;
>
> - ret = intel_ring_begin(ring, len);
> + ret = intel_ring_begin(req, len);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
> index 228c9d1..1fb7653 100644
> --- a/drivers/gpu/drm/i915/intel_overlay.c
> +++ b/drivers/gpu/drm/i915/intel_overlay.c
> @@ -251,7 +251,7 @@ static int intel_overlay_on(struct intel_overlay *overlay)
> if (ret)
> return ret;
>
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret) {
> i915_gem_request_unreference(req);
> return ret;
> @@ -292,7 +292,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
> if (ret)
> return ret;
>
> - ret = intel_ring_begin(ring, 2);
> + ret = intel_ring_begin(req, 2);
> if (ret) {
> i915_gem_request_unreference(req);
> return ret;
> @@ -359,7 +359,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
> if (ret)
> return ret;
>
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret) {
> i915_gem_request_unreference(req);
> return ret;
> @@ -434,7 +434,7 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
> if (ret)
> return ret;
>
> - ret = intel_ring_begin(ring, 2);
> + ret = intel_ring_begin(req, 2);
> if (ret) {
> i915_gem_request_unreference(req);
> return ret;
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index 6594a52..cc22536 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -5012,7 +5012,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
> * GPU can automatically power down the render unit if given a page
> * to save state.
> */
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> goto err;
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 109f283..5eef02e 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -106,7 +106,7 @@ gen2_render_ring_flush(struct drm_i915_gem_request *req,
> if (invalidate_domains & I915_GEM_DOMAIN_SAMPLER)
> cmd |= MI_READ_FLUSH;
>
> - ret = intel_ring_begin(ring, 2);
> + ret = intel_ring_begin(req, 2);
> if (ret)
> return ret;
>
> @@ -165,7 +165,7 @@ gen4_render_ring_flush(struct drm_i915_gem_request *req,
> (IS_G4X(dev) || IS_GEN5(dev)))
> cmd |= MI_INVALIDATE_ISP;
>
> - ret = intel_ring_begin(ring, 2);
> + ret = intel_ring_begin(req, 2);
> if (ret)
> return ret;
>
> @@ -220,8 +220,7 @@ intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
> u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
> int ret;
>
> -
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> return ret;
>
> @@ -234,7 +233,7 @@ intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
> intel_ring_emit(ring, MI_NOOP);
> intel_ring_advance(ring);
>
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> return ret;
>
> @@ -289,7 +288,7 @@ gen6_render_ring_flush(struct drm_i915_gem_request *req,
> flags |= PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL;
> }
>
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret)
> return ret;
>
> @@ -308,7 +307,7 @@ gen7_render_ring_cs_stall_wa(struct drm_i915_gem_request *req)
> struct intel_engine_cs *ring = req->ring;
> int ret;
>
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret)
> return ret;
>
> @@ -330,7 +329,7 @@ static int gen7_ring_fbc_flush(struct drm_i915_gem_request *req, u32 value)
> if (!ring->fbc_dirty)
> return 0;
>
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> return ret;
> /* WaFbcNukeOn3DBlt:ivb/hsw */
> @@ -395,7 +394,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req,
> gen7_render_ring_cs_stall_wa(req);
> }
>
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret)
> return ret;
>
> @@ -418,7 +417,7 @@ gen8_emit_pipe_control(struct drm_i915_gem_request *req,
> struct intel_engine_cs *ring = req->ring;
> int ret;
>
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> return ret;
>
> @@ -760,7 +759,7 @@ static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
> if (ret)
> return ret;
>
> - ret = intel_ring_begin(ring, (w->count * 2 + 2));
> + ret = intel_ring_begin(req, (w->count * 2 + 2));
> if (ret)
> return ret;
>
> @@ -1119,7 +1118,7 @@ static int gen8_rcs_signal(struct drm_i915_gem_request *signaller_req,
> num_dwords += (num_rings-1) * MBOX_UPDATE_DWORDS;
> #undef MBOX_UPDATE_DWORDS
>
> - ret = intel_ring_begin(signaller, num_dwords);
> + ret = intel_ring_begin(signaller_req, num_dwords);
> if (ret)
> return ret;
>
> @@ -1160,7 +1159,7 @@ static int gen8_xcs_signal(struct drm_i915_gem_request *signaller_req,
> num_dwords += (num_rings-1) * MBOX_UPDATE_DWORDS;
> #undef MBOX_UPDATE_DWORDS
>
> - ret = intel_ring_begin(signaller, num_dwords);
> + ret = intel_ring_begin(signaller_req, num_dwords);
> if (ret)
> return ret;
>
> @@ -1199,7 +1198,7 @@ static int gen6_signal(struct drm_i915_gem_request *signaller_req,
> num_dwords += round_up((num_rings-1) * MBOX_UPDATE_DWORDS, 2);
> #undef MBOX_UPDATE_DWORDS
>
> - ret = intel_ring_begin(signaller, num_dwords);
> + ret = intel_ring_begin(signaller_req, num_dwords);
> if (ret)
> return ret;
>
> @@ -1237,7 +1236,7 @@ gen6_add_request(struct drm_i915_gem_request *req)
> if (ring->semaphore.signal)
> ret = ring->semaphore.signal(req, 4);
> else
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
>
> if (ret)
> return ret;
> @@ -1275,7 +1274,7 @@ gen8_ring_sync(struct drm_i915_gem_request *waiter_req,
> struct drm_i915_private *dev_priv = waiter->dev->dev_private;
> int ret;
>
> - ret = intel_ring_begin(waiter, 4);
> + ret = intel_ring_begin(waiter_req, 4);
> if (ret)
> return ret;
>
> @@ -1312,7 +1311,7 @@ gen6_ring_sync(struct drm_i915_gem_request *waiter_req,
>
> WARN_ON(wait_mbox == MI_SEMAPHORE_SYNC_INVALID);
>
> - ret = intel_ring_begin(waiter, 4);
> + ret = intel_ring_begin(waiter_req, 4);
> if (ret)
> return ret;
>
> @@ -1357,7 +1356,7 @@ pc_render_add_request(struct drm_i915_gem_request *req)
> * incoherence by flushing the 6 PIPE_NOTIFY buffers out to
> * memory before requesting an interrupt.
> */
> - ret = intel_ring_begin(ring, 32);
> + ret = intel_ring_begin(req, 32);
> if (ret)
> return ret;
>
> @@ -1542,7 +1541,7 @@ bsd_ring_flush(struct drm_i915_gem_request *req,
> struct intel_engine_cs *ring = req->ring;
> int ret;
>
> - ret = intel_ring_begin(ring, 2);
> + ret = intel_ring_begin(req, 2);
> if (ret)
> return ret;
>
> @@ -1558,7 +1557,7 @@ i9xx_add_request(struct drm_i915_gem_request *req)
> struct intel_engine_cs *ring = req->ring;
> int ret;
>
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret)
> return ret;
>
> @@ -1703,7 +1702,7 @@ i965_dispatch_execbuffer(struct drm_i915_gem_request *req,
> struct intel_engine_cs *ring = req->ring;
> int ret;
>
> - ret = intel_ring_begin(ring, 2);
> + ret = intel_ring_begin(req, 2);
> if (ret)
> return ret;
>
> @@ -1731,7 +1730,7 @@ i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
> u32 cs_offset = ring->scratch.gtt_offset;
> int ret;
>
> - ret = intel_ring_begin(ring, 6);
> + ret = intel_ring_begin(req, 6);
> if (ret)
> return ret;
>
> @@ -1748,7 +1747,7 @@ i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
> if (len > I830_BATCH_LIMIT)
> return -ENOSPC;
>
> - ret = intel_ring_begin(ring, 6 + 2);
> + ret = intel_ring_begin(req, 6 + 2);
> if (ret)
> return ret;
>
> @@ -1771,7 +1770,7 @@ i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
> offset = cs_offset;
> }
>
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret)
> return ret;
>
> @@ -1793,7 +1792,7 @@ i915_dispatch_execbuffer(struct drm_i915_gem_request *req,
> struct intel_engine_cs *ring = req->ring;
> int ret;
>
> - ret = intel_ring_begin(ring, 2);
> + ret = intel_ring_begin(req, 2);
> if (ret)
> return ret;
>
> @@ -2232,13 +2231,15 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring,
> return 0;
> }
>
> -int intel_ring_begin(struct intel_engine_cs *ring,
> +int intel_ring_begin(struct drm_i915_gem_request *req,
> int num_dwords)
> {
> - struct drm_i915_gem_request *req;
> + struct intel_engine_cs *ring = req->ring;
The WARN_ON below will only fire _after_ we've already gotten a null
pointer exception here at the req->ring dereference. You might want to
rearrange this a bit so that the WARN_ON appears before the dereference.
Thanks,
Tomas
> struct drm_i915_private *dev_priv = ring->dev->dev_private;
> int ret;
>
> + WARN_ON(req == NULL);
> +
> ret = i915_gem_check_wedge(&dev_priv->gpu_error,
> dev_priv->mm.interruptible);
> if (ret)
> @@ -2248,11 +2249,6 @@ int intel_ring_begin(struct intel_engine_cs *ring,
> if (ret)
> return ret;
>
> - /* Preallocate the olr before touching the ring */
> - ret = intel_ring_alloc_request(ring, NULL, &req);
> - if (ret)
> - return ret;
> -
> ring->buffer->space -= num_dwords * sizeof(uint32_t);
> return 0;
> }
> @@ -2268,7 +2264,7 @@ int intel_ring_cacheline_align(struct drm_i915_gem_request *req)
> return 0;
>
> num_dwords = CACHELINE_BYTES / sizeof(uint32_t) - num_dwords;
> - ret = intel_ring_begin(ring, num_dwords);
> + ret = intel_ring_begin(req, num_dwords);
> if (ret)
> return ret;
>
> @@ -2338,7 +2334,7 @@ static int gen6_bsd_ring_flush(struct drm_i915_gem_request *req,
> uint32_t cmd;
> int ret;
>
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret)
> return ret;
>
> @@ -2385,7 +2381,7 @@ gen8_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
> !(dispatch_flags & I915_DISPATCH_SECURE);
> int ret;
>
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret)
> return ret;
>
> @@ -2407,7 +2403,7 @@ hsw_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
> struct intel_engine_cs *ring = req->ring;
> int ret;
>
> - ret = intel_ring_begin(ring, 2);
> + ret = intel_ring_begin(req, 2);
> if (ret)
> return ret;
>
> @@ -2430,7 +2426,7 @@ gen6_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
> struct intel_engine_cs *ring = req->ring;
> int ret;
>
> - ret = intel_ring_begin(ring, 2);
> + ret = intel_ring_begin(req, 2);
> if (ret)
> return ret;
>
> @@ -2456,7 +2452,7 @@ static int gen6_ring_flush(struct drm_i915_gem_request *req,
> uint32_t cmd;
> int ret;
>
> - ret = intel_ring_begin(ring, 4);
> + ret = intel_ring_begin(req, 4);
> if (ret)
> return ret;
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 80eb399..e83fbbb 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -386,7 +386,7 @@ int intel_alloc_ringbuffer_obj(struct drm_device *dev,
> void intel_stop_ring_buffer(struct intel_engine_cs *ring);
> void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
>
> -int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
> +int __must_check intel_ring_begin(struct drm_i915_gem_request *req, int n);
> int __must_check intel_ring_cacheline_align(struct drm_i915_gem_request *req);
> int __must_check intel_ring_alloc_request(struct intel_engine_cs *ring,
> struct intel_context *ctx,
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 49/53] drm/i915: Make intel_logical_ring_begin() static
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (47 preceding siblings ...)
2015-02-19 17:18 ` [PATCH 48/53] drm/i915: Update intel_ring_begin() to take a request structure John.C.Harrison
@ 2015-02-19 17:18 ` John.C.Harrison
2015-03-09 23:24 ` Tomas Elf
2015-02-19 17:18 ` [PATCH 50/53] drm/i915: Update intel_logical_ring_begin() to take a request structure John.C.Harrison
` (5 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:18 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The only usage of intel_logical_ring_begin() is within intel_lrc.c so it can be
made static. To avoid a forward declaration at the top of the file, it and bunch
of other functions have been shuffled upwards.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_lrc.c | 394 +++++++++++++++++++-------------------
drivers/gpu/drm/i915/intel_lrc.h | 3 -
2 files changed, 197 insertions(+), 200 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 5212b54..b40501d 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -606,6 +606,203 @@ static int execlists_move_to_gpu(struct drm_i915_gem_request *req,
return logical_ring_invalidate_all_caches(req);
}
+static int logical_ring_wait_request(struct intel_ringbuffer *ringbuf,
+ int bytes)
+{
+ struct intel_engine_cs *ring = ringbuf->ring;
+ struct drm_i915_gem_request *request;
+ int ret;
+
+ if (intel_ring_space(ringbuf) >= bytes)
+ return 0;
+
+ list_for_each_entry(request, &ring->request_list, list) {
+ /*
+ * The request queue is per-engine, so can contain requests
+ * from multiple ringbuffers. Here, we must ignore any that
+ * aren't from the ringbuffer we're considering.
+ */
+ struct intel_context *ctx = request->ctx;
+ if (ctx->engine[ring->id].ringbuf != ringbuf)
+ continue;
+
+ /* Would completion of this request free enough space? */
+ if (__intel_ring_space(request->tail, ringbuf->tail,
+ ringbuf->size) >= bytes) {
+ break;
+ }
+ }
+
+ if (&request->list == &ring->request_list)
+ return -ENOSPC;
+
+ ret = i915_wait_request(request);
+ if (ret)
+ return ret;
+
+ i915_gem_retire_requests_ring(ring);
+
+ return intel_ring_space(ringbuf) >= bytes ? 0 : -ENOSPC;
+}
+
+/*
+ * intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
+ * @ringbuf: Logical Ringbuffer to advance.
+ *
+ * The tail is updated in our logical ringbuffer struct, not in the actual context. What
+ * really happens during submission is that the context and current tail will be placed
+ * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
+ * point, the tail *inside* the context is updated and the ELSP written to.
+ */
+static void
+intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
+ struct intel_context *ctx,
+ struct drm_i915_gem_request *request)
+{
+ struct intel_engine_cs *ring = ringbuf->ring;
+
+ intel_logical_ring_advance(ringbuf);
+
+ if (intel_ring_stopped(ring))
+ return;
+
+ execlists_context_queue(ring, ctx, ringbuf->tail, request);
+}
+
+static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
+ struct intel_context *ctx,
+ int bytes)
+{
+ struct intel_engine_cs *ring = ringbuf->ring;
+ struct drm_device *dev = ring->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ unsigned long end;
+ int ret;
+
+ ret = logical_ring_wait_request(ringbuf, bytes);
+ if (ret != -ENOSPC)
+ return ret;
+
+ /* Force the context submission in case we have been skipping it */
+ intel_logical_ring_advance_and_submit(ringbuf, ctx, NULL);
+
+ /* With GEM the hangcheck timer should kick us out of the loop,
+ * leaving it early runs the risk of corrupting GEM state (due
+ * to running on almost untested codepaths). But on resume
+ * timers don't work yet, so prevent a complete hang in that
+ * case by choosing an insanely large timeout. */
+ end = jiffies + 60 * HZ;
+
+ ret = 0;
+ do {
+ if (intel_ring_space(ringbuf) >= bytes)
+ break;
+
+ msleep(1);
+
+ if (dev_priv->mm.interruptible && signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ break;
+ }
+
+ ret = i915_gem_check_wedge(&dev_priv->gpu_error,
+ dev_priv->mm.interruptible);
+ if (ret)
+ break;
+
+ if (time_after(jiffies, end)) {
+ ret = -EBUSY;
+ break;
+ }
+ } while (1);
+
+ return ret;
+}
+
+static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf,
+ struct intel_context *ctx)
+{
+ uint32_t __iomem *virt;
+ int rem = ringbuf->size - ringbuf->tail;
+
+ if (ringbuf->space < rem) {
+ int ret = logical_ring_wait_for_space(ringbuf, ctx, rem);
+
+ if (ret)
+ return ret;
+ }
+
+ virt = ringbuf->virtual_start + ringbuf->tail;
+ rem /= 4;
+ while (rem--)
+ iowrite32(MI_NOOP, virt++);
+
+ ringbuf->tail = 0;
+ intel_ring_update_space(ringbuf);
+
+ return 0;
+}
+
+static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
+ struct intel_context *ctx, int bytes)
+{
+ int ret;
+
+ if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
+ ret = logical_ring_wrap_buffer(ringbuf, ctx);
+ if (unlikely(ret))
+ return ret;
+ }
+
+ if (unlikely(ringbuf->space < bytes)) {
+ ret = logical_ring_wait_for_space(ringbuf, ctx, bytes);
+ if (unlikely(ret))
+ return ret;
+ }
+
+ return 0;
+}
+
+/**
+ * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
+ *
+ * @ringbuf: Logical ringbuffer.
+ * @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
+ *
+ * The ringbuffer might not be ready to accept the commands right away (maybe it needs to
+ * be wrapped, or wait a bit for the tail to be updated). This function takes care of that
+ * and also preallocates a request (every workload submission is still mediated through
+ * requests, same as it did with legacy ringbuffer submission).
+ *
+ * Return: non-zero if the ringbuffer is not ready to be written to.
+ */
+static int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
+ struct intel_context *ctx, int num_dwords)
+{
+ struct drm_i915_gem_request *req;
+ struct intel_engine_cs *ring = ringbuf->ring;
+ struct drm_device *dev = ring->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int ret;
+
+ ret = i915_gem_check_wedge(&dev_priv->gpu_error,
+ dev_priv->mm.interruptible);
+ if (ret)
+ return ret;
+
+ ret = logical_ring_prepare(ringbuf, ctx, num_dwords * sizeof(uint32_t));
+ if (ret)
+ return ret;
+
+ /* Preallocate the olr before touching the ring */
+ ret = intel_logical_ring_alloc_request(ring, ctx, &req);
+ if (ret)
+ return ret;
+
+ ringbuf->space -= num_dwords * sizeof(uint32_t);
+ return 0;
+}
+
/**
* execlists_submission() - submit a batchbuffer for execution, Execlists style
* @dev: DRM device.
@@ -783,30 +980,6 @@ int logical_ring_flush_all_caches(struct drm_i915_gem_request *req)
return 0;
}
-/*
- * intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
- * @ringbuf: Logical Ringbuffer to advance.
- *
- * The tail is updated in our logical ringbuffer struct, not in the actual context. What
- * really happens during submission is that the context and current tail will be placed
- * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
- * point, the tail *inside* the context is updated and the ELSP written to.
- */
-static void
-intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
- struct drm_i915_gem_request *request)
-{
- struct intel_engine_cs *ring = ringbuf->ring;
-
- intel_logical_ring_advance(ringbuf);
-
- if (intel_ring_stopped(ring))
- return;
-
- execlists_context_queue(ring, ctx, ringbuf->tail, request);
-}
-
static int intel_lr_context_pin(struct intel_engine_cs *ring,
struct intel_context *ctx)
{
@@ -901,179 +1074,6 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
return 0;
}
-static int logical_ring_wait_request(struct intel_ringbuffer *ringbuf,
- int bytes)
-{
- struct intel_engine_cs *ring = ringbuf->ring;
- struct drm_i915_gem_request *request;
- int ret;
-
- if (intel_ring_space(ringbuf) >= bytes)
- return 0;
-
- list_for_each_entry(request, &ring->request_list, list) {
- /*
- * The request queue is per-engine, so can contain requests
- * from multiple ringbuffers. Here, we must ignore any that
- * aren't from the ringbuffer we're considering.
