summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/asm-generic/checksum.h8
-rw-r--r--include/dt-bindings/clock/rk3036-cru.h2
-rw-r--r--include/linux/bcma/bcma.h3
-rw-r--r--include/linux/bcma/bcma_driver_chipcommon.h42
-rw-r--r--include/linux/bitmap.h10
-rw-r--r--include/linux/bpf.h32
-rw-r--r--include/linux/ethtool.h102
-rw-r--r--include/linux/ieee80211.h26
-rw-r--r--include/linux/if_bridge.h4
-rw-r--r--include/linux/if_team.h1
-rw-r--r--include/linux/igmp.h5
-rw-r--r--include/linux/inet_lro.h142
-rw-r--r--include/linux/ipv6.h3
-rw-r--r--include/linux/kernel.h2
-rw-r--r--include/linux/mbus.h3
-rw-r--r--include/linux/mlx4/driver.h3
-rw-r--r--include/linux/mlx5/device.h17
-rw-r--r--include/linux/mlx5/driver.h40
-rw-r--r--include/linux/mlx5/mlx5_ifc.h109
-rw-r--r--include/linux/mlx5/port.h87
-rw-r--r--include/linux/net.h1
-rw-r--r--include/linux/netdev_features.h3
-rw-r--r--include/linux/netdevice.h101
-rw-r--r--include/linux/netfilter.h29
-rw-r--r--include/linux/netfilter/nfnetlink.h2
-rw-r--r--include/linux/netfilter/x_tables.h6
-rw-r--r--include/linux/netfilter_arp/arp_tables.h9
-rw-r--r--include/linux/netfilter_ipv4/ip_tables.h9
-rw-r--r--include/linux/netfilter_ipv6/ip6_tables.h9
-rw-r--r--include/linux/netlink.h10
-rw-r--r--include/linux/perf_event.h13
-rw-r--r--include/linux/phy.h3
-rw-r--r--include/linux/phy_fixed.h5
-rw-r--r--include/linux/platform_data/brcmfmac-sdio.h135
-rw-r--r--include/linux/platform_data/brcmfmac.h185
-rw-r--r--include/linux/platform_data/microread.h35
-rw-r--r--include/linux/qed/common_hsi.h36
-rw-r--r--include/linux/qed/eth_common.h171
-rw-r--r--include/linux/qed/qed_chain.h4
-rw-r--r--include/linux/qed/qed_eth_if.h14
-rw-r--r--include/linux/qed/qed_if.h14
-rw-r--r--include/linux/rculist.h21
-rw-r--r--include/linux/rfkill-gpio.h37
-rw-r--r--include/linux/rfkill.h18
-rw-r--r--include/linux/skbuff.h69
-rw-r--r--include/linux/socket.h7
-rw-r--r--include/linux/stmmac.h17
-rw-r--r--include/linux/tcp.h14
-rw-r--r--include/net/6lowpan.h32
-rw-r--r--include/net/act_api.h84
-rw-r--r--include/net/addrconf.h2
-rw-r--r--include/net/bluetooth/hci.h1
-rw-r--r--include/net/bluetooth/hci_core.h3
-rw-r--r--include/net/bond_3ad.h1
-rw-r--r--include/net/bonding.h1
-rw-r--r--include/net/cfg80211.h8
-rw-r--r--include/net/checksum.h17
-rw-r--r--include/net/codel.h4
-rw-r--r--include/net/devlink.h140
-rw-r--r--include/net/dsa.h15
-rw-r--r--include/net/dst.h12
-rw-r--r--include/net/dst_cache.h97
-rw-r--r--include/net/dst_metadata.h6
-rw-r--r--include/net/flow_dissector.h13
-rw-r--r--include/net/genetlink.h4
-rw-r--r--include/net/hwbm.h28
-rw-r--r--include/net/inet6_hashtables.h13
-rw-r--r--include/net/inet_frag.h1
-rw-r--r--include/net/inet_hashtables.h25
-rw-r--r--include/net/ip.h8
-rw-r--r--include/net/ip6_checksum.h3
-rw-r--r--include/net/ip6_tunnel.h14
-rw-r--r--include/net/ip_tunnels.h55
-rw-r--r--include/net/ip_vs.h17
-rw-r--r--include/net/ipv6.h8
-rw-r--r--include/net/kcm.h226
-rw-r--r--include/net/l3mdev.h4
-rw-r--r--include/net/lwtunnel.h4
-rw-r--r--include/net/mac80211.h198
-rw-r--r--include/net/mac802154.h15
-rw-r--r--include/net/netfilter/nft_masq.h4
-rw-r--r--include/net/netns/ipv4.h19
-rw-r--r--include/net/netns/ipv6.h3
-rw-r--r--include/net/phonet/phonet.h2
-rw-r--r--include/net/ping.h2
-rw-r--r--include/net/pkt_cls.h65
-rw-r--r--include/net/raw.h2
-rw-r--r--include/net/route.h5
-rw-r--r--include/net/sch_generic.h26
-rw-r--r--include/net/sctp/sm.h2
-rw-r--r--include/net/sctp/structs.h11
-rw-r--r--include/net/sock.h6
-rw-r--r--include/net/tc_act/tc_gact.h16
