diff options
| -rw-r--r-- | drivers/gpu/drm/i915/i915_gem.c | 30 |
1 files changed, 24 insertions, 6 deletions
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 8fd8e82ebda4..a34e8e2ba98a 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2668,7 +2668,6 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, drm_i915_private_t *dev_priv = dev->dev_private; int fence_reg; int fence_pitch_shift; - uint64_t val; if (INTEL_INFO(dev)->gen >= 6) { fence_reg = FENCE_REG_SANDYBRIDGE_0; @@ -2678,8 +2677,23 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, fence_pitch_shift = I965_FENCE_PITCH_SHIFT; } + fence_reg += reg * 8; + + /* To w/a incoherency with non-atomic 64-bit register updates, + * we split the 64-bit update into two 32-bit writes. In order + * for a partial fence not to be evaluated between writes, we + * precede the update with write to turn off the fence register, + * and only enable the fence as the last step. + * + * For extra levels of paranoia, we make sure each step lands + * before applying the next step. + */ + I915_WRITE(fence_reg, 0); + POSTING_READ(fence_reg); + if (obj) { u32 size = obj->gtt_space->size; + uint64_t val; val = (uint64_t)((obj->gtt_offset + size - 4096) & 0xfffff000) << 32; @@ -2688,12 +2702,16 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, if (obj->tiling_mode == I915_TILING_Y) val |= 1 << I965_FENCE_TILING_Y_SHIFT; val |= I965_FENCE_REG_VALID; - } else - val = 0; - fence_reg += reg * 8; - I915_WRITE64(fence_reg, val); - POSTING_READ(fence_reg); + I915_WRITE(fence_reg + 4, val >> 32); + POSTING_READ(fence_reg + 4); + + I915_WRITE(fence_reg + 0, val); + POSTING_READ(fence_reg); + } else { + I915_WRITE(fence_reg + 4, 0); + POSTING_READ(fence_reg + 4); + } } static void i915_write_fence_reg(struct drm_device *dev, int reg, |