- */
- struct intel_context *ctx = request->ctx;
- if (ctx->engine[ring->id].ringbuf != ringbuf)
- continue;
-
- /* Would completion of this request free enough space? */
- if (__intel_ring_space(request->tail, ringbuf->tail,
- ringbuf->size) >= bytes) {
- break;
- }
- }
-
- if (&request->list == &ring->request_list)
- return -ENOSPC;
-
- ret = i915_wait_request(request);
- if (ret)
- return ret;
-
- i915_gem_retire_requests_ring(ring);
-
- return intel_ring_space(ringbuf) >= bytes ? 0 : -ENOSPC;
-}
-
-static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
- int bytes)
-{
- struct intel_engine_cs *ring = ringbuf->ring;
- struct drm_device *dev = ring->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- unsigned long end;
- int ret;
-
- ret = logical_ring_wait_request(ringbuf, bytes);
- if (ret != -ENOSPC)
- return ret;
-
- /* Force the context submission in case we have been skipping it */
- intel_logical_ring_advance_and_submit(ringbuf, ctx, NULL);
-
- /* With GEM the hangcheck timer should kick us out of the loop,
- * leaving it early runs the risk of corrupting GEM state (due
- * to running on almost untested codepaths). But on resume
- * timers don't work yet, so prevent a complete hang in that
- * case by choosing an insanely large timeout. */
- end = jiffies + 60 * HZ;
-
- ret = 0;
- do {
- if (intel_ring_space(ringbuf) >= bytes)
- break;
-
- msleep(1);
-
- if (dev_priv->mm.interruptible && signal_pending(current)) {
- ret = -ERESTARTSYS;
- break;
- }
-
- ret = i915_gem_check_wedge(&dev_priv->gpu_error,
- dev_priv->mm.interruptible);
- if (ret)
- break;
-
- if (time_after(jiffies, end)) {
- ret = -EBUSY;
- break;
- }
- } while (1);
-
- return ret;
-}
-
-static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx)
-{
- uint32_t __iomem *virt;
- int rem = ringbuf->size - ringbuf->tail;
-
- if (ringbuf->space < rem) {
- int ret = logical_ring_wait_for_space(ringbuf, ctx, rem);
-
- if (ret)
- return ret;
- }
-
- virt = ringbuf->virtual_start + ringbuf->tail;
- rem /= 4;
- while (rem--)
- iowrite32(MI_NOOP, virt++);
-
- ringbuf->tail = 0;
- intel_ring_update_space(ringbuf);
-
- return 0;
-}
-
-static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx, int bytes)
-{
- int ret;
-
- if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
- ret = logical_ring_wrap_buffer(ringbuf, ctx);
- if (unlikely(ret))
- return ret;
- }
-
- if (unlikely(ringbuf->space < bytes)) {
- ret = logical_ring_wait_for_space(ringbuf, ctx, bytes);
- if (unlikely(ret))
- return ret;
- }
-
- return 0;
-}
-
-/**
- * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
- *
- * @ringbuf: Logical ringbuffer.
- * @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
- *
- * The ringbuffer might not be ready to accept the commands right away (maybe it needs to
- * be wrapped, or wait a bit for the tail to be updated). This function takes care of that
- * and also preallocates a request (every workload submission is still mediated through
- * requests, same as it did with legacy ringbuffer submission).
- *
- * Return: non-zero if the ringbuffer is not ready to be written to.
- */
-int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx, int num_dwords)
-{
- struct drm_i915_gem_request *req;
- struct intel_engine_cs *ring = ringbuf->ring;
- struct drm_device *dev = ring->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- int ret;
-
- ret = i915_gem_check_wedge(&dev_priv->gpu_error,
- dev_priv->mm.interruptible);
- if (ret)
- return ret;
-
- ret = logical_ring_prepare(ringbuf, ctx, num_dwords * sizeof(uint32_t));
- if (ret)
- return ret;
-
- /* Preallocate the olr before touching the ring */
- ret = intel_logical_ring_alloc_request(ring, ctx, &req);
- if (ret)
- return ret;
-
- ringbuf->space -= num_dwords * sizeof(uint32_t);
- return 0;
-}
-
static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
{
int ret, i;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 40848b0..dceecc6 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -65,9 +65,6 @@ static inline void intel_logical_ring_emit(struct intel_ringbuffer *ringbuf,
iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
ringbuf->tail += 4;
}
-int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
- int num_dwords);
/* Logical Ring Contexts */
void intel_lr_context_free(struct intel_context *ctx);
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 49/53] drm/i915: Make intel_logical_ring_begin() static
2015-02-19 17:18 ` [PATCH 49/53] drm/i915: Make intel_logical_ring_begin() static John.C.Harrison
@ 2015-03-09 23:24 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 23:24 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:18, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The only usage of intel_logical_ring_begin() is within intel_lrc.c so it can be
> made static. To avoid a forward declaration at the top of the file, it and bunch
> of other functions have been shuffled upwards.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_lrc.c | 394 +++++++++++++++++++-------------------
> drivers/gpu/drm/i915/intel_lrc.h | 3 -
> 2 files changed, 197 insertions(+), 200 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 5212b54..b40501d 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -606,6 +606,203 @@ static int execlists_move_to_gpu(struct drm_i915_gem_request *req,
> return logical_ring_invalidate_all_caches(req);
> }
>
> +static int logical_ring_wait_request(struct intel_ringbuffer *ringbuf,
> + int bytes)
> +{
> + struct intel_engine_cs *ring = ringbuf->ring;
> + struct drm_i915_gem_request *request;
> + int ret;
> +
> + if (intel_ring_space(ringbuf) >= bytes)
> + return 0;
> +
> + list_for_each_entry(request, &ring->request_list, list) {
> + /*
> + * The request queue is per-engine, so can contain requests
> + * from multiple ringbuffers. Here, we must ignore any that
> + * aren't from the ringbuffer we're considering.
> + */
> + struct intel_context *ctx = request->ctx;
> + if (ctx->engine[ring->id].ringbuf != ringbuf)
> + continue;
> +
> + /* Would completion of this request free enough space? */
> + if (__intel_ring_space(request->tail, ringbuf->tail,
> + ringbuf->size) >= bytes) {
> + break;
> + }
> + }
> +
> + if (&request->list == &ring->request_list)
> + return -ENOSPC;
> +
> + ret = i915_wait_request(request);
> + if (ret)
> + return ret;
> +
> + i915_gem_retire_requests_ring(ring);
> +
> + return intel_ring_space(ringbuf) >= bytes ? 0 : -ENOSPC;
> +}
> +
> +/*
> + * intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
> + * @ringbuf: Logical Ringbuffer to advance.
> + *
> + * The tail is updated in our logical ringbuffer struct, not in the actual context. What
> + * really happens during submission is that the context and current tail will be placed
> + * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
> + * point, the tail *inside* the context is updated and the ELSP written to.
> + */
> +static void
> +intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
> + struct intel_context *ctx,
> + struct drm_i915_gem_request *request)
> +{
> + struct intel_engine_cs *ring = ringbuf->ring;
> +
> + intel_logical_ring_advance(ringbuf);
> +
> + if (intel_ring_stopped(ring))
> + return;
> +
> + execlists_context_queue(ring, ctx, ringbuf->tail, request);
> +}
> +
> +static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
> + struct intel_context *ctx,
> + int bytes)
> +{
> + struct intel_engine_cs *ring = ringbuf->ring;
> + struct drm_device *dev = ring->dev;
> + struct drm_i915_private *dev_priv = dev->dev_private;
> + unsigned long end;
> + int ret;
> +
> + ret = logical_ring_wait_request(ringbuf, bytes);
> + if (ret != -ENOSPC)
> + return ret;
> +
> + /* Force the context submission in case we have been skipping it */
> + intel_logical_ring_advance_and_submit(ringbuf, ctx, NULL);
> +
> + /* With GEM the hangcheck timer should kick us out of the loop,
> + * leaving it early runs the risk of corrupting GEM state (due
> + * to running on almost untested codepaths). But on resume
> + * timers don't work yet, so prevent a complete hang in that
> + * case by choosing an insanely large timeout. */
> + end = jiffies + 60 * HZ;
> +
> + ret = 0;
> + do {
> + if (intel_ring_space(ringbuf) >= bytes)
> + break;
> +
> + msleep(1);
> +
> + if (dev_priv->mm.interruptible && signal_pending(current)) {
> + ret = -ERESTARTSYS;
> + break;
> + }
> +
> + ret = i915_gem_check_wedge(&dev_priv->gpu_error,
> + dev_priv->mm.interruptible);
> + if (ret)
> + break;
> +
> + if (time_after(jiffies, end)) {
> + ret = -EBUSY;
> + break;
> + }
> + } while (1);
> +
> + return ret;
> +}
> +
> +static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf,
> + struct intel_context *ctx)
> +{
> + uint32_t __iomem *virt;
> + int rem = ringbuf->size - ringbuf->tail;
> +
> + if (ringbuf->space < rem) {
> + int ret = logical_ring_wait_for_space(ringbuf, ctx, rem);
> +
> + if (ret)
> + return ret;
> + }
> +
> + virt = ringbuf->virtual_start + ringbuf->tail;
> + rem /= 4;
> + while (rem--)
> + iowrite32(MI_NOOP, virt++);
> +
> + ringbuf->tail = 0;
> + intel_ring_update_space(ringbuf);
> +
> + return 0;
> +}
> +
> +static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
> + struct intel_context *ctx, int bytes)
> +{
> + int ret;
> +
> + if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
> + ret = logical_ring_wrap_buffer(ringbuf, ctx);
> + if (unlikely(ret))
> + return ret;
> + }
> +
> + if (unlikely(ringbuf->space < bytes)) {
> + ret = logical_ring_wait_for_space(ringbuf, ctx, bytes);
> + if (unlikely(ret))
> + return ret;
> + }
> +
> + return 0;
> +}
> +
> +/**
> + * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
> + *
> + * @ringbuf: Logical ringbuffer.
> + * @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
> + *
> + * The ringbuffer might not be ready to accept the commands right away (maybe it needs to
> + * be wrapped, or wait a bit for the tail to be updated). This function takes care of that
> + * and also preallocates a request (every workload submission is still mediated through
> + * requests, same as it did with legacy ringbuffer submission).
> + *
> + * Return: non-zero if the ringbuffer is not ready to be written to.
> + */
> +static int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
> + struct intel_context *ctx, int num_dwords)
> +{
> + struct drm_i915_gem_request *req;
> + struct intel_engine_cs *ring = ringbuf->ring;
> + struct drm_device *dev = ring->dev;
> + struct drm_i915_private *dev_priv = dev->dev_private;
> + int ret;
> +
> + ret = i915_gem_check_wedge(&dev_priv->gpu_error,
> + dev_priv->mm.interruptible);
> + if (ret)
> + return ret;
> +
> + ret = logical_ring_prepare(ringbuf, ctx, num_dwords * sizeof(uint32_t));
> + if (ret)
> + return ret;
> +
> + /* Preallocate the olr before touching the ring */
> + ret = intel_logical_ring_alloc_request(ring, ctx, &req);
> + if (ret)
> + return ret;
> +
> + ringbuf->space -= num_dwords * sizeof(uint32_t);
> + return 0;
> +}
> +
> /**
> * execlists_submission() - submit a batchbuffer for execution, Execlists style
> * @dev: DRM device.
> @@ -783,30 +980,6 @@ int logical_ring_flush_all_caches(struct drm_i915_gem_request *req)
> return 0;
> }
>
> -/*
> - * intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
> - * @ringbuf: Logical Ringbuffer to advance.
> - *
> - * The tail is updated in our logical ringbuffer struct, not in the actual context. What
> - * really happens during submission is that the context and current tail will be placed
> - * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
> - * point, the tail *inside* the context is updated and the ELSP written to.
> - */
> -static void
> -intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx,
> - struct drm_i915_gem_request *request)
> -{
> - struct intel_engine_cs *ring = ringbuf->ring;
> -
> - intel_logical_ring_advance(ringbuf);
> -
> - if (intel_ring_stopped(ring))
> - return;
> -
> - execlists_context_queue(ring, ctx, ringbuf->tail, request);
> -}
> -
> static int intel_lr_context_pin(struct intel_engine_cs *ring,
> struct intel_context *ctx)
> {
> @@ -901,179 +1074,6 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> return 0;
> }
>
> -static int logical_ring_wait_request(struct intel_ringbuffer *ringbuf,
> - int bytes)
> -{
> - struct intel_engine_cs *ring = ringbuf->ring;
> - struct drm_i915_gem_request *request;
> - int ret;
> -
> - if (intel_ring_space(ringbuf) >= bytes)
> - return 0;
> -
> - list_for_each_entry(request, &ring->request_list, list) {
> - /*
> - * The request queue is per-engine, so can contain requests
> - * from multiple ringbuffers. Here, we must ignore any that
> - * aren't from the ringbuffer we're considering.
> - */
> - struct intel_context *ctx = request->ctx;
> - if (ctx->engine[ring->id].ringbuf != ringbuf)
> - continue;
> -
> - /* Would completion of this request free enough space? */
> - if (__intel_ring_space(request->tail, ringbuf->tail,
> - ringbuf->size) >= bytes) {
> - break;
> - }
> - }
> -
> - if (&request->list == &ring->request_list)
> - return -ENOSPC;
> -
> - ret = i915_wait_request(request);
> - if (ret)
> - return ret;
> -
> - i915_gem_retire_requests_ring(ring);
> -
> - return intel_ring_space(ringbuf) >= bytes ? 0 : -ENOSPC;
> -}
> -
> -static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx,
> - int bytes)
> -{
> - struct intel_engine_cs *ring = ringbuf->ring;
> - struct drm_device *dev = ring->dev;
> - struct drm_i915_private *dev_priv = dev->dev_private;
> - unsigned long end;
> - int ret;
> -
> - ret = logical_ring_wait_request(ringbuf, bytes);
> - if (ret != -ENOSPC)
> - return ret;
> -
> - /* Force the context submission in case we have been skipping it */
> - intel_logical_ring_advance_and_submit(ringbuf, ctx, NULL);
> -
> - /* With GEM the hangcheck timer should kick us out of the loop,
> - * leaving it early runs the risk of corrupting GEM state (due
> - * to running on almost untested codepaths). But on resume
> - * timers don't work yet, so prevent a complete hang in that
> - * case by choosing an insanely large timeout. */
> - end = jiffies + 60 * HZ;
> -
> - ret = 0;
> - do {
> - if (intel_ring_space(ringbuf) >= bytes)
> - break;
> -
> - msleep(1);
> -
> - if (dev_priv->mm.interruptible && signal_pending(current)) {
> - ret = -ERESTARTSYS;
> - break;
> - }
> -
> - ret = i915_gem_check_wedge(&dev_priv->gpu_error,
> - dev_priv->mm.interruptible);
> - if (ret)
> - break;
> -
> - if (time_after(jiffies, end)) {
> - ret = -EBUSY;
> - break;
> - }
> - } while (1);
> -
> - return ret;
> -}
> -
> -static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx)
> -{
> - uint32_t __iomem *virt;
> - int rem = ringbuf->size - ringbuf->tail;
> -
> - if (ringbuf->space < rem) {
> - int ret = logical_ring_wait_for_space(ringbuf, ctx, rem);
> -
> - if (ret)
> - return ret;
> - }
> -
> - virt = ringbuf->virtual_start + ringbuf->tail;
> - rem /= 4;
> - while (rem--)
> - iowrite32(MI_NOOP, virt++);
> -
> - ringbuf->tail = 0;
> - intel_ring_update_space(ringbuf);
> -
> - return 0;
> -}
> -
> -static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx, int bytes)
> -{
> - int ret;
> -
> - if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
> - ret = logical_ring_wrap_buffer(ringbuf, ctx);
> - if (unlikely(ret))
> - return ret;
> - }
> -
> - if (unlikely(ringbuf->space < bytes)) {
> - ret = logical_ring_wait_for_space(ringbuf, ctx, bytes);
> - if (unlikely(ret))
> - return ret;
> - }
> -
> - return 0;
> -}
> -
> -/**
> - * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
> - *
> - * @ringbuf: Logical ringbuffer.
> - * @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
> - *
> - * The ringbuffer might not be ready to accept the commands right away (maybe it needs to
> - * be wrapped, or wait a bit for the tail to be updated). This function takes care of that
> - * and also preallocates a request (every workload submission is still mediated through
> - * requests, same as it did with legacy ringbuffer submission).
> - *
> - * Return: non-zero if the ringbuffer is not ready to be written to.
> - */
> -int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx, int num_dwords)
> -{
> - struct drm_i915_gem_request *req;
> - struct intel_engine_cs *ring = ringbuf->ring;
> - struct drm_device *dev = ring->dev;
> - struct drm_i915_private *dev_priv = dev->dev_private;
> - int ret;
> -
> - ret = i915_gem_check_wedge(&dev_priv->gpu_error,
> - dev_priv->mm.interruptible);
> - if (ret)
> - return ret;
> -
> - ret = logical_ring_prepare(ringbuf, ctx, num_dwords * sizeof(uint32_t));
> - if (ret)
> - return ret;
> -
> - /* Preallocate the olr before touching the ring */
> - ret = intel_logical_ring_alloc_request(ring, ctx, &req);
> - if (ret)
> - return ret;
> -
> - ringbuf->space -= num_dwords * sizeof(uint32_t);
> - return 0;
> -}
> -
> static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
> {
> int ret, i;
> diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
> index 40848b0..dceecc6 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.h
> +++ b/drivers/gpu/drm/i915/intel_lrc.h
> @@ -65,9 +65,6 @@ static inline void intel_logical_ring_emit(struct intel_ringbuffer *ringbuf,
> iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
> ringbuf->tail += 4;
> }
> -int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx,
> - int num_dwords);
>
> /* Logical Ring Contexts */
> void intel_lr_context_free(struct intel_context *ctx);
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 50/53] drm/i915: Update intel_logical_ring_begin() to take a request structure
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (48 preceding siblings ...)
2015-02-19 17:18 ` [PATCH 49/53] drm/i915: Make intel_logical_ring_begin() static John.C.Harrison
@ 2015-02-19 17:18 ` John.C.Harrison
2015-03-09 23:33 ` Tomas Elf
2015-02-19 17:18 ` [PATCH 51/53] drm/i915: Remove the now obsolete intel_ring_get_request() John.C.Harrison
` (4 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:18 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Now that everything above has been converted to use requests,
intel_logical_ring_begin() can be updated to take a request instead of a
ringbuf/context pair. This also means that it no longer needs to lazily allocate
a request if no-one happens to have done it earlier.
Note that this change makes the execlist signature the same as the legacy
version. Thus the two functions could be merged into a ring->begin() wrapper if
required.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_lrc.c | 33 +++++++++++++++------------------
1 file changed, 15 insertions(+), 18 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index b40501d..2911cf6 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -766,7 +766,7 @@ static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
/**
* intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
*
- * @ringbuf: Logical ringbuffer.
+ * @request: The request to start some new work for
* @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
*
* The ringbuffer might not be ready to accept the commands right away (maybe it needs to
@@ -776,30 +776,27 @@ static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
*
* Return: non-zero if the ringbuffer is not ready to be written to.
*/
-static int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx, int num_dwords)
+static int intel_logical_ring_begin(struct drm_i915_gem_request *req,
+ int num_dwords)
{
- struct drm_i915_gem_request *req;
- struct intel_engine_cs *ring = ringbuf->ring;
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
int ret;
+ WARN_ON(req == NULL);
+
ret = i915_gem_check_wedge(&dev_priv->gpu_error,
dev_priv->mm.interruptible);
if (ret)
return ret;
- ret = logical_ring_prepare(ringbuf, ctx, num_dwords * sizeof(uint32_t));
- if (ret)
- return ret;
-
- /* Preallocate the olr before touching the ring */
- ret = intel_logical_ring_alloc_request(ring, ctx, &req);
+ ret = logical_ring_prepare(req->ringbuf, req->ctx,
+ num_dwords * sizeof(uint32_t));
if (ret)
return ret;
- ringbuf->space -= num_dwords * sizeof(uint32_t);
+ req->ringbuf->space -= num_dwords * sizeof(uint32_t);
return 0;
}
@@ -885,7 +882,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
if (ring == &dev_priv->ring[RCS] &&
instp_mode != dev_priv->relative_constants_mode) {
- ret = intel_logical_ring_begin(ringbuf, params->ctx, 4);
+ ret = intel_logical_ring_begin(params->request, 4);
if (ret)
return ret;
@@ -1091,7 +1088,7 @@ static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
if (ret)
return ret;
- ret = intel_logical_ring_begin(ringbuf, req->ctx, w->count * 2 + 2);
+ ret = intel_logical_ring_begin(req, w->count * 2 + 2);
if (ret)
return ret;
@@ -1173,7 +1170,7 @@ static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
bool ppgtt = !(dispatch_flags & I915_DISPATCH_SECURE);
int ret;
- ret = intel_logical_ring_begin(ringbuf, req->ctx, 4);
+ ret = intel_logical_ring_begin(req, 4);
if (ret)
return ret;
@@ -1231,7 +1228,7 @@ static int gen8_emit_flush(struct drm_i915_gem_request *request,
uint32_t cmd;
int ret;
- ret = intel_logical_ring_begin(ringbuf, request->ctx, 4);
+ ret = intel_logical_ring_begin(request, 4);
if (ret)
return ret;
@@ -1289,7 +1286,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
}
- ret = intel_logical_ring_begin(ringbuf, request->ctx, 6);
+ ret = intel_logical_ring_begin(request, 6);
if (ret)
return ret;
@@ -1321,7 +1318,7 @@ static int gen8_emit_request(struct drm_i915_gem_request *request)
u32 cmd;
int ret;
- ret = intel_logical_ring_begin(ringbuf, request->ctx, 6);
+ ret = intel_logical_ring_begin(request, 6);
if (ret)
return ret;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 50/53] drm/i915: Update intel_logical_ring_begin() to take a request structure
2015-02-19 17:18 ` [PATCH 50/53] drm/i915: Update intel_logical_ring_begin() to take a request structure John.C.Harrison
@ 2015-03-09 23:33 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 23:33 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:18, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Now that everything above has been converted to use requests,
> intel_logical_ring_begin() can be updated to take a request instead of a
> ringbuf/context pair. This also means that it no longer needs to lazily allocate
> a request if no-one happens to have done it earlier.
