e1000e: enable ECC on I217/I218 to catch packet buffer memory errors

In rare instances, memory errors have been detected in the internal packet
buffer memory on I217/I218 when stressed under certain environmental
conditions.  Enable Error Correcting Code (ECC) in hardware to catch both
correctable and uncorrectable errors.  Correctable errors will be handled
by the hardware.  Uncorrectable errors in the packet buffer will cause the
packet to be received with an error indication in the buffer descriptor
causing the packet to be discarded.  If the uncorrectable error is in the
descriptor itself, the hardware will stop and interrupt the driver
indicating the error.  The driver will then reset the hardware in order to
clear the error and restart.

Both types of errors will be accounted for in statistics counters.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Cc: <stable@vger.kernel.org> # 3.5.x & 3.6.x
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/e1000e/defines.h

@@ -232,6 +232,7 @@
 #define E1000_CTRL_FRCDPX   0x00001000  /* Force Duplex */
 #define E1000_CTRL_LANPHYPC_OVERRIDE 0x00010000 /* SW control of LANPHYPC */
 #define E1000_CTRL_LANPHYPC_VALUE    0x00020000 /* SW value of LANPHYPC */
+#define E1000_CTRL_MEHE     0x00080000  /* Memory Error Handling Enable */
 #define E1000_CTRL_SWDPIN0  0x00040000  /* SWDPIN 0 value */
 #define E1000_CTRL_SWDPIN1  0x00080000  /* SWDPIN 1 value */
 #define E1000_CTRL_SWDPIO0  0x00400000  /* SWDPIN 0 Input or output */
@@ -389,6 +390,12 @@
 
 #define E1000_PBS_16K E1000_PBA_16K
 
+/* Uncorrectable/correctable ECC Error counts and enable bits */
+#define E1000_PBECCSTS_CORR_ERR_CNT_MASK	0x000000FF
+#define E1000_PBECCSTS_UNCORR_ERR_CNT_MASK	0x0000FF00
+#define E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT	8
+#define E1000_PBECCSTS_ECC_ENABLE		0x00010000
+
 #define IFS_MAX       80
 #define IFS_MIN       40
 #define IFS_RATIO     4
@@ -408,6 +415,7 @@
 #define E1000_ICR_RXSEQ         0x00000008 /* Rx sequence error */
 #define E1000_ICR_RXDMT0        0x00000010 /* Rx desc min. threshold (0) */
 #define E1000_ICR_RXT0          0x00000080 /* Rx timer intr (ring 0) */
+#define E1000_ICR_ECCER         0x00400000 /* Uncorrectable ECC Error */
 #define E1000_ICR_INT_ASSERTED  0x80000000 /* If this bit asserted, the driver should claim the interrupt */
 #define E1000_ICR_RXQ0          0x00100000 /* Rx Queue 0 Interrupt */
 #define E1000_ICR_RXQ1          0x00200000 /* Rx Queue 1 Interrupt */
@@ -443,6 +451,7 @@
 #define E1000_IMS_RXSEQ     E1000_ICR_RXSEQ     /* Rx sequence error */
 #define E1000_IMS_RXDMT0    E1000_ICR_RXDMT0    /* Rx desc min. threshold */
 #define E1000_IMS_RXT0      E1000_ICR_RXT0      /* Rx timer intr */
+#define E1000_IMS_ECCER     E1000_ICR_ECCER     /* Uncorrectable ECC Error */
 #define E1000_IMS_RXQ0      E1000_ICR_RXQ0      /* Rx Queue 0 Interrupt */
 #define E1000_IMS_RXQ1      E1000_ICR_RXQ1      /* Rx Queue 1 Interrupt */
 #define E1000_IMS_TXQ0      E1000_ICR_TXQ0      /* Tx Queue 0 Interrupt */

drivers/net/ethernet/intel/e1000e/e1000.h

@@ -309,6 +309,8 @@ struct e1000_adapter {
 
 	struct napi_struct napi;
 
+	unsigned int uncorr_errors;	/* uncorrectable ECC errors */
+	unsigned int corr_errors;	/* correctable ECC errors */
 	unsigned int restart_queue;
 	u32 txd_cmd;
 

drivers/net/ethernet/intel/e1000e/ethtool.c

@@ -108,6 +108,8 @@ static const struct e1000_stats e1000_gstrings_stats[] = {
 	E1000_STAT("dropped_smbus", stats.mgpdc),
 	E1000_STAT("rx_dma_failed", rx_dma_failed),
 	E1000_STAT("tx_dma_failed", tx_dma_failed),
+	E1000_STAT("uncorr_ecc_errors", uncorr_errors),
+	E1000_STAT("corr_ecc_errors", corr_errors),
 };
 
