Re: [Intel-gfx] [PATCH v7] drm/i915: Add tracepoints to track a vm during its lifetime
On Mon, Nov 10, 2014 at 01:44:31PM +, daniele.ceraolospu...@intel.com wrote: > From: Daniele Ceraolo Spurio > > - ppgtt init/release: these tracepoints are useful for observing the > creation and destruction of Full PPGTTs. > > - ctx create/free: we can use the ctx_free trace in combination with the > ppgtt_release one to be sure that the ppgtt doesn't stay alive for too > long after the ctx is destroyed. ctx_create is there for simmetry > > - switch_mm: important point in the lifetime of the vm > > v4: add DOC information > v5: pull the DOC in drm.tmpl > v6: clean ppgtt init/release traces + add ctx create/free and switch_mm > tracepoints (Chris) > v7: drop execlist_submit_context tracepoint > > Cc: Chris Wilson > > Signed-off-by: Daniele Ceraolo Spurio > Reviewed-by: Chris Wilson Queued for -next, thanks for the patch. -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
Re: [Intel-gfx] [PATCH v7] drm/i915: Add tracepoints to track a vm
Tested-By: PRC QA PRTS (Patch Regression Test System Contact: shuang...@intel.com) -Summary- Platform: baseline_drm_intel_nightly_pass_rate->patch_applied_pass_rate BYT: pass/total=277/348->276/348 PNV: pass/total=323/328->325/328 ILK: pass/total=328/330->329/330 IVB: pass/total=545/546->544/546 SNB: pass/total=558/563->559/563 HSW: pass/total=577/581->574/581 BDW: pass/total=435/435->434/435 -Detailed- test_platform: test_suite, test_case, result_with_drm_intel_nightly(count, machine_id...)...->result_with_patch_applied(count, machine_id)... BYT: Intel_gpu_tools, igt_gem_bad_reloc_negative-reloc-lut, NSPT(1, M29)PASS(9, M36M29) -> NSPT(1, M29)PASS(3, M29) PNV: Intel_gpu_tools, igt_gem_mmap_offset_exhaustion, DMESG_WARN(2, M23M24)PASS(14, M24M23M7) -> PASS(4, M7) PNV: Intel_gpu_tools, igt_gem_unref_active_buffers, DMESG_WARN(2, M23)PASS(14, M24M23M7) -> PASS(4, M7) ILK: Intel_gpu_tools, igt_kms_render_gpu-blit, DMESG_WARN(1, M26)PASS(15, M6M26M37) -> PASS(4, M26) ILK: Intel_gpu_tools, igt_kms_flip_flip-vs-rmfb, PASS(4, M26) -> DMESG_WARN(2, M26)PASS(2, M26) ILK: Intel_gpu_tools, igt_kms_flip_wf_vblank-vs-dpms-interruptible, DMESG_WARN(1, M26)PASS(15, M6M26M37) -> PASS(4, M26) IVB: Intel_gpu_tools, igt_gem_bad_reloc_negative-reloc, NSPT(4, M4M34)PASS(9, M34M4) -> NSPT(2, M34)PASS(2, M34) SNB: Intel_gpu_tools, igt_kms_cursor_crc_cursor-256x256-sliding, DMESG_WARN(3, M35M22)PASS(7, M22M35) -> PASS(4, M22) HSW: Intel_gpu_tools, igt_gem_bad_reloc_negative-reloc, NSPT(4, M39M20M40)PASS(9, M40M39M20) -> NSPT(2, M39)PASS(2, M39) HSW: Intel_gpu_tools, igt_kms_cursor_crc_cursor-64x64-random, FAIL(1, M39)PASS(3, M40M39) -> FAIL(1, M39)DMESG_WARN(2, M39)PASS(1, M39) HSW: Intel_gpu_tools, igt_kms_rotation_crc_primary-rotation, PASS(4, M40M39) -> DMESG_WARN(1, M39)PASS(3, M39) BDW: Intel_gpu_tools, igt_gem_reset_stats_ban-bsd, PASS(16, M30M28M42) -> DMESG_WARN(1, M42)PASS(3, M42) ___ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/intel-gfx
[Intel-gfx] [PATCH v7] drm/i915: Add tracepoints to track a vm during its lifetime
