From: sashiko-bot@kernel.org
To: "Maarten Lankhorst" <dev@lankhorst.se>, intel-xe@lists.freedesktop.org
Cc: intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH v5 2/5] drm/xe/migrate: Support copying between sysmem and stolen
Date: Mon, 16 Nov 2026 13:29:06 +0000 [thread overview]
Message-ID: <sashiko-outbox-217075@kernel.org> (raw)
In-Reply-To: <20261116131349.333818-9-dev@lankhorst.se>
Thank you for your contribution! Sashiko AI review found 1 potential
issue to consider:
- [High] drm/xe/migrate: missing stolen base offset in emit_pte() on
pre-1270 iGPUs
--
commit 73a1bb32ca907a5d90c3e0d2392791649e5d6ca0
Author: Maarten Lankhorst <dev@lankhorst.se>
drm/xe/migrate: Support copying between sysmem and stolen
This commit adds support for XE_PL_STOLEN buffer objects to
__xe_migrate_copy() and xe_migrate_clear(), disabling identity mapping for
stolen memory and treating stolen resources as device memory when GGTT CPU
access is not required.
> diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
> index 19c37eb315893..2e194ac6fb4f0 100644
> --- a/drivers/gpu/drm/xe/xe_migrate.c
> +++ b/drivers/gpu/drm/xe/xe_migrate.c
[ ... ]
> @@ -1206,6 +1211,24 @@ static u32 xe_migrate_ccs_copy(struct xe_migrate *m,
> return flush_flags;
> }
>
> +static bool is_devmem(struct xe_bo *bo, struct ttm_resource *res)
> +{
> + if (mem_type_is_vram(res->mem_type))
> + return true;
> +
> + /*
> + * Stolen is only device memory on newer platforms.
> + *
> + * On older platforms where stolen is mapped to GGTT,
> + * it is mapped as system memory.
> + */
> + if (res->mem_type != XE_PL_STOLEN ||
> + xe_ttm_stolen_cpu_access_needs_ggtt(xe_bo_device(bo)))
> + return false;
> +
> + return true;
> +}
> +
> static struct dma_fence *__xe_migrate_copy(struct xe_migrate *m,
> struct xe_bo *src_bo,
> struct xe_bo *dst_bo,
> @@ -1226,8 +1249,8 @@ static struct dma_fence *__xe_migrate_copy(struct xe_migrate *m,
> int err;
> bool src_is_pltt = src->mem_type == XE_PL_TT;
> bool dst_is_pltt = dst->mem_type == XE_PL_TT;
> - bool src_is_vram = mem_type_is_vram(src->mem_type);
> - bool dst_is_vram = mem_type_is_vram(dst->mem_type);
> + bool src_is_vram = is_devmem(src_bo, src);
> + bool dst_is_vram = is_devmem(dst_bo, dst);
> bool type_device = src_bo->ttm.type == ttm_bo_type_device;
> bool needs_ccs_emit = type_device && xe_migrate_needs_ccs_emit(xe);
> bool copy_ccs = xe_device_has_flat_ccs(xe) &&
> @@ -1250,11 +1273,11 @@ static struct dma_fence *__xe_migrate_copy(struct xe_migrate *m,
> if (src_bo != dst_bo && XE_WARN_ON(xe_bo_size(src_bo) != xe_bo_size(dst_bo)))
> return ERR_PTR(-EINVAL);
>
> - if (!src_is_vram)
> + if (!src_is_vram && src->mem_type != XE_PL_STOLEN)
> xe_res_first_sg(xe_bo_sg(src_bo), 0, size, &src_it);
> else
> xe_res_first(src, 0, size, &src_it);
> - if (!dst_is_vram)
> + if (!dst_is_vram && dst->mem_type != XE_PL_STOLEN)
> xe_res_first_sg(xe_bo_sg(dst_bo), 0, size, &dst_it);
> else
> xe_res_first(dst, 0, size, &dst_it);
[Severity: High]
Does emit_pte() omit vram_region_gpu_offset(res) for XE_PL_STOLEN on
integrated platforms with GRAPHICS_VERx100(xe) < 1270?
On those platforms xe_ttm_stolen_cpu_access_needs_ggtt() is true, so
is_devmem() returns false for src_is_vram, dst_is_vram, and clear_vram
while xe_res_first() still initializes the cursor with a 0-based offset
into stolen memory. In emit_pte(), vram_region_gpu_offset(res) is only
added when is_vram is true:
drivers/gpu/drm/xe/xe_migrate.c:emit_pte() {
...
addr = xe_res_dma(cur) & PAGE_MASK;
if (is_vram) {
...
addr += vram_region_gpu_offset(res);
devmem = true;
}
...
}
As a result, __xe_migrate_copy() and xe_migrate_clear() encode physical
addresses starting at 0x0 instead of mgr->stolen_base, causing GPU DMA to
read or overwrite low host system RAM (for example during fbdev BIOS
framebuffer takeover).
--
Sashiko AI review · https://sashiko.dev/#/patchset/20261116131349.333818-7-dev@lankhorst.se?part=2
next prev parent reply other threads:[~2026-11-16 13:29 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-16 13:13 [PATCH v5 0/5] drm/xe/display: Transparant fallback from stolen to sysmem Maarten Lankhorst
2026-11-16 13:13 ` [PATCH v5 1/5] drm/xe/display: Avoid using stolen memory for framebuffer when media gt exists Maarten Lankhorst
2026-11-16 13:13 ` [PATCH v5 2/5] drm/xe/migrate: Support copying between sysmem and stolen Maarten Lankhorst
2026-11-16 13:29 ` sashiko-bot [this message]
2026-11-16 13:13 ` [PATCH v5 3/5] drm/xe: Raise gt frequency slightly earlier Maarten Lankhorst
2026-11-16 13:13 ` [PATCH v5 4/5] HACK: Always fallback Maarten Lankhorst
2026-11-16 13:25 ` sashiko-bot
2026-11-16 13:13 ` [PATCH v5 5/5] drm/i915: Introduce intel_bo_fbdev_bios_fb_takeover() Maarten Lankhorst
2026-11-16 13:26 ` Ville Syrjälä
2026-11-16 13:59 ` sashiko-bot
2026-11-16 15:53 ` ✗ CI.checkpatch: warning for drm/xe/display: Transparant fallback from stolen to sysmem. (rev6) Patchwork
2026-11-16 15:55 ` ✓ CI.KUnit: success " Patchwork
-- strict thread matches above, loose matches on Subject: below --
2026-11-13 12:44 [PATCH v5 0/5] drm/xe/display: Transparant fallback from stolen to sysmem Maarten Lankhorst
2026-11-13 12:44 ` [PATCH v5 2/5] drm/xe/migrate: Support copying between sysmem and stolen Maarten Lankhorst
2026-11-13 13:05 ` sashiko-bot
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=sashiko-outbox-217075@kernel.org \
--to=sashiko-bot@kernel.org \
--cc=dev@lankhorst.se \
--cc=intel-gfx@lists.freedesktop.org \
--cc=intel-xe@lists.freedesktop.org \
--cc=sashiko-reviews@lists.linux.dev \
/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