diff options
| author | Matthew Auld <matthew.auld@intel.com> | 2025-10-22 17:38:31 +0100 |
|---|---|---|
| committer | Matthew Auld <matthew.auld@intel.com> | 2025-10-23 10:48:34 +0100 |
| commit | aaeef7a9c8b9206039a588a23e4dc11dddbefe2d (patch) | |
| tree | dc0be6f6fd7d1399345bcff83cea247c0aac3fbd | |
| parent | 3c767f762be973711421876d9e05e4dfd93f74ce (diff) | |
drm/xe/migrate: rework size restrictions for sram pte emit
We allow the input size to not be aligned to PAGE_SIZE, which leads to
various bugs in build_pt_update_batch_sram() for PAGE_SIZE > 4K systems.
For example if ptes is exactly one gpu_page_size then the chunk size is
rounded down to zero. The simplest fix looks to be forcing PAGE_SIZE
aligned inputs.
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20251022163836.191405-3-matthew.auld@intel.com
| -rw-r--r-- | drivers/gpu/drm/xe/xe_migrate.c | 13 |
1 files changed, 8 insertions, 5 deletions
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index ce2ad876586c..451fae0106e5 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -1798,6 +1798,8 @@ static void build_pt_update_batch_sram(struct xe_migrate *m, u32 ptes; int i = 0; + xe_tile_assert(m->tile, PAGE_ALIGNED(size)); + ptes = DIV_ROUND_UP(size, gpu_page_size); while (ptes) { u32 chunk = min(MAX_PTE_PER_SDI, ptes); @@ -1811,12 +1813,13 @@ static void build_pt_update_batch_sram(struct xe_migrate *m, ptes -= chunk; while (chunk--) { - u64 addr = sram_addr[i].addr & ~(gpu_page_size - 1); - u64 pte, orig_addr = addr; + u64 addr = sram_addr[i].addr; + u64 pte; xe_tile_assert(m->tile, sram_addr[i].proto == DRM_INTERCONNECT_SYSTEM); xe_tile_assert(m->tile, addr); + xe_tile_assert(m->tile, PAGE_ALIGNED(addr)); again: pte = m->q->vm->pt_ops->pte_encode_addr(m->tile->xe, @@ -1827,7 +1830,7 @@ again: if (gpu_page_size < PAGE_SIZE) { addr += XE_PAGE_SIZE; - if (orig_addr + PAGE_SIZE != addr) { + if (!PAGE_ALIGNED(addr)) { chunk--; goto again; } @@ -1918,10 +1921,10 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, if (use_pde) build_pt_update_batch_sram(m, bb, m->large_page_copy_pdes, - sram_addr, len + sram_offset, 1); + sram_addr, npages << PAGE_SHIFT, 1); else build_pt_update_batch_sram(m, bb, pt_slot * XE_PAGE_SIZE, - sram_addr, len + sram_offset, 0); + sram_addr, npages << PAGE_SHIFT, 0); if (dir == XE_MIGRATE_COPY_TO_VRAM) { if (use_pde) |