diff mbox series

[1/3] drm/i915/gtt: pde entry encoding is identical

Message ID 20190618161731.15607-1-mika.kuoppala@linux.intel.com (mailing list archive)
State New, archived
Headers show
Series [1/3] drm/i915/gtt: pde entry encoding is identical | expand

Commit Message

Mika Kuoppala June 18, 2019, 4:17 p.m. UTC 
For all page directory entries, the pde encoding is
identical. Don't compilicate call sites with different
versions of doing the same thing. We check the existence of
physical page before writing the entry into it. This further
generalizes the pd so that manipulation in callsites will be
identical, removing the need to handle pdps differently for gen8.

v2: squash

Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 114 ++++++++++------------------
 drivers/gpu/drm/i915/i915_gem_gtt.h |   3 -
 2 files changed, 40 insertions(+), 77 deletions(-)

Comments

Chris Wilson June 18, 2019, 4:32 p.m. UTC | #1 
Quoting Mika Kuoppala (2019-06-18 17:17:29)
> For all page directory entries, the pde encoding is
> identical. Don't compilicate call sites with different
> versions of doing the same thing. We check the existence of
> physical page before writing the entry into it. This further
> generalizes the pd so that manipulation in callsites will be
> identical, removing the need to handle pdps differently for gen8.

And we can pull in the atomic_inc as well? At the top level the result
goes unused, but since we should not be as frequently inserting new
pages the higher up we go, that should be insignificant.
-Chris
diff mbox series

Patch

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 8ab820145ea6..5df17db68875 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -215,10 +215,10 @@  static u64 gen8_pte_encode(dma_addr_t addr,
 	return pte;
 }
 
-static gen8_pde_t gen8_pde_encode(const dma_addr_t addr,
-				  const enum i915_cache_level level)
+static u64 gen8_pde_encode(const dma_addr_t addr,
+			   const enum i915_cache_level level)
 {
-	gen8_pde_t pde = _PAGE_PRESENT | _PAGE_RW;
+	u64 pde = _PAGE_PRESENT | _PAGE_RW;
 	pde |= addr;
 	if (level != I915_CACHE_NONE)
 		pde |= PPAT_CACHED_PDE;
@@ -227,9 +227,6 @@  static gen8_pde_t gen8_pde_encode(const dma_addr_t addr,
 	return pde;
 }
 
-#define gen8_pdpe_encode gen8_pde_encode
-#define gen8_pml4e_encode gen8_pde_encode
-
 static u64 snb_pte_encode(dma_addr_t addr,
 			  enum i915_cache_level level,
 			  u32 flags)
@@ -734,24 +731,36 @@  static void free_pd(struct i915_address_space *vm,
 	kfree(pd);
 }
 
-static void init_pd_with_page(struct i915_address_space *vm,
-			      struct i915_page_directory * const pd,
-			      struct i915_page_table *pt)
-{
-	fill_px(vm, pd, gen8_pde_encode(px_dma(pt), I915_CACHE_LLC));
-	memset_p(pd->entry, pt, 512);
+#define init_pd(vm, pd, to) {					\
+	GEM_DEBUG_BUG_ON(!pd_has_phys_page(pd));		\
+	fill_px((vm), (pd), gen8_pde_encode(px_dma(to), I915_CACHE_LLC)); \
+	memset_p((pd)->entry, (to), 512);				\
 }
 
-static void init_pd(struct i915_address_space *vm,
-		    struct i915_page_directory * const pd,
-		    struct i915_page_directory * const to)
+static void __write_dma_entry(struct i915_page_dma * const pdma,
+			      const unsigned short pde,
+			      const u64 encoded_entry)
 {
-	GEM_DEBUG_BUG_ON(!pd_has_phys_page(pd));
+	u64 *vaddr;
 
-	fill_px(vm, pd, gen8_pdpe_encode(px_dma(to), I915_CACHE_LLC));
-	memset_p(pd->entry, to, 512);
+	vaddr = kmap_atomic(pdma->page);
+	vaddr[pde] = encoded_entry;
+	kunmap_atomic(vaddr);
 }
 
+static inline void
+__set_pd_entry(struct i915_page_directory * const pd,
+	       const unsigned short pde,
+	       struct i915_page_dma * const to,
+	       u64 (*encode)(const dma_addr_t, const enum i915_cache_level))
+{
+	pd->entry[pde] = to;
+	__write_dma_entry(px_base(pd), pde, encode(to->daddr, I915_CACHE_LLC));
+}
+
+#define set_pd_entry(pd, pde, to) \
+	__set_pd_entry((pd), (pde), px_base(to), gen8_pde_encode)
+
 /*
  * PDE TLBs are a pain to invalidate on GEN8+. When we modify
  * the page table structures, we mark them dirty so that
@@ -781,18 +790,6 @@  static bool gen8_ppgtt_clear_pt(const struct i915_address_space *vm,
 	return !atomic_sub_return(num_entries, &pt->used);
 }
 
