@@ -5628,39 +5628,6 @@ i915_gem_cleanup_engines(struct drm_i915_private *dev_priv)
dev_priv->gt.cleanup_engine(engine);
}
-void i915_ggtt_init_fences(struct i915_ggtt *ggtt)
-{
- struct drm_i915_private *dev_priv = ggtt->vm.i915;
- int i;
-
- if (INTEL_GEN(dev_priv) >= 7 && !IS_VALLEYVIEW(dev_priv) &&
- !IS_CHERRYVIEW(dev_priv))
- ggtt->num_fence_regs = 32;
- else if (INTEL_GEN(dev_priv) >= 4 ||
- IS_I945G(dev_priv) || IS_I945GM(dev_priv) ||
- IS_G33(dev_priv) || IS_PINEVIEW(dev_priv))
- ggtt->num_fence_regs = 16;
- else
- ggtt->num_fence_regs = 8;
-
- if (intel_vgpu_active(dev_priv))
- ggtt->num_fence_regs = I915_READ(vgtif_reg(avail_rs.fence_num));
-
- INIT_LIST_HEAD(&ggtt->fence_list);
-
- /* Initialize fence registers to zero */
- for (i = 0; i < ggtt->num_fence_regs; i++) {
- struct drm_i915_fence_reg *fence = &ggtt->fence_regs[i];
-
- fence->ggtt = ggtt;
- fence->id = i;
- list_add_tail(&fence->link, &ggtt->fence_list);
- }
- i915_gem_restore_fences(dev_priv);
-
- i915_gem_detect_bit_6_swizzle(dev_priv);
-}
-
static void i915_gem_init__mm(struct drm_i915_private *i915)
{
spin_lock_init(&i915->mm.object_stat_lock);
@@ -56,8 +56,6 @@ struct drm_i915_fence_reg {
bool dirty;
};
-void i915_ggtt_init_fences(struct i915_ggtt *ggtt);
-
struct drm_i915_fence_reg *
i915_reserve_fence(struct drm_i915_private *i915);
void i915_unreserve_fence(struct drm_i915_fence_reg *fence);
@@ -37,6 +37,7 @@
#include <drm/i915_drm.h>
#include "i915_drv.h"
+#include "i915_gem_fence_reg.h"
#include "i915_vgpu.h"
#include "i915_trace.h"
#include "intel_drv.h"
@@ -2898,6 +2899,51 @@ void i915_gem_fini_aliasing_ppgtt(struct drm_i915_private *i915)
ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma;
}
+static int i915_ggtt_init_fences(struct i915_ggtt *ggtt)
+{
+ struct drm_i915_private *dev_priv = ggtt->vm.i915;
+ int i;
+
+ if (INTEL_GEN(dev_priv) >= 7 &&
+ !(IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)))
+ ggtt->num_fence_regs = 32;
+ else if (INTEL_GEN(dev_priv) >= 4 ||
+ IS_I945G(dev_priv) || IS_I945GM(dev_priv) ||
+ IS_G33(dev_priv) || IS_PINEVIEW(dev_priv))
+ ggtt->num_fence_regs = 16;
+ else
+ ggtt->num_fence_regs = 8;
+
+ if (intel_vgpu_active(dev_priv))
+ ggtt->num_fence_regs = I915_READ(vgtif_reg(avail_rs.fence_num));
+
+ ggtt->fence_regs = kcalloc(ggtt->num_fence_regs,
+ sizeof(*ggtt->fence_regs),
+ GFP_KERNEL);
+ if (!ggtt->fence_regs)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&ggtt->fence_list);
+
+ /* Initialize fence registers to zero */
+ for (i = 0; i < ggtt->num_fence_regs; i++) {
+ struct drm_i915_fence_reg *fence = &ggtt->fence_regs[i];
+
+ fence->ggtt = ggtt;
+ fence->id = i;
+ list_add_tail(&fence->link, &ggtt->fence_list);
+ }
+ i915_gem_restore_fences(dev_priv);
+
+ i915_gem_detect_bit_6_swizzle(dev_priv);
+ return 0;
+}
+
+static void i915_ggtt_cleanup_fences(struct i915_ggtt *ggtt)
+{
+ kfree(ggtt->fence_regs);
+}
+
int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
{
/* Let GEM Manage all of the aperture.
@@ -2986,6 +3032,8 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
mutex_unlock(&dev_priv->drm.struct_mutex);
+ i915_ggtt_cleanup_fences(ggtt);
+
arch_phys_wc_del(ggtt->mtrr);
io_mapping_fini(&ggtt->iomap);
@@ -3591,13 +3639,15 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
ggtt->vm.mm.color_adjust = i915_gtt_color_adjust;
mutex_unlock(&dev_priv->drm.struct_mutex);
- i915_ggtt_init_fences(ggtt);
+ ret = i915_ggtt_init_fences(ggtt);
+ if (ret)
+ goto err_fini;
if (!io_mapping_init_wc(&ggtt->iomap,
ggtt->gmadr.start,
ggtt->mappable_end)) {
ret = -EIO;
- goto out_gtt_cleanup;
+ goto err_fences;
}
ggtt->mtrr = arch_phys_wc_add(ggtt->gmadr.start, ggtt->mappable_end);
@@ -3608,12 +3658,18 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
*/
ret = i915_gem_init_stolen(dev_priv);
if (ret)
- goto out_gtt_cleanup;
+ goto err_io;
return 0;
-out_gtt_cleanup:
+err_io:
+ arch_phys_wc_del(ggtt->mtrr);
+ io_mapping_fini(&ggtt->iomap);
+err_fences:
+ i915_ggtt_cleanup_fences(ggtt);
+err_fini:
ggtt->vm.cleanup(&ggtt->vm);
+ i915_address_space_fini(&ggtt->vm);
return ret;
}
@@ -38,7 +38,6 @@
#include <linux/mm.h>
#include <linux/pagevec.h>
-#include "i915_gem_fence_reg.h"
#include "i915_request.h"
#include "i915_selftest.h"
#include "i915_timeline.h"
@@ -378,7 +377,7 @@ struct i915_ggtt {
/** LRU list of objects with fence regs on them. */
struct list_head fence_list;
- struct drm_i915_fence_reg fence_regs[I915_MAX_NUM_FENCES];
+ struct drm_i915_fence_reg *fence_regs;
int num_fence_regs;
struct drm_mm_node error_capture;
@@ -30,6 +30,7 @@
#include <drm/drm_mm.h>
+#include "i915_gem_fence_reg.h"
#include "i915_gem_gtt.h"
#include "i915_gem_object.h"
If we dynamically allocate the correct sized array for the fence registers, we can avoid the 4x overallocation on older, typically smaller devices and avoid having to know the static layout in advance. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> --- drivers/gpu/drm/i915/i915_gem.c | 33 ------------ drivers/gpu/drm/i915/i915_gem_fence_reg.h | 2 - drivers/gpu/drm/i915/i915_gem_gtt.c | 64 +++++++++++++++++++++-- drivers/gpu/drm/i915/i915_gem_gtt.h | 3 +- drivers/gpu/drm/i915/i915_vma.h | 1 + 5 files changed, 62 insertions(+), 41 deletions(-)