From: Daniele Ceraolo Spurio - ppgtt init/release: these tracepoints are useful for observing the creation and destruction of Full PPGTTs. - ctx create/free: we can use the ctx_free trace in combination with the ppgtt_release one to be sure that the ppgtt doesn't stay alive for too long after the ctx is destroyed. ctx_create is there for simmetry - switch_mm: important point in the lifetime of the vm v4: add DOC information v5: pull the DOC in drm.tmpl v6: clean ppgtt init/release traces + add ctx create/free and switch_mm tracepoints (Chris) v7: drop execlist_submit_context tracepoint Cc: Chris Wilson Signed-off-by: Daniele Ceraolo Spurio Reviewed-by: Chris Wilson --- Documentation/DocBook/drm.tmpl | 21 +++ drivers/gpu/drm/i915/i915_gem_context.c | 6 ++ drivers/gpu/drm/i915/i915_gem_gtt.c | 4 ++ drivers/gpu/drm/i915/i915_trace.h | 104 4 files changed, 135 insertions(+) diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl index 7277a7f..0f485a0 100644 --- a/Documentation/DocBook/drm.tmpl +++ b/Documentation/DocBook/drm.tmpl @@ -3994,6 +3994,27 @@ int num_ioctls; !Idrivers/gpu/drm/i915/intel_lrc.c + + + Tracing + +This sections covers all things related to the tracepoints implemented in +the i915 driver. + + + i915_ppgtt_create and i915_ppgtt_release +!Pdrivers/gpu/drm/i915/i915_trace.h i915_ppgtt_create and i915_ppgtt_release tracepoints + + + i915_context_create and i915_context_free +!Pdrivers/gpu/drm/i915/i915_trace.h i915_context_create and i915_context_free tracepoints + + + switch_mm +!Pdrivers/gpu/drm/i915/i915_trace.h switch_mm tracepoint + + + !Cdrivers/gpu/drm/i915/i915_irq.c diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 7d32571..1fb 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -88,6 +88,7 @@ #include #include #include "i915_drv.h" +#include "i915_trace.h" /* This is a HW constraint. The value below is the largest known requirement * I've seen in a spec to date, and that was a workaround for a non-shipping @@ -137,6 +138,8 @@ void i915_gem_context_free(struct kref *ctx_ref) struct intel_context *ctx = container_of(ctx_ref, typeof(*ctx), ref); + trace_i915_context_free(ctx); + if (i915.enable_execlists) intel_lr_context_free(ctx); @@ -274,6 +277,8 @@ i915_gem_create_context(struct drm_device *dev, ctx->ppgtt = ppgtt; } + trace_i915_context_create(ctx); + return ctx; err_unpin: @@ -549,6 +554,7 @@ static int do_switch(struct intel_engine_cs *ring, from = ring->last_context; if (to->ppgtt) { + trace_switch_mm(ring, to); ret = to->ppgtt->switch_mm(to->ppgtt, ring); 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 c1cf332..7737e55 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1174,6 +1174,8 @@ i915_ppgtt_create(struct drm_device *dev, struct drm_i915_file_private *fpriv) ppgtt->file_priv = fpriv; + trace_i915_ppgtt_create(&ppgtt->base); + return ppgtt; } @@ -1182,6 +1184,8 @@ void i915_ppgtt_release(struct kref *kref) struct i915_hw_ppgtt *ppgtt = container_of(kref, struct i915_hw_ppgtt, ref); + trace_i915_ppgtt_release(&ppgtt->base); + /* vmas should already be unbound */ WARN_ON(!list_empty(&ppgtt->base.active_list)); WARN_ON(!list_empty(&ppgtt->base.inactive_list)); diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index f5aa006..751d4ad 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -587,6 +587,110 @@ TRACE_EVENT(intel_gpu_freq_change, TP_printk("new_freq=%u", __entry->freq) ); +/** + * DOC: i915_ppgtt_create and i915_ppgtt_release tracepoints + * + * With full ppgtt enabled each process using drm will allocate at least one + * translation table. With these traces it is possible to keep track of the + * allocation and of the lifetime of the tables; this can be used during + * testing/debug to verify that we are not leaking ppgtts. + * These traces identify the ppgtt through the vm pointer, which is also printed + * by the i915_vma_bind and i915_vma_unbind tracepoints. + */ +DECLARE_EVENT_CLASS(i915_ppgtt, + TP_PROTO(struct i915_address_space *vm), + TP_ARGS(vm), + + TP_STRUCT__entry( + __field(struct i915_address_space *, vm) + __field(u32, dev) + ), + + TP_fas