linux-kernel - [PATCH AUTOSEL 5.15 013/188] drm/nouveau/pmu/gm200-: avoid touching PMU outside of DEVINIT/PREOS/ACR

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: <20220118023152.1948105-13-sashal@kernel.org>
Date:   Mon, 17 Jan 2022 21:28:57 -0500
From:   Sasha Levin <sashal@...nel.org>
To:     linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc:     Ben Skeggs <bskeggs@...hat.com>,
        Diego Viola <diego.viola@...il.com>,
        Karol Herbst <kherbst@...hat.com>,
        Sasha Levin <sashal@...nel.org>, lyude@...hat.com,
        airlied@...ux.ie, daniel@...ll.ch, dri-devel@...ts.freedesktop.org,
        nouveau@...ts.freedesktop.org
Subject: [PATCH AUTOSEL 5.15 013/188] drm/nouveau/pmu/gm200-: avoid touching PMU outside of DEVINIT/PREOS/ACR

From: Ben Skeggs <bskeggs@...hat.com>

[ Upstream commit 1d2271d2fb85e54bfc9630a6c30ac0feb9ffb983 ]

There have been reports of the WFI timing out on some boards, and a
patch was proposed to just remove it.  This stuff is rather fragile,
and I believe the WFI might be needed with our FW prior to GM200.

However, we probably should not be touching PMU during init on GPUs
where we depend on NVIDIA FW, outside of limited circumstances, so
this should be a somewhat safer change that achieves the desired
result.

Reported-by: Diego Viola <diego.viola@...il.com>
Signed-off-by: Ben Skeggs <bskeggs@...hat.com>
Reviewed-by: Karol Herbst <kherbst@...hat.com>
Signed-off-by: Karol Herbst <kherbst@...hat.com>
Link: https://gitlab.freedesktop.org/drm/nouveau/-/merge_requests/10
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
 .../gpu/drm/nouveau/nvkm/subdev/pmu/base.c    | 37 +++++++++++--------
 1 file changed, 21 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c
index 24382875fb4f3..455e95a89259f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c
@@ -94,20 +94,13 @@ nvkm_pmu_fini(struct nvkm_subdev *subdev, bool suspend)
 	return 0;
 }
 
-static int
+static void
 nvkm_pmu_reset(struct nvkm_pmu *pmu)
 {
 	struct nvkm_device *device = pmu->subdev.device;
 
 	if (!pmu->func->enabled(pmu))
-		return 0;
-
-	/* Inhibit interrupts, and wait for idle. */
-	nvkm_wr32(device, 0x10a014, 0x0000ffff);
-	nvkm_msec(device, 2000,
-		if (!nvkm_rd32(device, 0x10a04c))
-			break;
-	);
+		return;
 
 	/* Reset. */
 	if (pmu->func->reset)
@@ -118,25 +111,37 @@ nvkm_pmu_reset(struct nvkm_pmu *pmu)
 		if (!(nvkm_rd32(device, 0x10a10c) & 0x00000006))
 			break;
 	);
-
-	return 0;
 }
 
 static int
 nvkm_pmu_preinit(struct nvkm_subdev *subdev)
 {
 	struct nvkm_pmu *pmu = nvkm_pmu(subdev);
-	return nvkm_pmu_reset(pmu);
+	nvkm_pmu_reset(pmu);
+	return 0;
 }
 
 static int
 nvkm_pmu_init(struct nvkm_subdev *subdev)
 {
 	struct nvkm_pmu *pmu = nvkm_pmu(subdev);
-	int ret = nvkm_pmu_reset(pmu);
-	if (ret == 0 && pmu->func->init)
-		ret = pmu->func->init(pmu);
-	return ret;
+	struct nvkm_device *device = pmu->subdev.device;
+
+	if (!pmu->func->init)
+		return 0;
+
+	if (pmu->func->enabled(pmu)) {
+		/* Inhibit interrupts, and wait for idle. */
+		nvkm_wr32(device, 0x10a014, 0x0000ffff);
+		nvkm_msec(device, 2000,
+			if (!nvkm_rd32(device, 0x10a04c))
+				break;
+		);
+
+		nvkm_pmu_reset(pmu);
+	}
+
+	return pmu->func->init(pmu);
 }
 
 static void *
-- 
2.34.1