>
> Note that this change makes the execlist signature the same as the legacy
> version. Thus the two functions could be merged into a ring->begin() wrapper if
> required.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_lrc.c | 33 +++++++++++++++------------------
> 1 file changed, 15 insertions(+), 18 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index b40501d..2911cf6 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -766,7 +766,7 @@ static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
> /**
> * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
> *
> - * @ringbuf: Logical ringbuffer.
> + * @request: The request to start some new work for
> * @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
> *
> * The ringbuffer might not be ready to accept the commands right away (maybe it needs to
> @@ -776,30 +776,27 @@ static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
> *
> * Return: non-zero if the ringbuffer is not ready to be written to.
> */
> -static int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
> - struct intel_context *ctx, int num_dwords)
> +static int intel_logical_ring_begin(struct drm_i915_gem_request *req,
> + int num_dwords)
> {
> - struct drm_i915_gem_request *req;
> - struct intel_engine_cs *ring = ringbuf->ring;
> + struct intel_engine_cs *ring = req->ring;
> struct drm_device *dev = ring->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> int ret;
>
> + WARN_ON(req == NULL);
This WARN_ON will only fire after there's been a null pointer exception
in the req->ring dereference above. Please rearrange these so that it
warns before the null pointer exception.
Thanks,
Tomas
> +
> ret = i915_gem_check_wedge(&dev_priv->gpu_error,
> dev_priv->mm.interruptible);
> if (ret)
> return ret;
>
> - ret = logical_ring_prepare(ringbuf, ctx, num_dwords * sizeof(uint32_t));
> - if (ret)
> - return ret;
> -
> - /* Preallocate the olr before touching the ring */
> - ret = intel_logical_ring_alloc_request(ring, ctx, &req);
> + ret = logical_ring_prepare(req->ringbuf, req->ctx,
> + num_dwords * sizeof(uint32_t));
> if (ret)
> return ret;
>
> - ringbuf->space -= num_dwords * sizeof(uint32_t);
> + req->ringbuf->space -= num_dwords * sizeof(uint32_t);
> return 0;
> }
>
> @@ -885,7 +882,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
>
> if (ring == &dev_priv->ring[RCS] &&
> instp_mode != dev_priv->relative_constants_mode) {
> - ret = intel_logical_ring_begin(ringbuf, params->ctx, 4);
> + ret = intel_logical_ring_begin(params->request, 4);
> if (ret)
> return ret;
>
> @@ -1091,7 +1088,7 @@ static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
> if (ret)
> return ret;
>
> - ret = intel_logical_ring_begin(ringbuf, req->ctx, w->count * 2 + 2);
> + ret = intel_logical_ring_begin(req, w->count * 2 + 2);
> if (ret)
> return ret;
>
> @@ -1173,7 +1170,7 @@ static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
> bool ppgtt = !(dispatch_flags & I915_DISPATCH_SECURE);
> int ret;
>
> - ret = intel_logical_ring_begin(ringbuf, req->ctx, 4);
> + ret = intel_logical_ring_begin(req, 4);
> if (ret)
> return ret;
>
> @@ -1231,7 +1228,7 @@ static int gen8_emit_flush(struct drm_i915_gem_request *request,
> uint32_t cmd;
> int ret;
>
> - ret = intel_logical_ring_begin(ringbuf, request->ctx, 4);
> + ret = intel_logical_ring_begin(request, 4);
> if (ret)
> return ret;
>
> @@ -1289,7 +1286,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
> flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
> }
>
> - ret = intel_logical_ring_begin(ringbuf, request->ctx, 6);
> + ret = intel_logical_ring_begin(request, 6);
> if (ret)
> return ret;
>
> @@ -1321,7 +1318,7 @@ static int gen8_emit_request(struct drm_i915_gem_request *request)
> u32 cmd;
> int ret;
>
> - ret = intel_logical_ring_begin(ringbuf, request->ctx, 6);
> + ret = intel_logical_ring_begin(request, 6);
> if (ret)
> return ret;
>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 51/53] drm/i915: Remove the now obsolete intel_ring_get_request()
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (49 preceding siblings ...)
2015-02-19 17:18 ` [PATCH 50/53] drm/i915: Update intel_logical_ring_begin() to take a request structure John.C.Harrison
@ 2015-02-19 17:18 ` John.C.Harrison
2015-03-09 23:35 ` Tomas Elf
2015-02-19 17:18 ` [PATCH 52/53] drm/i915: Remove the now obsolete 'outstanding_lazy_request' John.C.Harrison
` (3 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:18 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Much of the driver has now been converted to passing requests around instead of
rings/ringbufs/contexts. Thus the function for retreiving the request from a
ring (i.e. the OLR) is no longer used and can be removed.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_ringbuffer.h | 7 -------
1 file changed, 7 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index e83fbbb..3b0261f 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -431,11 +431,4 @@ static inline u32 intel_ring_get_tail(struct intel_ringbuffer *ringbuf)
return ringbuf->tail;
}
-static inline struct drm_i915_gem_request *
-intel_ring_get_request(struct intel_engine_cs *ring)
-{
- BUG_ON(ring->outstanding_lazy_request == NULL);
- return ring->outstanding_lazy_request;
-}
-
#endif /* _INTEL_RINGBUFFER_H_ */
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 51/53] drm/i915: Remove the now obsolete intel_ring_get_request()
2015-02-19 17:18 ` [PATCH 51/53] drm/i915: Remove the now obsolete intel_ring_get_request() John.C.Harrison
@ 2015-03-09 23:35 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 23:35 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:18, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Much of the driver has now been converted to passing requests around instead of
> rings/ringbufs/contexts. Thus the function for retreiving the request from a
> ring (i.e. the OLR) is no longer used and can be removed.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/intel_ringbuffer.h | 7 -------
> 1 file changed, 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index e83fbbb..3b0261f 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -431,11 +431,4 @@ static inline u32 intel_ring_get_tail(struct intel_ringbuffer *ringbuf)
> return ringbuf->tail;
> }
>
> -static inline struct drm_i915_gem_request *
> -intel_ring_get_request(struct intel_engine_cs *ring)
> -{
> - BUG_ON(ring->outstanding_lazy_request == NULL);
> - return ring->outstanding_lazy_request;
> -}
> -
> #endif /* _INTEL_RINGBUFFER_H_ */
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 52/53] drm/i915: Remove the now obsolete 'outstanding_lazy_request'
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (50 preceding siblings ...)
2015-02-19 17:18 ` [PATCH 51/53] drm/i915: Remove the now obsolete intel_ring_get_request() John.C.Harrison
@ 2015-02-19 17:18 ` John.C.Harrison
2015-03-09 23:51 ` Tomas Elf
2015-02-19 17:18 ` [PATCH 53/53] drm/i915: Move the request/file and request/pid association to creation time John.C.Harrison
` (2 subsequent siblings)
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:18 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The outstanding_lazy_request is no longer used anywhere in the driver.
Everything that was looking at it now has a request explicitly passed in from on
high. Everything that was relying upon behind the scenes is now explicitly
creating/passing/submitting it's own private request. Thus the OLR can be
removed.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 16 +---------------
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 4 +---
drivers/gpu/drm/i915/intel_lrc.c | 6 ++----
drivers/gpu/drm/i915/intel_ringbuffer.c | 17 ++---------------
drivers/gpu/drm/i915/intel_ringbuffer.h | 4 ----
5 files changed, 6 insertions(+), 41 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 60f6671..8e7418b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1156,15 +1156,9 @@ i915_gem_check_wedge(struct i915_gpu_error *error,
int
i915_gem_check_olr(struct drm_i915_gem_request *req)
{
- int ret;
-
WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
- ret = 0;
- if (req == req->ring->outstanding_lazy_request)
- ret = i915_add_request(req);
-
- return ret;
+ return 0;
}
static void fake_irq(unsigned long data)
@@ -2424,8 +2418,6 @@ int __i915_add_request(struct drm_i915_gem_request *request,
dev_priv = ring->dev->dev_private;
ringbuf = request->ringbuf;
- WARN_ON(request != ring->outstanding_lazy_request);
-
request_start = intel_ring_get_tail(ringbuf);
/*
* Emit any outstanding flushes - execbuf can fail to emit the flush
@@ -2486,7 +2478,6 @@ int __i915_add_request(struct drm_i915_gem_request *request,
}
trace_i915_gem_request_add(request);
- ring->outstanding_lazy_request = NULL;
i915_queue_hangcheck(ring->dev);
@@ -2672,9 +2663,6 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
i915_gem_free_request(request);
}
-
- /* This may not have been flushed before the reset, so clean it now */
- i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
}
void i915_gem_restore_fences(struct drm_device *dev)
@@ -3124,8 +3112,6 @@ int i915_gpu_idle(struct drm_device *dev)
}
}
- WARN_ON(ring->outstanding_lazy_request);
-
ret = intel_ring_idle(ring);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 6a703e6..0eae592 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1571,10 +1571,8 @@ err:
* must be freed again. If it was submitted then it is being tracked
* on the active request list and no clean up is required here.
*/
- if (ret && params->request) {
+ if (ret && params->request)
i915_gem_request_unreference(params->request);
- ring->outstanding_lazy_request = NULL;
- }
mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 2911cf6..db63ea0 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1032,8 +1032,7 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
if (!req_out)
return -EINVAL;
- if ((*req_out = ring->outstanding_lazy_request) != NULL)
- return 0;
+ *req_out = NULL;
request = kzalloc(sizeof(*request), GFP_KERNEL);
if (request == NULL)
@@ -1067,7 +1066,7 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
i915_gem_context_reference(request->ctx);
request->ringbuf = ctx->engine[ring->id].ringbuf;
- *req_out = ring->outstanding_lazy_request = request;
+ *req_out = request;
return 0;
}
@@ -1393,7 +1392,6 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *ring)
intel_logical_ring_stop(ring);
WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
- i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
if (ring->cleanup)
ring->cleanup(ring);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 5eef02e..85daa18 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2034,7 +2034,6 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
intel_unpin_ringbuffer_obj(ringbuf);
intel_destroy_ringbuffer_obj(ringbuf);
- i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
if (ring->cleanup)
ring->cleanup(ring);
@@ -2153,15 +2152,6 @@ static int intel_wrap_ring_buffer(struct intel_engine_cs *ring)
int intel_ring_idle(struct intel_engine_cs *ring)
{
struct drm_i915_gem_request *req;
- int ret;
-
- /* We need to add any requests required to flush the objects and ring */
- WARN_ON(ring->outstanding_lazy_request);
- if (ring->outstanding_lazy_request) {
- ret = i915_add_request(ring->outstanding_lazy_request);
- if (ret)
- return ret;
- }
/* Wait upon the last request to be completed */
if (list_empty(&ring->request_list))
@@ -2186,8 +2176,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring,
if (!req_out)
return -EINVAL;
- if ((*req_out = ring->outstanding_lazy_request) != NULL)
- return 0;
+ *req_out = NULL;
request = kzalloc(sizeof(*request), GFP_KERNEL);
if (request == NULL)
@@ -2206,7 +2195,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring,
return ret;
}
- *req_out = ring->outstanding_lazy_request = request;
+ *req_out = request;
return 0;
}
@@ -2281,8 +2270,6 @@ void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno)
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- BUG_ON(ring->outstanding_lazy_request);
-
if (INTEL_INFO(dev)->gen == 6 || INTEL_INFO(dev)->gen == 7) {
I915_WRITE(RING_SYNC_0(ring->mmio_base), 0);
I915_WRITE(RING_SYNC_1(ring->mmio_base), 0);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 3b0261f..d2c6427 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -258,10 +258,6 @@ struct intel_engine_cs {
*/
struct list_head request_list;
- /**
- * Do we have some not yet emitted requests outstanding?
- */
- struct drm_i915_gem_request *outstanding_lazy_request;
bool gpu_caches_dirty;
bool fbc_dirty;
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 52/53] drm/i915: Remove the now obsolete 'outstanding_lazy_request'
2015-02-19 17:18 ` [PATCH 52/53] drm/i915: Remove the now obsolete 'outstanding_lazy_request' John.C.Harrison
@ 2015-03-09 23:51 ` Tomas Elf
2015-03-10 10:18 ` Daniel Vetter
0 siblings, 1 reply; 234+ messages in thread
From: Tomas Elf @ 2015-03-09 23:51 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:18, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The outstanding_lazy_request is no longer used anywhere in the driver.
> Everything that was looking at it now has a request explicitly passed in from on
> high. Everything that was relying upon behind the scenes is now explicitly
> creating/passing/submitting it's own private request. Thus the OLR can be
> removed.
>
"Everything that was relying upon behind the scenes is now explicitly
creating/passing/submitting it's ..."
--->
"Everything that was relying on it behind the scenes is now explicitly
creating/passing/submitting its ..." ?
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 16 +---------------
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 4 +---
> drivers/gpu/drm/i915/intel_lrc.c | 6 ++----
> drivers/gpu/drm/i915/intel_ringbuffer.c | 17 ++---------------
> drivers/gpu/drm/i915/intel_ringbuffer.h | 4 ----
> 5 files changed, 6 insertions(+), 41 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 60f6671..8e7418b 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -1156,15 +1156,9 @@ i915_gem_check_wedge(struct i915_gpu_error *error,
> int
> i915_gem_check_olr(struct drm_i915_gem_request *req)
> {
> - int ret;
> -
> WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
>
> - ret = 0;
> - if (req == req->ring->outstanding_lazy_request)
> - ret = i915_add_request(req);
> -
> - return ret;
> + return 0;
> }
>
> static void fake_irq(unsigned long data)
> @@ -2424,8 +2418,6 @@ int __i915_add_request(struct drm_i915_gem_request *request,
> dev_priv = ring->dev->dev_private;
> ringbuf = request->ringbuf;
>
> - WARN_ON(request != ring->outstanding_lazy_request);
> -
> request_start = intel_ring_get_tail(ringbuf);
> /*
> * Emit any outstanding flushes - execbuf can fail to emit the flush
> @@ -2486,7 +2478,6 @@ int __i915_add_request(struct drm_i915_gem_request *request,
> }
>
> trace_i915_gem_request_add(request);
> - ring->outstanding_lazy_request = NULL;
>
> i915_queue_hangcheck(ring->dev);
>
> @@ -2672,9 +2663,6 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
>
> i915_gem_free_request(request);
> }
> -
> - /* This may not have been flushed before the reset, so clean it now */
> - i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
> }
>
> void i915_gem_restore_fences(struct drm_device *dev)
> @@ -3124,8 +3112,6 @@ int i915_gpu_idle(struct drm_device *dev)
> }
> }
>
> - WARN_ON(ring->outstanding_lazy_request);
> -
> ret = intel_ring_idle(ring);
> if (ret)
> return ret;
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 6a703e6..0eae592 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1571,10 +1571,8 @@ err:
> * must be freed again. If it was submitted then it is being tracked
> * on the active request list and no clean up is required here.
> */
> - if (ret && params->request) {
> + if (ret && params->request)
> i915_gem_request_unreference(params->request);
> - ring->outstanding_lazy_request = NULL;
> - }
>
> mutex_unlock(&dev->struct_mutex);
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 2911cf6..db63ea0 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -1032,8 +1032,7 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> if (!req_out)
> return -EINVAL;
>
> - if ((*req_out = ring->outstanding_lazy_request) != NULL)
> - return 0;
> + *req_out = NULL;
>
> request = kzalloc(sizeof(*request), GFP_KERNEL);
> if (request == NULL)
> @@ -1067,7 +1066,7 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> i915_gem_context_reference(request->ctx);
> request->ringbuf = ctx->engine[ring->id].ringbuf;
>
> - *req_out = ring->outstanding_lazy_request = request;
> + *req_out = request;
> return 0;
> }
>
> @@ -1393,7 +1392,6 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *ring)
>
> intel_logical_ring_stop(ring);
> WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
> - i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
>
> if (ring->cleanup)
> ring->cleanup(ring);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 5eef02e..85daa18 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -2034,7 +2034,6 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
>
> intel_unpin_ringbuffer_obj(ringbuf);
> intel_destroy_ringbuffer_obj(ringbuf);
> - i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
>
> if (ring->cleanup)
> ring->cleanup(ring);
> @@ -2153,15 +2152,6 @@ static int intel_wrap_ring_buffer(struct intel_engine_cs *ring)
> int intel_ring_idle(struct intel_engine_cs *ring)
> {
> struct drm_i915_gem_request *req;
> - int ret;
> -
> - /* We need to add any requests required to flush the objects and ring */
> - WARN_ON(ring->outstanding_lazy_request);
> - if (ring->outstanding_lazy_request) {
> - ret = i915_add_request(ring->outstanding_lazy_request);
> - if (ret)
> - return ret;
> - }
>
> /* Wait upon the last request to be completed */
> if (list_empty(&ring->request_list))
> @@ -2186,8 +2176,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring,
> if (!req_out)
> return -EINVAL;
>
> - if ((*req_out = ring->outstanding_lazy_request) != NULL)
> - return 0;
> + *req_out = NULL;
>
> request = kzalloc(sizeof(*request), GFP_KERNEL);
> if (request == NULL)
> @@ -2206,7 +2195,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring,
> return ret;
> }
>
> - *req_out = ring->outstanding_lazy_request = request;
> + *req_out = request;
> return 0;
> }
>
> @@ -2281,8 +2270,6 @@ void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno)
> struct drm_device *dev = ring->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
>
> - BUG_ON(ring->outstanding_lazy_request);
> -
> if (INTEL_INFO(dev)->gen == 6 || INTEL_INFO(dev)->gen == 7) {
> I915_WRITE(RING_SYNC_0(ring->mmio_base), 0);
> I915_WRITE(RING_SYNC_1(ring->mmio_base), 0);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 3b0261f..d2c6427 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -258,10 +258,6 @@ struct intel_engine_cs {
> */
> struct list_head request_list;
>
> - /**
> - * Do we have some not yet emitted requests outstanding?
> - */
> - struct drm_i915_gem_request *outstanding_lazy_request;
> bool gpu_caches_dirty;
> bool fbc_dirty;
>
>
Since we're removing the i915_add_request from i915_check_olr and
thereby removing the OLR emission the following comment at
i915_gem_object_flush_active is no longer valid:
/**
* Ensures that an object will eventually get non-busy by
flushing any required
* write domains, emitting any outstanding lazy request and
retiring and
* completed requests.
*/
static int
i915_gem_object_flush_active(struct drm_i915_gem_object *obj)
{
struct intel_engine_cs *ring;
int ret;
if (obj->active) {
ring =
i915_gem_request_get_ring(obj->last_read_req);
ret = i915_gem_check_olr(obj->last_read_req);
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 52/53] drm/i915: Remove the now obsolete 'outstanding_lazy_request'
2015-03-09 23:51 ` Tomas Elf
@ 2015-03-10 10:18 ` Daniel Vetter
2015-03-13 13:32 ` John Harrison
0 siblings, 1 reply; 234+ messages in thread
From: Daniel Vetter @ 2015-03-10 10:18 UTC (permalink / raw)
To: Tomas Elf; +Cc: Intel-GFX
On Mon, Mar 09, 2015 at 11:51:26PM +0000, Tomas Elf wrote:
> On 19/02/2015 17:18, John.C.Harrison@Intel.com wrote:
> >From: John Harrison <John.C.Harrison@Intel.com>
> >
> >The outstanding_lazy_request is no longer used anywhere in the driver.
> >Everything that was looking at it now has a request explicitly passed in from on
> >high. Everything that was relying upon behind the scenes is now explicitly
> >creating/passing/submitting it's own private request. Thus the OLR can be
> >removed.
> >
>
> "Everything that was relying upon behind the scenes is now explicitly
> creating/passing/submitting it's ..."
> --->
> "Everything that was relying on it behind the scenes is now explicitly
> creating/passing/submitting its ..." ?
