Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Support SPI based w5100 devices, from Akinobu Mita.

   2) Partial Segmentation Offload, from Alexander Duyck.

   3) Add GMAC4 support to stmmac driver, from Alexandre TORGUE.

   4) Allow cls_flower stats offload, from Amir Vadai.

   5) Implement bpf blinding, from Daniel Borkmann.

   6) Optimize _ASYNC_ bit twiddling on sockets, unless the socket is
      actually using FASYNC these atomics are superfluous.  From Eric
      Dumazet.

   7) Run TCP more preemptibly, also from Eric Dumazet.

   8) Support LED blinking, EEPROM dumps, and rxvlan offloading in mlx5e
      driver, from Gal Pressman.

   9) Allow creating ppp devices via rtnetlink, from Guillaume Nault.

  10) Improve BPF usage documentation, from Jesper Dangaard Brouer.

  11) Support tunneling offloads in qed, from Manish Chopra.

  12) aRFS offloading in mlx5e, from Maor Gottlieb.

  13) Add RFS and RPS support to SCTP protocol, from Marcelo Ricardo
      Leitner.

  14) Add MSG_EOR support to TCP, this allows controlling packet
      coalescing on application record boundaries for more accurate
      socket timestamp sampling.  From Martin KaFai Lau.

  15) Fix alignment of 64-bit netlink attributes across the board, from
      Nicolas Dichtel.

  16) Per-vlan stats in bridging, from Nikolay Aleksandrov.

  17) Several conversions of drivers to ethtool ksettings, from Philippe
      Reynes.

  18) Checksum neutral ILA in ipv6, from Tom Herbert.

  19) Factorize all of the various marvell dsa drivers into one, from
      Vivien Didelot

  20) Add VF support to qed driver, from Yuval Mintz"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1649 commits)
  Revert "phy dp83867: Fix compilation with CONFIG_OF_MDIO=m"
  Revert "phy dp83867: Make rgmii parameters optional"
  r8169: default to 64-bit DMA on recent PCIe chips
  phy dp83867: Make rgmii parameters optional
  phy dp83867: Fix compilation with CONFIG_OF_MDIO=m
  bpf: arm64: remove callee-save registers use for tmp registers
  asix: Fix offset calculation in asix_rx_fixup() causing slow transmissions
  switchdev: pass pointer to fib_info instead of copy
  net_sched: close another race condition in tcf_mirred_release()
  tipc: fix nametable publication field in nl compat
  drivers: net: Don't print unpopulated net_device name
  qed: add support for dcbx.
  ravb: Add missing free_irq() calls to ravb_close()
  qed: Remove a stray tab
  net: ethernet: fec-mpc52xx: use phy_ethtool_{get|set}_link_ksettings
  net: ethernet: fec-mpc52xx: use phydev from struct net_device
  bpf, doc: fix typo on bpf_asm descriptions
  stmmac: hardware TX COE doesn't work when force_thresh_dma_mode is set
  net: ethernet: fs-enet: use phy_ethtool_{get|set}_link_ksettings
  net: ethernet: fs-enet: use phydev from struct net_device
  ...

40 files changed, 1236 insertions, 216 deletions

diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h
index 33eb274cd0e6..e66153d60bd5 100644
--- a/include/linux/ath9k_platform.h
+++ b/include/linux/ath9k_platform.h
@@ -31,6 +31,10 @@ struct ath9k_platform_data {
 	u32 gpio_mask;
 	u32 gpio_val;
 
+	u32 bt_active_pin;
+	u32 bt_priority_pin;
+	u32 wlan_active_pin;
+
 	bool endian_check;
 	bool is_clk_25mhz;
 	bool tx_gain_buffalo;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f1d5c5acc8dd..8ee27b8afe81 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -66,6 +66,11 @@ enum bpf_arg_type {
 	 * functions that access data on eBPF program stack
 	 */
 	ARG_PTR_TO_STACK,	/* any pointer to eBPF program stack */
+	ARG_PTR_TO_RAW_STACK,	/* any pointer to eBPF program stack, area does not
+				 * need to be initialized, helper function must fill
+				 * all bytes or clear them in error case.
+				 */
+
 	ARG_CONST_STACK_SIZE,	/* number of bytes accessed from stack */
 	ARG_CONST_STACK_SIZE_OR_ZERO, /* number of bytes accessed from stack or 0 */
 
