linux-kernel - [PATCH 09/12] habanalabs: handle events during soft-reset

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] [thread-next>] [day] [month] [year] [list]

Message-Id: <20211128193435.266534-9-ogabbay@kernel.org>
Date:   Sun, 28 Nov 2021 21:34:32 +0200
From:   Oded Gabbay <ogabbay@...nel.org>
To:     linux-kernel@...r.kernel.org
Cc:     Ofir Bitton <obitton@...ana.ai>
Subject: [PATCH 09/12] habanalabs: handle events during soft-reset

From: Ofir Bitton <obitton@...ana.ai>

Driver should handle events during soft-reset as F/W is not
going through reset and it keeps sending events towards host.

Signed-off-by: Ofir Bitton <obitton@...ana.ai>
Reviewed-by: Oded Gabbay <ogabbay@...nel.org>
Signed-off-by: Oded Gabbay <ogabbay@...nel.org>
---
 drivers/misc/habanalabs/common/device.c     | 4 ++++
 drivers/misc/habanalabs/common/habanalabs.h | 2 ++
 drivers/misc/habanalabs/common/irq.c        | 2 +-
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 822d9cec5aaf..720eea0b7e9c 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -1019,6 +1019,8 @@ int hl_device_reset(struct hl_device *hdev, u32 flags)
 
 		handle_reset_trigger(hdev, flags);
 
+		hdev->is_in_soft_reset = !hard_reset;
+
 		/* This also blocks future CS/VM/JOB completion operations */
 		hdev->disabled = true;
 
@@ -1171,6 +1173,7 @@ int hl_device_reset(struct hl_device *hdev, u32 flags)
 	 * is required for the initialization itself
 	 */
 	hdev->disabled = false;
+	hdev->is_in_soft_reset = false;
 
 	rc = hdev->asic_funcs->hw_init(hdev);
 	if (rc) {
@@ -1242,6 +1245,7 @@ int hl_device_reset(struct hl_device *hdev, u32 flags)
 
 out_err:
 	hdev->disabled = true;
+	hdev->is_in_soft_reset = false;
 
 	if (hard_reset) {
 		dev_err(hdev->dev, "Failed to reset! Device is NOT usable\n");
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index a465b4a5f31d..c2129c9fe9e4 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -2591,6 +2591,7 @@ struct last_error_session_info {
  *                        protocol will throw an error. Relevant only for
  *                        cases where Linux was not loaded to device CPU
  * @supports_wait_for_multi_cs: true if wait for multi CS is supported
+ * @is_in_soft_reset: Device is currently in soft reset process.
  */
 struct hl_device {
 	struct pci_dev			*pdev;
@@ -2719,6 +2720,7 @@ struct hl_device {
 	u8				device_cpu_is_halted;
 	u8				supports_wait_for_multi_cs;
 	u8				stream_master_qid_arr_size;
+	u8				is_in_soft_reset;
 
 	/* Parameters for bring-up */
 	u64				nic_ports_mask;
diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c
index 9fd4c18e274e..64e0d9de21bd 100644
--- a/drivers/misc/habanalabs/common/irq.c
+++ b/drivers/misc/habanalabs/common/irq.c
@@ -245,7 +245,7 @@ irqreturn_t hl_irq_handler_eq(int irq, void *arg)
 		 */
 		dma_rmb();
 
-		if (hdev->disabled) {
+		if (hdev->disabled && !hdev->is_in_soft_reset) {
 			dev_warn(hdev->dev, "Device disabled but received an EQ event\n");
 			goto skip_irq;
 		}
-- 
2.25.1