From: Daniele Ceraolo Spurio Date: Mon, 10 Nov 2014 13:44:31 +0000 (+0000) Subject: drm/i915: Add tracepoints to track a vm during its lifetime X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=198c974d7e80a5135fc4a2e69a07ba3e64122f8a;p=linux-beck.git drm/i915: Add tracepoints to track a vm during its lifetime - 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 Signed-off-by: Daniel Vetter --- diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl index 9d9977211b23..9449cd65f1d0 100644 --- a/Documentation/DocBook/drm.tmpl +++ b/Documentation/DocBook/drm.tmpl @@ -4001,6 +4001,27 @@ 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 7d3257111737..1fb00008623d 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 de12017c809b..4498a068a5a7 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 f5aa0067755a..751d4ad14d62 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_fast_assign( + __entry->vm = vm; + __entry->dev = vm->dev->primary->index; + ), + + TP_printk("dev=%u, vm=%p", __entry->dev, __entry->vm) +) + +DEFINE_EVENT(i915_ppgtt, i915_ppgtt_create, + TP_PROTO(struct i915_address_space *vm), + TP_ARGS(vm) +); + +DEFINE_EVENT(i915_ppgtt, i915_ppgtt_release, + TP_PROTO(struct i915_address_space *vm), + TP_ARGS(vm) +); + +/** + * DOC: i915_context_create and i915_context_free tracepoints + * + * These tracepoints are used to track creation and deletion of contexts. + * If full ppgtt is enabled, they also print the address of the vm assigned to + * the context. + */ +DECLARE_EVENT_CLASS(i915_context, + TP_PROTO(struct intel_context *ctx), + TP_ARGS(ctx), + + TP_STRUCT__entry( + __field(u32, dev) + __field(struct intel_context *, ctx) + __field(struct i915_address_space *, vm) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->vm = ctx->ppgtt ? &ctx->ppgtt->base : NULL; + __entry->dev = ctx->file_priv->dev_priv->dev->primary->index; + ), + + TP_printk("dev=%u, ctx=%p, ctx_vm=%p", + __entry->dev, __entry->ctx, __entry->vm) +) + +DEFINE_EVENT(i915_context, i915_context_create, + TP_PROTO(struct intel_context *ctx), + TP_ARGS(ctx) +); + +DEFINE_EVENT(i915_context, i915_context_free, + TP_PROTO(struct intel_context *ctx), + TP_ARGS(ctx) +); + +/** + * DOC: switch_mm tracepoint + * + * This tracepoint allows tracking of the mm switch, which is an important point + * in the lifetime of the vm in the legacy submission path. This tracepoint is + * called only if full ppgtt is enabled. + */ +TRACE_EVENT(switch_mm, + TP_PROTO(struct intel_engine_cs *ring, struct intel_context *to), + + TP_ARGS(ring, to), + + TP_STRUCT__entry( + __field(u32, ring) + __field(struct intel_context *, to) + __field(struct i915_address_space *, vm) + __field(u32, dev) + ), + + TP_fast_assign( + __entry->ring = ring->id; + __entry->to = to; + __entry->vm = to->ppgtt? &to->ppgtt->base : NULL; + __entry->dev = ring->dev->primary->index; + ), + + TP_printk("dev=%u, ring=%u, ctx=%p, ctx_vm=%p", + __entry->dev, __entry->ring, __entry->to, __entry->vm) +); + #endif /* _I915_TRACE_H_ */ /* This part must be outside protection */