scsi: mpt3sas: Perform additional retries if doorbell read returns 0

The driver retries certain register reads 3 times if the returned value is
0. This was done because the controller could return 0 for certain
registers if other registers were being accessed concurrently by the BMC.

In certain systems with increased BMC interactions, the register values
returned can be 0 for longer than 3 retries. Change the retry count from 3
to 30 for the affected registers to prevent problems with out-of-band
management.

Fixes: b899202 ("scsi: mpt3sas: Add separate function for aero doorbell reads")
Cc: [email protected]
Signed-off-by: Ranjan Kumar <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Martin K. Petersen <[email protected]>

Author: Ranjan Kumar

drivers/scsi/mpt3sas/mpt3sas_base.c

@@ -138,6 +138,9 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc);
 static void
 _base_clear_outstanding_commands(struct MPT3SAS_ADAPTER *ioc);
 
+static u32
+_base_readl_ext_retry(const volatile void __iomem *addr);
+
 /**
  * mpt3sas_base_check_cmd_timeout - Function
  *		to check timeout and command termination due
@@ -213,6 +216,20 @@ _base_readl_aero(const volatile void __iomem *addr)
 	return ret_val;
 }
 
+static u32
+_base_readl_ext_retry(const volatile void __iomem *addr)
+{
+	u32 i, ret_val;
+
+	for (i = 0 ; i < 30 ; i++) {
+		ret_val = readl(addr);
+		if (ret_val == 0)
+			continue;
+	}
+
+	return ret_val;
+}
+
 static inline u32
 _base_readl(const volatile void __iomem *addr)
 {
@@ -940,7 +957,7 @@ mpt3sas_halt_firmware(struct MPT3SAS_ADAPTER *ioc)
 
 	dump_stack();
 
-	doorbell = ioc->base_readl(&ioc->chip->Doorbell);
+	doorbell = ioc->base_readl_ext_retry(&ioc->chip->Doorbell);
 	if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) {
 		mpt3sas_print_fault_code(ioc, doorbell &
 		    MPI2_DOORBELL_DATA_MASK);
@@ -6686,7 +6703,7 @@ mpt3sas_base_get_iocstate(struct MPT3SAS_ADAPTER *ioc, int cooked)
 {
 	u32 s, sc;
 
-	s = ioc->base_readl(&ioc->chip->Doorbell);
+	s = ioc->base_readl_ext_retry(&ioc->chip->Doorbell);
 	sc = s & MPI2_IOC_STATE_MASK;
 	return cooked ? sc : s;
 }
@@ -6831,7 +6848,7 @@ _base_wait_for_doorbell_ack(struct MPT3SAS_ADAPTER *ioc, int timeout)
 					   __func__, count, timeout));
 			return 0;
 		} else if (int_status & MPI2_HIS_IOC2SYS_DB_STATUS) {
-			doorbell = ioc->base_readl(&ioc->chip->Doorbell);
+			doorbell = ioc->base_readl_ext_retry(&ioc->chip->Doorbell);
 			if ((doorbell & MPI2_IOC_STATE_MASK) ==
 			    MPI2_IOC_STATE_FAULT) {
 				mpt3sas_print_fault_code(ioc, doorbell);
@@ -6871,7 +6888,7 @@ _base_wait_for_doorbell_not_used(struct MPT3SAS_ADAPTER *ioc, int timeout)
 	count = 0;
 	cntdn = 1000 * timeout;
 	do {
-		doorbell_reg = ioc->base_readl(&ioc->chip->Doorbell);
+		doorbell_reg = ioc->base_readl_ext_retry(&ioc->chip->Doorbell);
 		if (!(doorbell_reg & MPI2_DOORBELL_USED)) {
 			dhsprintk(ioc,
 				  ioc_info(ioc, "%s: successful count(%d), timeout(%d)\n",
@@ -7019,7 +7036,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 	__le32 *mfp;
 