-rw-r--r--include/net/tc_act/tc_ife.h61
-rw-r--r--include/net/tc_act/tc_skbedit.h16
-rw-r--r--include/net/tcp.h53
-rw-r--r--include/net/udp.h3
-rw-r--r--include/net/udp_tunnel.h6
-rw-r--r--include/net/vxlan.h187
-rw-r--r--include/rdma/ib_addr.h14
-rw-r--r--include/rxrpc/packet.h15
-rw-r--r--include/trace/events/sunvnet.h139
-rw-r--r--include/uapi/asm-generic/socket.h2
-rw-r--r--include/uapi/linux/Kbuild1
-rw-r--r--include/uapi/linux/bpf.h52
-rw-r--r--include/uapi/linux/devlink.h72
-rw-r--r--include/uapi/linux/ethtool.h437
-rw-r--r--include/uapi/linux/genetlink.h1
-rw-r--r--include/uapi/linux/if.h2
-rw-r--r--include/uapi/linux/if_bridge.h37
-rw-r--r--include/uapi/linux/if_ether.h1
-rw-r--r--include/uapi/linux/if_link.h43
-rw-r--r--include/uapi/linux/if_macsec.h161
-rw-r--r--include/uapi/linux/ip.h2
-rw-r--r--include/uapi/linux/ipv6.h3
-rw-r--r--include/uapi/linux/kcm.h40
-rw-r--r--include/uapi/linux/kernel.h1
-rw-r--r--include/uapi/linux/mroute6.h9
-rw-r--r--include/uapi/linux/netconf.h1
-rw-r--r--include/uapi/linux/netfilter/nf_conntrack_common.h12
-rw-r--r--include/uapi/linux/netfilter/nf_tables.h6
-rw-r--r--include/uapi/linux/netlink.h4
-rw-r--r--include/uapi/linux/netlink_diag.h2
-rw-r--r--include/uapi/linux/nl80211.h14
-rw-r--r--include/uapi/linux/openvswitch.h49
-rw-r--r--include/uapi/linux/pkt_cls.h3
-rw-r--r--include/uapi/linux/rfkill.h2
-rw-r--r--include/uapi/linux/tc_act/tc_ife.h38
-rw-r--r--include/uapi/linux/tcp.h5
-rw-r--r--include/xen/interface/io/netif.h861
130 files changed, 4241 insertions, 954 deletions
diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h
index 59811df58c5b..3150cbd8eb21 100644
--- a/include/asm-generic/checksum.h
+++ b/include/asm-generic/checksum.h
@@ -65,14 +65,14 @@ static inline __sum16 csum_fold(__wsum csum)
* returns a 16-bit checksum, already complemented
*/
extern __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
- unsigned short proto, __wsum sum);
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+ __u8 proto, __wsum sum);
#endif
#ifndef csum_tcpudp_magic
static inline __sum16
-csum_tcpudp_magic(__be32 saddr, __be32 daddr, unsigned short len,
- unsigned short proto, __wsum sum)
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+ __u8 proto, __wsum sum)
{
return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
}
diff --git a/include/dt-bindings/clock/rk3036-cru.h b/include/dt-bindings/clock/rk3036-cru.h
index ebc7a7b43f52..de44109a3a04 100644
--- a/include/dt-bindings/clock/rk3036-cru.h
+++ b/include/dt-bindings/clock/rk3036-cru.h
@@ -54,6 +54,7 @@
#define SCLK_PVTM_VIDEO 125
#define SCLK_MAC 151
#define SCLK_MACREF 152
+#define SCLK_MACPLL 153
#define SCLK_SFC 160
/* aclk gates */
@@ -92,6 +93,7 @@
#define HCLK_SDMMC 456
#define HCLK_SDIO 457
#define HCLK_EMMC 459
+#define HCLK_MAC 460
#define HCLK_I2S 462
#define HCLK_LCDC 465
#define HCLK_ROM 467
diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h
index 3feb1b2d75d8..0367c63f5960 100644
--- a/include/linux/bcma/bcma.h
+++ b/include/linux/bcma/bcma.h
@@ -151,6 +151,8 @@ struct bcma_host_ops {
#define BCMA_CORE_PCIE2 0x83C /* PCI Express Gen2 */
#define BCMA_CORE_USB30_DEV 0x83D
#define BCMA_CORE_ARM_CR4 0x83E
+#define BCMA_CORE_GCI 0x840
+#define BCMA_CORE_CMEM 0x846 /* CNDS DDR2/3 memory controller */
#define BCMA_CORE_ARM_CA7 0x847
#define BCMA_CORE_SYS_MEM 0x849
#define BCMA_CORE_DEFAULT 0xFFF
@@ -199,6 +201,7 @@ struct bcma_host_ops {
#define BCMA_PKG_ID_BCM4707 1
#define BCMA_PKG_ID_BCM4708 2
#define BCMA_PKG_ID_BCM4709 0
+#define BCMA_CHIP_ID_BCM47094 53030
#define BCMA_CHIP_ID_BCM53018 53018
