From d43f3ebf12f59c57782ec652da65ef61c2662b40 Mon Sep 17 00:00:00 2001 From: Akash Goel Date: Fri, 11 Mar 2016 14:56:42 +0530 Subject: drm/i915: Fixup the free space logic in ring_prepare Currently for the case where there is enough space at the end of Ring buffer for accommodating only the base request, the wrapround is done immediately and as a result the base request gets added at the start of Ring buffer. But there may not be enough free space at the beginning to accommodate the base request, as before the wraparound, the wait was effectively done for the reserved_size free space from the start of Ring buffer. In such a case there is a potential of Ring buffer overflow, the instructions at the head of Ring (ACTHD) can get overwritten. Since the base request can fit in the remaining space, there is no need to wraparound immediately. The wraparound will anyway happen later when the reserved part starts getting used. Cc: Chris Wilson Signed-off-by: Akash Goel Signed-off-by: Chris Wilson Link: http://patchwork.freedesktop.org/patch/msgid/1457688402-10411-1-git-send-email-akash.goel@intel.com Reviewed-by: Chris Wilson Cc: stable@vger.kernel.org (cherry picked from commit 782f6bc0aba037436d6a04d19b23f8b61020a576) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c') diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 45ce45a5e122..c2ea2cd80d70 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -2454,11 +2454,11 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes) if (unlikely(total_bytes > remain_usable)) { /* * The base request will fit but the reserved space - * falls off the end. So only need to to wait for the - * reserved size after flushing out the remainder. + * falls off the end. So don't need an immediate wrap + * and only need to effectively wait for the reserved + * size space from the start of ringbuffer. */ wait_bytes = remain_actual + ringbuf->reserved_size; - need_wrap = true; } else if (total_bytes > ringbuf->space) { /* No wrapping required, just waiting. */ wait_bytes = total_bytes; -- cgit v1.2.1 From 510650e8b2ab965931b35e9813467439d4df0b9c Mon Sep 17 00:00:00 2001 From: Mika Kuoppala Date: Tue, 5 Apr 2016 15:56:17 +0300 Subject: drm/i915/skl: Fix spurious gpu hang with gt3/gt4 revs Experiments with heaven 4.0 benchmark and skylake gt3e (rev 0xa) suggest that WaForceContextSaveRestoreNonCoherent is needed for all revs. Extending this to all revs cures a gpu hang with rev 0xa when running heaven4.0 gpu benchmark. We have been here before, with problems enabling gt4e and extending up to revision F0 instead of false claims of bspec of E0 only. See commit ("drm/i915/skl: Default to noncoherent access up to F0"). In retrospect we should have covered this with this big blanket back then already, as E0 vs F0 discrepancy was suspicious enough. Previously the WaForceEnableNonCoherent has been tied to context non-coherence, atleast in relevant hsds. So keep this tie and extended this alongside. Cc: Abdiel Janulgue Cc: Ben Widawsky Cc: Timo Aaltonen Cc: stable@vger.kernel.org Reported-by: Mike Lothian References: https://bugs.freedesktop.org/show_bug.cgi?id=93491 Signed-off-by: Mika Kuoppala Reviewed-by: Ben Widawsky Tested-by: Timo Aaltonen Link: http://patchwork.freedesktop.org/patch/msgid/1459860977-27751-2-git-send-email-mika.kuoppala@intel.com (cherry picked from commit 97ea6be161c55dec896b65c95157d953c330ae05) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_ringbuffer.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c') diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index c2ea2cd80d70..bd7321b9bbaf 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -968,7 +968,7 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring) /* WaForceContextSaveRestoreNonCoherent:skl,bxt */ tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT; - if (IS_SKL_REVID(dev, SKL_REVID_F0, SKL_REVID_F0) || + if (IS_SKL_REVID(dev, SKL_REVID_F0, REVID_FOREVER) || IS_BXT_REVID(dev, BXT_REVID_B0, REVID_FOREVER)) tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE; WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp); @@ -1085,7 +1085,8 @@ static int skl_init_workarounds(struct intel_engine_cs *ring) WA_SET_BIT_MASKED(HIZ_CHICKEN, BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE); - if (IS_SKL_REVID(dev, 0, SKL_REVID_F0)) { + /* This is tied to WaForceContextSaveRestoreNonCoherent */ + if (IS_SKL_REVID(dev, 0, REVID_FOREVER)) { /* *Use Force Non-Coherent whenever executing a 3D context. This * is a workaround for a possible hang in the unlikely event -- cgit v1.2.1 From 1b3e885a05d4f0a35dde035724e7c6453d2cbe71 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 13 Apr 2016 17:35:11 +0100 Subject: drm/i915: Force ringbuffers to not be at offset 0 For reasons unknown Sandybridge GT1 (at least) will eventually hang when it encounters a ring wraparound at offset 0. The test case that reproduces the bug reliably forces a large number of interrupted context switches, thereby causing very frequent ring wraparounds, but there are similar bug reports in the wild with the same symptoms, seqno writes stop just before the wrap and the ringbuffer at address 0. It is also timing crucial, but adding various delays hasn't helped pinpoint where the window lies. Whether the fault is restricted to the ringbuffer itself or the GTT addressing is unclear, but moving the ringbuffer fixes all the hangs I have been able to reproduce. References: (e.g.) https://bugs.freedesktop.org/show_bug.cgi?id=93262 Testcase: igt/gem_exec_whisper/render-contexts-interruptible #snb-gt1 Signed-off-by: Chris Wilson Cc: stable@vger.kernel.org Acked-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1460565315-7748-12-git-send-email-chris@chris-wilson.co.uk (cherry picked from commit a687a43a48f0f91ba37dce5a14b467258ed6f035) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_ringbuffer.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/i915/intel_ringbuffer.c') diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index bd7321b9bbaf..9121646d7c4d 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -2091,10 +2091,12 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev, { struct drm_i915_private *dev_priv = to_i915(dev); struct drm_i915_gem_object *obj = ringbuf->obj; + /* Ring wraparound at offset 0 sometimes hangs. No idea why. */ + unsigned flags = PIN_OFFSET_BIAS | 4096; int ret; if (HAS_LLC(dev_priv) && !obj->stolen) { - ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, 0); + ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, flags); if (ret) return ret; @@ -2110,7 +2112,8 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev, return -ENOMEM; } } else { - ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE); + ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, + flags | PIN_MAPPABLE); if (ret) return ret; -- cgit v1.2.1