admin/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2025-12-07 20:06:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

drm/xe/migrate: rework size restrictions for sram pte emit

Browse Source 
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
This commit is contained in:
Matthew Auld
2025-10-22 17:38:31 +01:00
parent 3c767f762b
commit aaeef7a9c8
1 changed files with 8 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
drivers/gpu/drm/xe/xe_migrate.c
View File

@@ -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)