@@ -131,6 +136,7 @@ struct bpf_prog_type_list {
 struct bpf_prog_aux {
 	atomic_t refcnt;
 	u32 used_map_cnt;
+	u32 max_ctx_offset;
 	const struct bpf_verifier_ops *ops;
 	struct bpf_map **used_maps;
 	struct bpf_prog *prog;
@@ -160,9 +166,12 @@ struct bpf_array {
 #define MAX_TAIL_CALL_CNT 32
 
 u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
+u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 void bpf_fd_array_map_clear(struct bpf_map *map);
 bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
+
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
+const struct bpf_func_proto *bpf_get_event_output_proto(void);
 
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 735f9f8c4e43..5261751f6bd4 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -40,8 +40,11 @@ struct can_priv {
 	struct can_clock clock;
 
 	enum can_state state;
-	u32 ctrlmode;
-	u32 ctrlmode_supported;
+
+	/* CAN controller features - see include/uapi/linux/can/netlink.h */
+	u32 ctrlmode;		/* current options setting */
+	u32 ctrlmode_supported;	/* options that can be modified by netlink */
+	u32 ctrlmode_static;	/* static enabled options for driver/hardware */
 
 	int restart_ms;
 	struct timer_list restart_timer;
@@ -108,6 +111,21 @@ static inline bool can_is_canfd_skb(const struct sk_buff *skb)
 	return skb->len == CANFD_MTU;
 }
 
+/* helper to define static CAN controller features at device creation time */
+static inline void can_set_static_ctrlmode(struct net_device *dev,
+					   u32 static_mode)
+{
+	struct can_priv *priv = netdev_priv(dev);
+
+	/* alloc_candev() succeeded => netdev_priv() is valid at this point */
+	priv->ctrlmode = static_mode;
+	priv->ctrlmode_static = static_mode;
+
+	/* override MTU which was set by default in can_setup()? */
+	if (static_mode & CAN_CTRLMODE_FD)
+		dev->mtu = CANFD_MTU;
+}
+
 /* get data length from can_dlc with sanitized can_dlc */
 u8 can_dlc2len(u8 can_dlc);
 
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index e2b7bf27c03e..9ded8c6d8176 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -150,6 +150,13 @@ extern int
 __ethtool_get_link_ksettings(struct net_device *dev,
 			     struct ethtool_link_ksettings *link_ksettings);
 
+void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst,
+					     u32 legacy_u32);
+
+/* return false if src had higher bits set. lower bits always updated. */
+bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
+				     const unsigned long *src);
+
 /**
  * struct ethtool_ops - optional netdev operations
  * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a51a5361695f..6fc31ef1da2d 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -13,6 +13,8 @@
 #include <linux/printk.h>
 #include <linux/workqueue.h>
 #include <linux/sched.h>
+#include <linux/capability.h>
+
 #include <net/sch_generic.h>
 
 #include <asm/cacheflush.h>
@@ -42,6 +44,15 @@ struct bpf_prog_aux;
 #define BPF_REG_X	BPF_REG_7
 #define BPF_REG_TMP	BPF_REG_8
 
+/* Kernel hidden auxiliary/helper register for hardening step.
+ * Only used by eBPF JITs. It's nothing more than a temporary
+ * register that JITs use internally, only that here it's part
+ * of eBPF instructions that have been rewritten for blinding
+ * constants. See JIT pre-step in bpf_jit_blind_constants().
+ */
+#define BPF_REG_AX		MAX_BPF_REG
+#define MAX_BPF_JIT_REG		(MAX_BPF_REG + 1)
+
 /* BPF program can access up to 512 bytes of stack space. */
 #define MAX_BPF_STACK	512
 
@@ -352,6 +363,22 @@ struct sk_filter {
 
 #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
 
+struct bpf_skb_data_end {
+	struct qdisc_skb_cb qdisc_cb;
+	void *data_end;
+};
+
+/* compute the linear packet data range [data, data_end) which
+ * will be accessed by cls_bpf and act_bpf programs
+ */
+static inline void bpf_compute_data_end(struct sk_buff *skb)
+{
+	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
+
+	BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb));
+	cb->data_end = skb->data + skb_headlen(skb);
+}
+
 static inline u8 *bpf_skb_cb(struct sk_buff *skb)
 {
 	/* eBPF programs may read/write skb->cb[] area to transfer meta
@@ -442,7 +469,7 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 
 int sk_filter(struct sock *sk, struct sk_buff *skb);
 
