Blob Blame History Raw
From: Monk Liu <Monk.Liu@amd.com>
Date: Tue, 17 Oct 2017 14:39:23 +0800
Subject: drm/amdgpu:don't change ctx->reset_couner upon query
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Git-commit: 668ca1b44de16a8182419cc1a5913d33cc6263bd
Patch-mainline: v4.16-rc1
References: FATE#326289 FATE#326079 FATE#326049 FATE#322398 FATE#326166

reset_counter marks the reset counter number once the context
is created, shouldn't be changed due to query.

To keep U/K interface on the ctx_query and keep ctx's reset_counter
logic compatible with GPU RESET feature, now use another var named
"reset_counter_query" to replace the original checked & updated in
amdgpu_ctx_query.

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h     |    1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c |    5 +++--
 2 files changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -735,6 +735,7 @@ struct amdgpu_ctx {
 	struct amdgpu_device    *adev;
 	struct amdgpu_queue_mgr queue_mgr;
 	unsigned		reset_counter;
+	unsigned        reset_counter_query;
 	uint32_t		vram_lost_counter;
 	spinlock_t		ring_lock;
 	struct dma_fence	**fences;
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -75,6 +75,7 @@ static int amdgpu_ctx_init(struct amdgpu
 	}
 
 	ctx->reset_counter = atomic_read(&adev->gpu_reset_counter);
+	ctx->reset_counter_query = ctx->reset_counter;
 	ctx->vram_lost_counter = atomic_read(&adev->vram_lost_counter);
 	ctx->init_priority = priority;
 	ctx->override_priority = AMD_SCHED_PRIORITY_UNSET;
@@ -216,11 +217,11 @@ static int amdgpu_ctx_query(struct amdgp
 	/* determine if a GPU reset has occured since the last call */
 	reset_counter = atomic_read(&adev->gpu_reset_counter);
 	/* TODO: this should ideally return NO, GUILTY, or INNOCENT. */
-	if (ctx->reset_counter == reset_counter)
+	if (ctx->reset_counter_query == reset_counter)
 		out->state.reset_status = AMDGPU_CTX_NO_RESET;
 	else
 		out->state.reset_status = AMDGPU_CTX_UNKNOWN_RESET;
-	ctx->reset_counter = reset_counter;
+	ctx->reset_counter_query = reset_counter;
 
 	mutex_unlock(&mgr->lock);
 	return 0;