scsi: hisi_sas: Fix the failure of recovering PHY from STP link timeout

There is an issue that link reset can't recover PHY when STP link timeout.
Because current process of enabling PHY for v3 hw will wait last
transmission done. The time of one transmission depends IO size, disk model
and so on. Normally, it should be shorter than 50ms. But the last
transmission could be never done for some abnormal scenarios, such as STP
link timeout.

This patch is to fix the issue. Check PHY status after starting process of
enabling PHY for 50ms. If the PHY is still active, we disable it forcibly
by PHY reset. Of course, we need to clear the PHY reset bit when enable
PHY.

Besides, the function disable_phy_v3_hw() should not be suitable to call in
interrupts for hilink bug for this 50ms delay. Then, we do link reset for
hilink bug directly. The change is that we don't clear the invalid dword
count register. This is better. Because we should not clear such error
count while not saved.

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, 16 insertions, 10 deletions

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index d7c377448ac8..70a6aa2daba2 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -120,6 +120,8 @@
 #define PHY_CFG_ENA_MSK			(0x1 << PHY_CFG_ENA_OFF)
 #define PHY_CFG_DC_OPT_OFF		2
 #define PHY_CFG_DC_OPT_MSK		(0x1 << PHY_CFG_DC_OPT_OFF)
+#define PHY_CFG_PHY_RST_OFF		3
+#define PHY_CFG_PHY_RST_MSK		(0x1 << PHY_CFG_PHY_RST_OFF)
 #define PROG_PHY_LINK_RATE		(PORT_BASE + 0x8)
 #define PHY_CTRL			(PORT_BASE + 0x14)
 #define PHY_CTRL_RESET_OFF		0
@@ -760,15 +762,25 @@ static void enable_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
 
 	cfg |= PHY_CFG_ENA_MSK;
+	cfg &= ~PHY_CFG_PHY_RST_MSK;
 	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
 }
 
 static void disable_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 {
 	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
+	u32 state;
 
 	cfg &= ~PHY_CFG_ENA_MSK;
 	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+
+	mdelay(50);
+
+	state = hisi_sas_read32(hisi_hba, PHY_STATE);
+	if (state & BIT(phy_no)) {
+		cfg |= PHY_CFG_PHY_RST_MSK;
+		hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+	}
 }
 
 static void start_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
@@ -1385,8 +1397,6 @@ static void handle_chl_int2_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 			hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
 	}
 
-	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2, irq_value);
-
 	if ((irq_value & BIT(CHL_INT2_RX_INVLD_DW_OFF)) &&
 	    (pci_dev->revision == 0x20)) {
 		u32 reg_value;
@@ -1396,15 +1406,11 @@ static void handle_chl_int2_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 				HILINK_ERR_DFX, reg_value,
 				!((reg_value >> 8) & BIT(phy_no)),
 				1000, 10000);
-		if (rc) {
-			disable_phy_v3_hw(hisi_hba, phy_no);
-			hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2,
-					     BIT(CHL_INT2_RX_INVLD_DW_OFF));
-			hisi_sas_phy_read32(hisi_hba, phy_no, ERR_CNT_INVLD_DW);
-			mdelay(1);
-			enable_phy_v3_hw(hisi_hba, phy_no);
-		}
+		if (rc)
+			hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
 	}
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2, irq_value);
 }
 
 static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)