public inbox for intel-gfx@lists.freedesktop.org
 help / color / mirror / Atom feed
From: Ben Widawsky <benjamin.widawsky@intel.com>
To: Intel GFX <intel-gfx@lists.freedesktop.org>
Cc: Ben Widawsky <ben@bwidawsk.net>,
	Ben Widawsky <benjamin.widawsky@intel.com>
Subject: [PATCH 4/7] drm/i915: Make clear/insert vfuncs args absolute
Date: Tue, 24 Dec 2013 13:42:34 -0800	[thread overview]
Message-ID: <1387921357-22942-5-git-send-email-benjamin.widawsky@intel.com> (raw)
In-Reply-To: <1387921357-22942-1-git-send-email-benjamin.widawsky@intel.com>

This patch converts insert_entries and clear_range, both functions which
are specific to the VM. These functions tend to encapsulate the gen
specific PTE writes. Passing absolute addresses to the insert_entries,
and clear_range will help make the logic clearer within the functions as
to what's going on. Currently, all callers simply do the appropriate
page shift, which IMO, ends up looking weird with an upcoming change for
the gen8 page table allocations.

Up until now, the PPGTT was a funky 2 level page table. GEN8 changes
this to look more like a 3 level page table, and to that extent we need
a significant amount more memory simply for the page tables. To address
this, the allocations will be split up in finer amounts.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_drv.h     |  6 +--
 drivers/gpu/drm/i915/i915_gem_gtt.c | 80 +++++++++++++++++++++----------------
 2 files changed, 49 insertions(+), 37 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index dc21963..43c2ee7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -614,12 +614,12 @@ struct i915_address_space {
 				     enum i915_cache_level level,
 				     bool valid); /* Create a valid PTE */
 	void (*clear_range)(struct i915_address_space *vm,
-			    unsigned int first_entry,
-			    unsigned int num_entries,
+			    uint64_t start,
+			    size_t length,
 			    bool use_scratch);
 	void (*insert_entries)(struct i915_address_space *vm,
 			       struct sg_table *st,
-			       unsigned int first_entry,
+			       uint64_t start,
 			       enum i915_cache_level cache_level);
 	void (*cleanup)(struct i915_address_space *vm);
 };
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 25687cf..af07371 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -253,13 +253,15 @@ static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
 }
 
 static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
-				   unsigned first_entry,
-				   unsigned num_entries,
+				   uint64_t start,
+				   size_t length,
 				   bool use_scratch)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
 	gen8_gtt_pte_t *pt_vaddr, scratch_pte;
+	unsigned first_entry = start >> PAGE_SHIFT;
+	unsigned num_entries = length >> PAGE_SHIFT;
 	unsigned act_pt = first_entry / GEN8_PTES_PER_PAGE;
 	unsigned first_pte = first_entry % GEN8_PTES_PER_PAGE;
 	unsigned last_pte, i;
@@ -289,12 +291,13 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
 
 static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 				      struct sg_table *pages,
-				      unsigned first_entry,
+				      uint64_t start,
 				      enum i915_cache_level cache_level)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
 	gen8_gtt_pte_t *pt_vaddr;
+	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned act_pt = first_entry / GEN8_PTES_PER_PAGE;
 	unsigned act_pte = first_entry % GEN8_PTES_PER_PAGE;
 	struct sg_page_iter sg_iter;
@@ -864,13 +867,15 @@ static int gen6_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
 
 /* PPGTT support for Sandybdrige/Gen6 and later */
 static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
-				   unsigned first_entry,
-				   unsigned num_entries,
+				   uint64_t start,
+				   size_t length,
 				   bool use_scratch)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
 	gen6_gtt_pte_t *pt_vaddr, scratch_pte;
+	unsigned first_entry = start >> PAGE_SHIFT;
+	unsigned num_entries = length >> PAGE_SHIFT;
 	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
 	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	unsigned last_pte, i;
@@ -897,12 +902,13 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 
 static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 				      struct sg_table *pages,
-				      unsigned first_entry,
+				      uint64_t start,
 				      enum i915_cache_level cache_level)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
 	gen6_gtt_pte_t *pt_vaddr;
+	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
 	unsigned act_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	struct sg_page_iter sg_iter;
@@ -1033,8 +1039,7 @@ alloc:
 		ppgtt->pt_dma_addr[i] = pt_addr;
 	}
 
