[next-queue 00/10] ixgbe: Add ipsec offload

@@ -2321,11 +2321,6 @@ enum {
 #define IXGBE_TXD_CMD_VLE    0x40000000 /* Add VLAN tag */
 #define IXGBE_TXD_STAT_DD    0x00000001 /* Descriptor Done */
 
-#define IXGBE_RXDADV_IPSEC_STATUS_SECP                  0x00020000
-#define IXGBE_RXDADV_IPSEC_ERROR_INVALID_PROTOCOL       0x08000000
-#define IXGBE_RXDADV_IPSEC_ERROR_INVALID_LENGTH         0x10000000
-#define IXGBE_RXDADV_IPSEC_ERROR_AUTH_FAILED            0x18000000
-#define IXGBE_RXDADV_IPSEC_ERROR_BIT_MASK               0x18000000
 /* Multiple Transmit Queue Command Register */
 #define IXGBE_MTQC_RT_ENA       0x1 /* DCB Enable */
 #define IXGBE_MTQC_VT_ENA       0x2 /* VMDQ2 Enable */

@@ -2377,6 +2372,9 @@ enum {
 #define IXGBE_RXDADV_ERR_LE     0x02000000 /* Length Error */
 #define IXGBE_RXDADV_ERR_PE     0x08000000 /* Packet Error */
 #define IXGBE_RXDADV_ERR_OSE    0x10000000 /* Oversize Error */
+#define IXGBE_RXDADV_ERR_IPSEC_INV_PROTOCOL  0x08000000 /* overlap ERR_PE  */
+#define IXGBE_RXDADV_ERR_IPSEC_INV_LENGTH    0x10000000 /* overlap ERR_OSE */
+#define IXGBE_RXDADV_ERR_IPSEC_AUTH_FAILED   0x18000000
 #define IXGBE_RXDADV_ERR_USE    0x20000000 /* Undersize Error */
 #define IXGBE_RXDADV_ERR_TCPE   0x40000000 /* TCP/UDP Checksum Error */
 #define IXGBE_RXDADV_ERR_IPE    0x80000000 /* IP Checksum Error */

@@ -2398,6 +2396,7 @@ enum {
 #define IXGBE_RXDADV_STAT_FCSTAT_FCPRSP 0x00000020 /* 10: Recv. FCP_RSP */
 #define IXGBE_RXDADV_STAT_FCSTAT_DDP    0x00000030 /* 11: Ctxt w/ DDP */
 #define IXGBE_RXDADV_STAT_TS		0x00010000 /* IEEE 1588 Time Stamp */
+#define IXGBE_RXDADV_STAT_SECP          0x00020000 /* IPsec/MACsec pkt found */
 
 /* PSRTYPE bit definitions */
 #define IXGBE_PSRTYPE_TCPHDR    0x00000010

@@ -2464,13 +2463,6 @@ enum {
 #define IXGBE_RXDADV_PKTTYPE_ETQF_MASK  0x00000070 /* ETQF has 8 indices */
 #define IXGBE_RXDADV_PKTTYPE_ETQF_SHIFT 4          /* Right-shift 4 bits */
 
-/* Security Processing bit Indication */
-#define IXGBE_RXDADV_LNKSEC_STATUS_SECP         0x00020000
-#define IXGBE_RXDADV_LNKSEC_ERROR_NO_SA_MATCH   0x08000000
-#define IXGBE_RXDADV_LNKSEC_ERROR_REPLAY_ERROR  0x10000000
-#define IXGBE_RXDADV_LNKSEC_ERROR_BIT_MASK      0x18000000
-#define IXGBE_RXDADV_LNKSEC_ERROR_BAD_SIG       0x18000000
-
 /* Masks to determine if packets should be dropped due to frame errors */
 #define IXGBE_RXD_ERR_FRAME_ERR_MASK ( \
 				      IXGBE_RXD_ERR_CE | \

@@ -2484,6 +2476,8 @@ enum {
 				      IXGBE_RXDADV_ERR_LE | \
 				      IXGBE_RXDADV_ERR_PE | \
 				      IXGBE_RXDADV_ERR_OSE | \
+				      IXGBE_RXDADV_ERR_IPSEC_INV_PROTOCOL | \
+				      IXGBE_RXDADV_ERR_IPSEC_INV_LENGTH | \
 				      IXGBE_RXDADV_ERR_USE)
 
