Skip to contentSkip to conversation

drm/i915: Reinstate order of operations in {intel, logical}_ring_begin()

PATCH In review Dave Gordon 4 participants 8 messages Jun 8, 2015 – Jun 16, 2015

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 drm/i915: Reinstate order of operations in {intel, logical}_ring_begin()

The original idea of preallocating the OLR was implemented in

Quoted 1 line

9d773091 drm/i915: Preallocate next seqno before touching the ring

and the sequence of operations was to allocate the OLR, then wrap past the end of the ring if necessary, then wait for space if necessary. But subsequently intel_ring_begin() was refactored, in

Quoted 1 line

304d695 drm/i915: Flush outstanding requests before allocating new seqno

to ensure that pending work that might need to be flushed used the old and not the newly-allocated request. This changed the sequence to wrap and/or wait, then allocate, although the comment still said

	/* Preallocate the olr before touching the ring */

which was no longer true as intel_wrap_ring_buffer() touches the ring.

The reversal didn't introduce any problems until the introduction of dynamic pinning, in

Quoted 1 line

7ba717c drm/i915/bdw: Pin the ringbuffer backing object to GGTT on-demand

With that came the possibility that the ringbuffer might not be pinned to the GTT or mapped into CPU address space when intel_ring_begin() is called. It gets pinned when the request is allocated, so it's now important that this comes before *anything* that can write into the ringbuffer, specifically intel_wrap_ring_buffer(), as this will fault if
(a) the ringbuffer happens not to be mapped, and (b) tail happens to be sufficiently close to the end of the ring to trigger wrapping.

The original rationale for this reversal seems to no longer apply, as we shouldn't ever have anything in the ringbuffer which is not associated with a specific request, and therefore shouldn't have anything to flush. So it should now be safe to reinstate the original sequence of allocate-wrap-wait :)

Between the original sequence swap and now, the ringbuffer code got cloned to become the execbuffer code, in

Quoted 1 line

82e104c drm/i915/bdw: New logical ring submission mechanism

So now we have to fix it in both paths ...

---
 drivers/gpu/drm/i915/intel_lrc.c        |    6 +++---
 drivers/gpu/drm/i915/intel_ringbuffer.c |    6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)
drivers/gpu/drm/i915/intel_lrc.c +3 -3
index 9b74ffa..4d82d9b 100644
@@ -809,12 +809,12 @@ static int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
 	if (ret)
 		return ret;
 
-	ret = logical_ring_prepare(ringbuf, ctx, num_dwords * sizeof(uint32_t));
+	/* Preallocate the olr before touching the ring */
+	ret = i915_gem_request_alloc(ring, ctx);
 	if (ret)
 		return ret;
 
-	/* Preallocate the olr before touching the ring */
-	ret = i915_gem_request_alloc(ring, ctx);
+	ret = logical_ring_prepare(ringbuf, ctx, num_dwords * sizeof(uint32_t));
 	if (ret)
 		return ret;
 
drivers/gpu/drm/i915/intel_ringbuffer.c +3 -3
index b70d25b..9f7a4d2 100644
@@ -2222,12 +2222,12 @@ int intel_ring_begin(struct intel_engine_cs *ring,
 	if (ret)
 		return ret;
 
-	ret = __intel_ring_prepare(ring, num_dwords * sizeof(uint32_t));
+	/* Preallocate the olr before touching the ring */
+	ret = i915_gem_request_alloc(ring, ring->default_context);
 	if (ret)
 		return ret;
 
-	/* Preallocate the olr before touching the ring */
-	ret = i915_gem_request_alloc(ring, ring->default_context);
+	ret = __intel_ring_prepare(ring, num_dwords * sizeof(uint32_t));
 	if (ret)
 		return ret;
 
Signature · 6 lines
1.7.9.5

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Tested-by on v1 1/1
#1 lore raw

Task id: 6557 -------------------------------------Summary-------------------------------------
Platform Delta drm-intel-nightly Series Applied

PNV                                  276/276              276/276
ILK                                  303/303              303/303
SNB                                  312/312              312/312
IVB                                  343/343              343/343
BYT                                  287/287              287/287
BDW                                  321/321              321/321

-------------------------------------Detailed-------------------------------------
Platform Test drm-intel-nightly Series Applied
Note: You need to pay more attention to line start with '*'
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

