From 6dc0e816bb7478fd4dfebddcc65257f9ef161f7a Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Mon, 23 Jan 2012 15:30:02 -0800 Subject: drm/i915: correct lock type in destroy This is only relevant when using module unloading, and really only helps get rid of a probably benign warning. I can't remember if I sent this out already, but it's not turning up in any of my searches. Signed-off-by: Ben Widawsky Reviewed-by: Keith Packard Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_irq.c') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 5d433fc11ace..275ab6fecbd8 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1017,11 +1017,12 @@ void i915_destroy_error_state(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_error_state *error; + unsigned long flags; - spin_lock(&dev_priv->error_lock); + spin_lock_irqsave(&dev_priv->error_lock, flags); error = dev_priv->first_error; dev_priv->first_error = NULL; - spin_unlock(&dev_priv->error_lock); + spin_unlock_irqrestore(&dev_priv->error_lock, flags); if (error) i915_error_state_free(dev, error); -- cgit v1.2.3 From 96154f2faba540281073243d61108d1705d19c6d Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 14 Dec 2011 13:57:00 +0100 Subject: drm/i915: switch ring->id to be a real id ... and add a helpr function for the places where we want a flag. This way we can use ring->id to index into arrays. v2: Resurrect the missing beautification-space Chris Wilson noted. I'm moving this space around because I'll reuse ring_str in the next patch. Reviewed-by: Chris Wilson Reviewed-by: Ben Widawsky Reviewed-by: Eugeni Dodonov Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/i915/i915_irq.c') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 275ab6fecbd8..ab53edb9f294 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -804,7 +804,7 @@ static u32 capture_bo_list(struct drm_i915_error_buffer *err, err->tiling = obj->tiling_mode; err->dirty = obj->dirty; err->purgeable = obj->madv != I915_MADV_WILLNEED; - err->ring = obj->ring ? obj->ring->id : 0; + err->ring = obj->ring ? obj->ring->id : -1; err->cache_level = obj->cache_level; if (++i == count) -- cgit v1.2.3 From d27b1e0ec2a0a04770b2ebf70a2e01281ef93562 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 14 Dec 2011 13:57:01 +0100 Subject: drm/i915: refactor ring error state capture to use arrays The code already got unwieldy and we want to dump more per-ring registers. Only functional change is that we now also capture the video ring registers on ilk. v2: fixup a refactor fumble spotted by Chris Wilson. Reviewed-by: Eugeni Dodonov Reviewed-by: Chris Wilson Signed-off-by: Ben Widawsky Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 70 +++++++++++++++++++++-------------------- 1 file changed, 36 insertions(+), 34 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_irq.c') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index ab53edb9f294..dffeef870b3b 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -876,6 +876,32 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv, return NULL; } +static void i915_record_ring_state(struct drm_device *dev, + struct drm_i915_error_state *error, + struct intel_ring_buffer *ring) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (INTEL_INFO(dev)->gen >= 4) { + error->ipeir[ring->id] = I915_READ(RING_IPEIR(ring->mmio_base)); + error->ipehr[ring->id] = I915_READ(RING_IPEHR(ring->mmio_base)); + error->instdone[ring->id] = I915_READ(RING_INSTDONE(ring->mmio_base)); + if (ring->id == RCS) { + error->instps = I915_READ(INSTPS); + error->instdone1 = I915_READ(INSTDONE1); + error->bbaddr = I915_READ64(BB_ADDR); + } + } else { + error->ipeir[ring->id] = I915_READ(IPEIR); + error->ipehr[ring->id] = I915_READ(IPEHR); + error->instdone[ring->id] = I915_READ(INSTDONE); + error->bbaddr = 0; + } + + error->seqno[ring->id] = ring->get_seqno(ring); + error->acthd[ring->id] = intel_ring_get_active_head(ring); +} + /** * i915_capture_error_state - capture an error record for later analysis * @dev: drm device @@ -909,47 +935,23 @@ static void i915_capture_error_state(struct drm_device *dev) DRM_INFO("capturing error event; look for more information in /debug/dri/%d/i915_error_state\n", dev->primary->index); - error->seqno = dev_priv->ring[RCS].get_seqno(&dev_priv->ring[RCS]); error->eir = I915_READ(EIR); error->pgtbl_er = I915_READ(PGTBL_ER); for_each_pipe(pipe) error->pipestat[pipe] = I915_READ(PIPESTAT(pipe)); error->instpm = I915_READ(INSTPM); - error->error = 0; - if (INTEL_INFO(dev)->gen >= 6) { + + if (INTEL_INFO(dev)->gen >= 6) error->error = I915_READ(ERROR_GEN6); + else + error->error = 0; + + i915_record_ring_state(dev, error, &dev_priv->ring[RCS]); + if (HAS_BLT(dev)) + i915_record_ring_state(dev, error, &dev_priv->ring[BCS]); + if (HAS_BSD(dev)) + i915_record_ring_state(dev, error, &dev_priv->ring[VCS]); - error->bcs_acthd = I915_READ(BCS_ACTHD); - error->bcs_ipehr = I915_READ(BCS_IPEHR); - error->bcs_ipeir = I915_READ(BCS_IPEIR); - error->bcs_instdone = I915_READ(BCS_INSTDONE); - error->bcs_seqno = 0; - if (dev_priv->ring[BCS].get_seqno) - error->bcs_seqno = dev_priv->ring[BCS].get_seqno(&dev_priv->ring[BCS]); - - error->vcs_acthd = I915_READ(VCS_ACTHD); - error->vcs_ipehr = I915_READ(VCS_IPEHR); - error->vcs_ipeir = I915_READ(VCS_IPEIR); - error->vcs_instdone = I915_READ(VCS_INSTDONE); - error->vcs_seqno = 0; - if (dev_priv->ring[VCS].get_seqno) - error->vcs_seqno = dev_priv->ring[VCS].get_seqno(&dev_priv->ring[VCS]); - } - if (INTEL_INFO(dev)->gen >= 4) { - error->ipeir = I915_READ(IPEIR_I965); - error->ipehr = I915_READ(IPEHR_I965); - error->instdone = I915_READ(INSTDONE_I965); - error->instps = I915_READ(INSTPS); - error->instdone1 = I915_READ(INSTDONE1); - error->acthd = I915_READ(ACTHD_I965); - error->bbaddr = I915_READ64(BB_ADDR); - } else { - error->ipeir = I915_READ(IPEIR); - error->ipehr = I915_READ(IPEHR); - error->instdone = I915_READ(INSTDONE); - error->acthd = I915_READ(ACTHD); - error->bbaddr = 0; - } i915_gem_record_fences(dev, error); /* Record the active batch and ring buffers */ -- cgit v1.2.3 From c1cd90ed7957d1dd8aa6138468d71003fbc095ce Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 14 Dec 2011 13:57:02 +0100 Subject: drm/i915: collect more per ring error state Based on a patch by Ben Widawsky, but with different colors for the bikeshed. In contrast to Ben's patch this one doesn't add the fault regs. Afaics they're for the optional page fault support which - we're not enabling - and which seems to be unsupported by the hw team. Recent bspec lacks tons of information about this that the public docs released half a year back still contain. Also dump ring HEAD/TAIL registers - I've recently seen a few error_state where just guessing these is not good enough. v2: Also dump INSTPM for every ring. v3: Fix a few really silly goof-ups spotted by Chris Wilson. Reviewed-by: Eugeni Dodonov Reviewed-by: Chris Wilson Signed-off-by: Ben Widawsky Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_irq.c') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index dffeef870b3b..1e75c44af56a 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -882,12 +882,15 @@ static void i915_record_ring_state(struct drm_device *dev, { struct drm_i915_private *dev_priv = dev->dev_private; + if (INTEL_INFO(dev)->gen >= 6) + error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base)); + if (INTEL_INFO(dev)->gen >= 