/* Board types (on PCI usually equals to the subsystem dev id) */
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index db51a6ffb7d6..846513c73606 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -217,6 +217,11 @@
#define BCMA_CC_CLKDIV_JTAG_SHIFT 8
#define BCMA_CC_CLKDIV_UART 0x000000FF
#define BCMA_CC_CAP_EXT 0x00AC /* Capabilities */
+#define BCMA_CC_CAP_EXT_SECI_PRESENT 0x00000001
+#define BCMA_CC_CAP_EXT_GSIO_PRESENT 0x00000002
+#define BCMA_CC_CAP_EXT_GCI_PRESENT 0x00000004
+#define BCMA_CC_CAP_EXT_SECI_PUART_PRESENT 0x00000008 /* UART present */
+#define BCMA_CC_CAP_EXT_AOB_PRESENT 0x00000040
#define BCMA_CC_PLLONDELAY 0x00B0 /* Rev >= 4 only */
#define BCMA_CC_FREFSELDELAY 0x00B4 /* Rev >= 4 only */
#define BCMA_CC_SLOWCLKCTL 0x00B8 /* 6 <= Rev <= 9 only */
@@ -351,12 +356,12 @@
#define BCMA_CC_PMU_RES_REQTS 0x0640 /* PMU res req timer sel */
#define BCMA_CC_PMU_RES_REQT 0x0644 /* PMU res req timer */
#define BCMA_CC_PMU_RES_REQM 0x0648 /* PMU res req mask */
-#define BCMA_CC_CHIPCTL_ADDR 0x0650
-#define BCMA_CC_CHIPCTL_DATA 0x0654
-#define BCMA_CC_REGCTL_ADDR 0x0658
-#define BCMA_CC_REGCTL_DATA 0x065C
-#define BCMA_CC_PLLCTL_ADDR 0x0660
-#define BCMA_CC_PLLCTL_DATA 0x0664
+#define BCMA_CC_PMU_CHIPCTL_ADDR 0x0650
+#define BCMA_CC_PMU_CHIPCTL_DATA 0x0654
+#define BCMA_CC_PMU_REGCTL_ADDR 0x0658
+#define BCMA_CC_PMU_REGCTL_DATA 0x065C
+#define BCMA_CC_PMU_PLLCTL_ADDR 0x0660
+#define BCMA_CC_PMU_PLLCTL_DATA 0x0664
#define BCMA_CC_PMU_STRAPOPT 0x0668 /* (corerev >= 28) */
#define BCMA_CC_PMU_XTAL_FREQ 0x066C /* (pmurev >= 10) */
#define BCMA_CC_PMU_XTAL_FREQ_ILPCTL_MASK 0x00001FFF
@@ -566,17 +571,16 @@
* Check availability with ((struct bcma_chipcommon)->capabilities & BCMA_CC_CAP_PMU)
*/
struct bcma_chipcommon_pmu {
+ struct bcma_device *core; /* Can be separated core or just ChipCommon one */
u8 rev; /* PMU revision */
u32 crystalfreq; /* The active crystal frequency (in kHz) */
};
-#ifdef CONFIG_BCMA_DRIVER_MIPS
+#ifdef CONFIG_BCMA_PFLASH
struct bcma_pflash {
bool present;
- u8 buswidth;
- u32 window;
- u32 window_size;
};
+#endif
#ifdef CONFIG_BCMA_SFLASH
struct mtd_info;
@@ -600,6 +604,7 @@ struct bcma_nflash {
};
#endif
+#ifdef CONFIG_BCMA_DRIVER_MIPS
struct bcma_serial_port {
void *regs;
unsigned long clockspeed;
@@ -619,8 +624,9 @@ struct bcma_drv_cc {
/* Fast Powerup Delay constant */
u16 fast_pwrup_delay;
struct bcma_chipcommon_pmu pmu;
-#ifdef CONFIG_BCMA_DRIVER_MIPS
+#ifdef CONFIG_BCMA_PFLASH
struct bcma_pflash pflash;
+#endif
#ifdef CONFIG_BCMA_SFLASH
struct bcma_sflash sflash;
#endif
@@ -628,6 +634,7 @@ struct bcma_drv_cc {
struct bcma_nflash nflash;
#endif
+#ifdef CONFIG_BCMA_DRIVER_MIPS
int nr_serial_ports;
struct bcma_serial_port serial_ports[4];
#endif /* CONFIG_BCMA_DRIVER_MIPS */
@@ -660,6 +667,19 @@ struct bcma_drv_cc_b {
#define bcma_cc_maskset32(cc, offset, mask, set) \
bcma_cc_write32(cc, offset, (bcma_cc_read32(cc, offset) & (mask)) | (set))
+/* PMU registers access */
+#define bcma_pmu_read32(cc, offset) \
+ bcma_read32((cc)->pmu.core, offset)
+#define bcma_pmu_write32(cc, offset, val) \
+ bcma_write32((cc)->pmu.core, offset, val)
+
+#define bcma_pmu_mask32(cc, offset, mask) \
+ bcma_pmu_write32(cc, offset, bcma_pmu_read32(cc, offset) & (mask))
+#define bcma_pmu_set32(cc, offset, set) \
+ bcma_pmu_write32(cc, offset, bcma_pmu_read32(cc, offset) | (set))
+#define bcma_pmu_maskset32(cc, offset, mask, set) \
+ bcma_pmu_write32(cc, offset, (bcma_pmu_read32(cc, offset) & (mask)) | (set))
+
extern u32 bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks);
