diff mbox series

[4/6] habanalabs: assert return value of hw_fini

Message ID 20230227111306.3985896-4-ogabbay@kernel.org (mailing list archive)
State New, archived
Headers show
Series [1/6] habanalabs: add helper function to get vm hash node | expand

Commit Message

Oded Gabbay Feb. 27, 2023, 11:13 a.m. UTC 
From: Dafna Hirschfeld <dhirschfeld@habana.ai>

Since hw_fini return error code for failure indication, we should
check its return value. Currently it might only fail upon soft-reset
from hl_device_reset. Later patch will add hw_fini failure in case of
polling timeout in hard-reset.

Signed-off-by: Dafna Hirschfeld <dhirschfeld@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/device.c | 12 +++++++++---
 drivers/accel/habanalabs/gaudi/gaudi.c   |  7 ++++++-
 drivers/accel/habanalabs/gaudi2/gaudi2.c |  7 ++++++-
 drivers/accel/habanalabs/goya/goya.c     |  7 ++++++-
 4 files changed, 27 insertions(+), 6 deletions(-)

Comments

Stanislaw Gruszka March 1, 2023, 1:31 p.m. UTC | #1 
On Mon, Feb 27, 2023 at 01:13:04PM +0200, Oded Gabbay wrote:
> From: Dafna Hirschfeld <dhirschfeld@habana.ai>
> 
> Since hw_fini return error code for failure indication, we should
> check its return value. Currently it might only fail upon soft-reset
> from hl_device_reset. Later patch will add hw_fini failure in case of
> polling timeout in hard-reset.
> 
> Signed-off-by: Dafna Hirschfeld <dhirschfeld@habana.ai>
> Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
diff mbox series

Patch

diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index 7ade32487138..99e793dfb126 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -1472,7 +1472,7 @@  int hl_device_reset(struct hl_device *hdev, u32 flags)
 		schedule_hard_reset = false, delay_reset, from_dev_release, from_watchdog_thread;
 	u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0};
 	struct hl_ctx *ctx;
-	int i, rc;
+	int i, rc, hw_fini_rc;
 
 	if (!hdev->init_done) {
 		dev_err(hdev->dev, "Can't reset before initialization is done\n");
@@ -1634,7 +1634,7 @@  int hl_device_reset(struct hl_device *hdev, u32 flags)
 	}
 
 	/* Reset the H/W. It will be in idle state after this returns */
-	hdev->asic_funcs->hw_fini(hdev, hard_reset, fw_reset);
+	hw_fini_rc = hdev->asic_funcs->hw_fini(hdev, hard_reset, fw_reset);
 
 	if (hard_reset) {
 		hdev->fw_loader.fw_comp_loaded = FW_TYPE_NONE;
@@ -1661,6 +1661,10 @@  int hl_device_reset(struct hl_device *hdev, u32 flags)
 		hl_ctx_put(ctx);
 	}
 
+	if (hw_fini_rc) {
+		rc = hw_fini_rc;
+		goto out_err;
+	}
 	/* Finished tear-down, starting to re-initialize */
 
 	if (hard_reset) {
@@ -2416,7 +2420,9 @@  void hl_device_fini(struct hl_device *hdev)
 	hl_cb_pool_fini(hdev);
 
 	/* Reset the H/W. It will be in idle state after this returns */
-	hdev->asic_funcs->hw_fini(hdev, true, false);
+	rc = hdev->asic_funcs->hw_fini(hdev, true, false);
+	if (rc)
+		dev_err(hdev->dev, "hw_fini failed in device fini while removing device %d\n", rc);
 
 	hdev->fw_loader.fw_comp_loaded = FW_TYPE_NONE;
 
diff --git a/drivers/accel/habanalabs/gaudi/gaudi.c b/drivers/accel/habanalabs/gaudi/gaudi.c
index 26287084a9e0..60146fd4de6b 100644
--- a/drivers/accel/habanalabs/gaudi/gaudi.c
+++ b/drivers/accel/habanalabs/gaudi/gaudi.c
@@ -868,13 +868,18 @@  static int gaudi_early_init(struct hl_device *hdev)
 	rc = hl_fw_read_preboot_status(hdev);
 	if (rc) {
 		if (hdev->reset_on_preboot_fail)
+			/* we are already on failure flow, so don't check if hw_fini fails. */
 			hdev->asic_funcs->hw_fini(hdev, true, false);
 		goto pci_fini;
 	}
 
 	if (gaudi_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
 		dev_dbg(hdev->dev, "H/W state is dirty, must reset before initializing\n");
-		hdev->asic_funcs->hw_fini(hdev, true, false);
+		rc = hdev->asic_funcs->hw_fini(hdev, true, false);
+		if (rc) {
+			dev_err(hdev->dev, "failed to reset HW in dirty state (%d)\n", rc);
+			goto pci_fini;
+		}
 	}
 
 	return 0;
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index 82448edfdfa0..f01fa4bca381 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -2886,13 +2886,18 @@  static int gaudi2_early_init(struct hl_device *hdev)
 	rc = hl_fw_read_preboot_status(hdev);
 	if (rc) {
 		if (hdev->reset_on_preboot_fail)
+			/* we are already on failure flow, so don't check if hw_fini fails. */
 			hdev->asic_funcs->hw_fini(hdev, true, false);
 		goto pci_fini;
 	}
 
 	if (gaudi2_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
 		dev_dbg(hdev->dev, "H/W state is dirty, must reset before initializing\n");
-		hdev->asic_funcs->hw_fini(hdev, true, false);
+		rc = hdev->asic_funcs->hw_fini(hdev, true, false);
+		if (rc) {
+			dev_err(hdev->dev, "failed to reset HW during early init (%d)\n", rc);
+			goto pci_fini;
+		}
 	}
 
 	return 0;
diff --git a/drivers/accel/habanalabs/goya/goya.c b/drivers/accel/habanalabs/goya/goya.c
index 7a45ab3ca43a..39f9e5de1f4c 100644
--- a/drivers/accel/habanalabs/goya/goya.c
+++ b/drivers/accel/habanalabs/goya/goya.c
@@ -669,13 +669,18 @@  static int goya_early_init(struct hl_device *hdev)
 	rc = hl_fw_read_preboot_status(hdev);
 	if (rc) {
 		if (hdev->reset_on_preboot_fail)
+			/* we are already on failure flow, so don't check if hw_fini fails. */
 			hdev->asic_funcs->hw_fini(hdev, true, false);
 		goto pci_fini;
 	}
 
 	if (goya_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
 		dev_dbg(hdev->dev, "H/W state is dirty, must reset before initializing\n");
-		hdev->asic_funcs->hw_fini(hdev, true, false);
+		rc = hdev->asic_funcs->hw_fini(hdev, true, false);
+		if (rc) {
+			dev_err(hdev->dev, "failed to reset HW in dirty state (%d)\n", rc);
+			goto pci_fini;
+		}
 	}
 
 	if (!hdev->pldm) {