4) { error->ipeir[ring->id] = I915_READ(RING_IPEIR(ring->mmio_base)); error->ipehr[ring->id] = I915_READ(RING_IPEHR(ring->mmio_base)); error->instdone[ring->id] = I915_READ(RING_INSTDONE(ring->mmio_base)); + error->instps[ring->id] = I915_READ(RING_INSTPS(ring->mmio_base)); if (ring->id == RCS) { - error->instps = I915_READ(INSTPS); error->instdone1 = I915_READ(INSTDONE1); error->bbaddr = I915_READ64(BB_ADDR); } @@ -898,8 +901,11 @@ static void i915_record_ring_state(struct drm_device *dev, error->bbaddr = 0; } + error->instpm[ring->id] = I915_READ(RING_INSTPM(ring->mmio_base)); error->seqno[ring->id] = ring->get_seqno(ring); error->acthd[ring->id] = intel_ring_get_active_head(ring); + error->head[ring->id] = I915_READ_HEAD(ring); + error->tail[ring->id] = I915_READ_TAIL(ring); } /** @@ -939,7 +945,6 @@ static void i915_capture_error_state(struct drm_device *dev) error->pgtbl_er = I915_READ(PGTBL_ER); for_each_pipe(pipe) error->pipestat[pipe] = I915_READ(PIPESTAT(pipe)); - error->instpm = I915_READ(INSTPM); if (INTEL_INFO(dev)->gen >= 6) error->error = I915_READ(ERROR_GEN6); -- cgit v1.2.3 From 653d7bed26a0c298dee7d60f6ab4bb442acf8b82 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 14 Dec 2011 13:57:21 +0100 Subject: drm/i915: capture error_state also for stuck rings Since quite a while we also the basic output configuration in the error_state, so it should contain enough information to diagnose these MI_WAIT hangs. Reviewed-and-tested-by: Chris Wilson Reviewed-by: Eugeni Dodonov Signed-Off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_irq.c') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 1e75c44af56a..4dedb3148066 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1706,6 +1706,7 @@ void i915_hangcheck_elapsed(unsigned long data) dev_priv->last_instdone1 == instdone1) { if (dev_priv->hangcheck_count++ > 1) { DRM_ERROR("Hangcheck timer elapsed... GPU hung\n"); + i915_handle_error(dev, true); if (!IS_GEN2(dev)) { /* Is the chip hanging on a WAIT_FOR_EVENT? @@ -1713,7 +1714,6 @@ void i915_hangcheck_elapsed(unsigned long data) * and break the hang. This should work on * all but the second generation chipsets. */ - if (kick_ring(&dev_priv->ring[RCS])) goto repeat; @@ -1726,7 +1726,6 @@ void i915_hangcheck_elapsed(unsigned long data) goto repeat; } - i915_handle_error(dev, true); return; } } else { -- cgit v1.2.3 From 33f3f518fbb65d86f163083b74823e8bbe561bfc Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 14 Dec 2011 13:57:39 +0100 Subject: drm/i915: add per-ring fault reg to error_state This was pretty handy when figuring out what exactly went wrong with ppgtt and it might also be useful when we stop filling the entire gart with scratch page entries. Also add the gen6+ DONE reg while at it. v2: Chris Wilson suggested to allocate the error_state with kzalloc for better paranoia. Also kill existing spurious clears of the error_state while at it. Reviewed-by: Ben Widawsky Reviewed-by: Eugeni Dodonov Signed-Off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_irq.c') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 4dedb3148066..64bb2127911e 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -882,8 +882,10 @@ static void i915_record_ring_state(struct drm_device *dev, { struct drm_i915_private *dev_priv = dev->dev_private; - if (INTEL_INFO(dev)->gen >= 6) + if (INTEL_INFO(dev)->gen >= 6) { error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base)); + error->fault_reg[ring->id] = I915_READ(RING_FAULT_REG(ring)); + } if (INTEL_INFO(dev)->gen >= 4) { error->ipeir[ring->id] = I915_READ(RING_IPEIR(ring->mmio_base)); @@ -898,7 +900,6 @@ static void i915_record_ring_state(struct drm_device *dev, error->ipeir[ring->id] = I915_READ(IPEIR); error->ipehr[ring->id] = I915_READ(IPEHR); error->instdone[ring->id] = I915_READ(INSTDONE); - error->bbaddr = 