blob: 41365ed157473a57d8472aeedf3d07109bfa3431 [file] [log] [blame]
From a8d15ffc168c6e4520621f5cb58e6515645b3254 Mon Sep 17 00:00:00 2001
From: Oded Gabbay <oded.gabbay@gmail.com>
Date: Mon, 23 Dec 2019 17:51:48 +0200
Subject: [PATCH] habanalabs: halt the engines before hard-reset
commit 908087ffbe896c100ed73d5f0ce11a5b7264af4a upstream.
The driver must halt the engines before doing hard-reset, otherwise the
device can go into undefined state. There is a place where the driver
didn't do that and this patch fixes it.
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index 0b19d3eefb98..065cb7f127fb 100644
--- a/drivers/misc/habanalabs/device.c
+++ b/drivers/misc/habanalabs/device.c
@@ -934,6 +934,7 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass)
if (hdev->asic_funcs->get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
dev_info(hdev->dev,
"H/W state is dirty, must reset before initializing\n");
+ hdev->asic_funcs->halt_engines(hdev, true);
hdev->asic_funcs->hw_fini(hdev, true);
}
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 4957f65f4683..369a5dfbb9ae 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -826,6 +826,11 @@ void goya_init_dma_qmans(struct hl_device *hdev)
*/
static void goya_disable_external_queues(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_DMA))
+ return;
+
WREG32(mmDMA_QM_0_GLBL_CFG0, 0);
WREG32(mmDMA_QM_1_GLBL_CFG0, 0);
WREG32(mmDMA_QM_2_GLBL_CFG0, 0);
@@ -887,6 +892,11 @@ static int goya_stop_external_queues(struct hl_device *hdev)
{
int rc, retval = 0;
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_DMA))
+ return retval;
+
rc = goya_stop_queue(hdev,
mmDMA_QM_0_GLBL_CFG1,
mmDMA_QM_0_CP_STS,
@@ -1678,9 +1688,18 @@ void goya_init_tpc_qmans(struct hl_device *hdev)
*/
static void goya_disable_internal_queues(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_MME))
+ goto disable_tpc;
+
WREG32(mmMME_QM_GLBL_CFG0, 0);
WREG32(mmMME_CMDQ_GLBL_CFG0, 0);
+disable_tpc:
+ if (!(goya->hw_cap_initialized & HW_CAP_TPC))
+ return;
+
WREG32(mmTPC0_QM_GLBL_CFG0, 0);
WREG32(mmTPC0_CMDQ_GLBL_CFG0, 0);
@@ -1716,8 +1735,12 @@ static void goya_disable_internal_queues(struct hl_device *hdev)
*/
static int goya_stop_internal_queues(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
int rc, retval = 0;
+ if (!(goya->hw_cap_initialized & HW_CAP_MME))
+ goto stop_tpc;
+
/*
* Each queue (QMAN) is a separate H/W logic. That means that each
* QMAN can be stopped independently and failure to stop one does NOT
@@ -1744,6 +1767,10 @@ static int goya_stop_internal_queues(struct hl_device *hdev)
retval = -EIO;
}
+stop_tpc:
+ if (!(goya->hw_cap_initialized & HW_CAP_TPC))
+ return retval;
+
rc = goya_stop_queue(hdev,
mmTPC0_QM_GLBL_CFG1,
mmTPC0_QM_CP_STS,
@@ -1909,6 +1936,11 @@ static int goya_stop_internal_queues(struct hl_device *hdev)
static void goya_dma_stall(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_DMA))
+ return;
+
WREG32(mmDMA_QM_0_GLBL_CFG1, 1 << DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT);
WREG32(mmDMA_QM_1_GLBL_CFG1, 1 << DMA_QM_1_GLBL_CFG1_DMA_STOP_SHIFT);
WREG32(mmDMA_QM_2_GLBL_CFG1, 1 << DMA_QM_2_GLBL_CFG1_DMA_STOP_SHIFT);
@@ -1918,6 +1950,11 @@ static void goya_dma_stall(struct hl_device *hdev)
static void goya_tpc_stall(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_TPC))
+ return;
+
WREG32(mmTPC0_CFG_TPC_STALL, 1 << TPC0_CFG_TPC_STALL_V_SHIFT);
WREG32(mmTPC1_CFG_TPC_STALL, 1 << TPC1_CFG_TPC_STALL_V_SHIFT);
WREG32(mmTPC2_CFG_TPC_STALL, 1 << TPC2_CFG_TPC_STALL_V_SHIFT);
@@ -1930,6 +1967,11 @@ static void goya_tpc_stall(struct hl_device *hdev)
static void goya_mme_stall(struct hl_device *hdev)
{
+ struct goya_device *goya = hdev->asic_specific;
+
+ if (!(goya->hw_cap_initialized & HW_CAP_MME))
+ return;
+
WREG32(mmMME_STALL, 0xFFFFFFFF);
}
--
2.7.4