[Intel-gfx] [PATCH v5 04/19] drm/i915/gen8: Add dynamic page trace events

[Michel Thierry]

The dynamic page allocation patch series added it for GEN6, this patch
adds them for GEN8.

v2: Consolidate pagetable/page_directory events
v3: Multiple rebases.
v4: Rebase after s/page_tables/page_table/.
v5: Rebase after Mika's ppgtt cleanup / scratch merge patch series.
v6: Rebase after gen8_map_pagetable_range removal.
v7: Use generic page name (px) in DECLARE_EVENT_CLASS (Akash)
v8: Defer define of i915_page_directory_pointer_entry_alloc (Akash)

Cc: Akash Goel <akash.goel at intel.com>
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
Signed-off-by: Michel Thierry <michel.thierry at intel.com> (v3+)
---
 drivers/gpu/drm/i915/i915_gem_gtt.c |  6 ++++++
 drivers/gpu/drm/i915/i915_trace.h   | 24 ++++++++++++++++--------
 2 files changed, 22 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index cc575c21..4583a54 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -818,6 +818,7 @@ static int gen8_ppgtt_alloc_pagetabs(struct i915_address_space *vm,
 		gen8_initialize_pt(vm, pt);
 		pd->page_table[pde] = pt;
 		__set_bit(pde, new_pts);
+		trace_i915_page_table_entry_alloc(vm, pde, start, GEN8_PDE_SHIFT);
 	}
 
 	return 0;
@@ -878,6 +879,7 @@ gen8_ppgtt_alloc_page_directories(struct i915_address_space *vm,
 		gen8_initialize_pd(vm, pd);
 		pdp->page_directory[pdpe] = pd;
 		__set_bit(pdpe, new_pds);
+		trace_i915_page_directory_entry_alloc(vm, pdpe, start, GEN8_PDPE_SHIFT);
 	}
 
 	return 0;
@@ -1027,6 +1029,10 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,
 			/* Map the PDE to the page table */
 			page_directory[pde] = gen8_pde_encode(px_dma(pt),
 							      I915_CACHE_LLC);
+			trace_i915_page_table_entry_map(&ppgtt->base, pde, pt,
+							gen8_pte_index(start),
+							gen8_pte_count(start, length),
+							GEN8_PTES);
 
 			/* NB: We haven't yet mapped ptes to pages. At this
 			 * point we're still relying on insert_entries() */
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 2f34c47..f230d76 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -186,33 +186,41 @@ DEFINE_EVENT(i915_va, i915_va_alloc,
 	     TP_ARGS(vm, start, length, name)
 );
 
-DECLARE_EVENT_CLASS(i915_page_table_entry,
-	TP_PROTO(struct i915_address_space *vm, u32 pde, u64 start, u64 pde_shift),
-	TP_ARGS(vm, pde, start, pde_shift),
+DECLARE_EVENT_CLASS(i915_px_entry,
+	TP_PROTO(struct i915_address_space *vm, u32 px, u64 start, u64 px_shift),
+	TP_ARGS(vm, px, start, px_shift),
 
 	TP_STRUCT__entry(
 		__field(struct i915_address_space *, vm)
-		__field(u32, pde)
+		__field(u32, px)
 		__field(u64, start)
 		__field(u64, end)
 	),
 
 	TP_fast_assign(
 		__entry->vm = vm;
-		__entry->pde = pde;
+		__entry->px = px;
 		__entry->start = start;
-		__entry->end = ((start + (1ULL << pde_shift)) & ~((1ULL << pde_shift)-1)) - 1;
+		__entry->end = ((start + (1ULL << px_shift)) & ~((1ULL << px_shift)-1)) - 1;
 	),
 
 	TP_printk("vm=%p, pde=%d (0x%llx-0x%llx)",
-		  __entry->vm, __entry->pde, __entry->start, __entry->end)
+		  __entry->vm, __entry->px, __entry->start, __entry->end)
 );
 
-DEFINE_EVENT(i915_page_table_entry, i915_page_table_entry_alloc,
+DEFINE_EVENT(i915_px_entry, i915_page_table_entry_alloc,
 	     TP_PROTO(struct i915_address_space *vm, u32 pde, u64 start, u64 pde_shift),
 	     TP_ARGS(vm, pde, start, pde_shift)
 );
 
+DEFINE_EVENT_PRINT(i915_px_entry, i915_page_directory_entry_alloc,
+		   TP_PROTO(struct i915_address_space *vm, u32 pdpe, u64 start, u64 pdpe_shift),
+		   TP_ARGS(vm, pdpe, start, pdpe_shift),
+
+		   TP_printk("vm=%p, pdpe=%d (0x%llx-0x%llx)",
+			     __entry->vm, __entry->px, __entry->start, __entry->end)
+);
+
 /* Avoid extra math because we only support two sizes. The format is defined by
  * bitmap_scnprintf. Each 32 bits is 8 HEX digits followed by comma */
 #define TRACE_PT_SIZE(bits) \
-- 
2.4.5