-int bpf_prog_select_runtime(struct bpf_prog *fp);
+struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err);
 void bpf_prog_free(struct bpf_prog *fp);
 
 struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);
@@ -465,14 +492,10 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
 void bpf_prog_destroy(struct bpf_prog *fp);
 
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
-int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk,
-		       bool locked);
 int sk_attach_bpf(u32 ufd, struct sock *sk);
 int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk);
 int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk);
 int sk_detach_filter(struct sock *sk);
-int __sk_detach_filter(struct sock *sk, bool locked);
-
 int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
 		  unsigned int len);
 
@@ -480,10 +503,17 @@ bool sk_filter_charge(struct sock *sk, struct sk_filter *fp);
 void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
 
 u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
-void bpf_int_jit_compile(struct bpf_prog *fp);
+
+struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog);
 bool bpf_helper_changes_skb_data(void *func);
 
+struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
+				       const struct bpf_insn *patch, u32 len);
+
 #ifdef CONFIG_BPF_JIT
+extern int bpf_jit_enable;
+extern int bpf_jit_harden;
+
 typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
 
 struct bpf_binary_header *
@@ -495,6 +525,9 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr);
 void bpf_jit_compile(struct bpf_prog *fp);
 void bpf_jit_free(struct bpf_prog *fp);
 
+struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp);
+void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other);
+
 static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
 				u32 pass, void *image)
 {
@@ -505,6 +538,33 @@ static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
 		print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
 			       16, 1, image, proglen, false);
 }
+
+static inline bool bpf_jit_is_ebpf(void)
+{
+# ifdef CONFIG_HAVE_EBPF_JIT
+	return true;
+# else
+	return false;
+# endif
+}
+
+static inline bool bpf_jit_blinding_enabled(void)
+{
+	/* These are the prerequisites, should someone ever have the
+	 * idea to call blinding outside of them, we make sure to
+	 * bail out.
+	 */
+	if (!bpf_jit_is_ebpf())
+		return false;
+	if (!bpf_jit_enable)
+		return false;
+	if (!bpf_jit_harden)
+		return false;
+	if (bpf_jit_harden == 1 && capable(CAP_SYS_ADMIN))
+		return false;
+
+	return true;
+}
 #else
 static inline void bpf_jit_compile(struct bpf_prog *fp)
 {
diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index eecd19b37001..6270a56e5edc 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -62,6 +62,11 @@ extern void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void);
 
 /* MAGIC helpers							{{{2 */
 
+static inline int nla_put_u64_0pad(struct sk_buff *skb, int attrtype, u64 value)
+{
+	return nla_put_64bit(skb, attrtype, sizeof(u64), &value, 0);
+}
+
 /* possible field types */
 #define __flg_field(attr_nr, attr_flag, name) \
 	__field(attr_nr, attr_flag, name, NLA_U8, char, \
@@ -80,7 +85,7 @@ extern void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void);
 			nla_get_u32, nla_put_u32, true)
 #define __u64_field(attr_nr, attr_flag, name)	\
 	__field(attr_nr, attr_flag, name, NLA_U64, __u64, \
-			nla_get_u64, nla_put_u64, false)
+			nla_get_u64, nla_put_u64_0pad, false)
 #define __str_field(attr_nr, attr_flag, name, maxlen) \
 	__array(attr_nr, attr_flag, name, NLA_NUL_STRING, char, maxlen, \
 			nla_strlcpy, nla_put, false)
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 3b1f6cef9513..b118744d3382 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -7,6 +7,7 @@
  * Copyright (c) 2005, Devicescape Software, Inc.
  * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
  * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright (c) 2016 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -163,6 +164,9 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2)
 /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */
 #define IEEE80211_MAX_FRAME_LEN		2352
 
+/* Maximal size of an A-MSDU that can be transported in a HT BA session */
+#define IEEE80211_MAX_MPDU_LEN_HT_BA		4095
+
 /* Maximal size of an A-MSDU */
 #define IEEE80211_MAX_MPDU_LEN_HT_3839		3839
 #define IEEE80211_MAX_MPDU_LEN_HT_7935		7935
@@ -637,6 +641,16 @@ static inline bool ieee80211_is_first_frag(__le16 seq_ctrl)
 	return (seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG)) == 0;
 }
 
