linux-kernel - [PATCH 2/2] drm/msm/gpu: Add param to get address space faults

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] [day] [month] [year] [list]

Message-Id: <20220127171045.541341-3-robdclark@gmail.com>
Date:   Thu, 27 Jan 2022 09:10:39 -0800
From:   Rob Clark <robdclark@...il.com>
To:     dri-devel@...ts.freedesktop.org
Cc:     freedreno@...ts.freedesktop.org, linux-arm-msm@...r.kernel.org,
        Rob Clark <robdclark@...omium.org>,
        Rob Clark <robdclark@...il.com>, Sean Paul <sean@...rly.run>,
        Abhinav Kumar <quic_abhinavk@...cinc.com>,
        David Airlie <airlied@...ux.ie>,
        Daniel Vetter <daniel@...ll.ch>,
        Jonathan Marek <jonathan@...ek.ca>,
        Jordan Crouse <jordan@...micpenguin.net>,
        Sai Prakash Ranjan <saiprakash.ranjan@...eaurora.org>,
        Christian König <christian.koenig@....com>,
        Yangtao Li <tiny.windzz@...il.com>,
        Stephen Boyd <swboyd@...omium.org>,
        linux-kernel@...r.kernel.org (open list)
Subject: [PATCH 2/2] drm/msm/gpu: Add param to get address space faults

From: Rob Clark <robdclark@...omium.org>

Add a param so that userspace can query the fault count for faults that
might effect them (ie. any context sharing the same address space).

Signed-off-by: Rob Clark <robdclark@...omium.org>
---
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 3 +++
 drivers/gpu/drm/msm/msm_drv.c           | 1 +
 drivers/gpu/drm/msm/msm_gem.h           | 3 +++
 drivers/gpu/drm/msm/msm_gpu.c           | 1 +
 include/uapi/drm/msm_drm.h              | 3 ++-
 5 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index caa9076197de..05899c77ca38 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -271,6 +271,9 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
 	case MSM_PARAM_FAULTS:
 		*value = gpu->global_faults;
 		return 0;
+	case MSM_PARAM_AS_FAULTS:
+		*value = ctx->aspace->faults;
+		return 0;
 	case MSM_PARAM_SUSPENDS:
 		*value = gpu->suspend_count;
 		return 0;
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 72060247e43c..39ab9a361d7f 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -41,6 +41,7 @@
  * - 1.6.0 - Syncobj support
  * - 1.7.0 - Add MSM_PARAM_SUSPENDS to access suspend count
  * - 1.8.0 - Add MSM_BO_CACHED_COHERENT for supported GPUs (a6xx)
+ * - 1.9.0 - Add MSM_PARAM_AS_FAULTS
  */
 #define MSM_VERSION_MAJOR	1
 #define MSM_VERSION_MINOR	8
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 54ca0817d807..af612add5264 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -35,6 +35,9 @@ struct msm_gem_address_space {
 	 * will be non-NULL:
 	 */
 	struct pid *pid;
+
+	/* @faults: the number of GPU hangs associated with this address space */
+	int faults;
 };
 
 struct msm_gem_vma {
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 2c1049c0ea14..1029a51cb016 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -372,6 +372,7 @@ static void recover_worker(struct kthread_work *work)
 		/* Increment the fault counts */
 		gpu->global_faults++;
 		submit->queue->faults++;
+		submit->aspace->faults++;
 
 		task = get_pid_task(submit->pid, PIDTYPE_PID);
 		if (task) {
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index 6b8fffc28a50..b7d92868b945 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -75,8 +75,9 @@ struct drm_msm_timespec {
 #define MSM_PARAM_GMEM_BASE  0x06
 #define MSM_PARAM_PRIORITIES 0x07  /* The # of priority levels */
 #define MSM_PARAM_PP_PGTABLE 0x08  /* => 1 for per-process pagetables, else 0 */
-#define MSM_PARAM_FAULTS     0x09
+#define MSM_PARAM_FAULTS     0x09  /* global fault count */
 #define MSM_PARAM_SUSPENDS   0x0a
+#define MSM_PARAM_AS_FAULTS  0x0b  /* faults in any context sharing same address space */
 
 /* For backwards compat.  The original support for preemption was based on
  * a single ring per priority level so # of priority levels equals the #
-- 
2.34.1