-	ppgtt->base.clear_range(&ppgtt->base, 0,
-				ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES, true);
+	ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);
 	ppgtt->debug_dump = gen6_dump_ppgtt;
 
 	DRM_DEBUG_DRIVER("Allocated pde space (%ldM) at GTT entry: %lx\n",
@@ -1098,20 +1103,17 @@ ppgtt_bind_vma(struct i915_vma *vma,
 	       enum i915_cache_level cache_level,
 	       u32 flags)
 {
-	const unsigned long entry = vma->node.start >> PAGE_SHIFT;
-
 	WARN_ON(flags);
 
-	vma->vm->insert_entries(vma->vm, vma->obj->pages, entry, cache_level);
+	vma->vm->insert_entries(vma->vm, vma->obj->pages, vma->node.start,
+				cache_level);
 }
 
 static void ppgtt_unbind_vma(struct i915_vma *vma)
 {
-	const unsigned long entry = vma->node.start >> PAGE_SHIFT;
-
 	vma->vm->clear_range(vma->vm,
-			     entry,
-			     vma->obj->base.size >> PAGE_SHIFT,
+			     vma->node.start,
+			     vma->obj->base.size,
 			     true);
 }
 
@@ -1272,10 +1274,11 @@ static inline void gen8_set_pte(void __iomem *addr, gen8_gtt_pte_t pte)
 
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
-				     unsigned int first_entry,
+				     uint64_t start,
 				     enum i915_cache_level level)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
+	unsigned first_entry = start >> PAGE_SHIFT;
 	gen8_gtt_pte_t __iomem *gtt_entries =
 		(gen8_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
 	int i = 0;
@@ -1319,10 +1322,11 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
  */
 static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
-				     unsigned int first_entry,
+				     uint64_t start,
 				     enum i915_cache_level level)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
+	unsigned first_entry = start >> PAGE_SHIFT;
 	gen6_gtt_pte_t __iomem *gtt_entries =
 		(gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
 	int i = 0;
@@ -1354,11 +1358,13 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 }
 
 static void gen8_ggtt_clear_range(struct i915_address_space *vm,
-				  unsigned int first_entry,
-				  unsigned int num_entries,
+				  uint64_t start,
+				  size_t length,
 				  bool use_scratch)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
+	unsigned first_entry = start >> PAGE_SHIFT;
+	unsigned num_entries = length >> PAGE_SHIFT;
 	gen8_gtt_pte_t scratch_pte, __iomem *gtt_base =
 		(gen8_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
 	const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
@@ -1378,11 +1384,13 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 }
 
 static void gen6_ggtt_clear_range(struct i915_address_space *vm,
-				  unsigned int first_entry,
-				  unsigned int num_entries,
+				  uint64_t start,
+				  size_t length,
 				  bool use_scratch)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
+	unsigned first_entry = start >> PAGE_SHIFT;
+	unsigned num_entries = length >> PAGE_SHIFT;
 	gen6_gtt_pte_t scratch_pte, __iomem *gtt_base =
 		(gen6_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
 	const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
@@ -1415,10 +1423,12 @@ static void i915_ggtt_bind_vma(struct i915_vma *vma,
 }
 
 static void i915_ggtt_clear_range(struct i915_address_space *vm,
-				  unsigned int first_entry,
-				  unsigned int num_entries,
+				  uint64_t start,
+				  size_t length,
 				  bool unused)
 {
+	unsigned first_entry = start >> PAGE_SHIFT;
+	unsigned num_entries = length >> PAGE_SHIFT;
 	intel_gtt_clear_range(first_entry, num_entries);
 }
 
@@ -1439,7 +1449,6 @@ static void ggtt_bind_vma(struct i915_vma *vma,
 	struct drm_device *dev = vma->vm->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj = vma->obj;
-	const unsigned long entry = vma->node.start >> PAGE_SHIFT;
 