 	/* make sure doorbell is not in use */
-	if ((ioc->base_readl(&ioc->chip->Doorbell) & MPI2_DOORBELL_USED)) {
+	if ((ioc->base_readl_ext_retry(&ioc->chip->Doorbell) & MPI2_DOORBELL_USED)) {
 		ioc_err(ioc, "doorbell is in use (line=%d)\n", __LINE__);
 		return -EFAULT;
 	}
@@ -7068,15 +7085,15 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 	}
 
 	/* read the first two 16-bits, it gives the total length of the reply */
-	reply[0] = le16_to_cpu(ioc->base_readl(&ioc->chip->Doorbell)
+	reply[0] = le16_to_cpu(ioc->base_readl_ext_retry(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 	if ((_base_wait_for_doorbell_int(ioc, 5))) {
 		ioc_err(ioc, "doorbell handshake int failed (line=%d)\n",
 			__LINE__);
 		return -EFAULT;
 	}
-	reply[1] = le16_to_cpu(ioc->base_readl(&ioc->chip->Doorbell)
+	reply[1] = le16_to_cpu(ioc->base_readl_ext_retry(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 
@@ -7087,10 +7104,10 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 			return -EFAULT;
 		}
 		if (i >=  reply_bytes/2) /* overflow case */
-			ioc->base_readl(&ioc->chip->Doorbell);
+			ioc->base_readl_ext_retry(&ioc->chip->Doorbell);
 		else
 			reply[i] = le16_to_cpu(
-			    ioc->base_readl(&ioc->chip->Doorbell)
+			    ioc->base_readl_ext_retry(&ioc->chip->Doorbell)
 			    & MPI2_DOORBELL_DATA_MASK);
 		writel(0, &ioc->chip->HostInterruptStatus);
 	}
@@ -7949,7 +7966,7 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc)
 			goto out;
 		}
 
-		host_diagnostic = ioc->base_readl(&ioc->chip->HostDiagnostic);
+		host_diagnostic = ioc->base_readl_ext_retry(&ioc->chip->HostDiagnostic);
 		drsprintk(ioc,
 			  ioc_info(ioc, "wrote magic sequence: count(%d), host_diagnostic(0x%08x)\n",
 				   count, host_diagnostic));
@@ -7969,7 +7986,7 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc)
 	for (count = 0; count < (300000000 /
 		MPI2_HARD_RESET_PCIE_SECOND_READ_DELAY_MICRO_SEC); count++) {
 
-		host_diagnostic = ioc->base_readl(&ioc->chip->HostDiagnostic);
+		host_diagnostic = ioc->base_readl_ext_retry(&ioc->chip->HostDiagnostic);
 
 		if (host_diagnostic == 0xFFFFFFFF) {
 			ioc_info(ioc,
@@ -8359,10 +8376,13 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 	ioc->rdpq_array_enable_assigned = 0;
 	ioc->use_32bit_dma = false;
 	ioc->dma_mask = 64;
-	if (ioc->is_aero_ioc)
+	if (ioc->is_aero_ioc) {
 		ioc->base_readl = &_base_readl_aero;
-	else
+		ioc->base_readl_ext_retry = &_base_readl_ext_retry;
+	} else {
 		ioc->base_readl = &_base_readl;
+		ioc->base_readl_ext_retry = &_base_readl;
+	}
 	r = mpt3sas_base_map_resources(ioc);
 	if (r)
 		goto out_free_resources;

drivers/scsi/mpt3sas/mpt3sas_base.h

@@ -1618,6 +1618,7 @@ struct MPT3SAS_ADAPTER {
 	u8		diag_trigger_active;
 	u8		atomic_desc_capable;
 	BASE_READ_REG	base_readl;
+	BASE_READ_REG	base_readl_ext_retry;
 	struct SL_WH_MASTER_TRIGGER_T diag_trigger_master;
 	struct SL_WH_EVENT_TRIGGERS_T diag_trigger_event;
 	struct SL_WH_SCSI_TRIGGERS_T diag_trigger_scsi;