+/**
+ * ieee80211_is_frag - check if a frame is a fragment
+ * @hdr: 802.11 header of the frame
+ */
+static inline bool ieee80211_is_frag(struct ieee80211_hdr *hdr)
+{
+	return ieee80211_has_morefrags(hdr->frame_control) ||
+	       hdr->seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG);
+}
+
 struct ieee80211s_hdr {
 	u8 flags;
 	u8 ttl;
@@ -1011,6 +1025,16 @@ struct ieee80211_mgmt {
 					u8 tpc_elem_length;
 					struct ieee80211_tpc_report_ie tpc;
 				} __packed tpc_report;
+				struct {
+					u8 action_code;
+					u8 dialog_token;
+					u8 follow_up;
+					u8 tod[6];
+					u8 toa[6];
+					__le16 tod_error;
+					__le16 toa_error;
+					u8 variable[0];
+				} __packed ftm;
 			} u;
 		} __packed action;
 	} u;
diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index d3e415674dac..acedbb68a5a3 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -47,6 +47,7 @@
 #define IEEE802154_ADDR_SHORT_UNSPEC	0xfffe
 
 #define IEEE802154_EXTENDED_ADDR_LEN	8
+#define IEEE802154_SHORT_ADDR_LEN	2
 
 #define IEEE802154_LIFS_PERIOD		40
 #define IEEE802154_SIFS_PERIOD		12
@@ -218,6 +219,7 @@ enum {
 /* frame control handling */
 #define IEEE802154_FCTL_FTYPE		0x0003
 #define IEEE802154_FCTL_ACKREQ		0x0020
+#define IEEE802154_FCTL_SECEN		0x0004
 #define IEEE802154_FCTL_INTRA_PAN	0x0040
 
 #define IEEE802154_FTYPE_DATA		0x0001
@@ -233,6 +235,15 @@ static inline int ieee802154_is_data(__le16 fc)
 }
 
 /**
+ * ieee802154_is_secen - check if Security bit is set
+ * @fc: frame control bytes in little-endian byteorder
+ */
+static inline bool ieee802154_is_secen(__le16 fc)
+{
+	return fc & cpu_to_le16(IEEE802154_FCTL_SECEN);
+}
+
+/**
  * ieee802154_is_ackreq - check if acknowledgment request bit is set
  * @fc: frame control bytes in little-endian byteorder
  */
@@ -260,17 +271,17 @@ static inline bool ieee802154_is_intra_pan(__le16 fc)
  *
  * @len: psdu len with (MHR + payload + MFR)
  */
-static inline bool ieee802154_is_valid_psdu_len(const u8 len)
+static inline bool ieee802154_is_valid_psdu_len(u8 len)
 {
 	return (len == IEEE802154_ACK_PSDU_LEN ||
 		(len >= IEEE802154_MIN_PSDU_LEN && len <= IEEE802154_MTU));
 }
 
 /**
- * ieee802154_is_valid_psdu_len - check if extended addr is valid
+ * ieee802154_is_valid_extended_unicast_addr - check if extended addr is valid
  * @addr: extended addr to check
  */
-static inline bool ieee802154_is_valid_extended_unicast_addr(const __le64 addr)
+static inline bool ieee802154_is_valid_extended_unicast_addr(__le64 addr)
 {
 	/* Bail out if the address is all zero, or if the group
 	 * address bit is set.
@@ -280,6 +291,34 @@ static inline bool ieee802154_is_valid_extended_unicast_addr(const __le64 addr)
 }
 
 /**
+ * ieee802154_is_broadcast_short_addr - check if short addr is broadcast
+ * @addr: short addr to check
+ */
+static inline bool ieee802154_is_broadcast_short_addr(__le16 addr)
+{
+	return (addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST));
+}
+
+/**
+ * ieee802154_is_unspec_short_addr - check if short addr is unspecified
+ * @addr: short addr to check
+ */
+static inline bool ieee802154_is_unspec_short_addr(__le16 addr)
+{
+	return (addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC));
+}
+
+/**
+ * ieee802154_is_valid_src_short_addr - check if source short address is valid
+ * @addr: short addr to check
+ */
+static inline bool ieee802154_is_valid_src_short_addr(__le16 addr)
+{
+	return !(ieee802154_is_broadcast_short_addr(addr) ||
+		 ieee802154_is_unspec_short_addr(addr));
+}
+
+/**
  * ieee802154_random_extended_addr - generates a random extended address
  * @addr: extended addr pointer to place the random address
  */
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 7edc14fb66b6..5c91b0b055d4 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -63,7 +63,8 @@ struct ipv6_devconf {
 	} stable_secret;
 	__s32		use_oif_addrs_only;
 	__s32		keep_addr_on_down;
-	void		*sysctl;
+
+	struct ctl_table_header *sysctl_header;
 };
 
 struct ipv6_params {
@@ -117,14 +118,29 @@ struct inet6_skb_parm {
 #define IP6SKB_ROUTERALERT	8
 #define IP6SKB_FRAGMENTED      16
 #define IP6SKB_HOPBYHOP        32
+#define IP6SKB_L3SLAVE         64
 };
 