>
>
> >For: VIZ-5115
> >Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> >---
> > drivers/gpu/drm/i915/i915_gem.c | 16 +---------------
> > drivers/gpu/drm/i915/i915_gem_execbuffer.c | 4 +---
> > drivers/gpu/drm/i915/intel_lrc.c | 6 ++----
> > drivers/gpu/drm/i915/intel_ringbuffer.c | 17 ++---------------
> > drivers/gpu/drm/i915/intel_ringbuffer.h | 4 ----
> > 5 files changed, 6 insertions(+), 41 deletions(-)
> >
> >diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> >index 60f6671..8e7418b 100644
> >--- a/drivers/gpu/drm/i915/i915_gem.c
> >+++ b/drivers/gpu/drm/i915/i915_gem.c
> >@@ -1156,15 +1156,9 @@ i915_gem_check_wedge(struct i915_gpu_error *error,
> > int
> > i915_gem_check_olr(struct drm_i915_gem_request *req)
> > {
> >- int ret;
> >-
> > WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
> >
> >- ret = 0;
> >- if (req == req->ring->outstanding_lazy_request)
> >- ret = i915_add_request(req);
> >-
> >- return ret;
> >+ return 0;
> > }
> >
> > static void fake_irq(unsigned long data)
> >@@ -2424,8 +2418,6 @@ int __i915_add_request(struct drm_i915_gem_request *request,
> > dev_priv = ring->dev->dev_private;
> > ringbuf = request->ringbuf;
> >
> >- WARN_ON(request != ring->outstanding_lazy_request);
> >-
> > request_start = intel_ring_get_tail(ringbuf);
> > /*
> > * Emit any outstanding flushes - execbuf can fail to emit the flush
> >@@ -2486,7 +2478,6 @@ int __i915_add_request(struct drm_i915_gem_request *request,
> > }
> >
> > trace_i915_gem_request_add(request);
> >- ring->outstanding_lazy_request = NULL;
> >
> > i915_queue_hangcheck(ring->dev);
> >
> >@@ -2672,9 +2663,6 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
> >
> > i915_gem_free_request(request);
> > }
> >-
> >- /* This may not have been flushed before the reset, so clean it now */
> >- i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
> > }
> >
> > void i915_gem_restore_fences(struct drm_device *dev)
> >@@ -3124,8 +3112,6 @@ int i915_gpu_idle(struct drm_device *dev)
> > }
> > }
> >
> >- WARN_ON(ring->outstanding_lazy_request);
> >-
> > ret = intel_ring_idle(ring);
> > if (ret)
> > return ret;
> >diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> >index 6a703e6..0eae592 100644
> >--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> >+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> >@@ -1571,10 +1571,8 @@ err:
> > * must be freed again. If it was submitted then it is being tracked
> > * on the active request list and no clean up is required here.
> > */
> >- if (ret && params->request) {
> >+ if (ret && params->request)
> > i915_gem_request_unreference(params->request);
> >- ring->outstanding_lazy_request = NULL;
> >- }
> >
> > mutex_unlock(&dev->struct_mutex);
> >
> >diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> >index 2911cf6..db63ea0 100644
> >--- a/drivers/gpu/drm/i915/intel_lrc.c
> >+++ b/drivers/gpu/drm/i915/intel_lrc.c
> >@@ -1032,8 +1032,7 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> > if (!req_out)
> > return -EINVAL;
> >
> >- if ((*req_out = ring->outstanding_lazy_request) != NULL)
> >- return 0;
> >+ *req_out = NULL;
> >
> > request = kzalloc(sizeof(*request), GFP_KERNEL);
> > if (request == NULL)
> >@@ -1067,7 +1066,7 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> > i915_gem_context_reference(request->ctx);
> > request->ringbuf = ctx->engine[ring->id].ringbuf;
> >
> >- *req_out = ring->outstanding_lazy_request = request;
> >+ *req_out = request;
> > return 0;
> > }
> >
> >@@ -1393,7 +1392,6 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *ring)
> >
> > intel_logical_ring_stop(ring);
> > WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
> >- i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
> >
> > if (ring->cleanup)
> > ring->cleanup(ring);
> >diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> >index 5eef02e..85daa18 100644
> >--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> >+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> >@@ -2034,7 +2034,6 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
> >
> > intel_unpin_ringbuffer_obj(ringbuf);
> > intel_destroy_ringbuffer_obj(ringbuf);
> >- i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
> >
> > if (ring->cleanup)
> > ring->cleanup(ring);
> >@@ -2153,15 +2152,6 @@ static int intel_wrap_ring_buffer(struct intel_engine_cs *ring)
> > int intel_ring_idle(struct intel_engine_cs *ring)
> > {
> > struct drm_i915_gem_request *req;
> >- int ret;
> >-
> >- /* We need to add any requests required to flush the objects and ring */
> >- WARN_ON(ring->outstanding_lazy_request);
> >- if (ring->outstanding_lazy_request) {
> >- ret = i915_add_request(ring->outstanding_lazy_request);
> >- if (ret)
> >- return ret;
> >- }
> >
> > /* Wait upon the last request to be completed */
> > if (list_empty(&ring->request_list))
> >@@ -2186,8 +2176,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring,
> > if (!req_out)
> > return -EINVAL;
> >
> >- if ((*req_out = ring->outstanding_lazy_request) != NULL)
> >- return 0;
> >+ *req_out = NULL;
> >
> > request = kzalloc(sizeof(*request), GFP_KERNEL);
> > if (request == NULL)
> >@@ -2206,7 +2195,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring,
> > return ret;
> > }
> >
> >- *req_out = ring->outstanding_lazy_request = request;
> >+ *req_out = request;
> > return 0;
> > }
> >
> >@@ -2281,8 +2270,6 @@ void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno)
> > struct drm_device *dev = ring->dev;
> > struct drm_i915_private *dev_priv = dev->dev_private;
> >
> >- BUG_ON(ring->outstanding_lazy_request);
> >-
> > if (INTEL_INFO(dev)->gen == 6 || INTEL_INFO(dev)->gen == 7) {
> > I915_WRITE(RING_SYNC_0(ring->mmio_base), 0);
> > I915_WRITE(RING_SYNC_1(ring->mmio_base), 0);
> >diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> >index 3b0261f..d2c6427 100644
> >--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> >+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> >@@ -258,10 +258,6 @@ struct intel_engine_cs {
> > */
> > struct list_head request_list;
> >
> >- /**
> >- * Do we have some not yet emitted requests outstanding?
> >- */
> >- struct drm_i915_gem_request *outstanding_lazy_request;
> > bool gpu_caches_dirty;
> > bool fbc_dirty;
> >
> >
>
> Since we're removing the i915_add_request from i915_check_olr and thereby
> removing the OLR emission the following comment at
> i915_gem_object_flush_active is no longer valid:
>
> /**
> * Ensures that an object will eventually get non-busy by flushing
> any required
> * write domains, emitting any outstanding lazy request and retiring
> and
> * completed requests.
> */
> static int
> i915_gem_object_flush_active(struct drm_i915_gem_object *obj)
> {
> struct intel_engine_cs *ring;
> int ret;
>
> if (obj->active) {
> ring =
> i915_gem_request_get_ring(obj->last_read_req);
> ret = i915_gem_check_olr(obj->last_read_req);
Nice catch! On top of that the int return value is no longer needed, so a
follow-up patch should simplify it to void.
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 52/53] drm/i915: Remove the now obsolete 'outstanding_lazy_request'
2015-03-10 10:18 ` Daniel Vetter
@ 2015-03-13 13:32 ` John Harrison
2015-03-13 17:09 ` Daniel Vetter
0 siblings, 1 reply; 234+ messages in thread
From: John Harrison @ 2015-03-13 13:32 UTC (permalink / raw)
To: Daniel Vetter, Tomas Elf; +Cc: Intel-GFX
On 10/03/2015 10:18, Daniel Vetter wrote:
> On Mon, Mar 09, 2015 at 11:51:26PM +0000, Tomas Elf wrote:
>> On 19/02/2015 17:18, John.C.Harrison@Intel.com wrote:
>>> From: John Harrison <John.C.Harrison@Intel.com>
>>>
>>> The outstanding_lazy_request is no longer used anywhere in the driver.
>>> Everything that was looking at it now has a request explicitly passed in from on
>>> high. Everything that was relying upon behind the scenes is now explicitly
>>> creating/passing/submitting it's own private request. Thus the OLR can be
>>> removed.
>>>
>> "Everything that was relying upon behind the scenes is now explicitly
>> creating/passing/submitting it's ..."
>> --->
>> "Everything that was relying on it behind the scenes is now explicitly
>> creating/passing/submitting its ..." ?
>>
>>
>>> For: VIZ-5115
>>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
>>> ---
>>> drivers/gpu/drm/i915/i915_gem.c | 16 +---------------
>>> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 4 +---
>>> drivers/gpu/drm/i915/intel_lrc.c | 6 ++----
>>> drivers/gpu/drm/i915/intel_ringbuffer.c | 17 ++---------------
>>> drivers/gpu/drm/i915/intel_ringbuffer.h | 4 ----
>>> 5 files changed, 6 insertions(+), 41 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
>>> index 60f6671..8e7418b 100644
>>> --- a/drivers/gpu/drm/i915/i915_gem.c
>>> +++ b/drivers/gpu/drm/i915/i915_gem.c
>>> @@ -1156,15 +1156,9 @@ i915_gem_check_wedge(struct i915_gpu_error *error,
>>> int
>>> i915_gem_check_olr(struct drm_i915_gem_request *req)
>>> {
>>> - int ret;
>>> -
>>> WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
>>>
>>> - ret = 0;
>>> - if (req == req->ring->outstanding_lazy_request)
>>> - ret = i915_add_request(req);
>>> -
>>> - return ret;
>>> + return 0;
>>> }
>>>
>>> static void fake_irq(unsigned long data)
>>> @@ -2424,8 +2418,6 @@ int __i915_add_request(struct drm_i915_gem_request *request,
>>> dev_priv = ring->dev->dev_private;
>>> ringbuf = request->ringbuf;
>>>
>>> - WARN_ON(request != ring->outstanding_lazy_request);
>>> -
>>> request_start = intel_ring_get_tail(ringbuf);
>>> /*
>>> * Emit any outstanding flushes - execbuf can fail to emit the flush
>>> @@ -2486,7 +2478,6 @@ int __i915_add_request(struct drm_i915_gem_request *request,
>>> }
>>>
>>> trace_i915_gem_request_add(request);
>>> - ring->outstanding_lazy_request = NULL;
>>>
>>> i915_queue_hangcheck(ring->dev);
>>>
>>> @@ -2672,9 +2663,6 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
>>>
>>> i915_gem_free_request(request);
>>> }
>>> -
>>> - /* This may not have been flushed before the reset, so clean it now */
>>> - i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
>>> }
>>>
>>> void i915_gem_restore_fences(struct drm_device *dev)
>>> @@ -3124,8 +3112,6 @@ int i915_gpu_idle(struct drm_device *dev)
>>> }
>>> }
>>>
>>> - WARN_ON(ring->outstanding_lazy_request);
>>> -
>>> ret = intel_ring_idle(ring);
>>> if (ret)
>>> return ret;
>>> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>> index 6a703e6..0eae592 100644
>>> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
>>> @@ -1571,10 +1571,8 @@ err:
>>> * must be freed again. If it was submitted then it is being tracked
>>> * on the active request list and no clean up is required here.
>>> */
>>> - if (ret && params->request) {
>>> + if (ret && params->request)
>>> i915_gem_request_unreference(params->request);
>>> - ring->outstanding_lazy_request = NULL;
>>> - }
>>>
>>> mutex_unlock(&dev->struct_mutex);
>>>
>>> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
>>> index 2911cf6..db63ea0 100644
>>> --- a/drivers/gpu/drm/i915/intel_lrc.c
>>> +++ b/drivers/gpu/drm/i915/intel_lrc.c
>>> @@ -1032,8 +1032,7 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
>>> if (!req_out)
>>> return -EINVAL;
>>>
>>> - if ((*req_out = ring->outstanding_lazy_request) != NULL)
>>> - return 0;
>>> + *req_out = NULL;
>>>
>>> request = kzalloc(sizeof(*request), GFP_KERNEL);
>>> if (request == NULL)
>>> @@ -1067,7 +1066,7 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
>>> i915_gem_context_reference(request->ctx);
>>> request->ringbuf = ctx->engine[ring->id].ringbuf;
>>>
>>> - *req_out = ring->outstanding_lazy_request = request;
>>> + *req_out = request;
>>> return 0;
>>> }
>>>
>>> @@ -1393,7 +1392,6 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *ring)
>>>
>>> intel_logical_ring_stop(ring);
>>> WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
>>> - i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
>>>
>>> if (ring->cleanup)
>>> ring->cleanup(ring);
>>> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
>>> index 5eef02e..85daa18 100644
>>> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
>>> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
>>> @@ -2034,7 +2034,6 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
>>>
>>> intel_unpin_ringbuffer_obj(ringbuf);
>>> intel_destroy_ringbuffer_obj(ringbuf);
>>> - i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
>>>
>>> if (ring->cleanup)
>>> ring->cleanup(ring);
>>> @@ -2153,15 +2152,6 @@ static int intel_wrap_ring_buffer(struct intel_engine_cs *ring)
>>> int intel_ring_idle(struct intel_engine_cs *ring)
>>> {
>>> struct drm_i915_gem_request *req;
>>> - int ret;
>>> -
>>> - /* We need to add any requests required to flush the objects and ring */
>>> - WARN_ON(ring->outstanding_lazy_request);
>>> - if (ring->outstanding_lazy_request) {
>>> - ret = i915_add_request(ring->outstanding_lazy_request);
>>> - if (ret)
>>> - return ret;
>>> - }
>>>
>>> /* Wait upon the last request to be completed */
>>> if (list_empty(&ring->request_list))
>>> @@ -2186,8 +2176,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring,
>>> if (!req_out)
>>> return -EINVAL;
>>>
>>> - if ((*req_out = ring->outstanding_lazy_request) != NULL)
>>> - return 0;
>>> + *req_out = NULL;
>>>
>>> request = kzalloc(sizeof(*request), GFP_KERNEL);
>>> if (request == NULL)
>>> @@ -2206,7 +2195,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring,
>>> return ret;
>>> }
>>>
>>> - *req_out = ring->outstanding_lazy_request = request;
>>> + *req_out = request;
>>> return 0;
>>> }
>>>
>>> @@ -2281,8 +2270,6 @@ void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno)
>>> struct drm_device *dev = ring->dev;
>>> struct drm_i915_private *dev_priv = dev->dev_private;
>>>
>>> - BUG_ON(ring->outstanding_lazy_request);
>>> -
>>> if (INTEL_INFO(dev)->gen == 6 || INTEL_INFO(dev)->gen == 7) {
>>> I915_WRITE(RING_SYNC_0(ring->mmio_base), 0);
>>> I915_WRITE(RING_SYNC_1(ring->mmio_base), 0);
>>> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
>>> index 3b0261f..d2c6427 100644
>>> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
>>> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
>>> @@ -258,10 +258,6 @@ struct intel_engine_cs {
>>> */
>>> struct list_head request_list;
>>>
>>> - /**
>>> - * Do we have some not yet emitted requests outstanding?
>>> - */
>>> - struct drm_i915_gem_request *outstanding_lazy_request;
>>> bool gpu_caches_dirty;
>>> bool fbc_dirty;
>>>
>>>
>> Since we're removing the i915_add_request from i915_check_olr and thereby
>> removing the OLR emission the following comment at
>> i915_gem_object_flush_active is no longer valid:
>>
>> /**
>> * Ensures that an object will eventually get non-busy by flushing
>> any required
>> * write domains, emitting any outstanding lazy request and retiring
>> and
>> * completed requests.
>> */
>> static int
>> i915_gem_object_flush_active(struct drm_i915_gem_object *obj)
>> {
>> struct intel_engine_cs *ring;
>> int ret;
>>
>> if (obj->active) {
>> ring =
>> i915_gem_request_get_ring(obj->last_read_req);
>> ret = i915_gem_check_olr(obj->last_read_req);
> Nice catch! On top of that the int return value is no longer needed, so a
> follow-up patch should simplify it to void.
> -Daniel
The comment also talks about flushing write domains but there is no
obvious flush call. All it does is the check_olr (which is now a no-op)
and the retire (which won't do anything unless the request has already
completed). So is there any need for this function at all anymore? Or
should it just be removed and replaced with a call to retire instead?
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 52/53] drm/i915: Remove the now obsolete 'outstanding_lazy_request'
2015-03-13 13:32 ` John Harrison
@ 2015-03-13 17:09 ` Daniel Vetter
0 siblings, 0 replies; 234+ messages in thread
From: Daniel Vetter @ 2015-03-13 17:09 UTC (permalink / raw)
To: John Harrison; +Cc: Intel-GFX
On Fri, Mar 13, 2015 at 01:32:38PM +0000, John Harrison wrote:
> On 10/03/2015 10:18, Daniel Vetter wrote:
> >On Mon, Mar 09, 2015 at 11:51:26PM +0000, Tomas Elf wrote:
> >>On 19/02/2015 17:18, John.C.Harrison@Intel.com wrote:
> >>>diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> >>>index 3b0261f..d2c6427 100644
> >>>--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> >>>+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> >>>@@ -258,10 +258,6 @@ struct intel_engine_cs {
> >>> */
> >>> struct list_head request_list;
> >>>
> >>>- /**
> >>>- * Do we have some not yet emitted requests outstanding?
> >>>- */
> >>>- struct drm_i915_gem_request *outstanding_lazy_request;
> >>> bool gpu_caches_dirty;
> >>> bool fbc_dirty;
> >>>
> >>>
> >>Since we're removing the i915_add_request from i915_check_olr and thereby
> >>removing the OLR emission the following comment at
> >>i915_gem_object_flush_active is no longer valid:
> >>
> >> /**
> >> * Ensures that an object will eventually get non-busy by flushing
> >>any required
> >> * write domains, emitting any outstanding lazy request and retiring
> >>and
> >> * completed requests.
> >> */
> >> static int
> >> i915_gem_object_flush_active(struct drm_i915_gem_object *obj)
> >> {
> >> struct intel_engine_cs *ring;
> >> int ret;
> >>
> >> if (obj->active) {
> >> ring =
> >>i915_gem_request_get_ring(obj->last_read_req);
> >> ret = i915_gem_check_olr(obj->last_read_req);
> >Nice catch! On top of that the int return value is no longer needed, so a
> >follow-up patch should simplify it to void.
> >-Daniel
>
> The comment also talks about flushing write domains but there is no obvious
> flush call. All it does is the check_olr (which is now a no-op) and the
> retire (which won't do anything unless the request has already completed).
> So is there any need for this function at all anymore? Or should it just be
> removed and replaced with a call to retire instead?
That's historical baggage - way back we've done lazy cache-flushing, which
mean on readback you might have needed to flush caches first. Massive case
of premature optimization, the comment is just plainly outdated. See
commit 65ce3027415d4dc9ee18ef0a135214b4fb76730b
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri Jul 20 12:41:02 2012 +0100
drm/i915: Remove the defunct flushing list
and
commit cc889e0f6ce6a63c62db17d702ecfed86d58083f
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed Jun 13 20:45:19 2012 +0200
drm/i915: disable flushing_list/gpu_write_list
You can savely remove the comment (maybe with the above commits referenced
in the commit message).
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 53/53] drm/i915: Move the request/file and request/pid association to creation time
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (51 preceding siblings ...)
2015-02-19 17:18 ` [PATCH 52/53] drm/i915: Remove the now obsolete 'outstanding_lazy_request' John.C.Harrison
@ 2015-02-19 17:18 ` John.C.Harrison
2015-03-10 0:12 ` Tomas Elf
2015-03-05 13:57 ` [PATCH 54/56] drm/i915: Rename 'do_execbuf' to 'execbuf_submit' John.C.Harrison
2015-03-05 14:03 ` [PATCH 01/53] drm/i915: Remove ironlake rc6 support John.C.Harrison
54 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-02-19 17:18 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
In _i915_add_request(), the request is associated with a userland client.
Specifically it is linked to the 'file' structure and the current user process
is recorded. One problem here is that the current user process is not
necessarily the same as when the request was submitted to the driver. This is
especially true when the GPU scheduler arrives and decouples driver submission
from hardware submission. Note also that it is only in the case where the add
request comes from an execbuff call that there is a client to associate. Any
other add request call is kernel only so does not need to do it.
This patch moves the client association into a separate function. This is then
called from the execbuffer code path itself at a sensible time. It also removes
the now redundant 'file' pointer from the add request parameter list.
