Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Nareshkumar Gollakoti <naresh.kumar.g@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: himal.prasad.ghimiray@intel.com,
	Nareshkumar Gollakoti <naresh.kumar.g@intel.com>
Subject: [PATCH v2 7/8] drm/xe/vm: validate large-page user BO bind alignment
Date: Wed,  1 Jul 2026 22:03:47 +0530	[thread overview]
Message-ID: <20260701163348.3432358-8-naresh.kumar.g@intel.com> (raw)
In-Reply-To: <20260701163348.3432358-1-naresh.kumar.g@intel.com>

Add VM bind validation for BOs that request 64K, 2M, or 1G pages.

When a BO is created with XE_BO_FLAG_NEEDS_64K, XE_BO_FLAG_NEEDS_2M,
or XE_BO_FLAG_NEEDS_1G, require the bind offset, virtual address, and
range to be aligned to the requested page size for map operations.
Skip these checks for unmap and unmap-all.

Also allow the corresponding VMA page table flags in the user-visible
VMA flag mask.

This prevents invalid bind requests for large-page BOs from reaching
later VM setup paths.

v2:(sashiko)
- add 64K alignment validation alongside 2M and 1G
  for user bindpaths
- keep large-page alignment checks skipped for
  UNMAP and UNMAP_ALL
- refine commit message wordings

Signed-off-by: Nareshkumar Gollakoti <naresh.kumar.g@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 50ca29a79533..3fc5f1db93d0 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -721,7 +721,10 @@ static void xe_vma_ops_incr_pt_update_ops(struct xe_vma_ops *vops, u8 tile_mask,
 	XE_VMA_DUMPABLE |		    \
 	XE_VMA_SYSTEM_ALLOCATOR |           \
 	DRM_GPUVA_SPARSE |		    \
-	XE_VMA_MADV_AUTORESET)
+	XE_VMA_MADV_AUTORESET |		    \
+	XE_VMA_PTE_64K |		    \
+	XE_VMA_PTE_2M  |		    \
+	XE_VMA_PTE_1G)
 
 static void xe_vm_populate_rebind(struct xe_vma_op *op, struct xe_vma *vma,
 				  u8 tile_mask)
@@ -3835,6 +3838,36 @@ static int xe_vm_bind_ioctl_validate_bo(struct xe_device *xe, struct xe_bo *bo,
 		}
 	}
 
+	if (bo->flags & XE_BO_FLAG_NEEDS_64K &&
+	    (op != DRM_XE_VM_BIND_OP_UNMAP &&
+	     op != DRM_XE_VM_BIND_OP_UNMAP_ALL)) {
+		if (XE_IOCTL_DBG(xe, obj_offset & (SZ_64K - 1)) ||
+		    XE_IOCTL_DBG(xe, addr & (SZ_64K - 1)) ||
+		    XE_IOCTL_DBG(xe, range & (SZ_64K - 1))) {
+			return -EINVAL;
+		}
+	}
+
+	if (bo->flags & XE_BO_FLAG_NEEDS_2M &&
+	    (op != DRM_XE_VM_BIND_OP_UNMAP &&
+	     op != DRM_XE_VM_BIND_OP_UNMAP_ALL)) {
+		if (XE_IOCTL_DBG(xe, obj_offset & (SZ_2M - 1)) ||
+		    XE_IOCTL_DBG(xe, addr & (SZ_2M - 1)) ||
+		    XE_IOCTL_DBG(xe, range & (SZ_2M - 1))) {
+			return -EINVAL;
+		}
+	}
+
+	if (bo->flags & XE_BO_FLAG_NEEDS_1G &&
+	    (op != DRM_XE_VM_BIND_OP_UNMAP &&
+	     op != DRM_XE_VM_BIND_OP_UNMAP_ALL)) {
+		if (XE_IOCTL_DBG(xe, obj_offset & (SZ_1G - 1)) ||
+		    XE_IOCTL_DBG(xe, addr & (SZ_1G - 1)) ||
+		    XE_IOCTL_DBG(xe, range & (SZ_1G - 1))) {
+			return -EINVAL;
+		}
+	}
+
 	coh_mode = xe_pat_index_get_coh_mode(xe, pat_index);
 	if (bo->cpu_caching) {
 		if (XE_IOCTL_DBG(xe, coh_mode == XE_COH_NONE &&
-- 
2.43.0


  parent reply	other threads:[~2026-07-01 16:33 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-01 16:33 [PATCH v2 0/8] drm/xe: add page size allocation mode control Nareshkumar Gollakoti
2026-07-01 16:33 ` [PATCH v2 1/8] drm/xe: add page size allocation control state to xe_device Nareshkumar Gollakoti
2026-07-01 16:33 ` [PATCH v2 2/8] drm/xe: add helper for multi page-size support Nareshkumar Gollakoti
2026-07-01 16:33 ` [PATCH v2 3/8] drm/xe/debugfs: add page size allocation mode knob Nareshkumar Gollakoti
2026-07-01 16:33 ` [PATCH v2 4/8] drm/xe: add 1G BO page-size alignment flag Nareshkumar Gollakoti
2026-07-01 16:33 ` [PATCH v2 5/8] drm/xe: apply debug page-size policy to user BO creation Nareshkumar Gollakoti
2026-07-01 16:33 ` [PATCH v2 6/8] drm/xe/vm: apply debug page-size policy to VMA map flags Nareshkumar Gollakoti
2026-07-01 16:33 ` Nareshkumar Gollakoti [this message]
2026-07-01 16:33 ` [PATCH v2 8/8] drm/xe/pt: allow selecting the bind leaf PTE level Nareshkumar Gollakoti
2026-07-01 17:19 ` ✓ CI.KUnit: success for drm/xe: add page size allocation mode control Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260701163348.3432358-8-naresh.kumar.g@intel.com \
    --to=naresh.kumar.g@intel.com \
    --cc=himal.prasad.ghimiray@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox