From f616f2830c1ed79245cfeca900f7e8a3b3c08c06 Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Thu, 1 Mar 2018 11:06:13 +0000 Subject: [PATCH 1/2] drm/i915/perf: fix perf stream opening lock We're seeing on CI that some contexts don't have the programmed OA period timer that directs the OA unit on how often to write reports. The issue is that we're not holding the drm lock from when we edit the context images down to when we set the exclusive_stream variable. This leaves a window for the deferred context allocation to call i915_oa_init_reg_state() that will not program the expected OA timer value, because we haven't set the exclusive_stream yet. v2: Drop need_lock from gen8_configure_all_contexts() (Matt) Signed-off-by: Lionel Landwerlin Reviewed-by: Matthew Auld Reviewed-by: Chris Wilson Fixes: 701f8231a2f ("drm/i915/perf: prune OA configs") Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102254 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103715 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103755 Link: https://patchwork.freedesktop.org/patch/msgid/20180301110613.1737-1-lionel.g.landwerlin@intel.com Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Rodrigo Vivi Cc: intel-gfx@lists.freedesktop.org Cc: # v4.14+ (cherry picked from commit 41d3fdcd15d5ecf29cc73e8b79c2327ebb54b960) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/i915_perf.c | 42 +++++++++++--------------------- 1 file changed, 14 insertions(+), 28 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 0be50e43507d..f8fe5ffcdcff 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1303,9 +1303,8 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) */ mutex_lock(&dev_priv->drm.struct_mutex); dev_priv->perf.oa.exclusive_stream = NULL; - mutex_unlock(&dev_priv->drm.struct_mutex); - dev_priv->perf.oa.ops.disable_metric_set(dev_priv); + mutex_unlock(&dev_priv->drm.struct_mutex); free_oa_buffer(dev_priv); @@ -1756,22 +1755,13 @@ static int gen8_switch_to_updated_kernel_context(struct drm_i915_private *dev_pr * Note: it's only the RCS/Render context that has any OA state. */ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv, - const struct i915_oa_config *oa_config, - bool interruptible) + const struct i915_oa_config *oa_config) { struct i915_gem_context *ctx; int ret; unsigned int wait_flags = I915_WAIT_LOCKED; - if (interruptible) { - ret = i915_mutex_lock_interruptible(&dev_priv->drm); - if (ret) - return ret; - - wait_flags |= I915_WAIT_INTERRUPTIBLE; - } else { - mutex_lock(&dev_priv->drm.struct_mutex); - } + lockdep_assert_held(&dev_priv->drm.struct_mutex); /* Switch away from any user context. */ ret = gen8_switch_to_updated_kernel_context(dev_priv, oa_config); @@ -1819,8 +1809,6 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv, } out: - mutex_unlock(&dev_priv->drm.struct_mutex); - return ret; } @@ -1863,7 +1851,7 @@ static int gen8_enable_metric_set(struct drm_i915_private *dev_priv, * to make sure all slices/subslices are ON before writing to NOA * registers. */ - ret = gen8_configure_all_contexts(dev_priv, oa_config, true); + ret = gen8_configure_all_contexts(dev_priv, oa_config); if (ret) return ret; @@ -1878,7 +1866,7 @@ static int gen8_enable_metric_set(struct drm_i915_private *dev_priv, static void gen8_disable_metric_set(struct drm_i915_private *dev_priv) { /* Reset all contexts' slices/subslices configurations. */ - gen8_configure_all_contexts(dev_priv, NULL, false); + gen8_configure_all_contexts(dev_priv, NULL); I915_WRITE(GDT_CHICKEN_BITS, (I915_READ(GDT_CHICKEN_BITS) & ~GT_NOA_ENABLE)); @@ -1888,7 +1876,7 @@ static void gen8_disable_metric_set(struct drm_i915_private *dev_priv) static void gen10_disable_metric_set(struct drm_i915_private *dev_priv) { /* Reset all contexts' slices/subslices configurations. */ - gen8_configure_all_contexts(dev_priv, NULL, false); + gen8_configure_all_contexts(dev_priv, NULL); /* Make sure we disable noa to save power. */ I915_WRITE(RPM_CONFIG1, @@ -2138,6 +2126,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, if (ret) goto err_oa_buf_alloc; + ret = i915_mutex_lock_interruptible(&dev_priv->drm); + if (ret) + goto err_lock; + ret = dev_priv->perf.oa.ops.enable_metric_set(dev_priv, stream->oa_config); if (ret) @@ -2145,23 +2137,17 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, stream->ops = &i915_oa_stream_ops; - /* Lock device for exclusive_stream access late because - * enable_metric_set() might lock as well on gen8+. - */ - ret = i915_mutex_lock_interruptible(&dev_priv->drm); - if (ret) - goto err_lock; - dev_priv->perf.oa.exclusive_stream = stream; mutex_unlock(&dev_priv->drm.struct_mutex); return 0; -err_lock: - dev_priv->perf.oa.ops.disable_metric_set(dev_priv); - err_enable: + dev_priv->perf.oa.ops.disable_metric_set(dev_priv); + mutex_unlock(&dev_priv->drm.struct_mutex); + +err_lock: free_oa_buffer(dev_priv); err_oa_buf_alloc: From 88d3dfb6a69042381161290c7ce19e1f53fc2a66 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 2 Mar 2018 11:33:24 +0000 Subject: [PATCH 2/2] drm/i915: Suspend submission tasklets around wedging After staring hard at sequences like [ 28.199013] systemd-1 2..s. 26062228us : execlists_submission_tasklet: rcs0 cs-irq head=0 [0?], tail=1 [1?] [ 28.199095] systemd-1 2..s. 26062229us : execlists_submission_tasklet: rcs0 csb[1]: status=0x00000018:0x00000000, active=0x1 [ 28.199177] systemd-1 2..s. 26062230us : execlists_submission_tasklet: rcs0 out[0]: ctx=0.1, seqno=3, prio=-1024 [ 28.199258] systemd-1 2..s. 26062231us : execlists_submission_tasklet: rcs0 completed ctx=0 [ 28.199340] gem_eio-829 1..s1 26066853us : execlists_submission_tasklet: rcs0 in[0]: ctx=1.1, seqno=1, prio=0 [ 28.199421] -0 2..s. 26066863us : execlists_submission_tasklet: rcs0 cs-irq head=1 [1?], tail=2 [2?] [ 28.199503] -0 2..s. 26066865us : execlists_submission_tasklet: rcs0 csb[2]: status=0x00000001:0x00000000, active=0x1 [ 28.199585] gem_eio-829 1..s1 26067077us : execlists_submission_tasklet: rcs0 in[1]: ctx=3.1, seqno=2, prio=0 [ 28.199667] gem_eio-829 1..s1 26067078us : execlists_submission_tasklet: rcs0 in[0]: ctx=1.2, seqno=1, prio=0 [ 28.199749] -0 2..s. 26067084us : execlists_submission_tasklet: rcs0 cs-irq head=2 [2?], tail=3 [3?] [ 28.199830] -0 2..s. 26067085us : execlists_submission_tasklet: rcs0 csb[3]: status=0x00008002:0x00000001, active=0x1 [ 28.199912] -0 2..s. 26067086us : execlists_submission_tasklet: rcs0 out[0]: ctx=1.2, seqno=1, prio=0 [ 28.199994] gem_eio-829 2..s. 28246084us : execlists_submission_tasklet: rcs0 cs-irq head=3 [3?], tail=4 [4?] [ 28.200096] gem_eio-829 2..s. 28246088us : execlists_submission_tasklet: rcs0 csb[4]: status=0x00000014:0x00000001, active=0x5 [ 28.200178] gem_eio-829 2..s. 28246089us : execlists_submission_tasklet: rcs0 out[0]: ctx=0.0, seqno=0, prio=0 [ 28.200260] gem_eio-829 2..s. 28246127us : execlists_submission_tasklet: execlists_submission_tasklet:886 GEM_BUG_ON(buf[2 * head + 1] != port->context_id) the conclusion is that the only place where the ports are reset to zero, is from engine->cancel_requests called during i915_gem_set_wedged(). The race is horrible as it results from calling set-wedged on active HW (the GPU reset failed) and as such we need to be careful as the HW state changes beneath us. Fortunately, it's the same scary conditions as affect normal reset, so we can reuse the same machinery to disable state tracking as we clobber it. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104945 Signed-off-by: Chris Wilson Cc: Mika Kuoppala Cc: Michel Thierry Fixes: af7a8ffad9c5 ("drm/i915: Use rcu instead of stop_machine in set_wedged") Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20180302113324.23189-2-chris@chris-wilson.co.uk (cherry picked from commit 963ddd63c314e9b5d9cd999873d473a93aed5380) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/i915_gem.c | 6 +++++- drivers/gpu/drm/i915/intel_lrc.c | 5 +++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index dd89abd2263d..66ee9d888d16 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -3205,8 +3205,10 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) * rolling the global seqno forward (since this would complete requests * for which we haven't set the fence error to EIO yet). */ - for_each_engine(engine, i915, id) + for_each_engine(engine, i915, id) { + i915_gem_reset_prepare_engine(engine); engine->submit_request = nop_submit_request; + } /* * Make sure no one is running the old callback before we proceed with @@ -3244,6 +3246,8 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) intel_engine_init_global_seqno(engine, intel_engine_last_submit(engine)); spin_unlock_irqrestore(&engine->timeline->lock, flags); + + i915_gem_reset_finish_engine(engine); } set_bit(I915_WEDGED, &i915->gpu_error.flags); diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 7ece2f061b9e..e0fca035ff78 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -719,6 +719,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) struct rb_node *rb; unsigned long flags; + GEM_TRACE("%s\n", engine->name); + spin_lock_irqsave(&engine->timeline->lock, flags); /* Cancel the requests on the HW and clear the ELSP tracker. */ @@ -765,6 +767,9 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) */ clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted); + /* Mark all CS interrupts as complete */ + execlists->active = 0; + spin_unlock_irqrestore(&engine->timeline->lock, flags); }