An extra cleanup of the client association is also added to the request clean up
code for the eventuality where the request is killed after association but
before being submitted (e.g. due to out of memory error somewhere). Once the
submission has happened, the request is on the request list and the regular
request list removal will clear the association. Note that this still needs to
happen at this point in time because the request might be kept floating around
much longer (due to someone holding a reference count) and the client should not
be worrying about this request after it has been retired.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 8 +++--
drivers/gpu/drm/i915/i915_gem.c | 49 +++++++++++++++++++---------
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 7 ++--
3 files changed, 44 insertions(+), 20 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 3955bef..4a9248f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2199,6 +2199,9 @@ struct drm_i915_gem_request {
};
void i915_gem_request_free(struct kref *req_ref);
+void i915_gem_request_remove_from_client(struct drm_i915_gem_request *request);
+int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
+ struct drm_file *file);
static inline uint32_t
i915_gem_request_get_seqno(struct drm_i915_gem_request *req)
@@ -2831,13 +2834,12 @@ void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
int __must_check i915_gpu_idle(struct drm_device *dev);
int __must_check i915_gem_suspend(struct drm_device *dev);
int __i915_add_request(struct drm_i915_gem_request *req,
- struct drm_file *file,
struct drm_i915_gem_object *batch_obj,
bool flush_caches);
#define i915_add_request(req) \
- __i915_add_request(req, NULL, NULL, true)
+ __i915_add_request(req, NULL, true)
#define i915_add_request_no_flush(req) \
- __i915_add_request(req, NULL, NULL, false)
+ __i915_add_request(req, NULL, false)
int __i915_wait_request(struct drm_i915_gem_request *req,
unsigned reset_counter,
bool interruptible,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 8e7418b..660518d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2401,7 +2401,6 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
}
int __i915_add_request(struct drm_i915_gem_request *request,
- struct drm_file *file,
struct drm_i915_gem_object *obj,
bool flush_caches)
{
@@ -2463,19 +2462,6 @@ int __i915_add_request(struct drm_i915_gem_request *request,
request->emitted_jiffies = jiffies;
list_add_tail(&request->list, &ring->request_list);
- request->file_priv = NULL;
-
- if (file) {
- struct drm_i915_file_private *file_priv = file->driver_priv;
-
- spin_lock(&file_priv->mm.lock);
- request->file_priv = file_priv;
- list_add_tail(&request->client_list,
- &file_priv->mm.request_list);
- spin_unlock(&file_priv->mm.lock);
-
- request->pid = get_pid(task_pid(current));
- }
trace_i915_gem_request_add(request);
@@ -2490,7 +2476,34 @@ int __i915_add_request(struct drm_i915_gem_request *request,
return 0;
}
-static inline void
+int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
+ struct drm_file *file)
+{
+ struct drm_i915_private *dev_private;
+ struct drm_i915_file_private *file_priv;
+
+ WARN_ON(!req || !file || req->file_priv);
+
+ if (!req || !file)
+ return -EINVAL;
+
+ if (req->file_priv)
+ return -EINVAL;
+
+ dev_private = req->ring->dev->dev_private;
+ file_priv = file->driver_priv;
+
+ spin_lock(&file_priv->mm.lock);
+ req->file_priv = file_priv;
+ list_add_tail(&req->client_list, &file_priv->mm.request_list);
+ spin_unlock(&file_priv->mm.lock);
+
+ req->pid = get_pid(task_pid(current));
+
+ return 0;
+}
+
+inline void
i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
{
struct drm_i915_file_private *file_priv = request->file_priv;
@@ -2565,6 +2578,9 @@ void i915_gem_request_free(struct kref *req_ref)
typeof(*req), ref);
struct intel_context *ctx = req->ctx;
+ if (req->file_priv)
+ i915_gem_request_remove_from_client(req);
+
if (ctx) {
if (i915.enable_execlists) {
struct intel_engine_cs *ring = req->ring;
@@ -4120,6 +4136,9 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
if (time_after_eq(request->emitted_jiffies, recent_enough))
break;
+ if (!request->emitted_jiffies)
+ continue;
+
target = request;
}
reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 0eae592..739aaeb 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -996,8 +996,7 @@ i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
params->ring->gpu_caches_dirty = true;
/* Add a breadcrumb for the completion of the batch buffer */
- return __i915_add_request(params->request, params->file,
- params->batch_obj, true);
+ return __i915_add_request(params->request, params->batch_obj, true);
}
static int
@@ -1537,6 +1536,10 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
if (ret)
goto err;
+ ret = i915_gem_request_add_to_client(params->request, file);
+ if (ret)
+ goto err;
+
/*
* Save assorted stuff away to pass through to *_submission().
* NB: This data should be 'persistent' and not local as it will
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 53/53] drm/i915: Move the request/file and request/pid association to creation time
2015-02-19 17:18 ` [PATCH 53/53] drm/i915: Move the request/file and request/pid association to creation time John.C.Harrison
@ 2015-03-10 0:12 ` Tomas Elf
0 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-10 0:12 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 19/02/2015 17:18, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> In _i915_add_request(), the request is associated with a userland client.
> Specifically it is linked to the 'file' structure and the current user process
> is recorded. One problem here is that the current user process is not
> necessarily the same as when the request was submitted to the driver. This is
> especially true when the GPU scheduler arrives and decouples driver submission
> from hardware submission. Note also that it is only in the case where the add
> request comes from an execbuff call that there is a client to associate. Any
> other add request call is kernel only so does not need to do it.
>
> This patch moves the client association into a separate function. This is then
> called from the execbuffer code path itself at a sensible time. It also removes
> the now redundant 'file' pointer from the add request parameter list.
>
> An extra cleanup of the client association is also added to the request clean up
> code for the eventuality where the request is killed after association but
> before being submitted (e.g. due to out of memory error somewhere). Once the
> submission has happened, the request is on the request list and the regular
> request list removal will clear the association. Note that this still needs to
> happen at this point in time because the request might be kept floating around
> much longer (due to someone holding a reference count) and the client should not
> be worrying about this request after it has been retired.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 8 +++--
> drivers/gpu/drm/i915/i915_gem.c | 49 +++++++++++++++++++---------
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 7 ++--
> 3 files changed, 44 insertions(+), 20 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 3955bef..4a9248f 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2199,6 +2199,9 @@ struct drm_i915_gem_request {
> };
>
> void i915_gem_request_free(struct kref *req_ref);
> +void i915_gem_request_remove_from_client(struct drm_i915_gem_request *request);
> +int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
> + struct drm_file *file);
>
> static inline uint32_t
> i915_gem_request_get_seqno(struct drm_i915_gem_request *req)
> @@ -2831,13 +2834,12 @@ void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
> int __must_check i915_gpu_idle(struct drm_device *dev);
> int __must_check i915_gem_suspend(struct drm_device *dev);
> int __i915_add_request(struct drm_i915_gem_request *req,
> - struct drm_file *file,
> struct drm_i915_gem_object *batch_obj,
> bool flush_caches);
> #define i915_add_request(req) \
> - __i915_add_request(req, NULL, NULL, true)
> + __i915_add_request(req, NULL, true)
> #define i915_add_request_no_flush(req) \
> - __i915_add_request(req, NULL, NULL, false)
> + __i915_add_request(req, NULL, false)
> int __i915_wait_request(struct drm_i915_gem_request *req,
> unsigned reset_counter,
> bool interruptible,
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 8e7418b..660518d 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2401,7 +2401,6 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
> }
>
> int __i915_add_request(struct drm_i915_gem_request *request,
> - struct drm_file *file,
> struct drm_i915_gem_object *obj,
> bool flush_caches)
> {
> @@ -2463,19 +2462,6 @@ int __i915_add_request(struct drm_i915_gem_request *request,
>
> request->emitted_jiffies = jiffies;
> list_add_tail(&request->list, &ring->request_list);
> - request->file_priv = NULL;
> -
> - if (file) {
> - struct drm_i915_file_private *file_priv = file->driver_priv;
> -
> - spin_lock(&file_priv->mm.lock);
> - request->file_priv = file_priv;
> - list_add_tail(&request->client_list,
> - &file_priv->mm.request_list);
> - spin_unlock(&file_priv->mm.lock);
> -
> - request->pid = get_pid(task_pid(current));
> - }
>
> trace_i915_gem_request_add(request);
>
> @@ -2490,7 +2476,34 @@ int __i915_add_request(struct drm_i915_gem_request *request,
> return 0;
> }
>
> -static inline void
> +int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
> + struct drm_file *file)
> +{
> + struct drm_i915_private *dev_private;
> + struct drm_i915_file_private *file_priv;
> +
> + WARN_ON(!req || !file || req->file_priv);
> +
> + if (!req || !file)
> + return -EINVAL;
> +
> + if (req->file_priv)
> + return -EINVAL;
> +
> + dev_private = req->ring->dev->dev_private;
> + file_priv = file->driver_priv;
> +
> + spin_lock(&file_priv->mm.lock);
> + req->file_priv = file_priv;
> + list_add_tail(&req->client_list, &file_priv->mm.request_list);
> + spin_unlock(&file_priv->mm.lock);
> +
> + req->pid = get_pid(task_pid(current));
> +
> + return 0;
> +}
> +
> +inline void
> i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
> {
> struct drm_i915_file_private *file_priv = request->file_priv;
> @@ -2565,6 +2578,9 @@ void i915_gem_request_free(struct kref *req_ref)
> typeof(*req), ref);
> struct intel_context *ctx = req->ctx;
>
> + if (req->file_priv)
> + i915_gem_request_remove_from_client(req);
> +
> if (ctx) {
> if (i915.enable_execlists) {
> struct intel_engine_cs *ring = req->ring;
> @@ -4120,6 +4136,9 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
> if (time_after_eq(request->emitted_jiffies, recent_enough))
> break;
>
> + if (!request->emitted_jiffies)
> + continue;
> +
Please add a comment clarifying the purpose of the emitted_jiffies check
above.
Thanks,
Tomas
> target = request;
> }
> reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 0eae592..739aaeb 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -996,8 +996,7 @@ i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
> params->ring->gpu_caches_dirty = true;
>
> /* Add a breadcrumb for the completion of the batch buffer */
> - return __i915_add_request(params->request, params->file,
> - params->batch_obj, true);
> + return __i915_add_request(params->request, params->batch_obj, true);
> }
>
> static int
> @@ -1537,6 +1536,10 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> if (ret)
> goto err;
>
> + ret = i915_gem_request_add_to_client(params->request, file);
> + if (ret)
> + goto err;
> +
> /*
> * Save assorted stuff away to pass through to *_submission().
> * NB: This data should be 'persistent' and not local as it will
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 54/56] drm/i915: Rename 'do_execbuf' to 'execbuf_submit'
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (52 preceding siblings ...)
2015-02-19 17:18 ` [PATCH 53/53] drm/i915: Move the request/file and request/pid association to creation time John.C.Harrison
@ 2015-03-05 13:57 ` John.C.Harrison
2015-03-05 13:57 ` [PATCH 55/56] drm/i915: Remove 'faked' request from LRC submission John.C.Harrison
` (2 more replies)
2015-03-05 14:03 ` [PATCH 01/53] drm/i915: Remove ironlake rc6 support John.C.Harrison
54 siblings, 3 replies; 234+ messages in thread
From: John.C.Harrison @ 2015-03-05 13:57 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The submission portion of the execbuffer code path was abstracted into a
function pointer indirection as part of the legacy vs execlist work. The two
implementation functions are called 'i915_gem_ringbuffer_submission' and
'intel_execlists_submission' but the pointer was called 'do_execbuf'. There is
already a 'i915_gem_do_execbuffer' function (which is what calls the pointer
indirection). The name of the pointer is therefore considered to be backwards
and should be changed.
This patch renames it to 'execbuf_submit' which is hopefully a bit clearer.
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 6 +++---
drivers/gpu/drm/i915/i915_gem.c | 4 ++--
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
3 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7c9e569..4e9a350 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1793,9 +1793,9 @@ struct drm_i915_private {
int (*alloc_request)(struct intel_engine_cs *ring,
struct intel_context *ctx,
struct drm_i915_gem_request **req_out);
- int (*do_execbuf)(struct i915_execbuffer_params *params,
- struct drm_i915_gem_execbuffer2 *args,
- struct list_head *vmas);
+ int (*execbuf_submit)(struct i915_execbuffer_params *params,
+ struct drm_i915_gem_execbuffer2 *args,
+ struct list_head *vmas);
int (*init_rings)(struct drm_device *dev);
void (*cleanup_ring)(struct intel_engine_cs *ring);
void (*stop_ring)(struct intel_engine_cs *ring);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ecff3f7..27abc9d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4928,13 +4928,13 @@ int i915_gem_init(struct drm_device *dev)
if (!i915.enable_execlists) {
dev_priv->gt.alloc_request = intel_ring_alloc_request;
- dev_priv->gt.do_execbuf = i915_gem_ringbuffer_submission;
+ dev_priv->gt.execbuf_submit = i915_gem_ringbuffer_submission;
dev_priv->gt.init_rings = i915_gem_init_rings;
dev_priv->gt.cleanup_ring = intel_cleanup_ring_buffer;
dev_priv->gt.stop_ring = intel_stop_ring_buffer;
} else {
dev_priv->gt.alloc_request = intel_logical_ring_alloc_request;
- dev_priv->gt.do_execbuf = intel_execlists_submission;
+ dev_priv->gt.execbuf_submit = intel_execlists_submission;
dev_priv->gt.init_rings = intel_logical_rings_init;
dev_priv->gt.cleanup_ring = intel_logical_ring_cleanup;
dev_priv->gt.stop_ring = intel_logical_ring_stop;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index dfad66a..d969eb5 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1558,7 +1558,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
params->batch_obj = batch_obj;
params->ctx = ctx;
- ret = dev_priv->gt.do_execbuf(params, args, &eb->vmas);
+ ret = dev_priv->gt.execbuf_submit(params, args, &eb->vmas);
err:
/*
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* [PATCH 55/56] drm/i915: Remove 'faked' request from LRC submission
2015-03-05 13:57 ` [PATCH 54/56] drm/i915: Rename 'do_execbuf' to 'execbuf_submit' John.C.Harrison
@ 2015-03-05 13:57 ` John.C.Harrison
2015-03-05 14:49 ` Daniel Vetter
2015-03-05 13:57 ` [PATCH 56/56] drm/i915: Update a bunch of LRC functions to take requests John.C.Harrison
2015-03-10 23:18 ` [PATCH 54/56] drm/i915: Rename 'do_execbuf' to 'execbuf_submit' Tomas Elf
2 siblings, 1 reply; 234+ messages in thread
From: John.C.Harrison @ 2015-03-05 13:57 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
The LRC submission code requires a request for tracking purposes. It does not
actually require that request to 'complete' it simply uses it for keeping hold
of reference counts on contexts and such like.
In the case where the ring buffer is completely full, the LRC code looks for a
pending request that would free up sufficient space upon completion and waits
for it. If no such request can be found it resorts to simply polling the free
space count until it is big enough. This situation should only occur when the
entire buffer is filled with the request currently being generated. I.e., the
user is trying to submit a single piece of work that is large than the ring
buffer itself (which should be impossible because very large batch buffers don't
consume any more ring buffer space). Before starting to poll, a submit call is
made to make sure that the currently queued up work in the buffer will actually
be submtted and thus the poll will eventually succeed.
The problem here is that the 'official' request cannot be used as that could
lead to multiple LRC submissions being tagged to a single request structure.
Instead, the code fakes up a private request structure and uses that.
This patch moves the faked request allocation higher up in the call stack to the
wait code itself (rather than being at the very lowest submission level). Thus
it is now obvious where the faked request is coming from and why it is
necessary. The patch also replaces it with a call to the official request
allocation code rather than attempting to duplicate that code. This becomes
especially important in the future when the request allocation changes to
accommodate a conversion to struct fence.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_lrc.c | 45 ++++++++++++++++++++++----------------
1 file changed, 26 insertions(+), 19 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 65eea51..1fa36de 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -507,23 +507,11 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
if (to != ring->default_context)
intel_lr_context_pin(ring, to);
- if (!request) {
- /*
- * If there isn't a request associated with this submission,
- * create one as a temporary holder.
- */
- request = kzalloc(sizeof(*request), GFP_KERNEL);
- if (request == NULL)
- return -ENOMEM;
- request->ring = ring;
- request->ctx = to;
- kref_init(&request->ref);
- request->uniq = dev_priv->request_uniq++;
- i915_gem_context_reference(request->ctx);
- } else {
- i915_gem_request_reference(request);
- WARN_ON(to != request->ctx);
- }
+ WARN_ON(!request);
+ WARN_ON(to != request->ctx);
+
+ i915_gem_request_reference(request);
+
request->tail = tail;
intel_runtime_pm_get(dev_priv);
@@ -677,6 +665,7 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
struct intel_engine_cs *ring = ringbuf->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_i915_gem_request *local_req;
unsigned long end;
int ret;
@@ -684,8 +673,23 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
if (ret != -ENOSPC)
return ret;
- /* Force the context submission in case we have been skipping it */
- intel_logical_ring_advance_and_submit(ringbuf, ctx, NULL);
+ /*
+ * Force the context submission in case we have been skipping it.
+ * This requires creating a place holder request so that the LRC
+ * submission can be tracked. Note that if this point has been
+ * reached then it is the current submission that is blocking the
+ * driver and the only course of action is to do a partial send and
+ * wait for it to complete.
+ * Note also that because there is no space left in the ring, it is
+ * not possible to write the request submission prologue (which does
+ * things like update seqno values and trigger completion interrupts).
+ * Thus the request cannot be submitted via i915_add_request() and
+ * can not be waiting on by i915_gem_wait_request().
+ */
+ ret = dev_priv->gt.alloc_request(ring, ctx, &local_req);
+ if (ret)
+ return ret;
+ intel_logical_ring_advance_and_submit(ringbuf, ctx, local_req);
/* With GEM the hangcheck timer should kick us out of the loop,
* leaving it early runs the risk of corrupting GEM state (due
@@ -717,6 +721,9 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
}
} while (1);
+ /* This request is now done with and can be disposed of. */
+ i915_gem_request_unreference(local_req);
+
return ret;
}
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 55/56] drm/i915: Remove 'faked' request from LRC submission
2015-03-05 13:57 ` [PATCH 55/56] drm/i915: Remove 'faked' request from LRC submission John.C.Harrison
@ 2015-03-05 14:49 ` Daniel Vetter
2015-03-11 14:53 ` John Harrison
0 siblings, 1 reply; 234+ messages in thread
From: Daniel Vetter @ 2015-03-05 14:49 UTC (permalink / raw)
To: John.C.Harrison; +Cc: Intel-GFX
On Thu, Mar 05, 2015 at 01:57:31PM +0000, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The LRC submission code requires a request for tracking purposes. It does not
> actually require that request to 'complete' it simply uses it for keeping hold
> of reference counts on contexts and such like.
>
> In the case where the ring buffer is completely full, the LRC code looks for a
> pending request that would free up sufficient space upon completion and waits
> for it. If no such request can be found it resorts to simply polling the free
> space count until it is big enough. This situation should only occur when the
> entire buffer is filled with the request currently being generated. I.e., the
> user is trying to submit a single piece of work that is large than the ring
> buffer itself (which should be impossible because very large batch buffers don't
> consume any more ring buffer space). Before starting to poll, a submit call is
> made to make sure that the currently queued up work in the buffer will actually
> be submtted and thus the poll will eventually succeed.
>
> The problem here is that the 'official' request cannot be used as that could
> lead to multiple LRC submissions being tagged to a single request structure.
> Instead, the code fakes up a private request structure and uses that.
>
> This patch moves the faked request allocation higher up in the call stack to the
> wait code itself (rather than being at the very lowest submission level). Thus
> it is now obvious where the faked request is coming from and why it is
> necessary. The patch also replaces it with a call to the official request
> allocation code rather than attempting to duplicate that code. This becomes
> especially important in the future when the request allocation changes to
> accommodate a conversion to struct fence.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
This is only possible if you pile up tons of olr. Since your patch series
fixes this design issue by removing olr I think we can just put a WARN_ON
in here if this ever happens and bail out with -ELOSTMYMARBLES or
something. And then rip out all this complexity.
Or do I miss something important?
-Daniel
> ---
> drivers/gpu/drm/i915/intel_lrc.c | 45 ++++++++++++++++++++++----------------
> 1 file changed, 26 insertions(+), 19 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 65eea51..1fa36de 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -507,23 +507,11 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
> if (to != ring->default_context)
> intel_lr_context_pin(ring, to);
>
> - if (!request) {
> - /*
> - * If there isn't a request associated with this submission,
> - * create one as a temporary holder.
> - */
> - request = kzalloc(sizeof(*request), GFP_KERNEL);
> - if (request == NULL)
> - return -ENOMEM;
> - request->ring = ring;
> - request->ctx = to;
> - kref_init(&request->ref);
> - request->uniq = dev_priv->request_uniq++;
> - i915_gem_context_reference(request->ctx);
> - } else {
> - i915_gem_request_reference(request);
> - WARN_ON(to != request->ctx);
> - }
> + WARN_ON(!request);
> + WARN_ON(to != request->ctx);
> +
> + i915_gem_request_reference(request);
> +
> request->tail = tail;
>
> intel_runtime_pm_get(dev_priv);
> @@ -677,6 +665,7 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
> struct intel_engine_cs *ring = ringbuf->ring;
> struct drm_device *dev = ring->dev;
> struct drm_i915_private *dev_priv = dev->dev_private;
> + struct drm_i915_gem_request *local_req;
> unsigned long end;
> int ret;
>
> @@ -684,8 +673,23 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
> if (ret != -ENOSPC)
> return ret;
>
> - /* Force the context submission in case we have been skipping it */
> - intel_logical_ring_advance_and_submit(ringbuf, ctx, NULL);
> + /*
> + * Force the context submission in case we have been skipping it.
