[PATCH] intel: new interface for cached bo create

[Zhenyu Wang <zhenyuw@linux.intel.com>]

This is required for special bo like PIPE_CONTROL store DW buffer
used in occlusion query.

Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 include/drm/i915_drm.h   |    5 ++++-
 intel/intel_bufmgr.h     |    3 +++
 intel/intel_bufmgr_gem.c |   38 +++++++++++++++++++++++++++++++++++++-
 3 files changed, 44 insertions(+), 2 deletions(-)

diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index 19da2c0..a0b97cf 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -279,6 +279,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_BSD		 10
 #define I915_PARAM_HAS_BLT		 11
 #define I915_PARAM_HAS_RELAXED_FENCING	 12
+#define I915_PARAM_HAS_CREATE_CACHED	 14
 
 typedef struct drm_i915_getparam {
 	int param;
@@ -360,6 +361,8 @@ struct drm_i915_gem_init {
 	__u64 gtt_end;
 };
 
+#define DRM_I915_GEM_CREATE_CACHED	1
+
 struct drm_i915_gem_create {
 	/**
 	 * Requested size for the object.
@@ -373,7 +376,7 @@ struct drm_i915_gem_create {
 	 * Object handles are nonzero.
 	 */
 	__u32 handle;
-	__u32 pad;
+	__u32 flags;
 };
 
 struct drm_i915_gem_pread {
diff --git a/intel/intel_bufmgr.h b/intel/intel_bufmgr.h
index e1b4c45..17a2d3b 100644
--- a/intel/intel_bufmgr.h
+++ b/intel/intel_bufmgr.h
@@ -84,6 +84,7 @@ struct _drm_intel_bo {
 };
 
 #define BO_ALLOC_FOR_RENDER (1<<0)
+#define BO_ALLOC_FORCE_CACHED (1<<1)
 
 drm_intel_bo *drm_intel_bo_alloc(drm_intel_bufmgr *bufmgr, const char *name,
 				 unsigned long size, unsigned int alignment);
@@ -97,6 +98,8 @@ drm_intel_bo *drm_intel_bo_alloc_tiled(drm_intel_bufmgr *bufmgr,
 				       uint32_t *tiling_mode,
 				       unsigned long *pitch,
 				       unsigned long flags);
+drm_intel_bo *drm_intel_gem_bo_alloc_cached(drm_intel_bufmgr *bufmgr, const char *name,
+					    unsigned long size, unsigned int alignment);
 void drm_intel_bo_reference(drm_intel_bo *bo);
 void drm_intel_bo_unreference(drm_intel_bo *bo);
 int drm_intel_bo_map(drm_intel_bo *bo, int write_enable);
diff --git a/intel/intel_bufmgr_gem.c b/intel/intel_bufmgr_gem.c
index c5bb588..019630f 100644
--- a/intel/intel_bufmgr_gem.c
+++ b/intel/intel_bufmgr_gem.c
@@ -103,6 +103,7 @@ typedef struct _drm_intel_bufmgr_gem {
 	unsigned int has_blt : 1;
 	unsigned int has_relaxed_fencing : 1;
 	unsigned int bo_reuse : 1;
+	unsigned int has_create_cached : 1;
 	char fenced_relocs;
 } drm_intel_bufmgr_gem;
 
@@ -584,7 +585,7 @@ drm_intel_gem_bo_alloc_internal(drm_intel_bufmgr *bufmgr,
 				unsigned long stride)
 {
 	drm_intel_bufmgr_gem *bufmgr_gem = (drm_intel_bufmgr_gem *) bufmgr;
-	drm_intel_bo_gem *bo_gem;
+	drm_intel_bo_gem *bo_gem = NULL;
 	unsigned int page_size = getpagesize();
 	int ret;
 	struct drm_intel_gem_bo_bucket *bucket;
@@ -592,6 +593,15 @@ drm_intel_gem_bo_alloc_internal(drm_intel_bufmgr *bufmgr,
 	unsigned long bo_size;
 	int for_render = 0;
 
+	if (flags & BO_ALLOC_FORCE_CACHED) {
+		DBG("bo_alloc_internal: alloc bo %s cached\n", name);
+		alloc_from_cache = 0;
+		bo_size = size;
+		if (bo_size < page_size)
+			bo_size = page_size;
+		goto kernel_alloc;
+	}
+
 	if (flags & BO_ALLOC_FOR_RENDER)
 		for_render = 1;
 
@@ -658,6 +668,7 @@ retry:
 	}
 	pthread_mutex_unlock(&bufmgr_gem->lock);
 
+kernel_alloc:
 	if (!alloc_from_cache) {
 		struct drm_i915_gem_create create;
 
@@ -668,6 +679,8 @@ retry:
 		bo_gem->bo.size = bo_size;
 		memset(&create, 0, sizeof(create));
 		create.size = bo_size;
+		if (flags & BO_ALLOC_FORCE_CACHED)
+			create.flags = DRM_I915_GEM_CREATE_CACHED;
 
 		ret = drmIoctl(bufmgr_gem->fd,
 			       DRM_IOCTL_I915_GEM_CREATE,
@@ -729,6 +742,25 @@ drm_intel_gem_bo_alloc(drm_intel_bufmgr *bufmgr,
 					       I915_TILING_NONE, 0);
 }
 
+drm_intel_bo *
+drm_intel_gem_bo_alloc_cached(drm_intel_bufmgr *bufmgr,
+			      const char *name,
+			      unsigned long size,
+			      unsigned int alignment)
+{
+	drm_intel_bufmgr_gem *bufmgr_gem = (drm_intel_bufmgr_gem *) bufmgr;
+
+	if (bufmgr_gem->has_create_cached)
+		return drm_intel_gem_bo_alloc_internal(bufmgr, name, size, 
+						       BO_ALLOC_FORCE_CACHED,
+						       I915_TILING_NONE, 0);
+	else {
+		DBG("bo_alloc_cached: kernel not support cached alloc!\n");
+		return drm_intel_gem_bo_alloc_internal(bufmgr, name, size, 0,
+						       I915_TILING_NONE, 0);
+	}
+}
+
 static drm_intel_bo *
 drm_intel_gem_bo_alloc_tiled(drm_intel_bufmgr *bufmgr, const char *name,
 			     int x, int y, int cpp, uint32_t *tiling_mode,
@@ -2146,6 +2178,10 @@ drm_intel_bufmgr_gem_init(int fd, int batch_size)
 	ret = drmIoctl(bufmgr_gem->fd, DRM_IOCTL_I915_GETPARAM, &gp);
 	bufmgr_gem->has_relaxed_fencing = ret == 0;
 
+	gp.param = I915_PARAM_HAS_CREATE_CACHED;
+	ret = drmIoctl(bufmgr_gem->fd, DRM_IOCTL_I915_GETPARAM, &gp);
+	bufmgr_gem->has_create_cached = ret == 0;
+
 	if (bufmgr_gem->gen < 4) {
 		gp.param = I915_PARAM_NUM_FENCES_AVAIL;
 		gp.value = &bufmgr_gem->available_fences;
-- 
1.7.1