 /* Multicast bit mask */

@@ -2893,6 +2887,7 @@ struct ixgbe_adv_tx_context_desc {
 				 IXGBE_ADVTXD_POPTS_SHIFT)
 #define IXGBE_ADVTXD_POPTS_TXSM (IXGBE_TXD_POPTS_TXSM << \
 				 IXGBE_ADVTXD_POPTS_SHIFT)
+#define IXGBE_ADVTXD_POPTS_IPSEC     0x00000400 /* IPSec offload request */
 #define IXGBE_ADVTXD_POPTS_ISCO_1ST  0x00000000 /* 1st TSO of iSCSI PDU */
 #define IXGBE_ADVTXD_POPTS_ISCO_MDL  0x00000800 /* Middle TSO of iSCSI PDU */
 #define IXGBE_ADVTXD_POPTS_ISCO_LAST 0x00001000 /* Last TSO of iSCSI PDU */

@@ -2908,7 +2903,6 @@ struct ixgbe_adv_tx_context_desc {
 #define IXGBE_ADVTXD_TUCMD_L4T_SCTP  0x00001000  /* L4 Packet TYPE of SCTP */
 #define IXGBE_ADVTXD_TUCMD_L4T_RSV     0x00001800 /* RSV L4 Packet TYPE */
 #define IXGBE_ADVTXD_TUCMD_MKRREQ    0x00002000 /*Req requires Markers and CRC*/
-#define IXGBE_ADVTXD_POPTS_IPSEC      0x00000400 /* IPSec offload request */
 #define IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP 0x00002000 /* IPSec Type ESP */
 #define IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN 0x00004000/* ESP Encrypt Enable */
 #define IXGBE_ADVTXT_TUCMD_FCOE      0x00008000       /* FCoE Frame Type */

@@ -148,10 +148,150 @@ void ixgbe_ipsec_clear_hw_tables(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_ipsec_stop_data
+ * @adapter: board private structure
+ **/
+static void ixgbe_ipsec_stop_data(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool link = adapter->link_up;
+	u32 t_rdy, r_rdy;
+	u32 reg;
+
+	/* halt data paths */
+	reg = IXGBE_READ_REG(hw, IXGBE_SECTXCTRL);
+	reg |= IXGBE_SECTXCTRL_TX_DIS;
+	IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, reg);
+
+	reg = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL);
+	reg |= IXGBE_SECRXCTRL_RX_DIS;
+	IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, reg);
+
+	IXGBE_WRITE_FLUSH(hw);
+
+	/* If the tx fifo doesn't have link, but still has data,
+	 * we can't clear the tx sec block.  Set the MAC loopback
+	 * before block clear
+	 */
+	if (!link) {
+		reg = IXGBE_READ_REG(hw, IXGBE_MACC);
+		reg |= IXGBE_MACC_FLU;
+		IXGBE_WRITE_REG(hw, IXGBE_MACC, reg);
+
+		reg = IXGBE_READ_REG(hw, IXGBE_HLREG0);
+		reg |= IXGBE_HLREG0_LPBK;
+		IXGBE_WRITE_REG(hw, IXGBE_HLREG0, reg);
+
+		IXGBE_WRITE_FLUSH(hw);
+		mdelay(3);
+	}
+
+	/* wait for the paths to empty */
+	do {
+		mdelay(10);
+		t_rdy = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT) &
+			IXGBE_SECTXSTAT_SECTX_RDY;
+		r_rdy = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT) &
+			IXGBE_SECRXSTAT_SECRX_RDY;
+	} while (!t_rdy && !r_rdy);
+
+	/* undo loopback if we played with it earlier */
+	if (!link) {
+		reg = IXGBE_READ_REG(hw, IXGBE_MACC);
+		reg &= ~IXGBE_MACC_FLU;
+		IXGBE_WRITE_REG(hw, IXGBE_MACC, reg);
+
+		reg = IXGBE_READ_REG(hw, IXGBE_HLREG0);
+		reg &= ~IXGBE_HLREG0_LPBK;
+		IXGBE_WRITE_REG(hw, IXGBE_HLREG0, reg);
+
+		IXGBE_WRITE_FLUSH(hw);
+	}
+}
+
+/**
+ * ixgbe_ipsec_stop_engine
+ * @adapter: board private structure
+ **/
+static void ixgbe_ipsec_stop_engine(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 reg;
+
+	ixgbe_ipsec_stop_data(adapter);
+
+	/* disable Rx and Tx SA lookup */
+	IXGBE_WRITE_REG(hw, IXGBE_IPSTXIDX, 0);
+	IXGBE_WRITE_REG(hw, IXGBE_IPSRXIDX, 0);
+
+	/* disable the Rx and Tx engines and full packet store-n-forward */
+	reg = IXGBE_READ_REG(hw, IXGBE_SECTXCTRL);
+	reg |= IXGBE_SECTXCTRL_SECTX_DIS;
+	reg &= ~IXGBE_SECTXCTRL_STORE_FORWARD;
+	IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, reg);
+
+	reg = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL);
+	reg |= IXGBE_SECRXCTRL_SECRX_DIS;
+	IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, reg);
+
+	/* restore the "tx security buffer almost full threshold" to 0x250 */
+	IXGBE_WRITE_REG(hw, IXGBE_SECTXBUFFAF, 0x250);
+
+	/* Set minimum IFG between packets back to the default 0x1 */
+	reg = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG);
+	reg = (reg & 0xfffffff0) | 0x1;
+	IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, reg);
+
+	/* final set for normal (no ipsec offload) processing */
+	IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, IXGBE_SECTXCTRL_SECTX_DIS);
+	IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, IXGBE_SECRXCTRL_SECRX_DIS);
+
+	IXGBE_WRITE_FLUSH(hw);
+}
+
+/**
+ * ixgbe_ipsec_start_engine
+ * @adapter: board private structure
+ *
+ * NOTE: this increases power consumption whether being used or not
+ **/
+static void ixgbe_ipsec_start_engine(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 reg;
+
+	ixgbe_ipsec_stop_data(adapter);
+
+	/* Set minimum IFG between packets to 3 */
+	reg = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG);
+	reg = (reg & 0xfffffff0) | 0x3;
+	IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, reg);
+
+	/* Set "tx security buffer almost full threshold" to 0x15 so that the
+	 * almost full indication is generated only after buffer contains at
+	 * least an entire jumbo packet.
+	 */
+	reg = IXGBE_READ_REG(hw, IXGBE_SECTXBUFFAF);
+	reg = (reg & 0xfffffc00) | 0x15;
+	IXGBE_WRITE_REG(hw, IXGBE_SECTXBUFFAF, reg);
+
+	/* restart the data paths by clearing the DISABLE bits */
+	IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, 0);
+	IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, IXGBE_SECTXCTRL_STORE_FORWARD);
+
+	/* enable Rx and Tx SA lookup */
+	IXGBE_WRITE_REG(hw, IXGBE_IPSTXIDX, IXGBE_RXTXIDX_IPS_EN);
+	IXGBE_WRITE_REG(hw, IXGBE_IPSRXIDX, IXGBE_RXTXIDX_IPS_EN);
+
+	IXGBE_WRITE_FLUSH(hw);
+}
+
+/**
  * ixgbe_init_ipsec_offload - initialize security registers for IPSec operation
  * @adapter: board private structure
  **/
 void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter)
 {
 	ixgbe_ipsec_clear_hw_tables(adapter);
+	ixgbe_ipsec_stop_engine(adapter);
 }

