be2net: Support UE recovery in BEx/Skyhawk adapters

This patch supports recovery from UEs caused due to Transient Parity
Errors (TPE), in BE2, BE3 and Skyhawk adapters. This change avoids
system reboot when such errors occur. The driver recovers from these
errors such that the adapter resumes full operational status as prior
to the UE.

Following is the list of changes in the driver to support this:

o The driver registers its UE recoverable capability with ARM FW at init
time. This also allows the driver to know if the feature is supported in
the FW.

o As the UE recovery requires precise time bound processing, the driver
creates its own error recovery work queue with a single worker thread (per
module, shared across functions).

o Each function runs an error detection task at an interval of 1 second as
required by the FW. The error detection logic already exists for BEx/SH,
but it now runs in the context of a separate worker thread.

o When an error is detected by the task, if it is recoverable, the PF0
driver instance initiates a soft reset, while other PF driver instances
wait for the reset to complete and the chip to become ready. Once
the chip is ready, all driver instances including PF0, resume to
reinitialize the respective functions.

o The PF0 driver checks for some recovery criteria, to determine if the
recovery can be initiated. If the criteria is not met, the PF0 driver does
not initiate a soft reset, it retains the existing behavior to stop
further processing and requires a reboot to get the chip to operational
state again.

o To allow each function to share the workq, while also making progress in
its recovery process, a per-function recovery state machine is used.
The per-function tasks avoid blocking operations like msleep() while in
this state machine (until reinit state) and instead reschedule for the
required delay.

o With these changes, the existing error recovery code for Lancer also
runs in the context of the new worker thread.

Signed-off-by: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 66 insertions, 2 deletions

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 86780b5c40ef..eecf24e92fd3 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -399,13 +399,13 @@ enum vf_state {
 #define BE_FLAGS_PHY_MISCONFIGURED		BIT(10)
 #define BE_FLAGS_ERR_DETECTION_SCHEDULED	BIT(11)
 #define BE_FLAGS_OS2BMC				BIT(12)
+#define BE_FLAGS_TRY_RECOVERY			BIT(13)
 
 #define BE_UC_PMAC_COUNT			30
 #define BE_VF_UC_PMAC_COUNT			2
 
 #define MAX_ERR_RECOVERY_RETRY_COUNT		3
 #define ERR_DETECTION_DELAY			1000
-#define ERR_RECOVERY_RETRY_DELAY		30000
 
 /* Ethtool set_dump flags */
 #define LANCER_INITIATE_FW_DUMP			0x1
@@ -512,6 +512,66 @@ struct be_eth_addr {
 	unsigned char mac[ETH_ALEN];
 };
 
+#define BE_SEC	1000			/* in msec */
+#define BE_MIN	(60 * BE_SEC)		/* in msec */
+#define BE_HOUR	(60 * BE_MIN)		/* in msec */
+
+#define ERR_RECOVERY_MAX_RETRY_COUNT		3
+#define ERR_RECOVERY_DETECTION_DELAY		BE_SEC
+#define ERR_RECOVERY_RETRY_DELAY		(30 * BE_SEC)
+
+/* UE-detection-duration in BEx/Skyhawk:
+ * All PFs must wait for this duration after they detect UE before reading
+ * SLIPORT_SEMAPHORE register. At the end of this duration, the Firmware
+ * guarantees that the SLIPORT_SEMAPHORE register is updated to indicate
+ * if the UE is recoverable.
+ */
+#define ERR_RECOVERY_UE_DETECT_DURATION			BE_SEC
+
+/* Initial idle time (in msec) to elapse after driver load,
+ * before UE recovery is allowed.
+ */
+#define ERR_IDLE_HR			24
+#define ERR_RECOVERY_IDLE_TIME		(ERR_IDLE_HR * BE_HOUR)
+
+/* Time interval (in msec) after which UE recovery can be repeated */
+#define ERR_INTERVAL_HR			72
+#define ERR_RECOVERY_INTERVAL		(ERR_INTERVAL_HR * BE_HOUR)
+
+/* BEx/SH UE recovery state machine */
+enum {
+	ERR_RECOVERY_ST_NONE = 0,		/* No Recovery */
+	ERR_RECOVERY_ST_DETECT = 1,		/* UE detection duration */
+	ERR_RECOVERY_ST_RESET = 2,		/* Reset Phase (PF0 only) */
+	ERR_RECOVERY_ST_PRE_POLL = 3,		/* Pre-Poll Phase (all PFs) */
+	ERR_RECOVERY_ST_REINIT = 4		/* Re-initialize Phase */
+};
+
+struct be_error_recovery {
+	/* Lancer error recovery variables */
+	u8 recovery_retries;
+
+	/* BEx/Skyhawk error recovery variables */
+	u8 recovery_state;
+	u16 ue_to_reset_time;		/* Time after UE, to soft reset
+					 * the chip - PF0 only
+					 */
+	u16 ue_to_poll_time;		/* Time after UE, to Restart Polling
+					 * of SLIPORT_SEMAPHORE reg
+					 */
+	u16 last_err_code;
+	bool recovery_supported;
+	unsigned long probe_time;
+	unsigned long last_recovery_time;
+
+	/* Common to both Lancer & BEx/SH error recovery */
+	u32 resched_delay;
+	struct delayed_work err_detection_work;
+};
+
+/* Ethtool priv_flags */
+#define	BE_DISABLE_TPE_RECOVERY	0x1
+
 struct be_adapter {
 	struct pci_dev *pdev;
 	struct net_device *netdev;
@@ -560,7 +620,6 @@ struct be_adapter {
 	struct delayed_work work;
 	u16 work_counter;
 
-	struct delayed_work be_err_detection_work;
 	u8 recovery_retries;
 	u8 err_flags;
 	bool pcicfg_mapped;	/* pcicfg obtained via pci_iomap() */
@@ -634,6 +693,8 @@ struct be_adapter {
 	u32 fat_dump_len;
 	u16 serial_num[CNTL_SERIAL_NUM_WORDS];
 	u8 phy_state; /* state of sfp optics (functional, faulted, etc.,) */
+	u32 priv_flags; /* ethtool get/set_priv_flags() */
+	struct be_error_recovery error_recovery;
 };
 
 /* Used for defered FW config cmds. Add fields to this struct as reqd */
@@ -867,6 +928,9 @@ static inline bool is_ipv4_pkt(struct sk_buff *skb)
 	return skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->version == 4;
 }
 
+#define be_error_recovering(adapter)	\
+		(adapter->flags & BE_FLAGS_TRY_RECOVERY)
+
 #define BE_ERROR_EEH		1
 #define BE_ERROR_UE		BIT(1)
 #define BE_ERROR_FW		BIT(2)