+#if defined(CONFIG_NET_L3_MASTER_DEV)
+static inline bool skb_l3mdev_slave(__u16 flags)
+{
+	return flags & IP6SKB_L3SLAVE;
+}
+#else
+static inline bool skb_l3mdev_slave(__u16 flags)
+{
+	return false;
+}
+#endif
+
 #define IP6CB(skb)	((struct inet6_skb_parm*)((skb)->cb))
 #define IP6CBMTU(skb)	((struct ip6_mtuinfo *)((skb)->cb))
 
 static inline int inet6_iif(const struct sk_buff *skb)
 {
-	return IP6CB(skb)->iif;
+	bool l3_slave = skb_l3mdev_slave(IP6CB(skb)->flags);
+
+	return l3_slave ? skb->skb_iif : IP6CB(skb)->iif;
 }
 
 struct tcp6_request_sock {
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 5bfd99d1a40a..bf9d1d750693 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -13,6 +13,17 @@
 
 struct mii_bus;
 
+/* Multiple levels of nesting are possible. However typically this is
+ * limited to nested DSA like layer, a MUX layer, and the normal
+ * user. Instead of trying to handle the general case, just define
+ * these cases.
+ */
+enum mdio_mutex_lock_class {
+	MDIO_MUTEX_NORMAL,
+	MDIO_MUTEX_MUX,
+	MDIO_MUTEX_NESTED,
+};
+
 struct mdio_device {
 	struct device dev;
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index d1f904c8b2cb..80dec87a94f8 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1058,7 +1058,7 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf);
 static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset)
 {
-	if (BITS_PER_LONG == 64 || buf->nbufs == 1)
+	if (buf->nbufs == 1)
 		return buf->direct.buf + offset;
 	else
 		return buf->page_list[offset >> PAGE_SHIFT].buf +
@@ -1098,7 +1098,7 @@ int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order,
 void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db);
 
 int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
-		       int size, int max_direct);
+		       int size);
 void mlx4_free_hwq_res(struct mlx4_dev *mdev, struct mlx4_hwq_resources *wqres,
 		       int size);
 
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index b3575f392492..035abdf62cfe 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -59,6 +59,7 @@
 #define MLX5_FLD_SZ_BYTES(typ, fld) (__mlx5_bit_sz(typ, fld) / 8)
 #define MLX5_ST_SZ_BYTES(typ) (sizeof(struct mlx5_ifc_##typ##_bits) / 8)
 #define MLX5_ST_SZ_DW(typ) (sizeof(struct mlx5_ifc_##typ##_bits) / 32)
+#define MLX5_ST_SZ_QW(typ) (sizeof(struct mlx5_ifc_##typ##_bits) / 64)
 #define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8)
 #define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32)
 #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8)
@@ -655,7 +656,9 @@ struct mlx5_err_cqe {
 };
 
 struct mlx5_cqe64 {
-	u8		rsvd0[4];
+	u8		outer_l3_tunneled;
+	u8		rsvd0;
+	__be16		wqe_id;
 	u8		lro_tcppsh_abort_dupack;
 	u8		lro_min_ttl;
 	__be16		lro_tcp_win;
@@ -668,7 +671,7 @@ struct mlx5_cqe64 {
 	__be16		slid;
 	__be32		flags_rqpn;
 	u8		hds_ip_ext;
-	u8		l4_hdr_type_etc;
+	u8		l4_l3_hdr_type;
 	__be16		vlan_info;
 	__be32		srqn; /* [31:24]: lro_num_seg, [23:0]: srqn */
 	__be32		imm_inval_pkey;
@@ -682,6 +685,40 @@ struct mlx5_cqe64 {
 	u8		op_own;
 };
 
+struct mlx5_mini_cqe8 {
+	union {
+		__be32 rx_hash_result;
+		struct {
+			__be16 checksum;
+			__be16 rsvd;
+		};
+		struct {
+			__be16 wqe_counter;
+			u8  s_wqe_opcode;
+			u8  reserved;
+		} s_wqe_info;
+	};
+	__be32 byte_cnt;
+};
+
+enum {
+	MLX5_NO_INLINE_DATA,
+	MLX5_INLINE_DATA32_SEG,
+	MLX5_INLINE_DATA64_SEG,
+	MLX5_COMPRESSED,
+};
+
+enum {
+	MLX5_CQE_FORMAT_CSUM = 0x1,
+};
+
+#define MLX5_MINI_CQE_ARRAY_SIZE 8
+
+static inline int mlx5_get_cqe_format(struct mlx5_cqe64 *cqe)
+{
+	return (cqe->op_own >> 2) & 0x3;
+}
+
 static inline int get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe)
 {
 	return (cqe->lro_tcppsh_abort_dupack >> 6) & 1;
@@ -689,12 +726,22 @@ static inline int get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe)
 
 static inline u8 get_cqe_l4_hdr_type(struct mlx5_cqe64 *cqe)
 {
-	return (cqe->l4_hdr_type_etc >> 4) & 0x7;
+	return (cqe->l4_l3_hdr_type >> 4) & 0x7;
+}
+
+static inline u8 get_cqe_l3_hdr_type(struct mlx5_cqe64 *cqe)
+{
+	return (cqe->l4_l3_hdr_type >> 2) & 0x3;
+}
+
+static inline u8 cqe_is_tunneled(struct mlx5_cqe64 *cqe)
+{
+	return cqe->outer_l3_tunneled & 0x1;
 }
 
 static inline int cqe_has_vlan(struct mlx5_cqe64 *cqe)
 {
-	return !!(cqe->l4_hdr_type_etc & 0x1);
+	return !!(cqe->l4_l3_hdr_type & 0x1);
 }
 
 static inline u64 get_cqe_ts(struct mlx5_cqe64 *cqe)
@@ -707,6 +754,42 @@ static inline u64 get_cqe_ts(struct mlx5_cqe64 *cqe)
 	return (u64)lo | ((u64)hi << 32);
 }
 
+struct mpwrq_cqe_bc {
+	__be16	filler_consumed_strides;
+	__be16	byte_cnt;
+};
+
+static inline u16 mpwrq_get_cqe_byte_cnt(struct mlx5_cqe64 *cqe)
+{
+	struct mpwrq_cqe_bc *bc = (struct mpwrq_cqe_bc *)&cqe->byte_cnt;
+
+	return be16_to_cpu(bc->byte_cnt);
+}
+
+static inline u16 mpwrq_get_cqe_bc_consumed_strides(struct mpwrq_cqe_bc *bc)
+{
+	return 0x7fff & be16_to_cpu(bc->filler_consumed_strides);
+}
+
+static inline u16 mpwrq_get_cqe_consumed_strides(struct mlx5_cqe64 *cqe)
+{
+	struct mpwrq_cqe_bc *bc = (struct mpwrq_cqe_bc *)&cqe->byte_cnt;
+
+	return mpwrq_get_cqe_bc_consumed_strides(bc);
+}
+
+static inline bool mpwrq_is_filler_cqe(struct mlx5_cqe64 *cqe)
+{
+	struct mpwrq_cqe_bc *bc = (struct mpwrq_cqe_bc *)&cqe->byte_cnt;
+
+	return 0x8000 & be16_to_cpu(bc->filler_consumed_strides);
+}
+
+static inline u16 mpwrq_get_cqe_stride_index(struct mlx5_cqe64 *cqe)
+{
+	return be16_to_cpu(cqe->wqe_counter);
+}
+
 enum {
 	CQE_L4_HDR_TYPE_NONE			= 0x0,
 	CQE_L4_HDR_TYPE_TCP_NO_ACK		= 0x1,
@@ -1300,6 +1383,18 @@ enum mlx5_cap_type {
 #define MLX5_CAP_ESW_FLOWTABLE_FDB_MAX(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_nic_esw_fdb.cap)
 
+#define MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) \
+	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_egress.cap)
+
+#define MLX5_CAP_ESW_EGRESS_ACL_MAX(mdev, cap) \
+	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_egress.cap)
+
+#define MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) \
+	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_ingress.cap)
+
+#define MLX5_CAP_ESW_INGRESS_ACL_MAX(mdev, cap) \</