extern u32 bcma_chipco_get_alp_clock(struct bcma_drv_cc *cc);
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 9653fdb76a42..e9b0b9ab07e5 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -59,6 +59,8 @@
* bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region
* bitmap_release_region(bitmap, pos, order) Free specified bit region
* bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region
+ * bitmap_from_u32array(dst, nbits, buf, nwords) *dst = *buf (nwords 32b words)
+ * bitmap_to_u32array(buf, nwords, src, nbits) *buf = *dst (nwords 32b words)
*/
/*
@@ -163,6 +165,14 @@ extern void bitmap_fold(unsigned long *dst, const unsigned long *orig,
extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order);
extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order);
extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order);
+extern unsigned int bitmap_from_u32array(unsigned long *bitmap,
+ unsigned int nbits,
+ const u32 *buf,
+ unsigned int nwords);
+extern unsigned int bitmap_to_u32array(u32 *buf,
+ unsigned int nwords,
+ const unsigned long *bitmap,
+ unsigned int nbits);
#ifdef __BIG_ENDIAN
extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits);
#else
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 83d1926c61e4..21ee41b92e8a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -10,6 +10,7 @@
#include <uapi/linux/bpf.h>
#include <linux/workqueue.h>
#include <linux/file.h>
+#include <linux/percpu.h>
struct bpf_map;
@@ -36,6 +37,7 @@ struct bpf_map {
u32 key_size;
u32 value_size;
u32 max_entries;
+ u32 map_flags;
u32 pages;
struct user_struct *user;
const struct bpf_map_ops *ops;
@@ -65,6 +67,7 @@ enum bpf_arg_type {
*/
ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */
ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */
+ ARG_CONST_STACK_SIZE_OR_ZERO, /* number of bytes accessed from stack or 0 */
ARG_PTR_TO_CTX, /* pointer to context */
ARG_ANYTHING, /* any (initialized) argument is ok */
@@ -151,6 +154,7 @@ struct bpf_array {
union {
char value[0] __aligned(8);
void *ptrs[0] __aligned(8);
+ void __percpu *pptrs[0] __aligned(8);
};
};
#define MAX_TAIL_CALL_CNT 32
@@ -161,6 +165,8 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f
const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
#ifdef CONFIG_BPF_SYSCALL
+DECLARE_PER_CPU(int, bpf_prog_active);
+
void bpf_register_prog_type(struct bpf_prog_type_list *tl);
void bpf_register_map_type(struct bpf_map_type_list *tl);
@@ -173,6 +179,7 @@ struct bpf_map *__bpf_map_get(struct fd f);
void bpf_map_inc(struct bpf_map *map, bool uref);
void bpf_map_put_with_uref(struct bpf_map *map);
void bpf_map_put(struct bpf_map *map);
+int bpf_map_precharge_memlock(u32 pages);
extern int sysctl_unprivileged_bpf_disabled;
@@ -182,6 +189,30 @@ int bpf_prog_new_fd(struct bpf_prog *prog);
int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
int bpf_obj_get_user(const char __user *pathname);
+int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
+int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
+int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
+ u64 flags);
+int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
+ u64 flags);
+int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
+
+/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
+ * forced to use 'long' read/writes to try to atomically copy long counters.
+ * Best-effort only. No barriers here, since it _will_ race with concurrent
+ * updates from BPF programs. Called from bpf syscall and mostly used with
+ * size 8 or 16 bytes, so ask compiler to inline it.
