From db7f92af626178ba59dbbcdd5dee9ec24a987a88 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Tue, 1 Oct 2024 09:43:47 +0100 Subject: drm/xe/ct: prevent UAF in send_recv() Ensure we serialize with completion side to prevent UAF with fence going out of scope on the stack, since we have no clue if it will fire after the timeout before we can erase from the xa. Also we have some dependent loads and stores for which we need the correct ordering, and we lack the needed barriers. Fix this by grabbing the ct->lock after the wait, which is also held by the completion side. v2 (Badal): - Also print done after acquiring the lock and seeing timeout. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Auld Cc: Matthew Brost Cc: Badal Nilawar Cc: # v6.8+ Reviewed-by: Badal Nilawar Link: https://patchwork.freedesktop.org/patch/msgid/20241001084346.98516-5-matthew.auld@intel.com (cherry picked from commit 52789ce35c55ccd30c4b67b9cc5b2af55e0122ea) Signed-off-by: Lucas De Marchi --- drivers/gpu/drm/xe/xe_guc_ct.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index f24dd5223926..79eb8e60137b 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -903,16 +903,26 @@ retry_same_fence: } ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ); + + /* + * Ensure we serialize with completion side to prevent UAF with fence going out of scope on + * the stack, since we have no clue if it will fire after the timeout before we can erase + * from the xa. Also we have some dependent loads and stores below for which we need the + * correct ordering, and we lack the needed barriers. + */ + mutex_lock(&ct->lock); if (!ret) { - xe_gt_err(gt, "Timed out wait for G2H, fence %u, action %04x", - g2h_fence.seqno, action[0]); + xe_gt_err(gt, "Timed out wait for G2H, fence %u, action %04x, done %s", + g2h_fence.seqno, action[0], str_yes_no(g2h_fence.done)); xa_erase_irq(&ct->fence_lookup, g2h_fence.seqno); + mutex_unlock(&ct->lock); return -ETIME; } if (g2h_fence.retry) { xe_gt_dbg(gt, "H2G action %#x retrying: reason %#x\n", action[0], g2h_fence.reason); + mutex_unlock(&ct->lock); goto retry; } if (g2h_fence.fail) { @@ -921,7 +931,12 @@ retry_same_fence: ret = -EIO; } - return ret > 0 ? response_buffer ? g2h_fence.response_len : g2h_fence.response_data : ret; + if (ret > 0) + ret = response_buffer ? g2h_fence.response_len : g2h_fence.response_data; + + mutex_unlock(&ct->lock); + + return ret; } /** -- cgit