linux-kernel - [PATCH AUTOSEL 5.19 34/64] habanalabs/gaudi: invoke device reset from one code block

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: <20220814152437.2374207-34-sashal@kernel.org>
Date:   Sun, 14 Aug 2022 11:24:07 -0400
From:   Sasha Levin <sashal@...nel.org>
To:     linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc:     Tal Cohen <talcohen@...ana.ai>, Oded Gabbay <ogabbay@...nel.org>,
        Sasha Levin <sashal@...nel.org>, gregkh@...uxfoundation.org,
        osharabi@...ana.ai, obitton@...ana.ai, ttayar@...ana.ai,
        ynudelman@...ana.ai, dliberman@...ana.ai, fkassabri@...ana.ai,
        dhirschfeld@...ana.ai
Subject: [PATCH AUTOSEL 5.19 34/64] habanalabs/gaudi: invoke device reset from one code block

From: Tal Cohen <talcohen@...ana.ai>

[ Upstream commit be572e67dafbf8004d46a2c9d97338c107efb60e ]

In order to prepare the driver code for device reset event
notification, change the event handler function flow to call
device reset from one code block.

In addition, the commit fixes an issue that reset was performed
w/o checking the 'hard_reset_on_fw_event' state and w/o setting
the HL_DRV_RESET_DELAY flag.

Signed-off-by: Tal Cohen <talcohen@...ana.ai>
Reviewed-by: Oded Gabbay <ogabbay@...nel.org>
Signed-off-by: Oded Gabbay <ogabbay@...nel.org>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
 drivers/misc/habanalabs/gaudi/gaudi.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 25d735aee6a3..e6bfaf55c6b6 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -7717,10 +7717,10 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 	struct gaudi_device *gaudi = hdev->asic_specific;
 	u64 data = le64_to_cpu(eq_entry->data[0]);
 	u32 ctl = le32_to_cpu(eq_entry->hdr.ctl);
-	u32 fw_fatal_err_flag = 0;
+	u32 fw_fatal_err_flag = 0, flags = 0;
 	u16 event_type = ((ctl & EQ_CTL_EVENT_TYPE_MASK)
 			>> EQ_CTL_EVENT_TYPE_SHIFT);
-	bool reset_required;
+	bool reset_required, reset_direct = false;
 	u8 cause;
 	int rc;
 
@@ -7808,7 +7808,8 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 			dev_err(hdev->dev, "reset required due to %s\n",
 				gaudi_irq_map_table[event_type].name);
 
-			hl_device_reset(hdev, 0);
+			reset_direct = true;
+			goto reset_device;
 		} else {
 			hl_fw_unmask_irq(hdev, event_type);
 		}
@@ -7830,7 +7831,8 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 			dev_err(hdev->dev, "reset required due to %s\n",
 				gaudi_irq_map_table[event_type].name);
 
-			hl_device_reset(hdev, 0);
+			reset_direct = true;
+			goto reset_device;
 		} else {
 			hl_fw_unmask_irq(hdev, event_type);
 		}
@@ -7981,12 +7983,17 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 	return;
 
 reset_device:
-	if (hdev->asic_prop.fw_security_enabled)
-		hl_device_reset(hdev, HL_DRV_RESET_HARD
-					| HL_DRV_RESET_BYPASS_REQ_TO_FW
-					| fw_fatal_err_flag);
+	reset_required = true;
+
+	if (hdev->asic_prop.fw_security_enabled && !reset_direct)
+		flags = HL_DRV_RESET_HARD | HL_DRV_RESET_BYPASS_REQ_TO_FW | fw_fatal_err_flag;
 	else if (hdev->hard_reset_on_fw_events)
-		hl_device_reset(hdev, HL_DRV_RESET_HARD | HL_DRV_RESET_DELAY | fw_fatal_err_flag);
+		flags = HL_DRV_RESET_HARD | HL_DRV_RESET_DELAY | fw_fatal_err_flag;
+	else
+		reset_required = false;
+
+	if (reset_required)
+		hl_device_reset(hdev, flags);
 	else
 		hl_fw_unmask_irq(hdev, event_type);
 }
-- 
2.35.1