@@ -446,6 +446,27 @@ enum i915_cache_level {
typedef uint32_t gen6_gtt_pte_t;
+/* To make things as simple as possible (ie. no refcounting), a VMA's lifetime
+ * will always be <= an objects lifetime. So object refcounting should cover us.
+ */
+struct i915_vma {
+ struct drm_mm_node node;
+ struct drm_i915_gem_object *obj;
+ struct i915_address_space *vm;
+
+ /**
+ * This is set if the object is on the active lists (has pending
+ * rendering and so a non-zero seqno), and is not set if it i s on
+ * inactive (ready to be unbound) list.
+ */
+ unsigned int active:1;
+
+ /** This object's place on the active/inactive lists */
+ struct list_head mm_list;
+
+ struct list_head vma_link; /* Link in the object's VMA list */
+};
+
struct i915_address_space {
struct drm_mm mm;
struct drm_device *dev;
@@ -484,9 +505,18 @@ struct i915_address_space {
/* FIXME: Need a more generic return type */
gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
enum i915_cache_level level);
+
+ /** Unmap an object from an address space. This usually consists of
+ * setting the valid PTE entries to a reserved scratch page. */
+ void (*unmap_vma)(struct i915_vma *vma);
void (*clear_range)(struct i915_address_space *vm,
unsigned int first_entry,
unsigned int num_entries);
+ /* Map an object into an address space with the given cache flags. */
+#define GLOBAL_BIND (1<<0)
+ void (*map_vma)(struct i915_vma *vma,
+ enum i915_cache_level cache_level,
+ u32 flags);
void (*insert_entries)(struct i915_address_space *vm,
struct sg_table *st,
unsigned int first_entry,
@@ -533,27 +563,6 @@ struct i915_hw_ppgtt {
int (*enable)(struct drm_device *dev);
};
-/* To make things as simple as possible (ie. no refcounting), a VMA's lifetime
- * will always be <= an objects lifetime. So object refcounting should cover us.
- */
-struct i915_vma {
- struct drm_mm_node node;
- struct drm_i915_gem_object *obj;
- struct i915_address_space *vm;
-
- /**
- * This is set if the object is on the active lists (has pending
- * rendering and so a non-zero seqno), and is not set if it i s on
- * inactive (ready to be unbound) list.
- */
- unsigned int active:1;
-
- /** This object's place on the active/inactive lists */
- struct list_head mm_list;
-
- struct list_head vma_link; /* Link in the object's VMA list */
-};
-
struct i915_ctx_hang_stats {
/* This context had batch pending when hang was declared */
unsigned batch_pending;
@@ -55,6 +55,11 @@
#define HSW_WB_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x3)
#define HSW_WB_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0xb)
+static void gen6_ppgtt_map_vma(struct i915_vma *vma,
+ enum i915_cache_level cache_level,
+ u32 flags);
+static void gen6_ppgtt_unmap_vma(struct i915_vma *vma);
+
static gen6_gtt_pte_t gen6_pte_encode(dma_addr_t addr,
enum i915_cache_level level)
{
@@ -307,7 +312,9 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
}
ppgtt->num_pd_entries = GEN6_PPGTT_PD_ENTRIES;
ppgtt->enable = gen6_ppgtt_enable;
+ ppgtt->base.unmap_vma = NULL;
ppgtt->base.clear_range = gen6_ppgtt_clear_range;
+ ppgtt->base.map_vma = NULL;
ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
ppgtt->base.cleanup = gen6_ppgtt_cleanup;
ppgtt->base.scratch = dev_priv->gtt.base.scratch;
@@ -419,6 +426,17 @@ void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt,
cache_level);
}
+static void __always_unused gen6_ppgtt_map_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);
+
+ gen6_ppgtt_insert_entries(vma->vm, vma->obj->pages, entry, cache_level);
+}
+
void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
struct drm_i915_gem_object *obj)
{
@@ -429,6 +447,14 @@ void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
obj->base.size >> PAGE_SHIFT);
}
+static void __always_unused gen6_ppgtt_unmap_vma(struct i915_vma *vma)
+{
+ const unsigned long entry = vma->node.start >> PAGE_SHIFT;
+
+ gen6_ppgtt_clear_range(vma->vm, entry,
+ vma->obj->base.size >> PAGE_SHIFT);
+}
+
extern int intel_iommu_gfx_mapped;
/* Certain Gen5 chipsets require require idling the GPU before
* unmapping anything from the GTT when VT-d is enabled.
@@ -577,6 +603,19 @@ static void i915_ggtt_insert_entries(struct i915_address_space *vm,
}
+static void i915_ggtt_map_vma(struct i915_vma *vma,
+ enum i915_cache_level cache_level,
+ u32 unused)
+{
+ const unsigned long entry = vma->node.start >> PAGE_SHIFT;
+ unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+ AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
+
+ BUG_ON(!i915_is_ggtt(vma->vm));
+ intel_gtt_insert_sg_entries(vma->obj->pages, entry, flags);
+ vma->obj->has_global_gtt_mapping = 1;
+}
+
static void i915_ggtt_clear_range(struct i915_address_space *vm,
unsigned int first_entry,
unsigned int num_entries)
@@ -584,6 +623,46 @@ static void i915_ggtt_clear_range(struct i915_address_space *vm,
intel_gtt_clear_range(first_entry, num_entries);
}
+static void i915_ggtt_unmap_vma(struct i915_vma *vma)
+{
+ const unsigned int first = vma->node.start >> PAGE_SHIFT;
+ const unsigned int size = vma->obj->base.size >> PAGE_SHIFT;
+
+ BUG_ON(!i915_is_ggtt(vma->vm));
+ vma->obj->has_global_gtt_mapping = 0;
+ intel_gtt_clear_range(first, size);
+}
+
+static void gen6_ggtt_map_vma(struct i915_vma *vma,
+ enum i915_cache_level cache_level,
+ u32 flags)
+{
+ 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 an aliasing PPGTT, and the user didn't explicitly ask for
+ * the global, just use aliasing */
+ if (dev_priv->mm.aliasing_ppgtt && !(flags & GLOBAL_BIND) &&
+ !obj->has_global_gtt_mapping) {
+ gen6_ppgtt_insert_entries(&dev_priv->mm.aliasing_ppgtt->base,
+ vma->obj->pages, entry, cache_level);
+ vma->obj->has_aliasing_ppgtt_mapping = 1;
+ return;
+ }
+
+ gen6_ggtt_insert_entries(vma->vm, obj->pages, entry, cache_level);
+ obj->has_global_gtt_mapping = 1;
+
+ /* If put the mapping in the aliasing PPGTT as well as Global if we have
+ * aliasing, but the user requested global. */
+ if (dev_priv->mm.aliasing_ppgtt) {
+ gen6_ppgtt_insert_entries(&dev_priv->mm.aliasing_ppgtt->base,
+ vma->obj->pages, entry, cache_level);
+ vma->obj->has_aliasing_ppgtt_mapping = 1;
+ }
+}
void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj,
enum i915_cache_level cache_level)
@@ -612,6 +691,23 @@ void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj)
obj->has_global_gtt_mapping = 0;
}
+static void gen6_ggtt_unmap_vma(struct i915_vma *vma)
+{
+ struct drm_device *dev = vma->vm->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ const unsigned long entry = vma->node.start >> PAGE_SHIFT;
+
+ gen6_ggtt_clear_range(vma->vm, entry,
+ vma->obj->base.size >> PAGE_SHIFT);
+ vma->obj->has_global_gtt_mapping = 0;
+ if (dev_priv->mm.aliasing_ppgtt && vma->obj->has_aliasing_ppgtt_mapping) {
+ gen6_ppgtt_clear_range(&dev_priv->mm.aliasing_ppgtt->base,
+ entry,
+ vma->obj->base.size >> PAGE_SHIFT);
+ vma->obj->has_aliasing_ppgtt_mapping = 0;
+ }
+}
+
void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj)
{
struct drm_device *dev = obj->base.dev;
@@ -845,7 +941,9 @@ static int gen6_gmch_probe(struct drm_device *dev,
DRM_ERROR("Scratch setup failed\n");
dev_priv->gtt.base.clear_range = gen6_ggtt_clear_range;
+ dev_priv->gtt.base.unmap_vma = gen6_ggtt_unmap_vma;
dev_priv->gtt.base.insert_entries = gen6_ggtt_insert_entries;
+ dev_priv->gtt.base.map_vma = gen6_ggtt_map_vma;
return ret;
}
@@ -877,7 +975,9 @@ static int i915_gmch_probe(struct drm_device *dev,
dev_priv->gtt.do_idle_maps = needs_idle_maps(dev_priv->dev);
dev_priv->gtt.base.clear_range = i915_ggtt_clear_range;
+ dev_priv->gtt.base.unmap_vma = i915_ggtt_unmap_vma;
dev_priv->gtt.base.insert_entries = i915_ggtt_insert_entries;
+ dev_priv->gtt.base.map_vma = i915_ggtt_map_vma;
return 0;
}
As we plumb the code with more VM information, it has become more obvious that the easiest way to deal with bind and unbind is to simply put the function pointers in the vm, and let those choose the correct way to handle the page table updates. This change allows many places in the code to simply be vm->map, and not have to worry about distinguishing PPGTT vs GGTT. Notice that this patch has no impact on functionality. I've decided to save the actual change until the next patch because I think it's easier to review that way. I'm happy to squash the two, or let Daniel do it on merge. v2: Make ggtt handle the quirky aliasing ppgtt Add flags to map object to support above Don't ever call bind/unbind directly for PPGTT until we have real, full PPGTT (use NULLs to assert this) Make sure we rebind the ggtt if there already is a ggtt binding. This happens on set cache levels Use VMA for map/unmap, call it map/unmap (Daniel, Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net> --- drivers/gpu/drm/i915/i915_drv.h | 51 ++++++++++-------- drivers/gpu/drm/i915/i915_gem_gtt.c | 100 ++++++++++++++++++++++++++++++++++++ 2 files changed, 130 insertions(+), 21 deletions(-)