@@ -622,6 +622,7 @@ struct ixgbe_adapter {
 #define IXGBE_FLAG2_EEE_CAPABLE			BIT(14)
 #define IXGBE_FLAG2_EEE_ENABLED			BIT(15)
 #define IXGBE_FLAG2_RX_LEGACY			BIT(16)
+#define IXGBE_FLAG2_IPSEC_ENABLED		BIT(17)
 
 	/* Tx fast path data */
 	int num_tx_queues;

@@ -772,6 +773,10 @@ struct ixgbe_adapter {
 
 #define IXGBE_RSS_KEY_SIZE     40  /* size of RSS Hash Key in bytes */
 	u32 *rss_key;
+
+#ifdef CONFIG_XFRM
+	struct ixgbe_ipsec *ipsec;
+#endif /* CONFIG_XFRM */
 };
 
 static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)

@@ -47,4 +47,44 @@
 #define IXGBE_RXMOD_DECRYPT		0x00000008
 #define IXGBE_RXMOD_IPV6		0x00000010
 
+struct rx_sa {
+	struct hlist_node hlist;
+	struct xfrm_state *xs;
+	u32 ipaddr[4];
+	u32 key[4];
+	u32 salt;
+	u32 mode;
+	u8  iptbl_ind;
+	bool used;
+	bool decrypt;
+};
+
+struct rx_ip_sa {
+	u32 ipaddr[4];
+	u32 ref_cnt;
+	bool used;
+};
+
+struct tx_sa {
+	struct xfrm_state *xs;
+	u32 key[4];
+	u32 salt;
+	bool encrypt;
+	bool used;
+};
+
+struct ixgbe_ipsec_tx_data {
+	u32 flags;
+	u16 trailer_len;
+	u16 sa_idx;
+};
+
+struct ixgbe_ipsec {
+	u16 num_rx_sa;
+	u16 num_tx_sa;
+	struct rx_ip_sa *ip_tbl;
+	struct rx_sa *rx_tbl;
+	struct tx_sa *tx_tbl;
+	DECLARE_HASHTABLE(rx_sa_list, 8);
+};
 #endif /* _IXGBE_IPSEC_H_ */

@@ -26,6 +26,8 @@
  ******************************************************************************/
 
