Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   John Garry <john.garry@huawei.com>
To:     <jejb@linux.ibm.com>, <martin.petersen@oracle.com>,
        <jinpu.wang@cloud.ionos.com>, <damien.lemoal@opensource.wdc.com>,
        <yangxingui@huawei.com>
CC:     <linux-scsi@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
        <linuxarm@huawei.com>, <hare@suse.de>,
        John Garry <john.garry@huawei.com>
Subject: [PATCH v2 5/6] scsi: hisi_sas: Add SATA_DISK_ERR bit handling for v3 hw
Date:   Wed, 17 Aug 2022 22:52:13 +0800
Message-ID: <1660747934-60059-6-git-send-email-john.garry@huawei.com>
In-Reply-To: <1660747934-60059-1-git-send-email-john.garry@huawei.com>
References: <1660747934-60059-1-git-send-email-john.garry@huawei.com>
MIME-Version: 1.0
Content-Type: text/plain
Precedence: bulk

From: Xingui Yang <yangxingui@huawei.com>

When CQ header dw3 SATA_DISK_ERR is set it means this SATA disk is in error
state and the current IPTT is invalid. An invalid IPTT does not correspond
to any slot.

In this scenario, new I/Os that delivered to disk will be rejected by the,
controller and all I/Os remained on the disk should be aborted, which we
add here with the sas_ata_device_link_abort() call.

Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index efe8c5be5870..86db4e19beed 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -423,6 +423,8 @@
 #define CMPLT_HDR_DEV_ID_OFF		16
 #define CMPLT_HDR_DEV_ID_MSK		(0xffff << CMPLT_HDR_DEV_ID_OFF)
 /* dw3 */
+#define CMPLT_HDR_SATA_DISK_ERR_OFF	16
+#define CMPLT_HDR_SATA_DISK_ERR_MSK	(0x1 << CMPLT_HDR_SATA_DISK_ERR_OFF)
 #define CMPLT_HDR_IO_IN_TARGET_OFF	17
 #define CMPLT_HDR_IO_IN_TARGET_MSK	(0x1 << CMPLT_HDR_IO_IN_TARGET_OFF)
 
@@ -2384,14 +2386,30 @@ static irqreturn_t  cq_thread_v3_hw(int irq_no, void *p)
 	while (rd_point != wr_point) {
 		struct hisi_sas_complete_v3_hdr *complete_hdr;
 		struct device *dev = hisi_hba->dev;
-		u32 dw1;
+		u32 dw0, dw1, dw3;
 		int iptt;
 
 		complete_hdr = &complete_queue[rd_point];
+		dw0 = le32_to_cpu(complete_hdr->dw0);
 		dw1 = le32_to_cpu(complete_hdr->dw1);
+		dw3 = le32_to_cpu(complete_hdr->dw3);
 
 		iptt = dw1 & CMPLT_HDR_IPTT_MSK;
-		if (likely(iptt < HISI_SAS_COMMAND_ENTRIES_V3_HW)) {
+		if (unlikely((dw0 & CMPLT_HDR_CMPLT_MSK) == 0x3) &&
+			     (dw3 & CMPLT_HDR_SATA_DISK_ERR_MSK)) {
+			int device_id = (dw1 & CMPLT_HDR_DEV_ID_MSK) >>
+					CMPLT_HDR_DEV_ID_OFF;
+			struct hisi_sas_itct *itct =
+				&hisi_hba->itct[device_id];
+			struct hisi_sas_device *sas_dev =
+				&hisi_hba->devices[device_id];
+			struct domain_device *device = sas_dev->sas_device;
+
+			dev_err(dev, "erroneous completion disk err dev id=%d sas_addr=0x%llx CQ hdr: 0x%x 0x%x 0x%x 0x%x\n",
+				device_id, itct->sas_addr, dw0, dw1,
+				complete_hdr->act, dw3);
+			sas_ata_device_link_abort(device);
+		} else if (likely(iptt < HISI_SAS_COMMAND_ENTRIES_V3_HW)) {
 			slot = &hisi_hba->slot_info[iptt];
 			slot->cmplt_queue_slot = rd_point;
 			slot->cmplt_queue = queue;
-- 
2.35.3