From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
Flushing l2 is only needed after all data has been written.
Fixes: 01570b446939 ("drm/xe/bmg: implement Wa_16023588340") Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Cc: Matthew Auld matthew.auld@intel.com Cc: stable@vger.kernel.org # v6.12+ Reviewed-by: Matthew Auld matthew.auld@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com --- drivers/gpu/drm/xe/display/xe_dsb_buffer.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c index f95375451e2f..9f941fc2e36b 100644 --- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c +++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c @@ -17,10 +17,7 @@ u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf)
void intel_dsb_buffer_write(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val) { - struct xe_device *xe = dsb_buf->vma->bo->tile->xe; - iosys_map_wr(&dsb_buf->vma->bo->vmap, idx * 4, u32, val); - xe_device_l2_flush(xe); }
u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx) @@ -30,12 +27,9 @@ u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx)
void intel_dsb_buffer_memset(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size) { - struct xe_device *xe = dsb_buf->vma->bo->tile->xe; - WARN_ON(idx > (dsb_buf->buf_size - size) / sizeof(*dsb_buf->cmd_buf));
iosys_map_memset(&dsb_buf->vma->bo->vmap, idx * 4, val, size); - xe_device_l2_flush(xe); }
bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *dsb_buf, size_t size) @@ -74,9 +68,12 @@ void intel_dsb_buffer_cleanup(struct intel_dsb_buffer *dsb_buf)
void intel_dsb_buffer_flush_map(struct intel_dsb_buffer *dsb_buf) { + struct xe_device *xe = dsb_buf->vma->bo->tile->xe; + /* * The memory barrier here is to ensure coherency of DSB vs MMIO, * both for weak ordering archs and discrete cards. */ - xe_device_wmb(dsb_buf->vma->bo->tile->xe); + xe_device_wmb(xe); + xe_device_l2_flush(xe); }
Only need the flush for DPT host updates here. Normal GGTT updates don't need special flush.
Fixes: 01570b446939 ("drm/xe/bmg: implement Wa_16023588340") Signed-off-by: Matthew Auld matthew.auld@intel.com Cc: Maarten Lankhorst maarten.lankhorst@linux.intel.com Cc: stable@vger.kernel.org # v6.12+ --- drivers/gpu/drm/xe/display/xe_fb_pin.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c index 461ecdfdb742..b16a6e3ff4b4 100644 --- a/drivers/gpu/drm/xe/display/xe_fb_pin.c +++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c @@ -165,6 +165,9 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb,
vma->dpt = dpt; vma->node = dpt->ggtt_node[tile0->id]; + + /* Ensure DPT writes are flushed */ + xe_device_l2_flush(xe); return 0; }
@@ -334,8 +337,6 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb, if (ret) goto err_unpin;
- /* Ensure DPT writes are flushed */ - xe_device_l2_flush(xe); return vma;
err_unpin:
On 06/06/2025 11:45, Matthew Auld wrote:
From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
Flushing l2 is only needed after all data has been written.
Fixes: 01570b446939 ("drm/xe/bmg: implement Wa_16023588340") Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Cc: Matthew Auld matthew.auld@intel.com Cc: stable@vger.kernel.org # v6.12+ Reviewed-by: Matthew Auld matthew.auld@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com
Tested this locally and noticed a pretty big improvement just playing around in the desktop environment, where stuff feels way smoother.
drivers/gpu/drm/xe/display/xe_dsb_buffer.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c index f95375451e2f..9f941fc2e36b 100644 --- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c +++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c @@ -17,10 +17,7 @@ u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf) void intel_dsb_buffer_write(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val) {
- struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
- iosys_map_wr(&dsb_buf->vma->bo->vmap, idx * 4, u32, val);
- xe_device_l2_flush(xe); }
u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx) @@ -30,12 +27,9 @@ u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx) void intel_dsb_buffer_memset(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size) {
- struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
- WARN_ON(idx > (dsb_buf->buf_size - size) / sizeof(*dsb_buf->cmd_buf));
iosys_map_memset(&dsb_buf->vma->bo->vmap, idx * 4, val, size);
- xe_device_l2_flush(xe); }
bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *dsb_buf, size_t size) @@ -74,9 +68,12 @@ void intel_dsb_buffer_cleanup(struct intel_dsb_buffer *dsb_buf) void intel_dsb_buffer_flush_map(struct intel_dsb_buffer *dsb_buf) {
- struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
- /*
*/
- The memory barrier here is to ensure coherency of DSB vs MMIO,
- both for weak ordering archs and discrete cards.
- xe_device_wmb(dsb_buf->vma->bo->tile->xe);
- xe_device_wmb(xe);
- xe_device_l2_flush(xe); }
linux-stable-mirror@lists.linaro.org