+ */
+static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
+{
+ const long *lsrc = src;
+ long *ldst = dst;
+
+ size /= sizeof(long);
+ while (size--)
+ *ldst++ = *lsrc++;
+}
+
/* verify correctness of eBPF program */
int bpf_check(struct bpf_prog **fp, union bpf_attr *attr);
#else
@@ -213,6 +244,7 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
extern const struct bpf_func_proto bpf_get_current_comm_proto;
extern const struct bpf_func_proto bpf_skb_vlan_push_proto;
extern const struct bpf_func_proto bpf_skb_vlan_pop_proto;
+extern const struct bpf_func_proto bpf_get_stackid_proto;
/* Shared helpers among cBPF and eBPF. */
void bpf_user_rnd_init_once(void);
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 653dc9c4ebac..e2b7bf27c03e 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -12,6 +12,7 @@
#ifndef _LINUX_ETHTOOL_H
#define _LINUX_ETHTOOL_H
+#include <linux/bitmap.h>
#include <linux/compat.h>
#include <uapi/linux/ethtool.h>
@@ -40,9 +41,6 @@ struct compat_ethtool_rxnfc {
#include <linux/rculist.h>
-extern int __ethtool_get_settings(struct net_device *dev,
- struct ethtool_cmd *cmd);
-
/**
* enum ethtool_phys_id_state - indicator state for physical identification
* @ETHTOOL_ID_INACTIVE: Physical ID indicator should be deactivated
@@ -97,13 +95,70 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
return index % n_rx_rings;
}
+/* number of link mode bits/ulongs handled internally by kernel */
+#define __ETHTOOL_LINK_MODE_MASK_NBITS \
+ (__ETHTOOL_LINK_MODE_LAST + 1)
+
+/* declare a link mode bitmap */
+#define __ETHTOOL_DECLARE_LINK_MODE_MASK(name) \
+ DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS)
+
+/* drivers must ignore base.cmd and base.link_mode_masks_nwords
+ * fields, but they are allowed to overwrite them (will be ignored).
+ */
+struct ethtool_link_ksettings {
+ struct ethtool_link_settings base;
+ struct {
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising);
+ } link_modes;
+};
+
+/**
+ * ethtool_link_ksettings_zero_link_mode - clear link_ksettings link mode mask
+ * @ptr : pointer to struct ethtool_link_ksettings
+ * @name : one of supported/advertising/lp_advertising
+ */
+#define ethtool_link_ksettings_zero_link_mode(ptr, name) \
+ bitmap_zero((ptr)->link_modes.name, __ETHTOOL_LINK_MODE_MASK_NBITS)
+
+/**
+ * ethtool_link_ksettings_add_link_mode - set bit in link_ksettings
+ * link mode mask
+ * @ptr : pointer to struct ethtool_link_ksettings
+ * @name : one of supported/advertising/lp_advertising
+ * @mode : one of the ETHTOOL_LINK_MODE_*_BIT
+ * (not atomic, no bound checking)
+ */
+#define ethtool_link_ksettings_add_link_mode(ptr, name, mode) \
+ __set_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name)
+
+/**
+ * ethtool_link_ksettings_test_link_mode - test bit in ksettings link mode mask
+ * @ptr : pointer to struct ethtool_link_ksettings
+ * @name : one of supported/advertising/lp_advertising
+ * @mode : one of the ETHTOOL_LINK_MODE_*_BIT
+ * (not atomic, no bound checking)
+ *
+ * Returns true/false.
+ */
+#define ethtool_link_ksettings_test_link_mode(ptr, name, mode) \
+ test_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name)
+
+extern int
+__ethtool_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *link_ksettings);
+
/**
* struct ethtool_ops - optional netdev operations
- * @get_settings: Get various device settings including Ethernet link
+ * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings
+ * API. Get various device settings including Ethernet link
* settings. The @cmd parameter is expected to have been cleared
- * before get_settings is called. Returns a negative error code or
- * zero.
- * @set_settings: Set various device settings including Ethernet link
+ * before get_settings is called. Returns a negative error code
+ * or zero.
+ * @set_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings
+ * API. Set various device settings including Ethernet link
* settings. Returns a negative error code or zero.
* @get_drvinfo: Report driver/device information. Should only set the
* @driver, @version, @fw_version and @bus_info fields. If not
@@ -201,6 +256,29 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
* @get_module_eeprom: Get the eeprom information from the plug-in module
* @get_eee: Get Energy-Efficient (EEE) supported and status.
* @set_eee: Set EEE status (enable/disable) as well as LPI timers.
+ * @get_per_queue_coalesce: Get interrupt coalescing parameters per queue.