 #include "ixgbe.h"
+#include <net/xfrm.h>
+#include <crypto/aead.h>
 
 /**
  * ixgbe_ipsec_set_tx_sa - set the Tx SA registers

@@ -128,6 +130,7 @@ static void ixgbe_ipsec_set_rx_ip(struct ixgbe_hw *hw, u16 idx, u32 addr[])
  **/
 void ixgbe_ipsec_clear_hw_tables(struct ixgbe_adapter *adapter)
 {
+	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 buf[4] = {0, 0, 0, 0};
 	u16 idx;

@@ -139,9 +142,11 @@ void ixgbe_ipsec_clear_hw_tables(struct ixgbe_adapter *adapter)
 	/* scrub the tables */
 	for (idx = 0; idx < IXGBE_IPSEC_MAX_SA_COUNT; idx++)
 		ixgbe_ipsec_set_tx_sa(hw, idx, buf, 0);
+	ipsec->num_tx_sa = 0;
 
 	for (idx = 0; idx < IXGBE_IPSEC_MAX_SA_COUNT; idx++)
 		ixgbe_ipsec_set_rx_sa(hw, idx, 0, buf, 0, 0, 0);
+	ipsec->num_rx_sa = 0;
 
 	for (idx = 0; idx < IXGBE_IPSEC_MAX_RX_IP_COUNT; idx++)
 		ixgbe_ipsec_set_rx_ip(hw, idx, buf);