 #define E1000_GLOBAL_STATS_LEN	ARRAY_SIZE(e1000_gstrings_stats)

drivers/net/ethernet/intel/e1000e/hw.h

@@ -77,6 +77,7 @@ enum e1e_registers {
 #define E1000_POEMB	E1000_PHY_CTRL	/* PHY OEM Bits */
 	E1000_PBA      = 0x01000, /* Packet Buffer Allocation - RW */
 	E1000_PBS      = 0x01008, /* Packet Buffer Size */
+	E1000_PBECCSTS = 0x0100C, /* Packet Buffer ECC Status - RW */
 	E1000_EEMNGCTL = 0x01010, /* MNG EEprom Control */
 	E1000_EEWR     = 0x0102C, /* EEPROM Write Register - RW */
 	E1000_FLOP     = 0x0103C, /* FLASH Opcode Register */

drivers/net/ethernet/intel/e1000e/ich8lan.c

@@ -3624,6 +3624,17 @@ static void e1000_initialize_hw_bits_ich8lan(struct e1000_hw *hw)
 	if (hw->mac.type == e1000_ich8lan)
 		reg |= (E1000_RFCTL_IPV6_EX_DIS | E1000_RFCTL_NEW_IPV6_EXT_DIS);
 	ew32(RFCTL, reg);
+
+	/* Enable ECC on Lynxpoint */
+	if (hw->mac.type == e1000_pch_lpt) {
+		reg = er32(PBECCSTS);
+		reg |= E1000_PBECCSTS_ECC_ENABLE;
+		ew32(PBECCSTS, reg);
+
+		reg = er32(CTRL);
+		reg |= E1000_CTRL_MEHE;
+		ew32(CTRL, reg);
+	}
 }
 
 /**

drivers/net/ethernet/intel/e1000e/netdev.c

@@ -1678,6 +1678,23 @@ static irqreturn_t e1000_intr_msi(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+	/* Reset on uncorrectable ECC error */
+	if ((icr & E1000_ICR_ECCER) && (hw->mac.type == e1000_pch_lpt)) {
+		u32 pbeccsts = er32(PBECCSTS);
+
+		adapter->corr_errors +=
+		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
+		adapter->uncorr_errors +=
+		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
+		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
+
+		/* Do the reset outside of interrupt context */
+		schedule_work(&adapter->reset_task);
+
+		/* return immediately since reset is imminent */
+		return IRQ_HANDLED;
+	}
+
 	if (napi_schedule_prep(&adapter->napi)) {
 		adapter->total_tx_bytes = 0;
 		adapter->total_tx_packets = 0;
@@ -1741,6 +1758,23 @@ static irqreturn_t e1000_intr(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+	/* Reset on uncorrectable ECC error */
+	if ((icr & E1000_ICR_ECCER) && (hw->mac.type == e1000_pch_lpt)) {
+		u32 pbeccsts = er32(PBECCSTS);
+
+		adapter->corr_errors +=
+		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
+		adapter->uncorr_errors +=
+		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
+		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
+
+		/* Do the reset outside of interrupt context */
+		schedule_work(&adapter->reset_task);
+
+		/* return immediately since reset is imminent */
+		return IRQ_HANDLED;
+	}
+
 	if (napi_schedule_prep(&adapter->napi)) {
 		adapter->total_tx_bytes = 0;
 		adapter->total_tx_packets = 0;
@@ -2104,6 +2138,8 @@ static void e1000_irq_enable(struct e1000_adapter *adapter)
 	if (adapter->msix_entries) {
 		ew32(EIAC_82574, adapter->eiac_mask & E1000_EIAC_MASK_82574);
 		ew32(IMS, adapter->eiac_mask | E1000_IMS_OTHER | E1000_IMS_LSC);
+	} else if (hw->mac.type == e1000_pch_lpt) {
+		ew32(IMS, IMS_ENABLE_MASK | E1000_IMS_ECCER);
 	} else {
 		ew32(IMS, IMS_ENABLE_MASK);
 	}
@@ -4251,6 +4287,16 @@ static void e1000e_update_stats(struct e1000_adapter *adapter)
 	adapter->stats.mgptc += er32(MGTPTC);
 	adapter->stats.mgprc += er32(MGTPRC);
 	adapter->stats.mgpdc += er32(MGTPDC);
+
+	/* Correctable ECC Errors */
+	if (hw->mac.type == e1000_pch_lpt) {
+		u32 pbeccsts = er32(PBECCSTS);
+		adapter->corr_errors +=
+		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
+		adapter->uncorr_errors +=
+		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
+		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
+	}
 }
 
 /**