+ * It must check that the given queue number is valid. If neither a RX nor
+ * a TX queue has this number, return -EINVAL. If only a RX queue or a TX
+ * queue has this number, set the inapplicable fields to ~0 and return 0.
+ * Returns a negative error code or zero.
+ * @set_per_queue_coalesce: Set interrupt coalescing parameters per queue.
+ * It must check that the given queue number is valid. If neither a RX nor
+ * a TX queue has this number, return -EINVAL. If only a RX queue or a TX
+ * queue has this number, ignore the inapplicable fields.
+ * Returns a negative error code or zero.
+ * @get_link_ksettings: When defined, takes precedence over the
+ * %get_settings method. Get various device settings
+ * including Ethernet link settings. The %cmd and
+ * %link_mode_masks_nwords fields should be ignored (use
+ * %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), any
+ * change to them will be overwritten by kernel. Returns a
+ * negative error code or zero.
+ * @set_link_ksettings: When defined, takes precedence over the
+ * %set_settings method. Set various device settings including
+ * Ethernet link settings. The %cmd and %link_mode_masks_nwords
+ * fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS
+ * instead of the latter), any change to them will be overwritten
+ * by kernel. Returns a negative error code or zero.
*
* All operations are optional (i.e. the function pointer may be set
* to %NULL) and callers must take this into account. Callers must
@@ -279,7 +357,13 @@ struct ethtool_ops {
const struct ethtool_tunable *, void *);
int (*set_tunable)(struct net_device *,
const struct ethtool_tunable *, const void *);
-
-
+ int (*get_per_queue_coalesce)(struct net_device *, u32,
+ struct ethtool_coalesce *);
+ int (*set_per_queue_coalesce)(struct net_device *, u32,
+ struct ethtool_coalesce *);
+ int (*get_link_ksettings)(struct net_device *,
+ struct ethtool_link_ksettings *);
+ int (*set_link_ksettings)(struct net_device *,
+ const struct ethtool_link_ksettings *);
};
#endif /* _LINUX_ETHTOOL_H */
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 452c0b0d2f32..3b1f6cef9513 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -163,6 +163,14 @@ 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 */
+#define IEEE80211_MAX_MPDU_LEN_HT_3839 3839
+#define IEEE80211_MAX_MPDU_LEN_HT_7935 7935
+
+#define IEEE80211_MAX_MPDU_LEN_VHT_3895 3895
+#define IEEE80211_MAX_MPDU_LEN_VHT_7991 7991
+#define IEEE80211_MAX_MPDU_LEN_VHT_11454 11454
+
#define IEEE80211_MAX_SSID_LEN 32
#define IEEE80211_MAX_MESH_ID_LEN 32
@@ -843,6 +851,8 @@ enum ieee80211_vht_opmode_bits {
};
#define WLAN_SA_QUERY_TR_ID_LEN 2
+#define WLAN_MEMBERSHIP_LEN 8
+#define WLAN_USER_POSITION_LEN 16
/**
* struct ieee80211_tpc_report_ie
@@ -991,6 +1001,11 @@ struct ieee80211_mgmt {
} __packed vht_opmode_notif;
struct {
u8 action_code;
+ u8 membership[WLAN_MEMBERSHIP_LEN];
+ u8 position[WLAN_USER_POSITION_LEN];
+ } __packed vht_group_notif;
+ struct {
+ u8 action_code;
u8 dialog_token;
u8 tpc_elem_id;
u8 tpc_elem_length;
@@ -1498,6 +1513,7 @@ struct ieee80211_vht_operation {
#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000
#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001
#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 0x00000002
+#define IEEE80211_VHT_CAP_MAX_MPDU_MASK 0x00000003
#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004
#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008
#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C
@@ -2079,6 +2095,16 @@ enum ieee80211_tdls_actioncode {
#define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(5)
#define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6)
+/* Defines the maximal number of MSDUs in an A-MSDU. */
+#define WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB BIT(7)
+#define WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB BIT(0)
+
+/*
+ * Fine Timing Measurement Initiator - bit 71 of @WLAN_EID_EXT_CAPABILITY
+ * information element
+ */
+#define WLAN_EXT_CAPA9_FTM_INITIATOR BIT(7)
+
/* TDLS specific payload type in the LLC/SNAP header */