@@ -287,11 +292,383 @@ static void ixgbe_ipsec_start_engine(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_ipsec_find_empty_idx - find the first unused security parameter index
+ * @ipsec: pointer to ipsec struct
+ * @rxtable: true if we need to look in the Rx table
+ *
+ * Returns the first unused index in either the Rx or Tx SA table
+ **/
+static int ixgbe_ipsec_find_empty_idx(struct ixgbe_ipsec *ipsec, bool rxtable)
+{
+	u32 i;
+
+	if (rxtable) {
+		if (ipsec->num_rx_sa == IXGBE_IPSEC_MAX_SA_COUNT)
+			return -ENOSPC;
+
+		/* search rx sa table */
+		for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) {
+			if (!ipsec->rx_tbl[i].used)
+				return i;
+		}
+	} else {
+		if (ipsec->num_rx_sa == IXGBE_IPSEC_MAX_SA_COUNT)
+			return -ENOSPC;
+
+		/* search tx sa table */
+		for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) {
+			if (!ipsec->tx_tbl[i].used)
+				return i;
+		}
+	}
+
+	return -ENOSPC;
+}
+
+/**
+ * ixgbe_ipsec_parse_proto_keys - find the key and salt based on the protocol
+ * @xs: pointer to xfrm_state struct
+ * @mykey: pointer to key array to populate
+ * @mysalt: pointer to salt value to populate
+ *
+ * This copies the protocol keys and salt to our own data tables.  The
+ * 82599 family only supports the one algorithm.
+ **/
+static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs,
+					u32 *mykey, u32 *mysalt)
+{
+	struct net_device *dev = xs->xso.dev;
+	unsigned char *key_data;
+	char *alg_name = NULL;
+	char *aes_gcm_name = "rfc4106(gcm(aes))";
+	int key_len;
+
+	if (xs->aead) {
+		key_data = &xs->aead->alg_key[0];
+		key_len = xs->aead->alg_key_len;
+		alg_name = xs->aead->alg_name;
+	} else {
+		netdev_err(dev, "Unsupported IPsec algorithm\n");
+		return -EINVAL;
+	}
+
+	if (strcmp(alg_name, aes_gcm_name)) {
+		netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n",
+			   aes_gcm_name);
+		return -EINVAL;
+	}
+
+	/* 160 accounts for 16 byte key and 4 byte salt */
+	if (key_len == 128) {
+		netdev_info(dev, "IPsec hw offload parameters missing 32 bit salt value\n");
+	} else if (key_len != 160) {
+		netdev_err(dev, "IPsec hw offload only supports keys up to 128 bits with a 32 bit salt\n");
+		return -EINVAL;
+	}
+
+	/* The key bytes come down in a bigendian array of bytes, and
+	 * salt is always the last 4 bytes of the key array.
+	 * We don't need to do any byteswapping.
+	 */
+	memcpy(mykey, key_data, 16);
+	if (key_len == 160)
+		*mysalt = ((u32 *)key_data)[4];
+	else
+		*mysalt = 0;
+
+	return 0;
+}
+
+/**
+ * ixgbe_ipsec_add_sa - program device with a security association
+ * @xs: pointer to transformer state struct
+ **/
+static int ixgbe_ipsec_add_sa(struct xfrm_state *xs)
+{
+	struct net_device *dev = xs->xso.dev;
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_ipsec *ipsec = adapter->ipsec;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int checked, match, first;
+	u16 sa_idx;
+	int ret;
+	int i;
+
+	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+		netdev_err(dev, "Unsupported protocol 0x%04x for ipsec offload\n",
+			   xs->id.proto);
+		return -EINVAL;
+	}
+
+	if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
+		struct rx_sa rsa;
+
+		if (xs->calg) {
+			netdev_err(dev, "Compression offload not supported\n");
+			return -EINVAL;
+		}
+
+		/* find the first unused index */
+		ret = ixgbe_ipsec_find_empty_idx(ipsec, true);
+		if (ret < 0) {
+			netdev_err(dev, "No space for SA in Rx table!\n");
+			return ret;
+		}
+		sa_idx = (u16)ret;
+
+		memset(&rsa, 0, sizeof(rsa));
+		rsa.used = true;
+		rsa.xs = xs;
+
+		if (rsa.xs->id.proto & IPPROTO_ESP)
+			rsa.decrypt = xs->ealg || xs->aead;
+
+		/* get the key and salt */
+		ret = ixgbe_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt);
+		if (ret) {
+			netdev_err(dev, "Failed to get key data for Rx SA table\n");
+			return ret;
+		}
+
+		/* get ip for rx sa table */
+		if (xs->xso.flags & XFRM_OFFLOAD_IPV6)
+			memcpy(rsa.ipaddr, &xs->id.daddr.a6, 16);
+		else
+			memcpy(&rsa.ipaddr[3], &xs->id.daddr.a4, 4);
+
+		/* The HW does not have a 1:1 mapping from keys to IP addrs, so
+		 * check for a matching IP addr entry in the table.  If the addr
+		 * already exists, use it; else find an unused slot and add the
+		 * addr.  If one does not exist and there are no unused table
+		 * entries, fail the request.
+		 */
+
+		/* Find an existing match or first not used, and stop looking
+		 * after we've checked all we know we have.
+		 */
+		checked = 0;
+		match = -1;
+		first = -1;
+		for (i = 0;
+		     i < IXGBE_IPSEC_MAX_RX_IP_COUNT &&
+		     (checked < ipsec->num_rx_sa || first < 0);
+		     i++) {
+			if (ipsec->ip_tbl[i].used) {
+				if (!memcmp(ipsec->ip_tbl[i].ipaddr,
+					    rsa.ipaddr, sizeof(rsa.ipaddr))) {
+					match = i;
+					break;
+				}
+				checked++;
+			} else if (first < 0) {
+				first = i;  /* track the first empty seen */
+			}
+		}
+
+		if (ipsec->num_rx_sa == 0)
+			first = 0;
+
+		if (match >= 0) {
+			/* addrs are the same, we should use this one */
+			rsa.iptbl_ind = match;
+			ipsec->ip_tbl[match].ref_cnt++;
+
+		} else if (first >= 0) {
+			/* no matches, but here's an empty slot */
+			rsa.iptbl_ind = first;
+
+			memcpy(ipsec->ip_tbl[first].ipaddr,
+			       rsa.ipaddr, sizeof(rsa.ipaddr));
+			ipsec->ip_tbl[first].ref_cnt = 1;
+			ipsec->ip_tbl[first].used = true;
+
+			ixgbe_ipsec_set_rx_ip(hw, rsa.iptbl_ind, rsa.ipaddr);
+
+		} else {
+			/* no match and no empty slot */
+			netdev_err(dev, "No space for SA in Rx IP SA table\n");
+			memset(&rsa, 0, sizeof(rsa));
+			return -ENOSPC;
+		}
+
+		rsa.mode = IXGBE_RXMOD_VALID;
+		if (rsa.xs->id.proto & IPPROTO_ESP)
+			rsa.mode |= IXGBE_RXMOD_PROTO_ESP;
+		if (rsa.decrypt)
+			rsa.mode |= IXGBE_RXMOD_DECRYPT;
+		if (rsa.xs->xso.flags & XFRM_OFFLOAD_IPV6)
+			rsa.mode |= IXGBE_RXMOD_IPV6;
+
+		/* the preparations worked, so save the info */
+		memcpy(&ipsec->rx_tbl[sa_idx], &rsa, sizeof(rsa));
+
+		ixgbe_ipsec_set_rx_sa(hw, sa_idx, rsa.xs->id.spi, rsa.key,
+				      rsa.salt, rsa.mode, rsa.iptbl_ind);
+		xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_RX_INDEX;
+
+		ipsec->num_rx_sa++;
+
+		/* hash the new entry for faster search in Rx path */
+		hash_add_rcu(ipsec->rx_sa_list, &ipsec->rx_tbl[sa_idx].hlist,
+			     rsa.xs->id.spi);
+	} else {
+		struct tx_sa tsa;
+
+		/* find the first unused index */
+		ret = ixgbe_ipsec_find_empty_idx(ipsec, false);
+		if (ret < 0) {
+			netdev_err(dev, "No space for SA in Tx table\n");
+			return ret;
+		}
+		sa_idx = (u16)ret;
+
+		memset(&tsa, 0, sizeof(tsa));
+		tsa.used = true;
+		tsa.xs = xs;
+
+		if (xs->id.proto & IPPROTO_ESP)
+			tsa.encrypt = xs->ealg || xs->aead;
+
+		ret = ixgbe_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt);
+		if (ret) {
+			netdev_err(dev, "Failed to get key data for Tx SA table\n");
+			memset(&tsa, 0, sizeof(tsa));
+			return ret;
+		}
+
+		/* the preparations worked, so save the info */
+		memcpy(&ipsec->tx_tbl[sa_idx], &tsa, sizeof(tsa));
+
+		ixgbe_ipsec_set_tx_sa(hw, sa_idx, tsa.key, tsa.salt);
+
+		xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_TX_INDEX;
+
+		ipsec->num_tx_sa++;
+	}
+
+	/* enable the engine if not already warmed up */
+	if (!(adapter->flags2 & IXGBE_FLAG2_IPSEC_ENABLED)) {
+		ixgbe_ipsec_start_engine(adapter);
+		adapter->flags2 |= IXGBE_FLAG2_IPSEC_ENABLED;
+	}
+
+	return 0;
+}
+
+/**
+ * ixgbe_ipsec_del_sa - clear out this specific SA
+ * @xs: pointer to transformer state struct
+ **/
+static void ixgbe_ipsec_del_sa(struct xfrm_state *xs)
+{
+	struct net_device *dev = xs->xso.dev;
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ixgbe_ipsec *ipsec = adapter->ipsec;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 zerobuf[4] = {0, 0, 0, 0};
+	u16 sa_idx;
+
+	if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
+		struct rx_sa *rsa;
+		u8 ipi;
+
+		sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX;
+		rsa = &ipsec->rx_tbl[sa_idx];
+
+		if (!rsa->used) {
+			netdev_err(dev, "Invalid Rx SA selected sa_idx=%d offload_handle=%lu\n",
+				   sa_idx, xs->xso.offload_handle);
+			return;
+		}
+
+		ixgbe_ipsec_set_rx_sa(hw, sa_idx, 0, zerobuf, 0, 0, 0);
+		hash_del_rcu(&rsa->hlist);
+
+		/* if the IP table entry is referenced by only this SA,
+		 * i.e. ref_cnt is only 1, clear the IP table entry as well
+		 */
+		ipi = rsa->iptbl_ind;
+		if (ipsec->ip_tbl[ipi].ref_cnt > 0) {
+			ipsec->ip_tbl[ipi].ref_cnt--;
+
+			if (!ipsec->ip_tbl[ipi].ref_cnt) {
+				memset(&ipsec->ip_tbl[ipi], 0,
+				       sizeof(struct rx_ip_sa));
+				ixgbe_ipsec_set_rx_ip(hw, ipi, zerobuf);
+			}
+		}
+
+		memset(rsa, 0, sizeof(struct rx_sa));
+		ipsec->num_rx_sa--;
+	} else {
+		sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX;
+
+		if (!ipsec->tx_tbl[sa_idx].used) {
+			netdev_err(dev, "Invalid Tx SA selected sa_idx=%d offload_handle=%lu\n",
+				   sa_idx, xs->xso.offload_handle);
+			return;
+		}
+
+		ixgbe_ipsec_set_tx_sa(hw, sa_idx, zerobuf, 0);
+		memset(&ipsec->tx_tbl[sa_idx], 0, sizeof(struct tx_sa));
+		ipsec->num_tx_sa--;
+	}
+
+	/* if there are no SAs left, stop the engine to save energy */
+	if (ipsec->num_rx_sa == 0 && ipsec->num_tx_sa == 0) {
+		adapter->flags2 &= ~IXGBE_FLAG2_IPSEC_ENABLED;
+		ixgbe_ipsec_stop_engine(adapter);
+	}
+}
+
+static const struct xfrmdev_ops ixgbe_xfrmdev_ops = {
+	.xdo_dev_state_add = ixgbe_ipsec_add_sa,
+	.xdo_dev_state_delete = ixgbe_ipsec_del_sa,
+};
+
+/**
  * ixgbe_init_ipsec_offload - initialize security registers for IPSec operation
  * @adapter: board private structure
  **/
 void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter)
 {
+	struct ixgbe_ipsec *ipsec;
+	size_t size;
+
+	ipsec = kzalloc(sizeof(*ipsec), GFP_KERNEL);
+	if (!ipsec)
+		goto err;
+	hash_init(ipsec->rx_sa_list);
+
+	size = sizeof(struct rx_sa) * IXGBE_IPSEC_MAX_SA_COUNT;
+	ipsec->rx_tbl = kzalloc(size, GFP_KERNEL);
+	if (!ipsec->rx_tbl)
+		goto err;
+
+	size = sizeof(struct tx_sa) * IXGBE_IPSEC_MAX_SA_COUNT;
+	ipsec->tx_tbl = kzalloc(size, GFP_KERNEL);
+	if (!ipsec->tx_tbl)
+		goto err;
+
+	size = sizeof(struct rx_ip_sa) * IXGBE_IPSEC_MAX_RX_IP_COUNT;
+	ipsec->ip_tbl = kzalloc(size, GFP_KERNEL);
+	if (!ipsec->ip_tbl)
+		goto err;
+
+	ipsec->num_rx_sa = 0;
+	ipsec->num_tx_sa = 0;
+
+	adapter->ipsec = ipsec;
 	ixgbe_ipsec_clear_hw_tables(adapter);
 	ixgbe_ipsec_stop_engine(adapter);
+
+	return;
+err:
+	if (ipsec) {
+		kfree(ipsec->ip_tbl);
+		kfree(ipsec->rx_tbl);
+		kfree(ipsec->tx_tbl);
+		kfree(adapter->ipsec);
+	}
+	netdev_err(adapter->netdev, "Unable to allocate memory for SA tables");
 }