0; } error->instpm[ring->id] = I915_READ(RING_INSTPM(ring->mmio_base)); @@ -932,7 +933,7 @@ static void i915_capture_error_state(struct drm_device *dev) return; /* Account for pipe specific data like PIPE*STAT */ - error = kmalloc(sizeof(*error), GFP_ATOMIC); + error = kzalloc(sizeof(*error), GFP_ATOMIC); if (!error) { DRM_DEBUG_DRIVER("out of memory, not capturing error state\n"); return; @@ -946,10 +947,10 @@ static void i915_capture_error_state(struct drm_device *dev) for_each_pipe(pipe) error->pipestat[pipe] = I915_READ(PIPESTAT(pipe)); - if (INTEL_INFO(dev)->gen >= 6) + if (INTEL_INFO(dev)->gen >= 6) { error->error = I915_READ(ERROR_GEN6); - else - error->error = 0; + error->done_reg = I915_READ(DONE_REG); + } i915_record_ring_state(dev, error, &dev_priv->ring[RCS]); if (HAS_BLT(dev)) -- cgit v1.2.3 From 172975aa746e155533cb386c7159c2d6510e2bc8 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 14 Dec 2011 13:57:25 +0100 Subject: drm/i915: Handle unmappable buffers during error state capture As the buffer is not necessarily accessible through the GTT at the time of a GPU hang, and capturing some of its contents is far more valuable than skipping it, provide a clflushed fallback read path. We still prefer to read through the GTT as that is more consistent with the GPU access of the same buffer. So example it will demonstrate any errorneous tiling or swizzling of the command buffer as seen by the GPU. This becomes necessary with use of CPU relocations and lazy GTT binding, but could potentially happen anyway as a result of a pathological error. Signed-off-by: Chris Wilson Reviewed-by: Daniel Vetter Reviewed-by: Eugeni Dodonov Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_irq.c') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 64bb2127911e..8ea1ca4158a0 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -720,7 +720,6 @@ i915_error_object_create(struct drm_i915_private *dev_priv, reloc_offset = src->gtt_offset; for (page = 0; page < page_count; page++) { unsigned long flags; - void __iomem *s; void *d; d = kmalloc(PAGE_SIZE, GFP_ATOMIC); @@ -728,10 +727,29 @@ i915_error_object_create(struct drm_i915_private *dev_priv, goto unwind; local_irq_save(flags); - s = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, - reloc_offset); - memcpy_fromio(d, s, PAGE_SIZE); - io_mapping_unmap_atomic(s); + if (reloc_offset < dev_priv->mm.gtt_mappable_end) { + void __iomem *s; + + /* Simply ignore tiling or any overlapping fence. + * It's part of the error state, and this hopefully + * captures what the GPU read. + */ + + s = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, + reloc_offset); + memcpy_fromio(d, s, PAGE_SIZE); + io_mapping_unmap_atomic(s); + } else { + void *s; + + drm_clflush_pages(&src->pages[page], 1); + + s = kmap_atomic(src->pages[page]); + memcpy(d, s, PAGE_SIZE); + kunmap_atomic(s); + + drm_clflush_pages(&src->pages[page], 1); + } local_irq_restore(flags); dst->pages[page] = d; -- cgit v1.2.3 From 7e3b8737e719c4de7dd79b096b80ece444b2f0ba Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 1 Feb 2012 22:26:45 +0100 Subject: drm/i915: dump even more into the error_state Chris Wilson and me have again stared at funny error states and it's been pretty clear from the start that something was seriously amiss. The seqnos last seen by the cpu were a few hundred behind those that the gpu could have possibly emitted last before it died ... Chris now tracked it down (hopefully, definit verdict's still out), but in hindsight we'd have found the bug by simply dumping the cpu side tracking of the ring head and tail registers. Fix this and prevent an identical time-waster in the future. Because the hangs always involved semaphores in one way or another, we've tried