diff mbox series

[v4,6/7] drm/msm/a6xx: Improve gpu recovery sequence

Message ID 20220817204224.v4.6.Idf2ba51078e87ae7ceb75cc77a5bd4ff2bd31eab@changeid
State New
Headers show
Series Improve GPU Recovery | expand

Commit Message

Akhil P Oommen Aug. 17, 2022, 3:14 p.m. UTC
We can do a few more things to improve our chance at a successful gpu
recovery, especially during a hangcheck timeout:
1. Halt CP and GMU core
2. Do RBBM GBIF HALT sequence
3. Do a soft reset of GPU core

Signed-off-by: Akhil P Oommen <quic_akhilpo@quicinc.com>
---

(no changes since v1)

 drivers/gpu/drm/msm/adreno/a6xx.xml.h |  4 ++
 drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 77 +++++++++++++++++++++--------------
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c |  7 ++++
 3 files changed, 58 insertions(+), 30 deletions(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/msm/adreno/a6xx.xml.h b/drivers/gpu/drm/msm/adreno/a6xx.xml.h
index b03e2c4..beea4a7 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx.xml.h
@@ -1413,6 +1413,10 @@  static inline uint32_t REG_A6XX_RBBM_PERFCTR_RBBM_SEL(uint32_t i0) { return 0x00
 
 #define REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL			0x00000011
 
+#define REG_A6XX_RBBM_GBIF_HALT					0x00000016
+
+#define REG_A6XX_RBBM_GBIF_HALT_ACK				0x00000017
+
 #define REG_A6XX_RBBM_WAIT_FOR_GPU_IDLE_CMD			0x0000001c
 #define A6XX_RBBM_WAIT_FOR_GPU_IDLE_CMD_WAIT_GPU_IDLE		0x00000001
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 9f76f5b..db05942 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -869,9 +869,47 @@  static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu)
 		(val & 1), 100, 1000);
 }
 
+#define GBIF_CLIENT_HALT_MASK             BIT(0)
+#define GBIF_ARB_HALT_MASK                BIT(1)
+
+static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
+{
+	struct msm_gpu *gpu = &adreno_gpu->base;
+
+	if (!a6xx_has_gbif(adreno_gpu)) {
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
+		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
+								0xf) == 0xf);
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+
+		return;
+	}
+
+	/* Halt the gx side of GBIF */
+	gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 1);
+	spin_until(gpu_read(gpu, REG_A6XX_RBBM_GBIF_HALT_ACK) & 1);
+
+	/* Halt new client requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
+	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
+
+	/* Halt all AXI requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
+	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
+
+	/* The GBIF halt needs to be explicitly cleared */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
+}
+
 /* Force the GMU off in case it isn't responsive */
 static void a6xx_gmu_force_off(struct a6xx_gmu *gmu)
 {
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	struct msm_gpu *gpu = &adreno_gpu->base;
+
 	/* Flush all the queues */
 	a6xx_hfi_stop(gmu);
 
@@ -883,6 +921,15 @@  static void a6xx_gmu_force_off(struct a6xx_gmu *gmu)
 
 	/* Make sure there are no outstanding RPMh votes */
 	a6xx_gmu_rpmh_off(gmu);
+
+	/* Halt the gmu cm3 core */
+	gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1);
+
+	a6xx_bus_clear_pending_transactions(adreno_gpu);
+
+	/* Reset GPU core blocks */
+	gpu_write(gpu, REG_A6XX_RBBM_SW_RESET_CMD, 1);
+	udelay(100);
 }
 
 static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu)
@@ -1010,36 +1057,6 @@  bool a6xx_gmu_isidle(struct a6xx_gmu *gmu)
 	return true;
 }
 
-#define GBIF_CLIENT_HALT_MASK             BIT(0)
-#define GBIF_ARB_HALT_MASK                BIT(1)
-
-static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
-{
-	struct msm_gpu *gpu = &adreno_gpu->base;
-
-	if (!a6xx_has_gbif(adreno_gpu)) {
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
-		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
-								0xf) == 0xf);
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
-
-		return;
-	}
-
-	/* Halt new client requests on GBIF */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
-	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
-			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
-
-	/* Halt all AXI requests on GBIF */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
-	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
-			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
-
-	/* The GBIF halt needs to be explicitly cleared */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
-}
-
 /* Gracefully try to shut down the GMU and by extension the GPU */
 static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 {
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 0ec4fcd..a9335bc 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -920,6 +920,10 @@  static int hw_init(struct msm_gpu *gpu)
 	/* Make sure the GMU keeps the GPU on while we set it up */
 	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
 
+	/* Clear GBIF halt in case GX domain was not collapsed */
+	if (a6xx_has_gbif(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 0);
+
 	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_CNTL, 0);
 
 	/*
@@ -1205,6 +1209,9 @@  static void a6xx_recover(struct msm_gpu *gpu)
 	if (hang_debug)
 		a6xx_dump(gpu);
 
+	/* Halt SQE first */
+	gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3);
+
 	/*
 	 * Turn off keep alive that might have been enabled by the hang
 	 * interrupt