linux-kernel - [PATCH 3/7] habanalabs: report EQ fault during heartbeat

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: <20210609150343.4712-3-ogabbay@kernel.org>
Date:   Wed,  9 Jun 2021 18:03:39 +0300
From:   Oded Gabbay <ogabbay@...nel.org>
To:     linux-kernel@...r.kernel.org
Cc:     Ohad Sharabi <osharabi@...ana.ai>
Subject: [PATCH 3/7] habanalabs: report EQ fault during heartbeat

From: Ohad Sharabi <osharabi@...ana.ai>

In case we have EQ fault we would like to know about it.
For this, a status bitmask was added in which EQ_FAULT bit is
set by FW in case of EQ fault.

Signed-off-by: Ohad Sharabi <osharabi@...ana.ai>
Reviewed-by: Oded Gabbay <ogabbay@...nel.org>
Signed-off-by: Oded Gabbay <ogabbay@...nel.org>
---
 drivers/misc/habanalabs/common/firmware_if.c  |  8 +++++++-
 .../misc/habanalabs/include/common/cpucp_if.h | 20 +++++++++++++++++++
 2 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 9412e6707906..d5a3c786d4c9 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -362,7 +362,7 @@ void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
 
 int hl_fw_send_heartbeat(struct hl_device *hdev)
 {
-	struct cpucp_packet hb_pkt = {};
+	struct cpucp_packet hb_pkt = {0};
 	u64 result;
 	int rc;
 
@@ -374,7 +374,13 @@ int hl_fw_send_heartbeat(struct hl_device *hdev)
 						sizeof(hb_pkt), 0, &result);
 
 	if ((rc) || (result != CPUCP_PACKET_FENCE_VAL))
+		return -EIO;
+
+	if (le32_to_cpu(hb_pkt.status_mask) &
+					CPUCP_PKT_HB_STATUS_EQ_FAULT_MASK) {
+		dev_warn(hdev->dev, "FW reported EQ fault during heartbeat\n");
 		rc = -EIO;
+	}
 
 	return rc;
 }
diff --git a/drivers/misc/habanalabs/include/common/cpucp_if.h b/drivers/misc/habanalabs/include/common/cpucp_if.h
index d4dc189a6c92..80b1d5a9d9f1 100644
--- a/drivers/misc/habanalabs/include/common/cpucp_if.h
+++ b/drivers/misc/habanalabs/include/common/cpucp_if.h
@@ -404,6 +404,20 @@ enum cpucp_packet_id {
 #define CPUCP_PKT_RES_PLL_OUT3_SHIFT	48
 #define CPUCP_PKT_RES_PLL_OUT3_MASK	0xFFFF000000000000ull
 
+#define CPUCP_PKT_VAL_PFC_IN1_SHIFT	0
+#define CPUCP_PKT_VAL_PFC_IN1_MASK	0x0000000000000001ull
+#define CPUCP_PKT_VAL_PFC_IN2_SHIFT	1
+#define CPUCP_PKT_VAL_PFC_IN2_MASK	0x000000000000001Eull
+
+#define CPUCP_PKT_VAL_LPBK_IN1_SHIFT	0
+#define CPUCP_PKT_VAL_LPBK_IN1_MASK	0x0000000000000001ull
+#define CPUCP_PKT_VAL_LPBK_IN2_SHIFT	1
+#define CPUCP_PKT_VAL_LPBK_IN2_MASK	0x000000000000001Eull
+
+/* heartbeat status bits */
+#define CPUCP_PKT_HB_STATUS_EQ_FAULT_SHIFT		0
+#define CPUCP_PKT_HB_STATUS_EQ_FAULT_MASK		0x00000001
+
 struct cpucp_packet {
 	union {
 		__le64 value;	/* For SET packets */
@@ -445,6 +459,12 @@ struct cpucp_packet {
 
 		/* For get CpuCP info/EEPROM data/NIC info */
 		__le32 data_max_size;
+
+		/*
+		 * For any general status bitmask. Shall be used whenever the
+		 * result cannot be used to hold general purpose data.
+		 */
+		__le32 status_mask;
 	};
 
 	__le32 reserved;
-- 
2.25.1