[PATCH v3] drm/xe: Enable ATS if enabled on the PCI side
Matthew Brost
matthew.brost at intel.com
Tue Jun 10 00:46:13 UTC 2025
On Mon, Jun 09, 2025 at 03:54:08PM +0200, Thomas Hellström wrote:
> If IOMMU and device supports ATS, enable it in an effort to offload
> IOMMU TLB.
>
Can you explain what exactly you mean by offload 'IOMMU TLB'.
Does that mean physical addresses are cached on the device rather than
dma-addresses for system memory?
Matt
> v2:
> - Set the FORCE_FAULT PTE flag when clearing a PTE for faulting VM. (CI)
> v3:
> - More instances of FORCE_FAULT flag. (CI)
>
> Signed-off-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
> ---
> drivers/gpu/drm/xe/regs/xe_gtt_defs.h | 1 +
> drivers/gpu/drm/xe/xe_lrc.c | 5 ++++
> drivers/gpu/drm/xe/xe_pt.c | 36 +++++++++++++++------------
> 3 files changed, 26 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/regs/xe_gtt_defs.h b/drivers/gpu/drm/xe/regs/xe_gtt_defs.h
> index 4389e5a76f89..c6b32516b008 100644
> --- a/drivers/gpu/drm/xe/regs/xe_gtt_defs.h
> +++ b/drivers/gpu/drm/xe/regs/xe_gtt_defs.h
> @@ -33,5 +33,6 @@
>
> #define XE_PAGE_PRESENT BIT_ULL(0)
> #define XE_PAGE_RW BIT_ULL(1)
> +#define XE_PAGE_FORCE_FAULT BIT_ULL(2)
>
> #endif
> diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
> index 61a2e87990a9..085f7e0568e9 100644
> --- a/drivers/gpu/drm/xe/xe_lrc.c
> +++ b/drivers/gpu/drm/xe/xe_lrc.c
> @@ -976,6 +976,7 @@ static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
>
> #define PVC_CTX_ASID (0x2e + 1)
> #define PVC_CTX_ACC_CTR_THOLD (0x2a + 1)
> +#define XE_CTX_PASID (0x2c + 1)
>
> static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
> struct xe_vm *vm, u32 ring_size, u16 msix_vec,
> @@ -1104,6 +1105,10 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
> if (xe->info.has_asid && vm)
> xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, vm->usm.asid);
>
> + /* If possible, enable ATS to offload the IOMMU TLB */
> + if (to_pci_dev(xe->drm.dev)->ats_enabled)
> + xe_lrc_write_ctx_reg(lrc, XE_CTX_PASID, (1 << 31));
> +
> lrc->desc = LRC_VALID;
> lrc->desc |= FIELD_PREP(LRC_ADDRESSING_MODE, LRC_LEGACY_64B_CONTEXT);
> /* TODO: Priority */
> diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
> index c9c41fbe125c..6227ea238b1b 100644
> --- a/drivers/gpu/drm/xe/xe_pt.c
> +++ b/drivers/gpu/drm/xe/xe_pt.c
> @@ -65,7 +65,7 @@ static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
> u8 id = tile->id;
>
> if (!xe_vm_has_scratch(vm))
> - return 0;
> + return XE_PAGE_FORCE_FAULT;
>
> if (level > MAX_HUGEPTE_LEVEL)
> return vm->pt_ops->pde_encode_bo(vm->scratch_pt[id][level - 1]->bo,
> @@ -163,17 +163,9 @@ void xe_pt_populate_empty(struct xe_tile *tile, struct xe_vm *vm,
> u64 empty;
> int i;
>
> - if (!xe_vm_has_scratch(vm)) {
> - /*
> - * FIXME: Some memory is allocated already allocated to zero?
> - * Find out which memory that is and avoid this memset...
> - */
> - xe_map_memset(vm->xe, map, 0, 0, SZ_4K);
> - } else {
> - empty = __xe_pt_empty_pte(tile, vm, pt->level);
> - for (i = 0; i < XE_PDES; i++)
> - xe_pt_write(vm->xe, map, i, empty);
> - }
> + empty = __xe_pt_empty_pte(tile, vm, pt->level);
> + for (i = 0; i < XE_PDES; i++)
> + xe_pt_write(vm->xe, map, i, empty);
> }
>
> /**
> @@ -535,7 +527,7 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset,
> XE_WARN_ON(xe_walk->va_curs_start != addr);
>
> if (xe_walk->clear_pt) {
> - pte = 0;
> + pte = XE_PAGE_FORCE_FAULT;
> } else {
> pte = vm->pt_ops->pte_encode_vma(is_null ? 0 :
> xe_res_dma(curs) +
> @@ -865,9 +857,21 @@ static int xe_pt_zap_ptes_entry(struct xe_ptw *parent, pgoff_t offset,
> */
> if (xe_pt_nonshared_offsets(addr, next, --level, walk, action, &offset,
> &end_offset)) {
> - xe_map_memset(tile_to_xe(xe_walk->tile), &xe_child->bo->vmap,
> - offset * sizeof(u64), 0,
> - (end_offset - offset) * sizeof(u64));
> + struct iosys_map *map = &xe_child->bo->vmap;
> + struct xe_device *xe = tile_to_xe(xe_walk->tile);
> +
> + /*
> + * Write only the low dword in 32-bit case to avoid potential
> + * issues with the high dword being non-atomically written first
> + * resulting in an out-of-bounds address with the present
> + * bit set.
> + */
> + for (; offset < end_offset; offset++) {
> + if (IS_ENABLED(CONFIG_64BIT))
> + xe_map_wr(xe, map, offset * sizeof(u64), u64, XE_PAGE_FORCE_FAULT);
> + else
> + xe_map_wr(xe, map, offset * sizeof(u64), u32, XE_PAGE_FORCE_FAULT);
> + }
> xe_walk->needs_invalidate = true;
> }
>
> --
> 2.49.0
>
More information about the Intel-xe
mailing list