[Intel-gfx] [PATCH 57/68] drm/i915/bdw: Add dynamic page trace events

[Ben Widawsky]

This works the same as GEN6.

I was disappointed that I need to pass vm around now, but it's not so
much uglier than the drm_device, and having the vm in trace events is
hugely important.

QUESTION: Now that I've rebased this on the zombie change, we probably want
to call it teardown and track unmaps as opposed to destruction.

v2: Consolidate pagetable/pagedirectory events

Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 35 +++++++++++++++++++++++++++--------
 drivers/gpu/drm/i915/i915_trace.h   | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7cc6cf9..679fe0d 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -588,19 +588,24 @@ static void __gen8_do_map_pt(gen8_ppgtt_pde_t * const pde,
 /* It's likely we'll map more than one pagetable at a time. This function will
  * save us unnecessary kmap calls, but do no more functionally than multiple
  * calls to map_pt. */
-static void gen8_map_pagetable_range(struct i915_pagedir *pd,
+static void gen8_map_pagetable_range(struct i915_address_space *vm,
+				     struct i915_pagedir *pd,
 				     uint64_t start,
-				     uint64_t length,
-				     struct drm_device *dev)
+				     uint64_t length)
 {
 	gen8_ppgtt_pde_t * const pagedir = kmap_atomic(pd->page);
 	struct i915_pagetab *pt;
 	uint64_t temp, pde;
 
-	gen8_for_each_pde(pt, pd, start, length, temp, pde)
-		__gen8_do_map_pt(pagedir + pde, pt, dev);
+	gen8_for_each_pde(pt, pd, start, length, temp, pde) {
+		__gen8_do_map_pt(pagedir + pde, pt, vm->dev);
+		trace_i915_pagetable_map(vm, pde, pt,
+					 gen8_pte_index(start),
+					 gen8_pte_count(start, length),
+					 GEN8_PTES_PER_PT);
+	}
 
-	if (!HAS_LLC(dev))
+	if (!HAS_LLC(vm->dev))
 		drm_clflush_virt_range(pagedir, PAGE_SIZE);
 
 	kunmap_atomic(pagedir);
@@ -668,6 +673,11 @@ static void gen8_teardown_va_range_3lvl(struct i915_address_space *vm,
 				     pde, vm);
 			}
 
+			trace_i915_pagetable_unmap(vm, pde, pt,
+						   gen8_pte_index(pd_start),
+						   gen8_pte_count(pd_start, pd_len),
+						   GEN8_PTES_PER_PT);
+
 			bitmap_clear(pt->used_ptes,
 				     gen8_pte_index(pd_start),
 				     gen8_pte_count(pd_start, pd_len));
@@ -680,6 +690,10 @@ static void gen8_teardown_va_range_3lvl(struct i915_address_space *vm,
 					continue;
 				}
 				free_pt_single(pt, dev);
+				trace_i915_pagetable_destroy(vm,
+							     pde,
+							     pd_start & GENMASK_ULL(64, GEN8_PDE_SHIFT),
+							     GEN8_PDE_SHIFT);
 				pd->page_tables[pde] = NULL;
 			}
 		}
@@ -696,6 +710,9 @@ static void gen8_teardown_va_range_3lvl(struct i915_address_space *vm,
 			}
 			free_pd_single(pd, dev);
 			pdp->pagedirs[pdpe] = NULL;
+			trace_i915_pagedirectory_destroy(vm, pdpe,
+							 start & GENMASK_ULL(64, GEN8_PDPE_SHIFT),
+							 GEN8_PDPE_SHIFT);
 		}
 	}
 
@@ -793,6 +810,7 @@ static int gen8_ppgtt_alloc_pagetabs(struct i915_address_space *vm,
 
 		pd->page_tables[pde] = pt;
 		set_bit(pde, new_pts);
+		trace_i915_pagetable_alloc(vm, pde, start, GEN8_PDE_SHIFT);
 	}
 
 	return 0;
@@ -854,6 +872,7 @@ static int gen8_ppgtt_alloc_pagedirs(struct i915_address_space *vm,
 
 		pdp->pagedirs[pdpe] = pd;
 		set_bit(pdpe, new_pds);
+		trace_i915_pagedirectory_alloc(vm, pdpe, start, GEN8_PDPE_SHIFT);
 	}
 
 	return 0;
@@ -990,7 +1009,7 @@ static int gen8_alloc_va_range_3lvl(struct i915_address_space *vm,
 		}
 
 		set_bit(pdpe, pdp->used_pdpes);
-		gen8_map_pagetable_range(pd, start, length, dev);
+		gen8_map_pagetable_range(vm, pd, start, length);
 		pd->zombie = 0;
 	}
 
@@ -1095,7 +1114,7 @@ static int gen8_aliasing_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	}
 
 	gen8_for_each_pdpe(pd, pdp, start, size, temp, pdpe)
-		gen8_map_pagetable_range(pd, start, size, dev);
+		gen8_map_pagetable_range(&ppgtt->base, pd,start, size);
 
 	ppgtt->base.allocate_va_range = NULL;
 	ppgtt->base.teardown_va_range = NULL;
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 2d21c54..c6137de 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -225,6 +225,38 @@ DEFINE_EVENT(i915_pagetable, i915_pagetable_destroy,
 	     TP_ARGS(vm, pde, start, pde_shift)
 );
 
+DEFINE_EVENT_PRINT(i915_pagetable, i915_pagedirectory_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->pde, __entry->start, __entry->end)
+);
+
+DEFINE_EVENT_PRINT(i915_pagetable, i915_pagedirectory_destroy,
+		   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->pde, __entry->start, __entry->end)
+);
+
+DEFINE_EVENT_PRINT(i915_pagetable, i915_pagedirpo_alloc,
+		   TP_PROTO(struct i915_address_space *vm, u32 pml4e, u64 start, u64 pml4e_shift),
+		   TP_ARGS(vm, pml4e, start, pml4e_shift),
+
+		   TP_printk("vm=%p, pml4e=%d (0x%llx-0x%llx)",
+			     __entry->vm, __entry->pde, __entry->start, __entry->end)
+);
+
+DEFINE_EVENT_PRINT(i915_pagetable, i915_pagedirpo_destroy,
+		   TP_PROTO(struct i915_address_space *vm, u32 pml4e, u64 start, u64 pml4e_shift),
+		   TP_ARGS(vm, pml4e, start, pml4e_shift),
+
+		   TP_printk("vm=%p, pml4e=%d (0x%llx-0x%llx)",
+			     __entry->vm, __entry->pde, __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) \
-- 
2.0.4