From: Rodrigo Vivi <rodrigo.vivi@intel.com>
To: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: intel-xe@lists.freedesktop.org,
"Piotr Piórkowski" <piotr.piorkowski@intel.com>
Subject: Re: [PATCH] drm/xe/pf: Assert LMEM provisioning is done only on DGFX
Date: Fri, 7 Jun 2024 12:08:58 -0400 [thread overview]
Message-ID: <ZmMwmm1H2ylPCKa1@intel.com> (raw)
In-Reply-To: <20240607153155.1592-1-michal.wajdeczko@intel.com>
On Fri, Jun 07, 2024 at 05:31:55PM +0200, Michal Wajdeczko wrote:
> The Local Memory (aka VRAM) is only available on DGFX platforms.
> We shouldn't attempt to provision VFs with LMEM or attempt to
> update the LMTT on non-DGFX platforms. Add missing asserts that
> would enforce that and fix release code that could crash on iGFX
> due to uninitialized LMTT.
>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Fixes: c063cce7df3a ("drm/xe/pf: Update the LMTT when freeing VF GT config")
> Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
> Cc: Piotr Piórkowski <piotr.piorkowski@intel.com>
> ---
> drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c | 15 +++++++++++++--
> 1 file changed, 13 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
> index f49fc2917f93..694671497f6e 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
> @@ -1290,6 +1290,9 @@ static void pf_reset_vf_lmtt(struct xe_device *xe, unsigned int vfid)
> struct xe_tile *tile;
> unsigned int tid;
>
> + xe_assert(xe, IS_DGFX(xe));
> + xe_assert(xe, IS_SRIOV_PF(xe));
> +
> for_each_tile(tile, xe, tid) {
> lmtt = &tile->sriov.pf.lmtt;
> xe_lmtt_drop_pages(lmtt, vfid);
> @@ -1308,6 +1311,9 @@ static int pf_update_vf_lmtt(struct xe_device *xe, unsigned int vfid)
> unsigned int tid;
> int err;
>
> + xe_assert(xe, IS_DGFX(xe));
> + xe_assert(xe, IS_SRIOV_PF(xe));
> +
> total = 0;
> for_each_tile(tile, xe, tid)
> total += pf_get_vf_config_lmem(tile->primary_gt, vfid);
> @@ -1353,6 +1359,7 @@ static int pf_update_vf_lmtt(struct xe_device *xe, unsigned int vfid)
>
> static void pf_release_vf_config_lmem(struct xe_gt *gt, struct xe_gt_sriov_config *config)
> {
> + xe_gt_assert(gt, IS_DGFX(gt_to_xe(gt)));
> xe_gt_assert(gt, !xe_gt_is_media_type(gt));
> lockdep_assert_held(xe_gt_sriov_pf_master_mutex(gt));
>
> @@ -1371,6 +1378,7 @@ static int pf_provision_vf_lmem(struct xe_gt *gt, unsigned int vfid, u64 size)
> int err;
>
> xe_gt_assert(gt, vfid);
> + xe_gt_assert(gt, IS_DGFX(xe));
> xe_gt_assert(gt, !xe_gt_is_media_type(gt));
>
> size = round_up(size, pf_get_lmem_alignment(gt));
> @@ -1838,11 +1846,14 @@ u32 xe_gt_sriov_pf_config_get_threshold(struct xe_gt *gt, unsigned int vfid,
> static void pf_release_vf_config(struct xe_gt *gt, unsigned int vfid)
> {
> struct xe_gt_sriov_config *config = pf_pick_vf_config(gt, vfid);
> + struct xe_device *xe = gt_to_xe(gt);
>
> if (!xe_gt_is_media_type(gt)) {
> pf_release_vf_config_ggtt(gt, config);
> - pf_release_vf_config_lmem(gt, config);
> - pf_update_vf_lmtt(gt_to_xe(gt), vfid);
> + if (IS_DGFX(xe)) {
> + pf_release_vf_config_lmem(gt, config);
> + pf_update_vf_lmtt(xe, vfid);
> + }
> }
> pf_release_config_ctxs(gt, config);
> pf_release_config_dbs(gt, config);
> --
> 2.43.0
>
next prev parent reply other threads:[~2024-06-07 16:09 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-07 15:31 [PATCH] drm/xe/pf: Assert LMEM provisioning is done only on DGFX Michal Wajdeczko
2024-06-07 15:37 ` ✓ CI.Patch_applied: success for " Patchwork
2024-06-07 15:37 ` ✓ CI.checkpatch: " Patchwork
2024-06-07 15:38 ` ✓ CI.KUnit: " Patchwork
2024-06-07 15:57 ` ✓ CI.Build: " Patchwork
2024-06-07 16:00 ` ✓ CI.Hooks: " Patchwork
2024-06-07 16:01 ` ✓ CI.checksparse: " Patchwork
2024-06-07 16:08 ` Rodrigo Vivi [this message]
2024-06-07 16:53 ` ✓ CI.BAT: " Patchwork
2024-06-08 2:21 ` ✗ CI.FULL: failure " Patchwork
2024-06-08 16:14 ` Michal Wajdeczko
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=ZmMwmm1H2ylPCKa1@intel.com \
--to=rodrigo.vivi@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=michal.wajdeczko@intel.com \
--cc=piotr.piorkowski@intel.com \
/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