#define WLAN_TDLS_SNAP_RFTYPE 0x2
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index a338a688ee4a..dcb89e3515db 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -46,10 +46,6 @@ struct br_ip_list {
#define BR_LEARNING_SYNC BIT(9)
#define BR_PROXYARP_WIFI BIT(10)
-/* values as per ieee8021QBridgeFdbAgingTime */
-#define BR_MIN_AGEING_TIME (10 * HZ)
-#define BR_MAX_AGEING_TIME (1000000 * HZ)
-
#define BR_DEFAULT_AGEING_TIME (300 * HZ)
extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *));
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index b84e49c3a738..174f43f43aff 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -24,6 +24,7 @@ struct team_pcpu_stats {
struct u64_stats_sync syncp;
u32 rx_dropped;
u32 tx_dropped;
+ u32 rx_nohandler;
};
struct team;
diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index 9c9de11549a7..12f6fba6d21a 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -37,11 +37,6 @@ static inline struct igmpv3_query *
return (struct igmpv3_query *)skb_transport_header(skb);
}
-extern int sysctl_igmp_llm_reports;
-extern int sysctl_igmp_max_memberships;
-extern int sysctl_igmp_max_msf;
-extern int sysctl_igmp_qrv;
-
struct ip_sf_socklist {
unsigned int sl_max;
unsigned int sl_count;
diff --git a/include/linux/inet_lro.h b/include/linux/inet_lro.h
deleted file mode 100644
index 9a715cfa1fe3..000000000000
--- a/include/linux/inet_lro.h
+++ /dev/null
@@ -1,142 +0,0 @@
-/*
- * linux/include/linux/inet_lro.h
- *
- * Large Receive Offload (ipv4 / tcp)
- *
- * (C) Copyright IBM Corp. 2007
- *
- * Authors:
- * Jan-Bernd Themann <themann@de.ibm.com>
- * Christoph Raisch <raisch@de.ibm.com>
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#ifndef __INET_LRO_H_
-#define __INET_LRO_H_
-
-#include <net/ip.h>
-#include <net/tcp.h>
-
-/*
- * LRO statistics
- */
-
-struct net_lro_stats {
- unsigned long aggregated;
- unsigned long flushed;
- unsigned long no_desc;
-};
-
-/*
- * LRO descriptor for a tcp session
- */
-struct net_lro_desc {
- struct sk_buff *parent;
- struct sk_buff *last_skb;
- struct skb_frag_struct *next_frag;
- struct iphdr *iph;
- struct tcphdr *tcph;
- __wsum data_csum;
- __be32 tcp_rcv_tsecr;
- __be32 tcp_rcv_tsval;
- __be32 tcp_ack;
- u32 tcp_next_seq;
- u32 skb_tot_frags_len;
- u16 ip_tot_len;
- u16 tcp_saw_tstamp; /* timestamps enabled */
- __be16 tcp_window;
- int pkt_aggr_cnt; /* counts aggregated packets */
- int vlan_packet;
- int mss;
- int active;
-};
-
-/*
- * Large Receive Offload (LRO) Manager
- *
- * Fields must be set by driver
- */
-
-struct net_lro_mgr {
- struct net_device *dev;
- struct net_lro_stats stats;
-
- /* LRO features */
- unsigned long features;
-#define LRO_F_NAPI 1 /* Pass packets to stack via NAPI */
-#define LRO_F_EXTRACT_VLAN_ID 2 /* Set flag if VLAN IDs are extracted
- from received packets and eth protocol
- is still ETH_P_8021Q */
-
- /*
- * Set for generated SKBs that are not added to
- * the frag list in fragmented mode
- */
- u32 ip_summed;
- u32 ip_summed_aggr; /* Set in aggregated SKBs: CHECKSUM_UNNECESSARY
- * or CHECKSUM_NONE */
-
- int max_desc; /* Max number of LRO descriptors */
- int max_aggr; /* Max number of LRO packets to be aggregated */
-
- int frag_align_pad; /* Padding required to properly align layer 3
- * headers in generated skb when using frags */
-
- struct net_lro_desc *lro_arr; /* Array of LRO descriptors */
-
- /*
- * Optimized driver functions
- *
- * get_skb_header: returns tcp and ip header for packet in SKB
- */
- int (*get_skb_header)(struct sk_buff *skb, void **ip_hdr,
- void **tcpudp_hdr, u64 *hdr_flags, void *priv);
-
- /* hdr_flags: */
-#define LRO_IPV4 1 /* ip_hdr is IPv4 header */
-#define LRO_TCP 2 /* tcpudp_hdr is TCP header */
-
- /*
- * get_frag_header: returns mac, tcp and ip header for packet in SKB
- *
- * @hdr_flags: Indicate what kind of LRO has to be done
- * (IPv4/IPv6/TCP/UDP)
- */
- int (*get_frag_header)(struct skb_frag_struct *frag, void **mac_hdr,
- void **ip_hdr, void **tcpudp_hdr, u64 *hdr_flags,
- void *priv);
-};
-
-/*
- * Processes a SKB
- *