#2 lore raw
In reply to Dave Gordon
Quoted 29 lines · Dave Gordon

The original idea of preallocating the OLR was implemented in

Quoted 1 line

9d773091 drm/i915: Preallocate next seqno before touching the ring

and the sequence of operations was to allocate the OLR, then wrap past the end of the ring if necessary, then wait for space if necessary. But subsequently intel_ring_begin() was refactored, in

Quoted 1 line

304d695 drm/i915: Flush outstanding requests before allocating new seqno

to ensure that pending work that might need to be flushed used the old and not the newly-allocated request. This changed the sequence to wrap and/or wait, then allocate, although the comment still said

	/* Preallocate the olr before touching the ring */

which was no longer true as intel_wrap_ring_buffer() touches the ring.

The reversal didn't introduce any problems until the introduction of dynamic pinning, in

Quoted 1 line

7ba717c drm/i915/bdw: Pin the ringbuffer backing object to GGTT on-demand

With that came the possibility that the ringbuffer might not be pinned to the GTT or mapped into CPU address space when intel_ring_begin() is called. It gets pinned when the request is allocated, so it's now important that this comes before *anything* that can write into the ringbuffer, specifically intel_wrap_ring_buffer(), as this will fault if
(a) the ringbuffer happens not to be mapped, and (b) tail happens to be sufficiently close to the end of the ring to trigger wrapping.

Quoted 5 lines

The original rationale for this reversal seems to no longer apply, as we shouldn't ever have anything in the ringbuffer which is not associated with a specific request, and therefore shouldn't have anything to flush. So it should now be safe to reinstate the original sequence of allocate-wrap-wait :)

It still applies. If you submit say 1024 interrupted execbuffers they all share the same request. Then so does the 1025. Except the 1025th (for the sake of argument) requires extra space on the ring. To make that space it finishes the only request (since all 1024 are one and the same) the continues onwardsly blithely unaware it just lost the olr/seqno.

To fix this requires request create/commit semantics, where the request create manages the pinning of the context for itself, and also imposes the limitation that a single request cannot occupy the full ringbuffer. -Chris

Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#3 lore raw
Quoted 30 lines · Chris Wilson
Quoted 29 lines · Dave Gordon

The original idea of preallocating the OLR was implemented in

Quoted 1 line

9d773091 drm/i915: Preallocate next seqno before touching the ring

and the sequence of operations was to allocate the OLR, then wrap past the end of the ring if necessary, then wait for space if necessary. But subsequently intel_ring_begin() was refactored, in

Quoted 1 line

304d695 drm/i915: Flush outstanding requests before allocating new seqno

to ensure that pending work that might need to be flushed used the old and not the newly-allocated request. This changed the sequence to wrap and/or wait, then allocate, although the comment still said

	/* Preallocate the olr before touching the ring */

which was no longer true as intel_wrap_ring_buffer() touches the ring.

The reversal didn't introduce any problems until the introduction of dynamic pinning, in

Quoted 1 line

7ba717c drm/i915/bdw: Pin the ringbuffer backing object to GGTT on-demand

With that came the possibility that the ringbuffer might not be pinned to the GTT or mapped into CPU address space when intel_ring_begin() is called. It gets pinned when the request is allocated, so it's now important that this comes before *anything* that can write into the ringbuffer, specifically intel_wrap_ring_buffer(), as this will fault if
(a) the ringbuffer happens not to be mapped, and (b) tail happens to be sufficiently close to the end of the ring to trigger wrapping.

Quoted 7 lines
Quoted 5 lines

The original rationale for this reversal seems to no longer apply, as we shouldn't ever have anything in the ringbuffer which is not associated with a specific request, and therefore shouldn't have anything to flush. So it should now be safe to reinstate the original sequence of allocate-wrap-wait :)

It still applies. If you submit say 1024 interrupted execbuffers they

What is an interrupted execbuffer? AFAICT we hold the struct_mutex while stuffing the ringbuffer so we can only ever be in the process of adding instructions to one ringbuffer at a time, and we don't (now) interleave any flip commands (execlists mode requires mmio flip). Is there still something that just adds random stuff to someone else's OLR?

Quoted 10 lines

all share the same request. Then so does the 1025. Except the 1025th (for the sake of argument) requires extra space on the ring. To make that space it finishes the only request (since all 1024 are one and the same) the continues onwardsly blithely unaware it just lost the olr/seqno.

To fix this requires request create/commit semantics, where the request create manages the pinning of the context for itself, and also imposes the limitation that a single request cannot occupy the full ringbuffer. -Chris

Well I'd very much like create/commit semantics, so that we can roll back any sequence that breaks rather than leaving halfbaked command streams.

I'm pretty sure that no single request can occupy the full ringbuffer though. Last time I measured it, the maximal sequence for any single request was ~190 Dwords, considerably less than 1Kb, and not enough to fill even the small (4-page) rings used with GuC submission.

.Dave.
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

#4 lore raw
Quoted 7 lines · Dave Gordon
Quoted 1 line

It still applies. If you submit say 1024 interrupted execbuffers they

What is an interrupted execbuffer? AFAICT we hold the struct_mutex while stuffing the ringbuffer so we can only ever be in the process of adding instructions to one ringbuffer at a time, and we don't (now) interleave any flip commands (execlists mode requires mmio flip). Is there still something that just adds random stuff to someone else's OLR?

Write commands to stream, fail to add the request because the wait for ring space fails due to a pending signals. Repeat until the entire ring is filled by a single pending request.
-Chris

Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#5 lore raw
Quoted 9 lines · Chris Wilson
Quoted 7 lines · Dave Gordon
Quoted 1 line

It still applies. If you submit say 1024 interrupted execbuffers they

What is an interrupted execbuffer? AFAICT we hold the struct_mutex while stuffing the ringbuffer so we can only ever be in the process of adding instructions to one ringbuffer at a time, and we don't (now) interleave any flip commands (execlists mode requires mmio flip). Is there still something that just adds random stuff to someone else's OLR?

Quoted 4 lines

Write commands to stream, fail to add the request because the wait for ring space fails due to a pending signals. Repeat until the entire ring is filled by a single pending request.
-Chris

Uuuurgh ... I always said there was something wrong with leaving partial command streams in the ringbuffer :(

In the Android version we make sure that can't happen by checking that there's going to be enough space for all the commands generated by the request before we start writing into the ringbuffer, so no ring_begin() call thereafter can ever have to wait for more space.

Of course, having a global lock doesn't help. With multiple ringbuffers per engine, one should really only need a per-ringbuffer lock for writing into the ringbuffer ... and we should reset the tail pointer if writing the request is interrupted or aborted.

.Dave.
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

#6 lore raw
Quoted 15 lines · Dave Gordon
Quoted 9 lines · Chris Wilson
Quoted 7 lines · Dave Gordon
Quoted 1 line

It still applies. If you submit say 1024 interrupted execbuffers they

What is an interrupted execbuffer? AFAICT we hold the struct_mutex while stuffing the ringbuffer so we can only ever be in the process of adding instructions to one ringbuffer at a time, and we don't (now) interleave any flip commands (execlists mode requires mmio flip). Is there still something that just adds random stuff to someone else's OLR?

Quoted 4 lines

Write commands to stream, fail to add the request because the wait for ring space fails due to a pending signals. Repeat until the entire ring is filled by a single pending request.
-Chris

Quoted 7 lines

Uuuurgh ... I always said there was something wrong with leaving partial command streams in the ringbuffer :(

In the Android version we make sure that can't happen by checking that there's going to be enough space for all the commands generated by the request before we start writing into the ringbuffer, so no ring_begin() call thereafter can ever have to wait for more space.

Yeah that's the guarantee that the olr removal series should finally put into place by pre-reserving sufficient amounts of ringspace to guarantee we can put the execbuf in fully or not at all.

Quoted 4 lines

Of course, having a global lock doesn't help. With multiple ringbuffers per engine, one should really only need a per-ringbuffer lock for writing into the ringbuffer ... and we should reset the tail pointer if writing the request is interrupted or aborted.

Maybe someone should look at per-buffer locks before trying to split up the low-level hw locks ;-)
-Daniel

Signature · 7 lines
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#7 lore raw
Quoted 2 lines · Daniel Vetter

Maybe someone should look at per-buffer locks before trying to split up the low-level hw locks ;-)

Per-vm then per-buffer. Adding more locked operations to execbuf is scary though, with some workloads perf highlights the cost of the atomic for an uncontested mutex as being where the majority of the time is going.

At this point I am questing perf, but it is the last remaining locked instruction in that path...
-Chris

Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx