linux-kernel - Re: [PATCH-resent-to-correct-ml 5/8] drm/xe/coredump: Use guard helpers for xe_force

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <x5ziofhtmnqt22b5nlmnsomyc7qp4bvrhjrlnif6r3mw4xp3xm@ke75kmsh3i3w>
Date: Tue, 4 Feb 2025 09:40:32 -0600
From: Lucas De Marchi <lucas.demarchi@...el.com>
To: Maarten Lankhorst <dev@...khorst.se>
CC: <intel-xe@...ts.freedesktop.org>, <dri-devel@...ts.freedesktop.org>,
	<linux-kernel@...r.kernel.org>, Ingo Molnar <mingo@...nel.org>, David Lechner
	<dlechner@...libre.com>, Peter Zijlstra <peterz@...radead.org>, Will Deacon
	<will@...nel.org>, Waiman Long <longman@...hat.com>, Boqun Feng
	<boqun.feng@...il.com>
Subject: Re: [PATCH-resent-to-correct-ml 5/8] drm/xe/coredump: Use guard
 helpers for xe_force_wake.

On Tue, Feb 04, 2025 at 02:22:34PM +0100, Maarten Lankhorst wrote:
>---
> drivers/gpu/drm/xe/xe_devcoredump.c | 36 ++++++++++++++---------------
> 1 file changed, 17 insertions(+), 19 deletions(-)
>
>diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
>index 39fe485d20858..afe229fba8a9c 100644
>--- a/drivers/gpu/drm/xe/xe_devcoredump.c
>+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
>@@ -233,7 +233,6 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
> 	struct xe_devcoredump_snapshot *ss = container_of(work, typeof(*ss), work);
> 	struct xe_devcoredump *coredump = container_of(ss, typeof(*coredump), snapshot);
> 	struct xe_device *xe = coredump_to_xe(coredump);
>-	unsigned int fw_ref;
>
> 	/*
> 	 * NB: Despite passing a GFP_ flags parameter here, more allocations are done
>@@ -247,12 +246,13 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
> 	xe_pm_runtime_get(xe);
>
> 	/* keep going if fw fails as we still want to save the memory and SW data */
>-	fw_ref = xe_force_wake_get(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL);
>-	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
>-		xe_gt_info(ss->gt, "failed to get forcewake for coredump capture\n");
>-	xe_vm_snapshot_capture_delayed(ss->vm);
>-	xe_guc_exec_queue_snapshot_capture_delayed(ss->ge);
>-	xe_force_wake_put(gt_to_fw(ss->gt), fw_ref);
>+	scoped_guard(xe_force_wake, gt_to_fw(ss->gt), XE_FORCEWXE_FORCEWAKE_ALLAKE_ALL) {
>+		if (!xe_force_wake_scope_has_domain(XE_FORCEWAKE_ALL))
>+			xe_gt_info(ss->gt, "failed to get forcewake for coredump capture\n");

not sure why we are emitting a xe_gt_info() to the kernel log and just
letting the 2 calls above add garbage to the devcoredump - whoever is
processing the devcoredump later may have no clue about that log
message.. but I'm also not seeing why we need XE_FORCEWAKE_ALL in those
calls. Aren't they just reading the memory?

Lucas De Marchi

>+
>+		xe_vm_snapshot_capture_delayed(ss->vm);
>+		xe_guc_exec_queue_snapshot_capture_delayed(ss->ge);
>+	}
>
> 	xe_pm_runtime_put(xe);
>
>@@ -277,7 +277,6 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
> 	u32 width_mask = (0x1 << q->width) - 1;
> 	const char *process_name = "no process";
>
>-	unsigned int fw_ref;
> 	bool cookie;
> 	int i;
>
>@@ -305,20 +304,19 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
> 	}
>
> 	/* keep going if fw fails as we still want to save the memory and SW data */
>-	fw_ref = xe_force_wake_get(gt_to_fw(q->gt), XE_FORCEWAKE_ALL);
>-
>-	ss->guc.log = xe_guc_log_snapshot_capture(&guc->log, true);
>-	ss->guc.ct = xe_guc_ct_snapshot_capture(&guc->ct);
>-	ss->ge = xe_guc_exec_queue_snapshot_capture(q);
>-	if (job)
>-		ss->job = xe_sched_job_snapshot_capture(job);
>-	ss->vm = xe_vm_snapshot_capture(q->vm);
>-
>-	xe_engine_snapshot_capture_for_queue(q);
>+	scoped_guard(xe_force_wake, gt_to_fw(ss->gt), XE_FORCEWAKE_ALL) {
>+		ss->guc.log = xe_guc_log_snapshot_capture(&guc->log, true);
>+		ss->guc.ct = xe_guc_ct_snapshot_capture(&guc->ct);
>+		ss->ge = xe_guc_exec_queue_snapshot_capture(q);
>+		if (job)
>+			ss->job = xe_sched_job_snapshot_capture(job);
>+		ss->vm = xe_vm_snapshot_capture(q->vm);
>+
>+		xe_engine_snapshot_capture_for_queue(q);
>+	}
>
> 	queue_work(system_unbound_wq, &ss->work);
>
>-	xe_force_wake_put(gt_to_fw(q->gt), fw_ref);
> 	dma_fence_end_signalling(cookie);
> }
>
>-- 
>2.47.1
>