 	/* If there is no aliasing PPGTT, or the caller needs a global mapping,
 	 * or we have a global mapping already but the cacheability flags have
@@ -1455,7 +1464,8 @@ static void ggtt_bind_vma(struct i915_vma *vma,
 	if (!dev_priv->mm.aliasing_ppgtt || flags & GLOBAL_BIND) {
 		if (!obj->has_global_gtt_mapping ||
 		    (cache_level != obj->cache_level)) {
-			vma->vm->insert_entries(vma->vm, obj->pages, entry,
+			vma->vm->insert_entries(vma->vm, obj->pages,
+						vma->node.start,
 						cache_level);
 			obj->has_global_gtt_mapping = 1;
 		}
@@ -1466,7 +1476,9 @@ static void ggtt_bind_vma(struct i915_vma *vma,
 	     (cache_level != obj->cache_level))) {
 		struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
 		appgtt->base.insert_entries(&appgtt->base,
-					    vma->obj->pages, entry, cache_level);
+					    vma->obj->pages,
+					    vma->node.start,
+					    cache_level);
 		vma->obj->has_aliasing_ppgtt_mapping = 1;
 	}
 }
@@ -1476,11 +1488,11 @@ static void ggtt_unbind_vma(struct i915_vma *vma)
 	struct drm_device *dev = vma->vm->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj = vma->obj;
-	const unsigned long entry = vma->node.start >> PAGE_SHIFT;
 
 	if (obj->has_global_gtt_mapping) {
-		vma->vm->clear_range(vma->vm, entry,
-				     vma->obj->base.size >> PAGE_SHIFT,
+		vma->vm->clear_range(vma->vm,
+				     vma->node.start,
+				     obj->base.size,
 				     true);
 		obj->has_global_gtt_mapping = 0;
 	}
@@ -1488,8 +1500,8 @@ static void ggtt_unbind_vma(struct i915_vma *vma)
 	if (obj->has_aliasing_ppgtt_mapping) {
 		struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
 		appgtt->base.clear_range(&appgtt->base,
-					 entry,
-					 obj->base.size >> PAGE_SHIFT,
+					 vma->node.start,
+					 obj->base.size,
 					 true);
 		obj->has_aliasing_ppgtt_mapping = 0;
 	}
@@ -1574,14 +1586,14 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 
 	/* Clear any non-preallocated blocks */
 	drm_mm_for_each_hole(entry, &ggtt_vm->mm, hole_start, hole_end) {
-		const unsigned long count = (hole_end - hole_start) / PAGE_SIZE;
 		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
 			      hole_start, hole_end);
-		ggtt_vm->clear_range(ggtt_vm, hole_start / PAGE_SIZE, count, true);
+		ggtt_vm->clear_range(ggtt_vm, hole_start,
+				     hole_end - hole_start, true);
 	}
 
 	/* And finally clear the reserved guard page */
-	ggtt_vm->clear_range(ggtt_vm, end / PAGE_SIZE - 1, 1, true);
+	ggtt_vm->clear_range(ggtt_vm, end - PAGE_SIZE, PAGE_SIZE, true);
 }
 
 void i915_gem_init_global_gtt(struct drm_device *dev)
-- 
1.8.5.2

  parent reply	other threads:[~2013-12-24 21:42 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-12-24 21:42 [PATCH 0/7] GEN8 PPGTT cleanups + 4GB support Ben Widawsky
2013-12-24 21:42 ` [PATCH 1/7] drm/i915/bdw: Split up PPGTT cleanup Ben Widawsky
2013-12-24 21:42 ` [PATCH 2/7] drm/i915/bdw: Reorganize PPGTT init Ben Widawsky
2013-12-25  6:58   ` [PATCH 2/7] [v2] " Ben Widawsky
2013-12-24 21:42 ` [PATCH 3/7] drm/i915/bdw: Split ppgtt initialization up Ben Widawsky
2013-12-25  7:04   ` [PATCH 3/7] [v2] " Ben Widawsky
2013-12-24 21:42 ` Ben Widawsky [this message]
2013-12-24 21:42 ` [PATCH 5/7] drm/i915/bdw: Reorganize PT allocations Ben Widawsky
2013-12-24 21:42 ` [PATCH 6/7] Revert "drm/i915/bdw: Limit GTT to 2GB" Ben Widawsky
2013-12-24 21:42 ` [PATCH 7/7] drm/i915: Update i915_gem_gtt.c copyright Ben Widawsky
2013-12-26  2:17 ` [PATCH 8/9] drm/i915: Split GEN6 PPGTT cleanup Ben Widawsky
2013-12-26  2:17   ` [PATCH 9/9] drm/i915: Split GEN6 PPGTT initialization up Ben Widawsky

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1387921357-22942-5-git-send-email-benjamin.widawsky@intel.com \
    --to=benjamin.widawsky@intel.com \
    --cc=ben@bwidawsk.net \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox