[PATCH 14/22] drm/i915: Make i915_vma_pin() small and inline

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Not only is i915_vma_pin() called for every single object on every single
execbuf, it is usually a simple increment as the VMA is already bound for
execution by the GPU. Rearrange the tests for unbound and pin_count
overflow so that we can do the increment and test very cheaply and
compact enough to inline the operation into execbuf. The trick used is
to note that we can check for an overflow bit (keeping space available
for it inside the flags) at the same time as checking the binding bits.

Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
---
 drivers/gpu/drm/i915/i915_gem.c     | 18 +++++--------
 drivers/gpu/drm/i915/i915_gem_gtt.h | 53 ++++++++++++++++++++++++++-----------
 2 files changed, 44 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index eeea7dab70f1..a666f72121eb 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3696,23 +3696,19 @@ void __i915_vma_set_map_and_fenceable(struct i915_vma *vma)
 	obj->map_and_fenceable = mappable && fenceable;
 }
 
-int
-i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
+int __i915_vma_do_pin(struct i915_vma *vma,
+		      u64 size, u64 alignment, u64 flags)
 {
-	unsigned int bound;
+	unsigned int bound = vma->flags;
 	int ret;
 
 	GEM_BUG_ON((flags & (PIN_GLOBAL | PIN_USER)) == 0);
 	GEM_BUG_ON((flags & PIN_GLOBAL) && !i915_vma_is_ggtt(vma));
 
-	bound = vma->flags;
-	if (WARN_ON((bound & I915_VMA_PIN_MASK) == I915_VMA_PIN_MASK))
-		return -EBUSY;
-
-	/* Pin early to prevent the shrinker/eviction logic from destroying
-	 * our vma as we insert and bind.
-	 */
-	__i915_vma_pin(vma);
+	if (WARN_ON(bound & I915_VMA_PIN_OVERFLOW)) {
+		ret = -EBUSY;
+		goto err;
+	}
 
 	if ((bound & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND)) == 0) {
 		ret = i915_vma_insert(vma, size, alignment, flags);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 0308c7401405..a7e05b4d7d2b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -193,13 +193,15 @@ struct i915_vma {
 	 * In the worst case this is 1 + 1 + 1 + 2*2 = 7. That would fit into 3
 	 * bits with absolutely no headroom. So use 4 bits. */
 #define I915_VMA_PIN_MASK 0xf
+#define I915_VMA_PIN_OVERFLOW	BIT(5)
 
 	/** Flags and address space this VMA is bound to */
-#define I915_VMA_GLOBAL_BIND	BIT(5)
-#define I915_VMA_LOCAL_BIND	BIT(6)
+#define I915_VMA_GLOBAL_BIND	BIT(6)
+#define I915_VMA_LOCAL_BIND	BIT(7)
+#define I915_VMA_BIND_MASK (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND | I915_VMA_PIN_OVERFLOW)
 
-#define I915_VMA_GGTT	BIT(7)
-#define I915_VMA_CLOSED BIT(8)
+#define I915_VMA_GGTT	BIT(8)
+#define I915_VMA_CLOSED BIT(9)
 
 	unsigned int active;
 	struct i915_gem_active last_read[I915_NUM_ENGINES];
@@ -616,20 +618,39 @@ i915_ggtt_view_equal(const struct i915_ggtt_view *a,
 	return true;
 }
 
-int __must_check
-i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags);
 /* Flags used by pin/bind&friends. */
-#define PIN_MAPPABLE		BIT(0)
-#define PIN_NONBLOCK		BIT(1)
-#define PIN_GLOBAL		BIT(2)
-#define PIN_OFFSET_BIAS		BIT(3)
-#define PIN_USER		BIT(4)
-#define PIN_UPDATE		BIT(5)
-#define PIN_ZONE_4G		BIT(6)
-#define PIN_HIGH		BIT(7)
-#define PIN_OFFSET_FIXED	BIT(8)
+#define PIN_NONBLOCK		BIT(0)
+#define PIN_MAPPABLE		BIT(1)
+#define PIN_ZONE_4G		BIT(2)
+
+#define PIN_MBZ			BIT(5) /* I915_VMA_PIN_OVERFLOW */
+#define PIN_GLOBAL		BIT(6) /* I915_VMA_GLOBAL_BIND */
+#define PIN_USER		BIT(7) /* I915_VMA_LOCAL_BIND */
+#define PIN_UPDATE		BIT(8)
+
+#define PIN_HIGH		BIT(9)
+#define PIN_OFFSET_BIAS		BIT(10)
+#define PIN_OFFSET_FIXED	BIT(11)
 #define PIN_OFFSET_MASK		(~4095)
 
+int __i915_vma_do_pin(struct i915_vma *vma,
+		      u64 size, u64 alignment, u64 flags);
+static inline int __must_check
+i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
+{
+	BUILD_BUG_ON(PIN_MBZ != I915_VMA_PIN_OVERFLOW);
+	BUILD_BUG_ON(PIN_GLOBAL != I915_VMA_GLOBAL_BIND);
+	BUILD_BUG_ON(PIN_USER != I915_VMA_LOCAL_BIND);
+
+	/* Pin early to prevent the shrinker/eviction logic from destroying
+	 * our vma as we insert and bind.
+	 */
+	if (likely(((++vma->flags ^ flags) & I915_VMA_BIND_MASK) == 0))
+		return 0;
+
+	return __i915_vma_do_pin(vma, size, alignment, flags);
+}
+
 static inline int i915_vma_pin_count(const struct i915_vma *vma)
 {
 	return vma->flags & I915_VMA_PIN_MASK;
@@ -643,7 +664,7 @@ static inline bool i915_vma_is_pinned(const struct i915_vma *vma)
 static inline void __i915_vma_pin(struct i915_vma *vma)
 {
 	vma->flags++;
-	GEM_BUG_ON(!i915_vma_is_pinned(vma));
+	GEM_BUG_ON(vma->flags & I915_VMA_PIN_OVERFLOW);
 }
 
 static inline void __i915_vma_unpin(struct i915_vma *vma)
-- 
2.8.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx




[Index of Archives]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]
  Powered by Linux