to dump the mbox registers, but couldn't find any inconsistencies. Still, dump them too. Reviewed-and-wanted-by: Chris Wilson Reviewed-by: Eugeni Dodonov Signed-Off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'drivers/gpu/drm/i915/i915_irq.c') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 8ea1ca4158a0..cde1ce94563c 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -903,6 +903,10 @@ static void i915_record_ring_state(struct drm_device *dev, if (INTEL_INFO(dev)->gen >= 6) { error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base)); error->fault_reg[ring->id] = I915_READ(RING_FAULT_REG(ring)); + error->semaphore_mboxes[ring->id][0] + = I915_READ(RING_SYNC_0(ring->mmio_base)); + error->semaphore_mboxes[ring->id][1] + = I915_READ(RING_SYNC_1(ring->mmio_base)); } if (INTEL_INFO(dev)->gen >= 4) { @@ -925,6 +929,9 @@ static void i915_record_ring_state(struct drm_device *dev, error->acthd[ring->id] = intel_ring_get_active_head(ring); error->head[ring->id] = I915_READ_HEAD(ring); error->tail[ring->id] = I915_READ_TAIL(ring); + + error->cpu_ring_head[ring->id] = ring->head; + error->cpu_ring_tail[ring->id] = ring->tail; } /** -- cgit v1.2.3 From 99ffa1629d737295e569267cf5940758139f9ddb Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 25 Jan 2012 14:04:00 +0100 Subject: drm/i915: enable forcewake voodoo also for gen6 We still have reports of missed irqs even on Sandybridge with the HWSTAM workaround in place. Testing by the bug reporter gets rid of them with the forcewake voodoo and no HWSTAM writes. Because I've slightly botched the rebasing I've left out the ACTHD readback which is also required to get IVB working. Seems to still work on the tester's machine, so I think we should go with the more minmal approach on SNB. Especially since I've only found weak evidence for holding forcewake while waiting for an interrupt to arrive, but none for the ACTHD readback. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=45181 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=45332 Tested-by: Nicolas Kalkhof nkalkhof()at()web.de Acked-by: Chris Wilson Signed-Off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_irq.c') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 063b4577d4c6..bd6168be63d3 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1785,18 +1785,6 @@ static void ironlake_irq_preinstall(struct drm_device *dev) I915_WRITE(HWSTAM, 0xeffe); - if (IS_GEN6(dev)) { - /* Workaround stalls observed on Sandy Bridge GPUs by - * making the blitter command streamer generate a - * write to the Hardware Status Page for - * MI_USER_INTERRUPT. This appears to serialize the - * previous seqno write out before the interrupt - * happens. - */ - I915_WRITE(GEN6_BLITTER_HWSTAM, ~GEN6_BLITTER_USER_INTERRUPT); - I915_WRITE(GEN6_BSD_HWSTAM, ~GEN6_BSD_USER_INTERRUPT); - } - /* XXX hotplug from PCH */ I915_WRITE(DEIMR, 0xffffffff); -- cgit v1.2.3 From 52d39a21350531063bf8f4f704101bd371ea5d7d Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 15 Feb 2012 11:25:37 +0000 Subject: drm/i915: Record the in-flight requests at the time of a hang Being able to tally the list of outstanding requests with the sequence of commands in the ringbuffer is often useful evidence with respect to driver corruption. Note that since this is the umpteenth per-ring data structure to be added to the error state, I've coallesced the nearby loops (the ringbuffer and batchbuffer) into a single structure along with the list of requests. A later task would be to refactor the ring register state into the same structure. v2: Fix pretty printing of requests so that they are parsed correctly by intel_error_decode and use the 0x%08x format for seqno for consistency Signed-off-by: Chris