> + * This requires creating a place holder request so that the LRC
> + * submission can be tracked. Note that if this point has been
> + * reached then it is the current submission that is blocking the
> + * driver and the only course of action is to do a partial send and
> + * wait for it to complete.
> + * Note also that because there is no space left in the ring, it is
> + * not possible to write the request submission prologue (which does
> + * things like update seqno values and trigger completion interrupts).
> + * Thus the request cannot be submitted via i915_add_request() and
> + * can not be waiting on by i915_gem_wait_request().
> + */
> + ret = dev_priv->gt.alloc_request(ring, ctx, &local_req);
> + if (ret)
> + return ret;
> + intel_logical_ring_advance_and_submit(ringbuf, ctx, local_req);
>
> /* With GEM the hangcheck timer should kick us out of the loop,
> * leaving it early runs the risk of corrupting GEM state (due
> @@ -717,6 +721,9 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
> }
> } while (1);
>
> + /* This request is now done with and can be disposed of. */
> + i915_gem_request_unreference(local_req);
> +
> return ret;
> }
>
> --
> 1.7.9.5
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 55/56] drm/i915: Remove 'faked' request from LRC submission
2015-03-05 14:49 ` Daniel Vetter
@ 2015-03-11 14:53 ` John Harrison
2015-03-11 16:14 ` Daniel Vetter
0 siblings, 1 reply; 234+ messages in thread
From: John Harrison @ 2015-03-11 14:53 UTC (permalink / raw)
To: Daniel Vetter; +Cc: Intel-GFX
On 05/03/2015 14:49, Daniel Vetter wrote:
> On Thu, Mar 05, 2015 at 01:57:31PM +0000, John.C.Harrison@Intel.com wrote:
>> From: John Harrison <John.C.Harrison@Intel.com>
>>
>> The LRC submission code requires a request for tracking purposes. It does not
>> actually require that request to 'complete' it simply uses it for keeping hold
>> of reference counts on contexts and such like.
>>
>> In the case where the ring buffer is completely full, the LRC code looks for a
>> pending request that would free up sufficient space upon completion and waits
>> for it. If no such request can be found it resorts to simply polling the free
>> space count until it is big enough. This situation should only occur when the
>> entire buffer is filled with the request currently being generated. I.e., the
>> user is trying to submit a single piece of work that is large than the ring
>> buffer itself (which should be impossible because very large batch buffers don't
>> consume any more ring buffer space). Before starting to poll, a submit call is
>> made to make sure that the currently queued up work in the buffer will actually
>> be submtted and thus the poll will eventually succeed.
>>
>> The problem here is that the 'official' request cannot be used as that could
>> lead to multiple LRC submissions being tagged to a single request structure.
>> Instead, the code fakes up a private request structure and uses that.
>>
>> This patch moves the faked request allocation higher up in the call stack to the
>> wait code itself (rather than being at the very lowest submission level). Thus
>> it is now obvious where the faked request is coming from and why it is
>> necessary. The patch also replaces it with a call to the official request
>> allocation code rather than attempting to duplicate that code. This becomes
>> especially important in the future when the request allocation changes to
>> accommodate a conversion to struct fence.
>>
>> For: VIZ-5115
>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> This is only possible if you pile up tons of olr. Since your patch series
> fixes this design issue by removing olr I think we can just put a WARN_ON
> in here if this ever happens and bail out with -ELOSTMYMARBLES or
> something. And then rip out all this complexity.
>
> Or do I miss something important?
> -Daniel
Yeah, you missed the extremely important bug in the free space
calculation that meant this impossible code path was being hit on a
regular basis. The LRC wait_request code differed from the legacy
wait_request code in the the latter was updated with request->postfix
changes and the former was not. Thus the LRC one would happily find a
request that frees up enough space, wait on it, retire it and then find
there was still not enough space!
New patches to fix the space calculation bug and to completely remove
the polling path will be forth coming...
>> ---
>> drivers/gpu/drm/i915/intel_lrc.c | 45 ++++++++++++++++++++++----------------
>> 1 file changed, 26 insertions(+), 19 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
>> index 65eea51..1fa36de 100644
>> --- a/drivers/gpu/drm/i915/intel_lrc.c
>> +++ b/drivers/gpu/drm/i915/intel_lrc.c
>> @@ -507,23 +507,11 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
>> if (to != ring->default_context)
>> intel_lr_context_pin(ring, to);
>>
>> - if (!request) {
>> - /*
>> - * If there isn't a request associated with this submission,
>> - * create one as a temporary holder.
>> - */
>> - request = kzalloc(sizeof(*request), GFP_KERNEL);
>> - if (request == NULL)
>> - return -ENOMEM;
>> - request->ring = ring;
>> - request->ctx = to;
>> - kref_init(&request->ref);
>> - request->uniq = dev_priv->request_uniq++;
>> - i915_gem_context_reference(request->ctx);
>> - } else {
>> - i915_gem_request_reference(request);
>> - WARN_ON(to != request->ctx);
>> - }
>> + WARN_ON(!request);
>> + WARN_ON(to != request->ctx);
>> +
>> + i915_gem_request_reference(request);
>> +
>> request->tail = tail;
>>
>> intel_runtime_pm_get(dev_priv);
>> @@ -677,6 +665,7 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
>> struct intel_engine_cs *ring = ringbuf->ring;
>> struct drm_device *dev = ring->dev;
>> struct drm_i915_private *dev_priv = dev->dev_private;
>> + struct drm_i915_gem_request *local_req;
>> unsigned long end;
>> int ret;
>>
>> @@ -684,8 +673,23 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
>> if (ret != -ENOSPC)
>> return ret;
>>
>> - /* Force the context submission in case we have been skipping it */
>> - intel_logical_ring_advance_and_submit(ringbuf, ctx, NULL);
>> + /*
>> + * Force the context submission in case we have been skipping it.
>> + * This requires creating a place holder request so that the LRC
>> + * submission can be tracked. Note that if this point has been
>> + * reached then it is the current submission that is blocking the
>> + * driver and the only course of action is to do a partial send and
>> + * wait for it to complete.
>> + * Note also that because there is no space left in the ring, it is
>> + * not possible to write the request submission prologue (which does
>> + * things like update seqno values and trigger completion interrupts).
>> + * Thus the request cannot be submitted via i915_add_request() and
>> + * can not be waiting on by i915_gem_wait_request().
>> + */
>> + ret = dev_priv->gt.alloc_request(ring, ctx, &local_req);
>> + if (ret)
>> + return ret;
>> + intel_logical_ring_advance_and_submit(ringbuf, ctx, local_req);
>>
>> /* With GEM the hangcheck timer should kick us out of the loop,
>> * leaving it early runs the risk of corrupting GEM state (due
>> @@ -717,6 +721,9 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
>> }
>> } while (1);
>>
>> + /* This request is now done with and can be disposed of. */
>> + i915_gem_request_unreference(local_req);
>> +
>> return ret;
>> }
>>
>> --
>> 1.7.9.5
>>
>> _______________________________________________
>> Intel-gfx mailing list
>> Intel-gfx@lists.freedesktop.org
>> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 55/56] drm/i915: Remove 'faked' request from LRC submission
2015-03-11 14:53 ` John Harrison
@ 2015-03-11 16:14 ` Daniel Vetter
2015-03-11 16:44 ` Jesse Barnes
0 siblings, 1 reply; 234+ messages in thread
From: Daniel Vetter @ 2015-03-11 16:14 UTC (permalink / raw)
To: John Harrison; +Cc: Intel-GFX
On Wed, Mar 11, 2015 at 02:53:39PM +0000, John Harrison wrote:
> On 05/03/2015 14:49, Daniel Vetter wrote:
> >On Thu, Mar 05, 2015 at 01:57:31PM +0000, John.C.Harrison@Intel.com wrote:
> >>From: John Harrison <John.C.Harrison@Intel.com>
> >>
> >>The LRC submission code requires a request for tracking purposes. It does not
> >>actually require that request to 'complete' it simply uses it for keeping hold
> >>of reference counts on contexts and such like.
> >>
> >>In the case where the ring buffer is completely full, the LRC code looks for a
> >>pending request that would free up sufficient space upon completion and waits
> >>for it. If no such request can be found it resorts to simply polling the free
> >>space count until it is big enough. This situation should only occur when the
> >>entire buffer is filled with the request currently being generated. I.e., the
> >>user is trying to submit a single piece of work that is large than the ring
> >>buffer itself (which should be impossible because very large batch buffers don't
> >>consume any more ring buffer space). Before starting to poll, a submit call is
> >>made to make sure that the currently queued up work in the buffer will actually
> >>be submtted and thus the poll will eventually succeed.
> >>
> >>The problem here is that the 'official' request cannot be used as that could
> >>lead to multiple LRC submissions being tagged to a single request structure.
> >>Instead, the code fakes up a private request structure and uses that.
> >>
> >>This patch moves the faked request allocation higher up in the call stack to the
> >>wait code itself (rather than being at the very lowest submission level). Thus
> >>it is now obvious where the faked request is coming from and why it is
> >>necessary. The patch also replaces it with a call to the official request
> >>allocation code rather than attempting to duplicate that code. This becomes
> >>especially important in the future when the request allocation changes to
> >>accommodate a conversion to struct fence.
> >>
> >>For: VIZ-5115
> >>Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> >This is only possible if you pile up tons of olr. Since your patch series
> >fixes this design issue by removing olr I think we can just put a WARN_ON
> >in here if this ever happens and bail out with -ELOSTMYMARBLES or
> >something. And then rip out all this complexity.
> >
> >Or do I miss something important?
> >-Daniel
>
> Yeah, you missed the extremely important bug in the free space calculation
> that meant this impossible code path was being hit on a regular basis. The
> LRC wait_request code differed from the legacy wait_request code in the the
> latter was updated with request->postfix changes and the former was not.
> Thus the LRC one would happily find a request that frees up enough space,
> wait on it, retire it and then find there was still not enough space!
>
> New patches to fix the space calculation bug and to completely remove the
> polling path will be forth coming...
Hm, Jesse did dig out a regression where gem_ringfill blows up on
execlist. That igt is specifically to exercise this cornercases. I'm not
sure whith bugzilla Jesse meant, there's two:
https://bugs.freedesktop.org/show_bug.cgi?id=89001
https://bugs.freedesktop.org/show_bug.cgi?id=88865
Can you please check whether your fixes help for those issues two?
Also adding Jesse since he's chasing these atm.
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* Re: [PATCH 55/56] drm/i915: Remove 'faked' request from LRC submission
2015-03-11 16:14 ` Daniel Vetter
@ 2015-03-11 16:44 ` Jesse Barnes
2015-03-11 20:45 ` John Harrison
0 siblings, 1 reply; 234+ messages in thread
From: Jesse Barnes @ 2015-03-11 16:44 UTC (permalink / raw)
To: Daniel Vetter, John Harrison; +Cc: Intel-GFX
On 03/11/2015 09:14 AM, Daniel Vetter wrote:
> On Wed, Mar 11, 2015 at 02:53:39PM +0000, John Harrison wrote:
>> On 05/03/2015 14:49, Daniel Vetter wrote:
>>> On Thu, Mar 05, 2015 at 01:57:31PM +0000, John.C.Harrison@Intel.com wrote:
>>>> From: John Harrison <John.C.Harrison@Intel.com>
>>>>
>>>> The LRC submission code requires a request for tracking purposes. It does not
>>>> actually require that request to 'complete' it simply uses it for keeping hold
>>>> of reference counts on contexts and such like.
>>>>
>>>> In the case where the ring buffer is completely full, the LRC code looks for a
>>>> pending request that would free up sufficient space upon completion and waits
>>>> for it. If no such request can be found it resorts to simply polling the free
>>>> space count until it is big enough. This situation should only occur when the
>>>> entire buffer is filled with the request currently being generated. I.e., the
>>>> user is trying to submit a single piece of work that is large than the ring
>>>> buffer itself (which should be impossible because very large batch buffers don't
>>>> consume any more ring buffer space). Before starting to poll, a submit call is
>>>> made to make sure that the currently queued up work in the buffer will actually
>>>> be submtted and thus the poll will eventually succeed.
>>>>
>>>> The problem here is that the 'official' request cannot be used as that could
>>>> lead to multiple LRC submissions being tagged to a single request structure.
>>>> Instead, the code fakes up a private request structure and uses that.
>>>>
>>>> This patch moves the faked request allocation higher up in the call stack to the
>>>> wait code itself (rather than being at the very lowest submission level). Thus
>>>> it is now obvious where the faked request is coming from and why it is
>>>> necessary. The patch also replaces it with a call to the official request
>>>> allocation code rather than attempting to duplicate that code. This becomes
>>>> especially important in the future when the request allocation changes to
>>>> accommodate a conversion to struct fence.
>>>>
>>>> For: VIZ-5115
>>>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
>>> This is only possible if you pile up tons of olr. Since your patch series
>>> fixes this design issue by removing olr I think we can just put a WARN_ON
>>> in here if this ever happens and bail out with -ELOSTMYMARBLES or
>>> something. And then rip out all this complexity.
>>>
>>> Or do I miss something important?
>>> -Daniel
>>
>> Yeah, you missed the extremely important bug in the free space calculation
>> that meant this impossible code path was being hit on a regular basis. The
>> LRC wait_request code differed from the legacy wait_request code in the the
>> latter was updated with request->postfix changes and the former was not.
>> Thus the LRC one would happily find a request that frees up enough space,
>> wait on it, retire it and then find there was still not enough space!
>>
>> New patches to fix the space calculation bug and to completely remove the
>> polling path will be forth coming...
>
> Hm, Jesse did dig out a regression where gem_ringfill blows up on
> execlist. That igt is specifically to exercise this cornercases. I'm not
> sure whith bugzilla Jesse meant, there's two:
>
> https://bugs.freedesktop.org/show_bug.cgi?id=89001
> https://bugs.freedesktop.org/show_bug.cgi?id=88865
>
> Can you please check whether your fixes help for those issues two?
>
> Also adding Jesse since he's chasing these atm.
Ah cool, sounds related at least. 89001 was the one I looked at
yesterday. The worrying thing was that this bug caused a hard system
hang. Not even the reset button worked... I guess we should have an
HSD for that too so we can root cause the system part of it.
Jesse
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* Re: [PATCH 55/56] drm/i915: Remove 'faked' request from LRC submission
2015-03-11 16:44 ` Jesse Barnes
@ 2015-03-11 20:45 ` John Harrison
0 siblings, 0 replies; 234+ messages in thread
From: John Harrison @ 2015-03-11 20:45 UTC (permalink / raw)
To: Jesse Barnes, Daniel Vetter; +Cc: Intel-GFX
On 11/03/2015 16:44, Jesse Barnes wrote:
> On 03/11/2015 09:14 AM, Daniel Vetter wrote:
>> On Wed, Mar 11, 2015 at 02:53:39PM +0000, John Harrison wrote:
>>> On 05/03/2015 14:49, Daniel Vetter wrote:
>>>> On Thu, Mar 05, 2015 at 01:57:31PM +0000, John.C.Harrison@Intel.com wrote:
>>>>> From: John Harrison <John.C.Harrison@Intel.com>
>>>>>
>>>>> The LRC submission code requires a request for tracking purposes. It does not
>>>>> actually require that request to 'complete' it simply uses it for keeping hold
>>>>> of reference counts on contexts and such like.
>>>>>
>>>>> In the case where the ring buffer is completely full, the LRC code looks for a
>>>>> pending request that would free up sufficient space upon completion and waits
>>>>> for it. If no such request can be found it resorts to simply polling the free
>>>>> space count until it is big enough. This situation should only occur when the
>>>>> entire buffer is filled with the request currently being generated. I.e., the
>>>>> user is trying to submit a single piece of work that is large than the ring
>>>>> buffer itself (which should be impossible because very large batch buffers don't
>>>>> consume any more ring buffer space). Before starting to poll, a submit call is
>>>>> made to make sure that the currently queued up work in the buffer will actually
>>>>> be submtted and thus the poll will eventually succeed.
>>>>>
>>>>> The problem here is that the 'official' request cannot be used as that could
>>>>> lead to multiple LRC submissions being tagged to a single request structure.
>>>>> Instead, the code fakes up a private request structure and uses that.
>>>>>
>>>>> This patch moves the faked request allocation higher up in the call stack to the
>>>>> wait code itself (rather than being at the very lowest submission level). Thus
>>>>> it is now obvious where the faked request is coming from and why it is
>>>>> necessary. The patch also replaces it with a call to the official request
>>>>> allocation code rather than attempting to duplicate that code. This becomes
>>>>> especially important in the future when the request allocation changes to
>>>>> accommodate a conversion to struct fence.
>>>>>
>>>>> For: VIZ-5115
>>>>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
>>>> This is only possible if you pile up tons of olr. Since your patch series
>>>> fixes this design issue by removing olr I think we can just put a WARN_ON
>>>> in here if this ever happens and bail out with -ELOSTMYMARBLES or
>>>> something. And then rip out all this complexity.
>>>>
>>>> Or do I miss something important?
>>>> -Daniel
>>> Yeah, you missed the extremely important bug in the free space calculation
>>> that meant this impossible code path was being hit on a regular basis. The
>>> LRC wait_request code differed from the legacy wait_request code in the the
>>> latter was updated with request->postfix changes and the former was not.
>>> Thus the LRC one would happily find a request that frees up enough space,
>>> wait on it, retire it and then find there was still not enough space!
>>>
>>> New patches to fix the space calculation bug and to completely remove the
>>> polling path will be forth coming...
>> Hm, Jesse did dig out a regression where gem_ringfill blows up on
>> execlist. That igt is specifically to exercise this cornercases. I'm not
>> sure whith bugzilla Jesse meant, there's two:
>>
>> https://bugs.freedesktop.org/show_bug.cgi?id=89001
>> https://bugs.freedesktop.org/show_bug.cgi?id=88865
I don't think the space calculation bug could cause the gem_ringfill
failure. As noted above, even when the calculation gets it horribly
wrong and flunks the wait for request path, the sit and poll path should
still do the right thing. Plus the 88865 bug report I've already tried
to reproduce and verified as fixed by the initial version of this patch
set (i.e. without the space calc bug fix or the clean up of the fake
request that follows it). It would go wrong pretty reliably on a clean
nightly but never failed on my anti-OLR branch after quite a large
amount of trying.
I've just realised that I somehow got completely the wrong bug number in
the cover letter. So where patch zero talks about fixing a gem_ringfill
bug, it was supposed to be BZ:88865 not BZ:4####! The second one,
BZ:89001 certainly looks like the same issue but I don't have a SKL to
test with.
>>
>> Can you please check whether your fixes help for those issues two?
>>
>> Also adding Jesse since he's chasing these atm.
> Ah cool, sounds related at least. 89001 was the one I looked at
> yesterday. The worrying thing was that this bug caused a hard system
> hang. Not even the reset button worked... I guess we should have an
> HSD for that too so we can root cause the system part of it.
>
> Jesse
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 56/56] drm/i915: Update a bunch of LRC functions to take requests
2015-03-05 13:57 ` [PATCH 54/56] drm/i915: Rename 'do_execbuf' to 'execbuf_submit' John.C.Harrison
2015-03-05 13:57 ` [PATCH 55/56] drm/i915: Remove 'faked' request from LRC submission John.C.Harrison
@ 2015-03-05 13:57 ` John.C.Harrison
2015-03-10 23:18 ` [PATCH 54/56] drm/i915: Rename 'do_execbuf' to 'execbuf_submit' Tomas Elf
2 siblings, 0 replies; 234+ messages in thread
From: John.C.Harrison @ 2015-03-05 13:57 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
A bunch of the low level LRC functions were passing around ringbuf and
ctx pairs. In a few cases, they took the r/c pair and a request as
well. This is all quite messy and unnecesary.
Updated those functions to just take the request structure.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/intel_lrc.c | 61 ++++++++++++++++----------------------
1 file changed, 26 insertions(+), 35 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 1fa36de..ce5c19a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -494,25 +494,20 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring)
((u32)ring->next_context_status_buffer & 0x07) << 8);
}
-static int execlists_context_queue(struct intel_engine_cs *ring,
- struct intel_context *to,
- u32 tail,
- struct drm_i915_gem_request *request)
+static int execlists_context_queue(struct drm_i915_gem_request *request)
{
+ struct intel_engine_cs *ring = request->ring;
struct drm_i915_gem_request *cursor;
struct drm_i915_private *dev_priv = ring->dev->dev_private;
unsigned long flags;
int num_elements = 0;
- if (to != ring->default_context)
- intel_lr_context_pin(ring, to);
-
- WARN_ON(!request);
- WARN_ON(to != request->ctx);
+ if (request->ctx != ring->default_context)
+ intel_lr_context_pin(ring, request->ctx);
i915_gem_request_reference(request);
- request->tail = tail;
+ request->tail = request->ringbuf->tail;
intel_runtime_pm_get(dev_priv);
@@ -529,7 +524,7 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
struct drm_i915_gem_request,
execlist_link);
- if (to == tail_req->ctx) {
+ if (request->ctx == tail_req->ctx) {
WARN(tail_req->elsp_submitted != 0,
"More than 2 already-submitted reqs queued\n");
list_del(&tail_req->execlist_link);
@@ -636,7 +631,7 @@ static int logical_ring_wait_request(struct intel_ringbuffer *ringbuf,
/*
* intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
- * @ringbuf: Logical Ringbuffer to advance.
+ * @request: Request to advance the logical ringbuffer of.
*
* The tail is updated in our logical ringbuffer struct, not in the actual context. What
* really happens during submission is that the context and current tail will be placed
@@ -644,32 +639,29 @@ static int logical_ring_wait_request(struct intel_ringbuffer *ringbuf,
* point, the tail *inside* the context is updated and the ELSP written to.
*/
static void
-intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
- struct drm_i915_gem_request *request)
+intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request)
{
- struct intel_engine_cs *ring = ringbuf->ring;
+ struct intel_engine_cs *ring = request->ring;
- intel_logical_ring_advance(ringbuf);
+ intel_logical_ring_advance(request->ringbuf);
if (intel_ring_stopped(ring))
return;
- execlists_context_queue(ring, ctx, ringbuf->tail, request);
+ execlists_context_queue(request);
}
-static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx,
+static int logical_ring_wait_for_space(struct drm_i915_gem_request *req,
int bytes)
{
- struct intel_engine_cs *ring = ringbuf->ring;
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_request *local_req;
unsigned long end;
int ret;
- ret = logical_ring_wait_request(ringbuf, bytes);
+ ret = logical_ring_wait_request(req->ringbuf, bytes);
if (ret != -ENOSPC)
return ret;
@@ -686,10 +678,10 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
* Thus the request cannot be submitted via i915_add_request() and
* can not be waiting on by i915_gem_wait_request().
*/
- ret = dev_priv->gt.alloc_request(ring, ctx, &local_req);
+ ret = dev_priv->gt.alloc_request(ring, req->ctx, &local_req);
if (ret)
return ret;
- intel_logical_ring_advance_and_submit(ringbuf, ctx, local_req);
+ intel_logical_ring_advance_and_submit(local_req);
/* With GEM the hangcheck timer should kick us out of the loop,
* leaving it early runs the risk of corrupting GEM state (due
@@ -700,7 +692,7 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
ret = 0;
do {
- if (intel_ring_space(ringbuf) >= bytes)
+ if (intel_ring_space(req->ringbuf) >= bytes)
break;
msleep(1);
@@ -727,14 +719,14 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
return ret;
}
-static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx)
+static int logical_ring_wrap_buffer(struct drm_i915_gem_request *req)
{
+ struct intel_ringbuffer *ringbuf = req->ringbuf;
uint32_t __iomem *virt;
int rem = ringbuf->size - ringbuf->tail;
if (ringbuf->space < rem) {
- int ret = logical_ring_wait_for_space(ringbuf, ctx, rem);
+ int ret = logical_ring_wait_for_space(req, rem);
if (ret)
return ret;
@@ -751,19 +743,19 @@ static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf,
return 0;
}
-static int logical_ring_prepare(struct intel_ringbuffer *ringbuf,
- struct intel_context *ctx, int bytes)
+static int logical_ring_prepare(struct drm_i915_gem_request *req, int bytes)
{
+ struct intel_ringbuffer *ringbuf = req->ringbuf;
int ret;
if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
- ret = logical_ring_wrap_buffer(ringbuf, ctx);
+ ret = logical_ring_wrap_buffer(req);
if (unlikely(ret))
return ret;
}
if (unlikely(ringbuf->space < bytes)) {
- ret = logical_ring_wait_for_space(ringbuf, ctx, bytes);
+ ret = logical_ring_wait_for_space(req, bytes);
if (unlikely(ret))
return ret;
}
@@ -799,8 +791,7 @@ static int intel_logical_ring_begin(struct drm_i915_gem_request *req,
if (ret)
return ret;
- ret = logical_ring_prepare(req->ringbuf, req->ctx,
- num_dwords * sizeof(uint32_t));
+ ret = logical_ring_prepare(req, num_dwords * sizeof(uint32_t));
if (ret)
return ret;
@@ -1334,7 +1325,7 @@ static int gen8_emit_request(struct drm_i915_gem_request *request)
intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
intel_logical_ring_emit(ringbuf, MI_NOOP);
- intel_logical_ring_advance_and_submit(ringbuf, request->ctx, request);
+ intel_logical_ring_advance_and_submit(request);
return 0;
}
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 54/56] drm/i915: Rename 'do_execbuf' to 'execbuf_submit'
2015-03-05 13:57 ` [PATCH 54/56] drm/i915: Rename 'do_execbuf' to 'execbuf_submit' John.C.Harrison
2015-03-05 13:57 ` [PATCH 55/56] drm/i915: Remove 'faked' request from LRC submission John.C.Harrison
2015-03-05 13:57 ` [PATCH 56/56] drm/i915: Update a bunch of LRC functions to take requests John.C.Harrison
@ 2015-03-10 23:18 ` Tomas Elf
2 siblings, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-10 23:18 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 05/03/2015 13:57, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> The submission portion of the execbuffer code path was abstracted into a
> function pointer indirection as part of the legacy vs execlist work. The two
> implementation functions are called 'i915_gem_ringbuffer_submission' and
> 'intel_execlists_submission' but the pointer was called 'do_execbuf'. There is
> already a 'i915_gem_do_execbuffer' function (which is what calls the pointer
> indirection). The name of the pointer is therefore considered to be backwards
> and should be changed.
>
> This patch renames it to 'execbuf_submit' which is hopefully a bit clearer.
>
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 6 +++---
> drivers/gpu/drm/i915/i915_gem.c | 4 ++--
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +-
> 3 files changed, 6 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 7c9e569..4e9a350 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -1793,9 +1793,9 @@ struct drm_i915_private {
> int (*alloc_request)(struct intel_engine_cs *ring,
> struct intel_context *ctx,
> struct drm_i915_gem_request **req_out);
> - int (*do_execbuf)(struct i915_execbuffer_params *params,
> - struct drm_i915_gem_execbuffer2 *args,
> - struct list_head *vmas);
> + int (*execbuf_submit)(struct i915_execbuffer_params *params,
> + struct drm_i915_gem_execbuffer2 *args,
> + struct list_head *vmas);
> int (*init_rings)(struct drm_device *dev);
> void (*cleanup_ring)(struct intel_engine_cs *ring);
> void (*stop_ring)(struct intel_engine_cs *ring);
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index ecff3f7..27abc9d 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -4928,13 +4928,13 @@ int i915_gem_init(struct drm_device *dev)
>
> if (!i915.enable_execlists) {
> dev_priv->gt.alloc_request = intel_ring_alloc_request;
> - dev_priv->gt.do_execbuf = i915_gem_ringbuffer_submission;
> + dev_priv->gt.execbuf_submit = i915_gem_ringbuffer_submission;
> dev_priv->gt.init_rings = i915_gem_init_rings;
> dev_priv->gt.cleanup_ring = intel_cleanup_ring_buffer;
> dev_priv->gt.stop_ring = intel_stop_ring_buffer;
> } else {
> dev_priv->gt.alloc_request = intel_logical_ring_alloc_request;
> - dev_priv->gt.do_execbuf = intel_execlists_submission;
> + dev_priv->gt.execbuf_submit = intel_execlists_submission;
> dev_priv->gt.init_rings = intel_logical_rings_init;
> dev_priv->gt.cleanup_ring = intel_logical_ring_cleanup;
> dev_priv->gt.stop_ring = intel_logical_ring_stop;
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index dfad66a..d969eb5 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1558,7 +1558,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> params->batch_obj = batch_obj;
> params->ctx = ctx;
>
> - ret = dev_priv->gt.do_execbuf(params, args, &eb->vmas);
> + ret = dev_priv->gt.execbuf_submit(params, args, &eb->vmas);
>
> err:
> /*
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* [PATCH 01/53] drm/i915: Remove ironlake rc6 support
2015-02-19 17:17 ` [PATCH 00/53] Remove the outstanding_lazy_request John.C.Harrison
` (53 preceding siblings ...)
2015-03-05 13:57 ` [PATCH 54/56] drm/i915: Rename 'do_execbuf' to 'execbuf_submit' John.C.Harrison
@ 2015-03-05 14:03 ` John.C.Harrison
2015-03-05 15:22 ` Daniel Vetter
2015-03-10 23:02 ` Tomas Elf
54 siblings, 2 replies; 234+ messages in thread
From: John.C.Harrison @ 2015-03-05 14:03 UTC (permalink / raw)
To: Intel-GFX
From: John Harrison <John.C.Harrison@Intel.com>
Apparently, this has never worked reliably and is currently disabled. Also, the
gains are not particularly impressive. Thus rather than try to keep unused code
from decaying and having to update it for other driver changes, it was decided
to simply remove it.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
drivers/gpu/drm/i915/i915_debugfs.c | 12 ---
drivers/gpu/drm/i915/i915_drv.h | 3 -
drivers/gpu/drm/i915/intel_display.c | 2 -
drivers/gpu/drm/i915/intel_drv.h | 1 -
drivers/gpu/drm/i915/intel_pm.c | 155 ----------------------------------
5 files changed, 173 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 68a1e6e..18e4900 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1846,18 +1846,6 @@ static int i915_context_status(struct seq_file *m, void *unused)
if (ret)
return ret;
- if (dev_priv->ips.pwrctx) {
- seq_puts(m, "power context ");
- describe_obj(m, dev_priv->ips.pwrctx);
- seq_putc(m, '\n');
- }
-
- if (dev_priv->ips.renderctx) {
- seq_puts(m, "render context ");
- describe_obj(m, dev_priv->ips.renderctx);
- seq_putc(m, '\n');
- }
-
list_for_each_entry(ctx, &dev_priv->context_list, link) {
if (!i915.enable_execlists &&
ctx->legacy_hw_ctx.rcs_state == NULL)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 798fa88..05f106d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1053,9 +1053,6 @@ struct intel_ilk_power_mgmt {
int c_m;
int r_t;
-
- struct drm_i915_gem_object *pwrctx;
- struct drm_i915_gem_object *renderctx;
};
struct drm_i915_private;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 5c35098..51f7ed4 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -13904,8 +13904,6 @@ void intel_modeset_cleanup(struct drm_device *dev)
intel_fbc_disable(dev);
- ironlake_teardown_rc6(dev);
-
mutex_unlock(&dev->struct_mutex);
/* flush any delayed tasks or pending work */
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index f4305be..b793558 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1229,7 +1229,6 @@ void intel_enable_gt_powersave(struct drm_device *dev);
void intel_disable_gt_powersave(struct drm_device *dev);
void intel_suspend_gt_powersave(struct drm_device *dev);
void intel_reset_gt_powersave(struct drm_device *dev);
-void ironlake_teardown_rc6(struct drm_device *dev);
void gen6_update_ring_freq(struct drm_device *dev);
void gen6_rps_idle(struct drm_i915_private *dev_priv);
void gen6_rps_boost(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 542cf68..0762572 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3539,41 +3539,6 @@ void intel_update_sprite_watermarks(struct drm_plane *plane,
pixel_size, enabled, scaled);
}
-static struct drm_i915_gem_object *
-intel_alloc_context_page(struct drm_device *dev)
-{
- struct drm_i915_gem_object *ctx;
- int ret;
-
- WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-
- ctx = i915_gem_alloc_object(dev, 4096);
- if (!ctx) {
- DRM_DEBUG("failed to alloc power context, RC6 disabled\n");
- return NULL;
- }
-
- ret = i915_gem_obj_ggtt_pin(ctx, 4096, 0);
- if (ret) {
- DRM_ERROR("failed to pin power context: %d\n", ret);
- goto err_unref;
- }
-
- ret = i915_gem_object_set_to_gtt_domain(ctx, 1);
- if (ret) {
- DRM_ERROR("failed to set-domain on power context: %d\n", ret);
- goto err_unpin;
- }
-
- return ctx;
-
-err_unpin:
- i915_gem_object_ggtt_unpin(ctx);
-err_unref:
- drm_gem_object_unreference(&ctx->base);
- return NULL;
-}
-
/**
* Lock protecting IPS related data structures
*/
@@ -4990,124 +4955,6 @@ static void valleyview_enable_rps(struct drm_device *dev)
intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
}
-void ironlake_teardown_rc6(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- if (dev_priv->ips.renderctx) {
- i915_gem_object_ggtt_unpin(dev_priv->ips.renderctx);
- drm_gem_object_unreference(&dev_priv->ips.renderctx->base);
- dev_priv->ips.renderctx = NULL;
- }
-
- if (dev_priv->ips.pwrctx) {
- i915_gem_object_ggtt_unpin(dev_priv->ips.pwrctx);
- drm_gem_object_unreference(&dev_priv->ips.pwrctx->base);
- dev_priv->ips.pwrctx = NULL;
- }
-}
-
-static void ironlake_disable_rc6(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- if (I915_READ(PWRCTXA)) {
- /* Wake the GPU, prevent RC6, then restore RSTDBYCTL */
- I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) | RCX_SW_EXIT);
- wait_for(((I915_READ(RSTDBYCTL) & RSX_STATUS_MASK) == RSX_STATUS_ON),
- 50);
-
- I915_WRITE(PWRCTXA, 0);
- POSTING_READ(PWRCTXA);
-
- I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
- POSTING_READ(RSTDBYCTL);
- }
-}
-
-static int ironlake_setup_rc6(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- if (dev_priv->ips.renderctx == NULL)
- dev_priv->ips.renderctx = intel_alloc_context_page(dev);
- if (!dev_priv->ips.renderctx)
- return -ENOMEM;
-
- if (dev_priv->ips.pwrctx == NULL)
- dev_priv->ips.pwrctx = intel_alloc_context_page(dev);
- if (!dev_priv->ips.pwrctx) {
- ironlake_teardown_rc6(dev);
- return -ENOMEM;
- }
-
- return 0;
-}
-
-static void ironlake_enable_rc6(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_engine_cs *ring = &dev_priv->ring[RCS];
- bool was_interruptible;
- int ret;
-
- /* rc6 disabled by default due to repeated reports of hanging during
- * boot and resume.
- */
- if (!intel_enable_rc6(dev))
- return;
-
- WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-
- ret = ironlake_setup_rc6(dev);
- if (ret)
- return;
-
- was_interruptible = dev_priv->mm.interruptible;
- dev_priv->mm.interruptible = false;
-
- /*
- * GPU can automatically power down the render unit if given a page
- * to save state.
- */
- ret = intel_ring_begin(ring, 6);
- if (ret) {
- ironlake_teardown_rc6(dev);
- dev_priv->mm.interruptible = was_interruptible;
- return;
- }
-
- intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
- intel_ring_emit(ring, MI_SET_CONTEXT);
- intel_ring_emit(ring, i915_gem_obj_ggtt_offset(dev_priv->ips.renderctx) |
- MI_MM_SPACE_GTT |
- MI_SAVE_EXT_STATE_EN |
- MI_RESTORE_EXT_STATE_EN |
- MI_RESTORE_INHIBIT);
- intel_ring_emit(ring, MI_SUSPEND_FLUSH);
- intel_ring_emit(ring, MI_NOOP);
- intel_ring_emit(ring, MI_FLUSH);
- intel_ring_advance(ring);
-
- /*
- * Wait for the command parser to advance past MI_SET_CONTEXT. The HW
- * does an implicit flush, combined with MI_FLUSH above, it should be
- * safe to assume that renderctx is valid
- */
- ret = intel_ring_idle(ring);
- dev_priv->mm.interruptible = was_interruptible;
- if (ret) {
- DRM_ERROR("failed to enable ironlake power savings\n");
- ironlake_teardown_rc6(dev);
- return;
- }
-
- I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN);
- I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
-
- intel_print_rc6_info(dev, GEN6_RC_CTL_RC6_ENABLE);
-}
-
static unsigned long intel_pxfreq(u32 vidfreq)
{
unsigned long freq;
@@ -5655,7 +5502,6 @@ void intel_disable_gt_powersave(struct drm_device *dev)
if (IS_IRONLAKE_M(dev)) {
ironlake_disable_drps(dev);
- ironlake_disable_rc6(dev);
} else if (INTEL_INFO(dev)->gen >= 6) {
intel_suspend_gt_powersave(dev);
@@ -5726,7 +5572,6 @@ void intel_enable_gt_powersave(struct drm_device *dev)
if (IS_IRONLAKE_M(dev)) {
mutex_lock(&dev->struct_mutex);
ironlake_enable_drps(dev);
- ironlake_enable_rc6(dev);
intel_init_emon(dev);
mutex_unlock(&dev->struct_mutex);
} else if (INTEL_INFO(dev)->gen >= 6) {
--
1.7.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 234+ messages in thread* Re: [PATCH 01/53] drm/i915: Remove ironlake rc6 support
2015-03-05 14:03 ` [PATCH 01/53] drm/i915: Remove ironlake rc6 support John.C.Harrison
@ 2015-03-05 15:22 ` Daniel Vetter
2015-03-05 15:36 ` John Harrison
2015-03-10 23:02 ` Tomas Elf
1 sibling, 1 reply; 234+ messages in thread
From: Daniel Vetter @ 2015-03-05 15:22 UTC (permalink / raw)
To: John.C.Harrison; +Cc: Intel-GFX
On Thu, Mar 05, 2015 at 02:03:03PM +0000, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Apparently, this has never worked reliably and is currently disabled. Also, the
> gains are not particularly impressive. Thus rather than try to keep unused code
> from decaying and having to update it for other driver changes, it was decided
> to simply remove it.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Queued for -next, thanks for the patch.
-Daniel
> ---
> drivers/gpu/drm/i915/i915_debugfs.c | 12 ---
> drivers/gpu/drm/i915/i915_drv.h | 3 -
> drivers/gpu/drm/i915/intel_display.c | 2 -
> drivers/gpu/drm/i915/intel_drv.h | 1 -
> drivers/gpu/drm/i915/intel_pm.c | 155 ----------------------------------
> 5 files changed, 173 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> index 68a1e6e..18e4900 100644
> --- a/drivers/gpu/drm/i915/i915_debugfs.c
> +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> @@ -1846,18 +1846,6 @@ static int i915_context_status(struct seq_file *m, void *unused)
> if (ret)
> return ret;
>
> - if (dev_priv->ips.pwrctx) {
> - seq_puts(m, "power context ");
> - describe_obj(m, dev_priv->ips.pwrctx);
> - seq_putc(m, '\n');
> - }
> -
> - if (dev_priv->ips.renderctx) {
> - seq_puts(m, "render context ");
> - describe_obj(m, dev_priv->ips.renderctx);
> - seq_putc(m, '\n');
> - }
> -
> list_for_each_entry(ctx, &dev_priv->context_list, link) {
> if (!i915.enable_execlists &&
> ctx->legacy_hw_ctx.rcs_state == NULL)
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 798fa88..05f106d 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -1053,9 +1053,6 @@ struct intel_ilk_power_mgmt {
>
> int c_m;
> int r_t;
> -
> - struct drm_i915_gem_object *pwrctx;
> - struct drm_i915_gem_object *renderctx;
> };
>
> struct drm_i915_private;
> diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> index 5c35098..51f7ed4 100644
> --- a/drivers/gpu/drm/i915/intel_display.c
> +++ b/drivers/gpu/drm/i915/intel_display.c
> @@ -13904,8 +13904,6 @@ void intel_modeset_cleanup(struct drm_device *dev)
>
> intel_fbc_disable(dev);
>
> - ironlake_teardown_rc6(dev);
> -
> mutex_unlock(&dev->struct_mutex);
>
> /* flush any delayed tasks or pending work */
> diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
> index f4305be..b793558 100644
> --- a/drivers/gpu/drm/i915/intel_drv.h
> +++ b/drivers/gpu/drm/i915/intel_drv.h
> @@ -1229,7 +1229,6 @@ void intel_enable_gt_powersave(struct drm_device *dev);
> void intel_disable_gt_powersave(struct drm_device *dev);
> void intel_suspend_gt_powersave(struct drm_device *dev);
> void intel_reset_gt_powersave(struct drm_device *dev);
> -void ironlake_teardown_rc6(struct drm_device *dev);
> void gen6_update_ring_freq(struct drm_device *dev);
> void gen6_rps_idle(struct drm_i915_private *dev_priv);
> void gen6_rps_boost(struct drm_i915_private *dev_priv);
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index 542cf68..0762572 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -3539,41 +3539,6 @@ void intel_update_sprite_watermarks(struct drm_plane *plane,
> pixel_size, enabled, scaled);
> }
>
> -static struct drm_i915_gem_object *
> -intel_alloc_context_page(struct drm_device *dev)
> -{
> - struct drm_i915_gem_object *ctx;
> - int ret;
> -
> - WARN_ON(!mutex_is_locked(&dev->struct_mutex));
> -
> - ctx = i915_gem_alloc_object(dev, 4096);
> - if (!ctx) {
> - DRM_DEBUG("failed to alloc power context, RC6 disabled\n");
> - return NULL;
> - }
> -
> - ret = i915_gem_obj_ggtt_pin(ctx, 4096, 0);
> - if (ret) {
> - DRM_ERROR("failed to pin power context: %d\n", ret);
> - goto err_unref;
> - }
> -
> - ret = i915_gem_object_set_to_gtt_domain(ctx, 1);
> - if (ret) {
> - DRM_ERROR("failed to set-domain on power context: %d\n", ret);
> - goto err_unpin;
> - }
> -
> - return ctx;
> -
> -err_unpin:
> - i915_gem_object_ggtt_unpin(ctx);
> -err_unref:
> - drm_gem_object_unreference(&ctx->base);
> - return NULL;
> -}
> -
> /**
> * Lock protecting IPS related data structures
> */
> @@ -4990,124 +4955,6 @@ static void valleyview_enable_rps(struct drm_device *dev)
> intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
> }
>
> -void ironlake_teardown_rc6(struct drm_device *dev)
> -{
> - struct drm_i915_private *dev_priv = dev->dev_private;
> -
> - if (dev_priv->ips.renderctx) {
> - i915_gem_object_ggtt_unpin(dev_priv->ips.renderctx);
> - drm_gem_object_unreference(&dev_priv->ips.renderctx->base);
> - dev_priv->ips.renderctx = NULL;
> - }
> -
> - if (dev_priv->ips.pwrctx) {
> - i915_gem_object_ggtt_unpin(dev_priv->ips.pwrctx);
> - drm_gem_object_unreference(&dev_priv->ips.pwrctx->base);
> - dev_priv->ips.pwrctx = NULL;
> - }
> -}
> -
> -static void ironlake_disable_rc6(struct drm_device *dev)
> -{
> - struct drm_i915_private *dev_priv = dev->dev_private;
> -
> - if (I915_READ(PWRCTXA)) {
> - /* Wake the GPU, prevent RC6, then restore RSTDBYCTL */
> - I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) | RCX_SW_EXIT);
> - wait_for(((I915_READ(RSTDBYCTL) & RSX_STATUS_MASK) == RSX_STATUS_ON),
> - 50);
> -
> - I915_WRITE(PWRCTXA, 0);
> - POSTING_READ(PWRCTXA);
> -
> - I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
> - POSTING_READ(RSTDBYCTL);
> - }
> -}
> -
> -static int ironlake_setup_rc6(struct drm_device *dev)
> -{
> - struct drm_i915_private *dev_priv = dev->dev_private;
> -
> - if (dev_priv->ips.renderctx == NULL)
> - dev_priv->ips.renderctx = intel_alloc_context_page(dev);
> - if (!dev_priv->ips.renderctx)
> - return -ENOMEM;
> -
> - if (dev_priv->ips.pwrctx == NULL)
> - dev_priv->ips.pwrctx = intel_alloc_context_page(dev);
> - if (!dev_priv->ips.pwrctx) {
> - ironlake_teardown_rc6(dev);
> - return -ENOMEM;
> - }
> -
> - return 0;
> -}
> -
> -static void ironlake_enable_rc6(struct drm_device *dev)
> -{
> - struct drm_i915_private *dev_priv = dev->dev_private;
> - struct intel_engine_cs *ring = &dev_priv->ring[RCS];
> - bool was_interruptible;
> - int ret;
> -
> - /* rc6 disabled by default due to repeated reports of hanging during
> - * boot and resume.
> - */
> - if (!intel_enable_rc6(dev))
> - return;
> -
> - WARN_ON(!mutex_is_locked(&dev->struct_mutex));
> -
> - ret = ironlake_setup_rc6(dev);
> - if (ret)
> - return;
> -
> - was_interruptible = dev_priv->mm.interruptible;
> - dev_priv->mm.interruptible = false;
> -
> - /*
> - * GPU can automatically power down the render unit if given a page
> - * to save state.
> - */
> - ret = intel_ring_begin(ring, 6);
> - if (ret) {
> - ironlake_teardown_rc6(dev);
> - dev_priv->mm.interruptible = was_interruptible;
> - return;
> - }
> -
> - intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
> - intel_ring_emit(ring, MI_SET_CONTEXT);
> - intel_ring_emit(ring, i915_gem_obj_ggtt_offset(dev_priv->ips.renderctx) |
> - MI_MM_SPACE_GTT |
> - MI_SAVE_EXT_STATE_EN |
> - MI_RESTORE_EXT_STATE_EN |
> - MI_RESTORE_INHIBIT);
> - intel_ring_emit(ring, MI_SUSPEND_FLUSH);
> - intel_ring_emit(ring, MI_NOOP);
> - intel_ring_emit(ring, MI_FLUSH);
> - intel_ring_advance(ring);
> -
> - /*
> - * Wait for the command parser to advance past MI_SET_CONTEXT. The HW
> - * does an implicit flush, combined with MI_FLUSH above, it should be
> - * safe to assume that renderctx is valid
> - */
> - ret = intel_ring_idle(ring);
> - dev_priv->mm.interruptible = was_interruptible;
> - if (ret) {
> - DRM_ERROR("failed to enable ironlake power savings\n");
> - ironlake_teardown_rc6(dev);
> - return;
> - }
> -
> - I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN);
> - I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
> -
> - intel_print_rc6_info(dev, GEN6_RC_CTL_RC6_ENABLE);
> -}
> -
> static unsigned long intel_pxfreq(u32 vidfreq)
> {
> unsigned long freq;
> @@ -5655,7 +5502,6 @@ void intel_disable_gt_powersave(struct drm_device *dev)
>
> if (IS_IRONLAKE_M(dev)) {
> ironlake_disable_drps(dev);
> - ironlake_disable_rc6(dev);
> } else if (INTEL_INFO(dev)->gen >= 6) {
> intel_suspend_gt_powersave(dev);
>
> @@ -5726,7 +5572,6 @@ void intel_enable_gt_powersave(struct drm_device *dev)
> if (IS_IRONLAKE_M(dev)) {
> mutex_lock(&dev->struct_mutex);
> ironlake_enable_drps(dev);
> - ironlake_enable_rc6(dev);
> intel_init_emon(dev);
> mutex_unlock(&dev->struct_mutex);
> } else if (INTEL_INFO(dev)->gen >= 6) {
> --
> 1.7.9.5
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread* Re: [PATCH 01/53] drm/i915: Remove ironlake rc6 support
2015-03-05 15:22 ` Daniel Vetter
@ 2015-03-05 15:36 ` John Harrison
2015-03-06 16:32 ` Daniel Vetter
0 siblings, 1 reply; 234+ messages in thread
From: John Harrison @ 2015-03-05 15:36 UTC (permalink / raw)
To: Daniel Vetter; +Cc: Intel-GFX
On 05/03/2015 15:22, Daniel Vetter wrote:
> On Thu, Mar 05, 2015 at 02:03:03PM +0000, John.C.Harrison@Intel.com wrote:
>> From: John Harrison <John.C.Harrison@Intel.com>
>>
>> Apparently, this has never worked reliably and is currently disabled. Also, the
>> gains are not particularly impressive. Thus rather than try to keep unused code
>> from decaying and having to update it for other driver changes, it was decided
>> to simply remove it.
>>
>> For: VIZ-5115
>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> Queued for -next, thanks for the patch.
> -Daniel
Can you hold off merging any of the other patches in the series for the
moment. Tomas Elf is currently posting review comments, some with R-B
some with change requests. Some of the re-work either for his comments
or for yours causes changes which ripple through a number of the patches
in the series. So I would like to repost the whole set once all the
comments have been addressed. Otherwise, it all just gets far too messy
as to which patches have or haven't been updated, what needs re-merging,
which version is which, etc.
Thanks,
John.
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* Re: [PATCH 01/53] drm/i915: Remove ironlake rc6 support
2015-03-05 15:36 ` John Harrison
@ 2015-03-06 16:32 ` Daniel Vetter
0 siblings, 0 replies; 234+ messages in thread
From: Daniel Vetter @ 2015-03-06 16:32 UTC (permalink / raw)
To: John Harrison; +Cc: Intel-GFX
On Thu, Mar 05, 2015 at 03:36:03PM +0000, John Harrison wrote:
> On 05/03/2015 15:22, Daniel Vetter wrote:
> >On Thu, Mar 05, 2015 at 02:03:03PM +0000, John.C.Harrison@Intel.com wrote:
> >>From: John Harrison <John.C.Harrison@Intel.com>
> >>
> >>Apparently, this has never worked reliably and is currently disabled. Also, the
> >>gains are not particularly impressive. Thus rather than try to keep unused code
> >>from decaying and having to update it for other driver changes, it was decided
> >>to simply remove it.
> >>
> >>For: VIZ-5115
> >>Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> >Queued for -next, thanks for the patch.
> >-Daniel
>
> Can you hold off merging any of the other patches in the series for the
> moment. Tomas Elf is currently posting review comments, some with R-B some
> with change requests. Some of the re-work either for his comments or for
> yours causes changes which ripple through a number of the patches in the
> series. So I would like to repost the whole set once all the comments have
> been addressed. Otherwise, it all just gets far too messy as to which
> patches have or haven't been updated, what needs re-merging, which version
> is which, etc.
Fully agreed since that was my plan. I specifically pulled this one here
in since it should be otherwise free-standing and would likely cause
needless conflicts. For all the other patches it's better to first
converge on the review a bit more before proceeding with merging.
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread
* Re: [PATCH 01/53] drm/i915: Remove ironlake rc6 support
2015-03-05 14:03 ` [PATCH 01/53] drm/i915: Remove ironlake rc6 support John.C.Harrison
2015-03-05 15:22 ` Daniel Vetter
@ 2015-03-10 23:02 ` Tomas Elf
1 sibling, 0 replies; 234+ messages in thread
From: Tomas Elf @ 2015-03-10 23:02 UTC (permalink / raw)
To: John.C.Harrison, Intel-GFX
On 05/03/2015 14:03, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Apparently, this has never worked reliably and is currently disabled. Also, the
> gains are not particularly impressive. Thus rather than try to keep unused code
> from decaying and having to update it for other driver changes, it was decided
> to simply remove it.
>
> For: VIZ-5115
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_debugfs.c | 12 ---
> drivers/gpu/drm/i915/i915_drv.h | 3 -
> drivers/gpu/drm/i915/intel_display.c | 2 -
> drivers/gpu/drm/i915/intel_drv.h | 1 -
> drivers/gpu/drm/i915/intel_pm.c | 155 ----------------------------------
> 5 files changed, 173 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> index 68a1e6e..18e4900 100644
> --- a/drivers/gpu/drm/i915/i915_debugfs.c
> +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> @@ -1846,18 +1846,6 @@ static int i915_context_status(struct seq_file *m, void *unused)
> if (ret)
> return ret;
>
> - if (dev_priv->ips.pwrctx) {
> - seq_puts(m, "power context ");
> - describe_obj(m, dev_priv->ips.pwrctx);
> - seq_putc(m, '\n');
> - }
> -
> - if (dev_priv->ips.renderctx) {
> - seq_puts(m, "render context ");
> - describe_obj(m, dev_priv->ips.renderctx);
> - seq_putc(m, '\n');
> - }
> -
> list_for_each_entry(ctx, &dev_priv->context_list, link) {
> if (!i915.enable_execlists &&
> ctx->legacy_hw_ctx.rcs_state == NULL)
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 798fa88..05f106d 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -1053,9 +1053,6 @@ struct intel_ilk_power_mgmt {
>
> int c_m;
> int r_t;
> -
> - struct drm_i915_gem_object *pwrctx;
> - struct drm_i915_gem_object *renderctx;
> };
>
> struct drm_i915_private;
> diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> index 5c35098..51f7ed4 100644
> --- a/drivers/gpu/drm/i915/intel_display.c
> +++ b/drivers/gpu/drm/i915/intel_display.c
> @@ -13904,8 +13904,6 @@ void intel_modeset_cleanup(struct drm_device *dev)
>
> intel_fbc_disable(dev);
>
> - ironlake_teardown_rc6(dev);
> -
> mutex_unlock(&dev->struct_mutex);
>
> /* flush any delayed tasks or pending work */
> diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
> index f4305be..b793558 100644
> --- a/drivers/gpu/drm/i915/intel_drv.h
> +++ b/drivers/gpu/drm/i915/intel_drv.h
> @@ -1229,7 +1229,6 @@ void intel_enable_gt_powersave(struct drm_device *dev);
> void intel_disable_gt_powersave(struct drm_device *dev);
> void intel_suspend_gt_powersave(struct drm_device *dev);
> void intel_reset_gt_powersave(struct drm_device *dev);
> -void ironlake_teardown_rc6(struct drm_device *dev);
> void gen6_update_ring_freq(struct drm_device *dev);
> void gen6_rps_idle(struct drm_i915_private *dev_priv);
> void gen6_rps_boost(struct drm_i915_private *dev_priv);
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index 542cf68..0762572 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -3539,41 +3539,6 @@ void intel_update_sprite_watermarks(struct drm_plane *plane,
> pixel_size, enabled, scaled);
> }
>
> -static struct drm_i915_gem_object *
> -intel_alloc_context_page(struct drm_device *dev)
> -{
> - struct drm_i915_gem_object *ctx;
> - int ret;
> -
> - WARN_ON(!mutex_is_locked(&dev->struct_mutex));
> -
> - ctx = i915_gem_alloc_object(dev, 4096);
> - if (!ctx) {
> - DRM_DEBUG("failed to alloc power context, RC6 disabled\n");
> - return NULL;
> - }
> -
> - ret = i915_gem_obj_ggtt_pin(ctx, 4096, 0);
> - if (ret) {
> - DRM_ERROR("failed to pin power context: %d\n", ret);
> - goto err_unref;
> - }
> -
> - ret = i915_gem_object_set_to_gtt_domain(ctx, 1);
> - if (ret) {
> - DRM_ERROR("failed to set-domain on power context: %d\n", ret);
> - goto err_unpin;
> - }
> -
> - return ctx;
> -
> -err_unpin:
> - i915_gem_object_ggtt_unpin(ctx);
> -err_unref:
> - drm_gem_object_unreference(&ctx->base);
> - return NULL;
> -}
> -
> /**
> * Lock protecting IPS related data structures
> */
> @@ -4990,124 +4955,6 @@ static void valleyview_enable_rps(struct drm_device *dev)
> intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
> }
>
> -void ironlake_teardown_rc6(struct drm_device *dev)
> -{
> - struct drm_i915_private *dev_priv = dev->dev_private;
> -
> - if (dev_priv->ips.renderctx) {
> - i915_gem_object_ggtt_unpin(dev_priv->ips.renderctx);
> - drm_gem_object_unreference(&dev_priv->ips.renderctx->base);
> - dev_priv->ips.renderctx = NULL;
> - }
> -
> - if (dev_priv->ips.pwrctx) {
> - i915_gem_object_ggtt_unpin(dev_priv->ips.pwrctx);
> - drm_gem_object_unreference(&dev_priv->ips.pwrctx->base);
> - dev_priv->ips.pwrctx = NULL;
> - }
> -}
> -
> -static void ironlake_disable_rc6(struct drm_device *dev)
> -{
> - struct drm_i915_private *dev_priv = dev->dev_private;
> -
> - if (I915_READ(PWRCTXA)) {
> - /* Wake the GPU, prevent RC6, then restore RSTDBYCTL */
> - I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) | RCX_SW_EXIT);
> - wait_for(((I915_READ(RSTDBYCTL) & RSX_STATUS_MASK) == RSX_STATUS_ON),
> - 50);
> -
> - I915_WRITE(PWRCTXA, 0);
> - POSTING_READ(PWRCTXA);
> -
> - I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
> - POSTING_READ(RSTDBYCTL);
> - }
> -}
> -
> -static int ironlake_setup_rc6(struct drm_device *dev)
> -{
> - struct drm_i915_private *dev_priv = dev->dev_private;
> -
> - if (dev_priv->ips.renderctx == NULL)
> - dev_priv->ips.renderctx = intel_alloc_context_page(dev);
> - if (!dev_priv->ips.renderctx)
> - return -ENOMEM;
> -
> - if (dev_priv->ips.pwrctx == NULL)
> - dev_priv->ips.pwrctx = intel_alloc_context_page(dev);
> - if (!dev_priv->ips.pwrctx) {
> - ironlake_teardown_rc6(dev);
> - return -ENOMEM;
> - }
> -
> - return 0;
> -}
> -
> -static void ironlake_enable_rc6(struct drm_device *dev)
> -{
> - struct drm_i915_private *dev_priv = dev->dev_private;
> - struct intel_engine_cs *ring = &dev_priv->ring[RCS];
> - bool was_interruptible;
> - int ret;
> -
> - /* rc6 disabled by default due to repeated reports of hanging during
> - * boot and resume.
> - */
> - if (!intel_enable_rc6(dev))
> - return;
> -
> - WARN_ON(!mutex_is_locked(&dev->struct_mutex));
> -
> - ret = ironlake_setup_rc6(dev);
> - if (ret)
> - return;
> -
> - was_interruptible = dev_priv->mm.interruptible;
> - dev_priv->mm.interruptible = false;
> -
> - /*
> - * GPU can automatically power down the render unit if given a page
> - * to save state.
> - */
> - ret = intel_ring_begin(ring, 6);
> - if (ret) {
> - ironlake_teardown_rc6(dev);
> - dev_priv->mm.interruptible = was_interruptible;
> - return;
> - }
> -
> - intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
> - intel_ring_emit(ring, MI_SET_CONTEXT);
> - intel_ring_emit(ring, i915_gem_obj_ggtt_offset(dev_priv->ips.renderctx) |
> - MI_MM_SPACE_GTT |
> - MI_SAVE_EXT_STATE_EN |
> - MI_RESTORE_EXT_STATE_EN |
> - MI_RESTORE_INHIBIT);
> - intel_ring_emit(ring, MI_SUSPEND_FLUSH);
> - intel_ring_emit(ring, MI_NOOP);
> - intel_ring_emit(ring, MI_FLUSH);
> - intel_ring_advance(ring);
> -
> - /*
> - * Wait for the command parser to advance past MI_SET_CONTEXT. The HW
> - * does an implicit flush, combined with MI_FLUSH above, it should be
> - * safe to assume that renderctx is valid
> - */
> - ret = intel_ring_idle(ring);
> - dev_priv->mm.interruptible = was_interruptible;
> - if (ret) {
> - DRM_ERROR("failed to enable ironlake power savings\n");
> - ironlake_teardown_rc6(dev);
> - return;
> - }
> -
> - I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN);
> - I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
> -
> - intel_print_rc6_info(dev, GEN6_RC_CTL_RC6_ENABLE);
> -}
> -
> static unsigned long intel_pxfreq(u32 vidfreq)
> {
> unsigned long freq;
> @@ -5655,7 +5502,6 @@ void intel_disable_gt_powersave(struct drm_device *dev)
>
> if (IS_IRONLAKE_M(dev)) {
> ironlake_disable_drps(dev);
> - ironlake_disable_rc6(dev);
> } else if (INTEL_INFO(dev)->gen >= 6) {
> intel_suspend_gt_powersave(dev);
>
> @@ -5726,7 +5572,6 @@ void intel_enable_gt_powersave(struct drm_device *dev)
> if (IS_IRONLAKE_M(dev)) {
> mutex_lock(&dev->struct_mutex);
> ironlake_enable_drps(dev);
> - ironlake_enable_rc6(dev);
> intel_init_emon(dev);
> mutex_unlock(&dev->struct_mutex);
> } else if (INTEL_INFO(dev)->gen >= 6) {
>
>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Thanks,
Tomas
(I know this one has already been queued for merge... I'm going through
these patches regardless, for my own bookkeeping)
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 234+ messages in thread