scsi: hisi_sas: Fix losing directly attached disk when hot-plug

Hot-plugging SAS wire of direct hard disk backplane may cause disk lost. We
have done this test with several types of SATA disk from different venders,
and only two models from Seagate has this problem, ST4000NM0035-1V4107 and
ST3000VM002-1ET166.

The root cause is that the disk doesn't send D2H frame after OOB finished.
SAS controller will issue phyup interrupt only when D2H frame is received,
otherwise, will be waiting there all the time.

When this issue happen, we can find the disk again with link reset.  To fix
this issue, we setup an timer after OOB finished. If the PHY is not up in
20s, do link reset. Notes: the 20s is an experience value.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 18 insertions, 9 deletions

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 4b628c20447d..f1009e27d9bc 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -1290,6 +1290,7 @@ static irqreturn_t phy_up_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 	struct device *dev = hisi_hba->dev;
 	unsigned long flags;
 
+	del_timer(&phy->timer);
 	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_PHY_ENA_MSK, 1);
 
 	port_id = hisi_sas_read32(hisi_hba, PHY_PORT_NUM_MA);
@@ -1383,9 +1384,11 @@ end:
 
 static irqreturn_t phy_down_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 {
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 	u32 phy_state, sl_ctrl, txid_auto;
 	struct device *dev = hisi_hba->dev;
 
+	del_timer(&phy->timer);
 	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_NOT_RDY_MSK, 1);
 
 	phy_state = hisi_sas_read32(hisi_hba, PHY_STATE);
@@ -1554,6 +1557,19 @@ static void handle_chl_int2_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2, irq_value);
 }
 
+static void handle_chl_int0_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	u32 irq_value0 = hisi_sas_phy_read32(hisi_hba, phy_no, CHL_INT0);
+
+	if (irq_value0 & CHL_INT0_PHY_RDY_MSK)
+		hisi_sas_phy_oob_ready(hisi_hba, phy_no);
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
+			     irq_value0 & (~CHL_INT0_SL_RX_BCST_ACK_MSK)
+			     & (~CHL_INT0_SL_PHY_ENABLE_MSK)
+			     & (~CHL_INT0_NOT_RDY_MSK));
+}
+
 static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
 {
 	struct hisi_hba *hisi_hba = p;
@@ -1564,8 +1580,8 @@ static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
 				& 0xeeeeeeee;
 
 	while (irq_msk) {
-		u32 irq_value0 = hisi_sas_phy_read32(hisi_hba, phy_no,
-						     CHL_INT0);
+		if (irq_msk & (2 << (phy_no * 4)))
+			handle_chl_int0_v3_hw(hisi_hba, phy_no);
 
 		if (irq_msk & (4 << (phy_no * 4)))
 			handle_chl_int1_v3_hw(hisi_hba, phy_no);
@@ -1573,13 +1589,6 @@ static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
 		if (irq_msk & (8 << (phy_no * 4)))
 			handle_chl_int2_v3_hw(hisi_hba, phy_no);
 
-		if (irq_msk & (2 << (phy_no * 4)) && irq_value0) {
-			hisi_sas_phy_write32(hisi_hba, phy_no,
-					CHL_INT0, irq_value0
-					& (~CHL_INT0_SL_RX_BCST_ACK_MSK)
-					& (~CHL_INT0_SL_PHY_ENABLE_MSK)
-					& (~CHL_INT0_NOT_RDY_MSK));
-		}
 		irq_msk &= ~(0xe << (phy_no * 4));
 		phy_no++;
 	}