Wilson Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 73 ++++++++++++++++++++++++++++------------- 1 file changed, 51 insertions(+), 22 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_irq.c') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index bd6168be63d3..85504fb1a4b3 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -788,11 +788,11 @@ i915_error_state_free(struct drm_device *dev, { int i; - for (i = 0; i < ARRAY_SIZE(error->batchbuffer); i++) - i915_error_object_free(error->batchbuffer[i]); - - for (i = 0; i < ARRAY_SIZE(error->ringbuffer); i++) - i915_error_object_free(error->ringbuffer[i]); + for (i = 0; i < ARRAY_SIZE(error->ring); i++) { + i915_error_object_free(error->ring[i].batchbuffer); + i915_error_object_free(error->ring[i].ringbuffer); + kfree(error->ring[i].requests); + } kfree(error->active_bo); kfree(error->overlay); @@ -934,6 +934,51 @@ static void i915_record_ring_state(struct drm_device *dev, error->cpu_ring_tail[ring->id] = ring->tail; } +static void i915_gem_record_rings(struct drm_device *dev, + struct drm_i915_error_state *error) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_gem_request *request; + int i, count; + + for (i = 0; i < I915_NUM_RINGS; i++) { + struct intel_ring_buffer *ring = &dev_priv->ring[i]; + + if (ring->obj == NULL) + continue; + + i915_record_ring_state(dev, error, ring); + + error->ring[i].batchbuffer = + i915_error_first_batchbuffer(dev_priv, ring); + + error->ring[i].ringbuffer = + i915_error_object_create(dev_priv, ring->obj); + + count = 0; + list_for_each_entry(request, &ring->request_list, list) + count++; + + error->ring[i].num_requests = count; + error->ring[i].requests = + kmalloc(count*sizeof(struct drm_i915_error_request), + GFP_ATOMIC); + if (error->ring[i].requests == NULL) { + error->ring[i].num_requests = 0; + continue; + } + + count = 0; + list_for_each_entry(request, &ring->request_list, list) { + struct drm_i915_error_request *erq; + + erq = &error->ring[i].requests[count++]; + erq->seqno = request->seqno; + erq->jiffies = request->emitted_jiffies; + } + } +} + /** * i915_capture_error_state - capture an error record for later analysis * @dev: drm device @@ -977,24 +1022,8 @@ static void i915_capture_error_state(struct drm_device *dev) error->done_reg = I915_READ(DONE_REG); } - i915_record_ring_state(dev, error, &dev_priv->ring[RCS]); - if (HAS_BLT(dev)) - i915_record_ring_state(dev, error, &dev_priv->ring[BCS]); - if (HAS_BSD(dev)) - i915_record_ring_state(dev, error, &dev_priv->ring[VCS]); - i915_gem_record_fences(dev, error); - - /* Record the active batch and ring buffers */ - for (i = 0; i < I915_NUM_RINGS; i++) { - error->batchbuffer[i] = - i915_error_first_batchbuffer(dev_priv, - &dev_priv->ring[i]); - - error->ringbuffer[i] = - i915_error_object_create(dev_priv, - dev_priv->ring[i].obj); - } + i915_gem_record_rings(dev, error); /* Record buffers on the active and pinned lists. */ error->active_bo = NULL; -- cgit v1.2.3 From ee4f42b10bbc404579c2e6f446b24d898592753c Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 15 Feb 2012 11:25:38 +0000 Subject: drm/i915: Record the position of the request upon error So that we can tally the request against the command sequence in the ringbuffer, or merely jump to the interesting locations. Signed-off-by: Chris Wilson Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/gpu/drm/i915/i915_irq.c') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 85504fb1a4b3..afd4e03e337e 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -975,6 +975,7 @@ static void i915_gem_record_rings(struct drm_device *dev, erq = &error->ring[i].requests[count++]; erq->seqno = request->seqno; erq->jiffies = request->emitted_jiffies; + erq->tail = request->tail; } } } -- cgit v1.2.3