@@ -10542,6 +10542,12 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	set_bit(__IXGBE_REMOVING, &adapter->state);
 	cancel_work_sync(&adapter->service_task);
 
+#ifdef CONFIG_XFRM
+	kfree(adapter->ipsec->ip_tbl);
+	kfree(adapter->ipsec->rx_tbl);
+	kfree(adapter->ipsec->tx_tbl);
+	kfree(adapter->ipsec);
+#endif /* CONFIG_XFRM */
 
 #ifdef CONFIG_IXGBE_DCA
 	if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {

@@ -1009,9 +1009,15 @@ s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg,
 		       u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm);
 #ifdef CONFIG_XFRM_OFFLOAD
 void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter);
+void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
+		    union ixgbe_adv_rx_desc *rx_desc,
+		    struct sk_buff *skb);
 void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter);
 #else
 static inline void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter) { };
+static inline void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
+				  union ixgbe_adv_rx_desc *rx_desc,
+				  struct sk_buff *skb) { };
 static inline void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) { };
 #endif /* CONFIG_XFRM_OFFLOAD */
 #endif /* _IXGBE_H_ */

@@ -379,6 +379,35 @@ static int ixgbe_ipsec_find_empty_idx(struct ixgbe_ipsec *ipsec, bool rxtable)
 }
 
 /**
+ * ixgbe_ipsec_find_rx_state - find the state that matches
+ * @ipsec: pointer to ipsec struct
+ * @daddr: inbound address to match
+ * @proto: protocol to match
+ * @spi: SPI to match
+ *
+ * Returns a pointer to the matching SA state information
+ **/
+static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec,
+						    __be32 daddr, u8 proto,
+						    __be32 spi)
+{
+	struct rx_sa *rsa;
+	struct xfrm_state *ret = NULL;
+
+	rcu_read_lock();
+	hash_for_each_possible_rcu(ipsec->rx_sa_list, rsa, hlist, spi)
+		if (spi == rsa->xs->id.spi &&
+		    daddr == rsa->xs->id.daddr.a4 &&
+		    proto == rsa->xs->id.proto) {
+			ret = rsa->xs;
+			xfrm_state_hold(ret);
+			break;
+		}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
  * ixgbe_ipsec_parse_proto_keys - find the key and salt based on the protocol
  * @xs: pointer to xfrm_state struct
  * @mykey: pointer to key array to populate

@@ -680,6 +709,66 @@ static const struct xfrmdev_ops ixgbe_xfrmdev_ops = {
 };
 