-static void gen8_ppgtt_set_pde(struct i915_address_space *vm,
-			       struct i915_page_directory *pd,
-			       struct i915_page_table *pt,
-			       unsigned int pde)
-{
-	gen8_pde_t *vaddr;
-
-	vaddr = kmap_atomic_px(pd);
-	vaddr[pde] = gen8_pde_encode(px_dma(pt), I915_CACHE_LLC);
-	kunmap_atomic(vaddr);
-}
-
 static bool gen8_ppgtt_clear_pd(struct i915_address_space *vm,
 				struct i915_page_directory *pd,
 				u64 start, u64 length)
@@ -810,8 +807,7 @@  static bool gen8_ppgtt_clear_pd(struct i915_address_space *vm,
 
 		spin_lock(&pd->lock);
 		if (!atomic_read(&pt->used)) {
-			gen8_ppgtt_set_pde(vm, pd, vm->scratch_pt, pde);
-			pd->entry[pde] = vm->scratch_pt;
+			set_pd_entry(pd, pde, vm->scratch_pt);
 
 			GEM_BUG_ON(!atomic_read(&pd->used));
 			atomic_dec(&pd->used);
@@ -825,20 +821,6 @@  static bool gen8_ppgtt_clear_pd(struct i915_address_space *vm,
 	return !atomic_read(&pd->used);
 }
 
-static void gen8_ppgtt_set_pdpe(struct i915_page_directory *pdp,
-				struct i915_page_directory *pd,
-				unsigned int pdpe)
-{
-	gen8_ppgtt_pdpe_t *vaddr;
-
-	if (!pd_has_phys_page(pdp))
-		return;
-
-	vaddr = kmap_atomic_px(pdp);
-	vaddr[pdpe] = gen8_pdpe_encode(px_dma(pd), I915_CACHE_LLC);
-	kunmap_atomic(vaddr);
-}
-
 /* Removes entries from a single page dir pointer, releasing it if it's empty.
  * Caller can use the return value to update higher-level entries
  */
@@ -859,8 +841,7 @@  static bool gen8_ppgtt_clear_pdp(struct i915_address_space *vm,
 
 		spin_lock(&pdp->lock);
 		if (!atomic_read(&pd->used)) {
-			gen8_ppgtt_set_pdpe(pdp, vm->scratch_pd, pdpe);
-			pdp->entry[pdpe] = vm->scratch_pd;
+			set_pd_entry(pdp, pdpe, vm->scratch_pd);
 
 			GEM_BUG_ON(!atomic_read(&pdp->used));
 			atomic_dec(&pdp->used);
@@ -880,17 +861,6 @@  static void gen8_ppgtt_clear_3lvl(struct i915_address_space *vm,
 	gen8_ppgtt_clear_pdp(vm, i915_vm_to_ppgtt(vm)->pd, start, length);
 }
 
-static void gen8_ppgtt_set_pml4e(struct i915_page_directory *pml4,
-				 struct i915_page_directory *pdp,
-				 unsigned int pml4e)
-{
-	gen8_ppgtt_pml4e_t *vaddr;
-
-	vaddr = kmap_atomic_px(pml4);
-	vaddr[pml4e] = gen8_pml4e_encode(px_dma(pdp), I915_CACHE_LLC);
-	kunmap_atomic(vaddr);
-}
-
 /* Removes entries from a single pml4.
  * This is the top-level structure in 4-level page tables used on gen8+.
  * Empty entries are always scratch pml4e.
@@ -914,8 +884,7 @@  static void gen8_ppgtt_clear_4lvl(struct i915_address_space *vm,
 
 		spin_lock(&pml4->lock);
 		if (!atomic_read(&pdp->used)) {
-			gen8_ppgtt_set_pml4e(pml4, vm->scratch_pdp, pml4e);
-			pml4->entry[pml4e] = vm->scratch_pdp;
+			set_pd_entry(pml4, pml4e, vm->scratch_pdp);
 			free = true;
 		}
 		spin_unlock(&pml4->lock);
@@ -1232,7 +1201,7 @@  static int gen8_init_scratch(struct i915_address_space *vm)
 	}
 
 	gen8_initialize_pt(vm, vm->scratch_pt);
-	init_pd_with_page(vm, vm->scratch_pd, vm->scratch_pt);
+	init_pd(vm, vm->scratch_pd, vm->scratch_pt);
 	if (i915_vm_is_4lvl(vm))
 		init_pd(vm, vm->scratch_pdp, vm->scratch_pd);
 
@@ -1371,8 +1340,7 @@  static int gen8_ppgtt_alloc_pd(struct i915_address_space *vm,
 
 			spin_lock(&pd->lock);
 			if (pd->entry[pde] == vm->scratch_pt) {
-				gen8_ppgtt_set_pde(vm, pd, pt, pde);
-				pd->entry[pde] = pt;
+				set_pd_entry(pd, pde, pt);
 				atomic_inc(&pd->used);
 			} else {
 				alloc = pt;
@@ -1415,12 +1383,11 @@  static int gen8_ppgtt_alloc_pdp(struct i915_address_space *vm,
 				goto unwind;
 			}
 
-			init_pd_with_page(vm, pd, vm->scratch_pt);
+			init_pd(vm, pd, vm->scratch_pt);
 
 			spin_lock(&pdp->lock);
 			if (pdp->entry[pdpe] == vm->scratch_pd) {
-				gen8_ppgtt_set_pdpe(pdp, pd, pdpe);
-				pdp->entry[pdpe] = pd;
+				set_pd_entry(pdp, pdpe, pd);
 				atomic_inc(&pdp->used);
 			} else {
 				alloc = pd;
@@ -1443,7 +1410,7 @@  static int gen8_ppgtt_alloc_pdp(struct i915_address_space *vm,
 unwind_pd:
 	spin_lock(&pdp->lock);
 	if (atomic_dec_and_test(&pd->used)) {
-		gen8_ppgtt_set_pdpe(pdp, vm->scratch_pd, pdpe);
+		set_pd_entry(pdp, pdpe, vm->scratch_pd);
 		GEM_BUG_ON(!atomic_read(&pdp->used));
 		atomic_dec(&pdp->used);
 		free_pd(vm, pd);
@@ -1491,8 +1458,7 @@  static int gen8_ppgtt_alloc_4lvl(struct i915_address_space *vm,
 
 			spin_lock(&pml4->lock);
 			if (pml4->entry[pml4e] == vm->scratch_pdp) {
-				gen8_ppgtt_set_pml4e(pml4, pdp, pml4e);
-				pml4->entry[pml4e] = pdp;
+				set_pd_entry(pml4, pml4e, pdp);
 			} else {
 				alloc = pdp;
 				pdp = pml4->entry[pml4e];
@@ -1514,7 +1480,7 @@  static int gen8_ppgtt_alloc_4lvl(struct i915_address_space *vm,
 unwind_pdp:
 	spin_lock(&pml4->lock);
 	if (atomic_dec_and_test(&pdp->used)) {
-		gen8_ppgtt_set_pml4e(pml4, vm->scratch_pdp, pml4e);
+		set_pd_entry(pml4, pml4e, vm->scratch_pdp);
 		free_pd(vm, pdp);
 	}
 	spin_unlock(&pml4->lock);
@@ -1540,8 +1506,8 @@  static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt)
 		if (IS_ERR(pd))
 			goto unwind;
 
-		init_pd_with_page(vm, pd, vm->scratch_pt);
-		gen8_ppgtt_set_pdpe(pdp, pd, pdpe);
+		init_pd(vm, pd, vm->scratch_pt);
+		set_pd_entry(pdp, pdpe, pd);
 
 		atomic_inc(&pdp->used);
 	}
@@ -1553,7 +1519,7 @@  static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt)
 unwind:
 	start -= from;
 	gen8_for_each_pdpe(pd, pdp, from, start, pdpe) {
-		gen8_ppgtt_set_pdpe(pdp, vm->scratch_pd, pdpe);
+		set_pd_entry(pdp, pdpe, vm->scratch_pd);
 		free_pd(vm, pd);
 	}
 	atomic_set(&pdp->used, 0);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 812717ccc69b..6a014d052952 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -67,9 +67,6 @@  struct i915_vma;
 
 typedef u32 gen6_pte_t;
 typedef u64 gen8_pte_t;
-typedef u64 gen8_pde_t;
-typedef u64 gen8_ppgtt_pdpe_t;
-typedef u64 gen8_ppgtt_pml4e_t;
 
 #define ggtt_total_entries(ggtt) ((ggtt)->vm.total >> PAGE_SHIFT)