From: Nirmoy Das Date: Fri, 13 Dec 2024 12:24:14 +0000 (+0100) Subject: drm/xe: Use non-interruptible wait when moving BO to system X-Git-Tag: v6.14-rc1~174^2~9^2~18 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=dc5e20ae1f8a7c354dc9833faa2720254e5a5443;p=thirdparty%2Flinux.git drm/xe: Use non-interruptible wait when moving BO to system Ensure a non-interruptible wait is used when moving a bo to XE_PL_SYSTEM. This prevents dma_mappings from being removed prematurely while a GPU job is still in progress, even if the CPU receives a signal during the operation. Fixes: 75521e8b56e8 ("drm/xe: Perform dma_map when moving system buffer objects to TT") Cc: Thomas Hellström Cc: Matthew Brost Cc: Lucas De Marchi Cc: stable@vger.kernel.org # v6.11+ Suggested-by: Matthew Auld Reviewed-by: Matthew Auld Reviewed-by: Thomas Hellström Link: https://patchwork.freedesktop.org/patch/msgid/20241213122415.3880017-1-nirmoy.das@intel.com Signed-off-by: Nirmoy Das --- diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 283cd02945708..06931df876aba 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -733,7 +733,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, new_mem->mem_type == XE_PL_SYSTEM) { long timeout = dma_resv_wait_timeout(ttm_bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, - true, + false, MAX_SCHEDULE_TIMEOUT); if (timeout < 0) { ret = timeout;