 /**
+ * ixgbe_ipsec_rx - decode ipsec bits from Rx descriptor
+ * @rx_ring: receiving ring
+ * @rx_desc: receive data descriptor
+ * @skb: current data packet
+ *
+ * Determine if there was an ipsec encapsulation noticed, and if so set up
+ * the resulting status for later in the receive stack.
+ **/
+void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
+		    union ixgbe_adv_rx_desc *rx_desc,
+		    struct sk_buff *skb)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(rx_ring->netdev);
+	u16 pkt_info = le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.pkt_info);
+	u16 ipsec_pkt_types = IXGBE_RXDADV_PKTTYPE_IPSEC_AH |
+				IXGBE_RXDADV_PKTTYPE_IPSEC_ESP;
+	struct ixgbe_ipsec *ipsec = adapter->ipsec;
+	struct xfrm_offload *xo = NULL;
+	struct xfrm_state *xs = NULL;
+	struct iphdr *iph;
+	u8 *c_hdr;
+	__be32 spi;
+	u8 proto;
+
+	/* we can assume no vlan header in the way, b/c the
+	 * hw won't recognize the IPsec packet and anyway the
+	 * currently vlan device doesn't support xfrm offload.
+	 */
+	/* TODO: not supporting IPv6 yet */
+	iph = (struct iphdr *)(skb->data + ETH_HLEN);
+	c_hdr = (u8 *)iph + iph->ihl * 4;
+	switch (pkt_info & ipsec_pkt_types) {
+	case IXGBE_RXDADV_PKTTYPE_IPSEC_AH:
+		spi = ((struct ip_auth_hdr *)c_hdr)->spi;
+		proto = IPPROTO_AH;
+		break;
+	case IXGBE_RXDADV_PKTTYPE_IPSEC_ESP:
+		spi = ((struct ip_esp_hdr *)c_hdr)->spi;
+		proto = IPPROTO_ESP;
+		break;
+	default:
+		return;
+	}
+
+	xs = ixgbe_ipsec_find_rx_state(ipsec, iph->daddr, proto, spi);
+	if (unlikely(!xs))
+		return;
+
+	skb->sp = secpath_dup(skb->sp);
+	if (unlikely(!skb->sp))
+		return;
+
+	skb->sp->xvec[skb->sp->len++] = xs;
+	skb->sp->olen++;
+	xo = xfrm_offload(skb);
+	xo->flags = CRYPTO_DONE;
+	xo->status = CRYPTO_SUCCESS;
+}
+
+/**
  * ixgbe_init_ipsec_offload - initialize security registers for IPSec operation
  * @adapter: board private structure
  **/

@@ -1755,6 +1755,9 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring,
 
 	skb_record_rx_queue(skb, rx_ring->queue_index);
 
+	if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_SECP))
+		ixgbe_ipsec_rx(rx_ring, rx_desc, skb);
+
 	skb->protocol = eth_type_trans(skb, dev);
 }
 

@@ -1009,7 +1009,9 @@ s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg,
 		       u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm);
 #ifdef CONFIG_XFRM_OFFLOAD
 void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter);
+void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter);
 #else
 static inline void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter) { };
+static inline void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) { };
 #endif /* CONFIG_XFRM_OFFLOAD */
 #endif /* _IXGBE_H_ */

@@ -292,6 +292,59 @@ static void ixgbe_ipsec_start_engine(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_ipsec_restore - restore the ipsec HW settings after a reset
+ * @adapter: board private structure
+ **/
+void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_ipsec *ipsec = adapter->ipsec;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 zbuf[4] = {0, 0, 0, 0};
+	int i;
+
+	if (!(adapter->flags2 & IXGBE_FLAG2_IPSEC_ENABLED))
+		return;
+
+	/* clean up the engine settings */
+	ixgbe_ipsec_stop_engine(adapter);
+
+	/* start the engine */
+	ixgbe_ipsec_start_engine(adapter);
+
+	/* reload the IP addrs */
+	for (i = 0; i < IXGBE_IPSEC_MAX_RX_IP_COUNT; i++) {
+		struct rx_ip_sa *ipsa = &ipsec->ip_tbl[i];
+
+		if (ipsa->used)
+			ixgbe_ipsec_set_rx_ip(hw, i, ipsa->ipaddr);
+		else
+			ixgbe_ipsec_set_rx_ip(hw, i, zbuf);
+	}
+
+	/* reload the Rx keys */
+	for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) {
+		struct rx_sa *rsa = &ipsec->rx_tbl[i];
+
+		if (rsa->used)
+			ixgbe_ipsec_set_rx_sa(hw, i, rsa->xs->id.spi,
+					      rsa->key, rsa->salt,
+					      rsa->mode, rsa->iptbl_ind);
+		else
+			ixgbe_ipsec_set_rx_sa(hw, i, 0, zbuf, 0, 0, 0);
+	}
+
+	/* reload the Tx keys */
+	for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) {
+		struct tx_sa *tsa = &ipsec->tx_tbl[i];
+
+		if (tsa->used)
+			ixgbe_ipsec_set_tx_sa(hw, i, tsa->key, tsa->salt);
+		else
+			ixgbe_ipsec_set_tx_sa(hw, i, zbuf, 0);
+	}
+}
+
+/**
  * ixgbe_ipsec_find_empty_idx - find the first unused security parameter index
  * @ipsec: pointer to ipsec struct
  * @rxtable: true if we need to look in the Rx table