- * @lro_mgr: LRO manager to use
- * @skb: SKB to aggregate
- * @priv: Private data that may be used by driver functions
- * (for example get_tcp_ip_hdr)
- */
-
-void lro_receive_skb(struct net_lro_mgr *lro_mgr,
- struct sk_buff *skb,
- void *priv);
-/*
- * Forward all aggregated SKBs held by lro_mgr to network stack
- */
-
-void lro_flush_all(struct net_lro_mgr *lro_mgr);
-
-#endif
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 402753bccafa..7edc14fb66b6 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -50,16 +50,19 @@ struct ipv6_devconf {
__s32 mc_forwarding;
#endif
__s32 disable_ipv6;
+ __s32 drop_unicast_in_l2_multicast;
__s32 accept_dad;
__s32 force_tllao;
__s32 ndisc_notify;
__s32 suppress_frag_ndisc;
__s32 accept_ra_mtu;
+ __s32 drop_unsolicited_na;
struct ipv6_stable_secret {
bool initialized;
struct in6_addr secret;
} stable_secret;
__s32 use_oif_addrs_only;
+ __s32 keep_addr_on_down;
void *sysctl;
};
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index f4fa2b29c38c..b82646ee70eb 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -64,7 +64,7 @@
#define round_down(x, y) ((x) & ~__round_mask(x, y))
#define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
-#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
+#define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP
#define DIV_ROUND_UP_ULL(ll,d) \
({ unsigned long long _tmp = (ll)+(d)-1; do_div(_tmp, d); _tmp; })
diff --git a/include/linux/mbus.h b/include/linux/mbus.h
index 1f7bc630d225..ea34a867caa0 100644
--- a/include/linux/mbus.h
+++ b/include/linux/mbus.h
@@ -69,6 +69,9 @@ static inline const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(vo
int mvebu_mbus_save_cpu_target(u32 *store_addr);
void mvebu_mbus_get_pcie_mem_aperture(struct resource *res);
void mvebu_mbus_get_pcie_io_aperture(struct resource *res);
+int mvebu_mbus_get_dram_win_info(phys_addr_t phyaddr, u8 *target, u8 *attr);
+int mvebu_mbus_get_io_win_info(phys_addr_t phyaddr, u32 *size, u8 *target,
+ u8 *attr);
int mvebu_mbus_add_window_remap_by_id(unsigned int target,
unsigned int attribute,
phys_addr_t base, size_t size,
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 2e8af001c5da..bd0e7075ea6d 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -33,6 +33,7 @@
#ifndef MLX4_DRIVER_H
#define MLX4_DRIVER_H
+#include <net/devlink.h>
#include <linux/mlx4/device.h>
struct mlx4_dev;
@@ -89,6 +90,8 @@ int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p);
void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port);
+struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port);
+
static inline u64 mlx4_mac_to_u64(u8 *addr)
{
u64 mac = 0;
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 9566b3b3b2c5..02ac3000ee3c 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -374,6 +374,12 @@ enum {
};
enum {
+ MLX5_BW_NO_LIMIT = 0,
+ MLX5_100_MBPS_UNIT = 3,
+ MLX5_GBPS_UNIT = 4,
+};
+
+enum {
MLX5_MAX_PAGE_SHIFT = 31
};
@@ -1200,6 +1206,17 @@ enum {
MLX5_RQC_RQ_TYPE_MEMORY_RQ_RPM = 0x1,
};
+enum mlx5_wol_mode {
+ MLX5_WOL_DISABLE = 0,
+ MLX5_WOL_SECURED_MAGIC = 1 << 1,
+ MLX5_WOL_MAGIC = 1 << 2,
+ MLX5_WOL_ARP = 1 << 3,
+ MLX5_WOL_BROADCAST = 1 << 4,
+ MLX5_WOL_MULTICAST = 1 << 5,
+ MLX5_WOL_UNICAST = 1 << 6,
+ MLX5_WOL_PHY_ACTIVITY = 1 << 7,
+};
+
/* MLX5 DEV CAPs */
/* TODO: EAT.ME */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 9108904a6a56..3a954465b2bf 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -54,7 +54,7 @@ enum {
/* one minute for the sake of bringup. Generally, commands must always
* complete and we may need to increase this timeout value
*/
- MLX5_CMD_TIMEOUT_MSEC = 7200 * 1000,
+ MLX5_CMD_TIMEOUT_MSEC = 60 * 1000,
MLX5_CMD_WQ_MAX_NAME = 32,
};
@@ -99,6 +99,8 @@ enum {
};
enum {
+ MLX5_REG_QETCR = 0x4005,
+ MLX5_REG_QTCT = 0x400a,
MLX5_REG_PCAP = 0x5001,
MLX5_REG_PMTU = 0x5003,
MLX5_REG_PTYS = 0x5004,
@@ -458,8 +460,6 @@ struct mlx5_priv {
struct mlx5_uuar_info uuari;
MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock);
- struct io_mapping *bf_mapping;
-
/* pages stuff */
struct workqueue_struct *pg_wq;
struct rb_root page_root;
@@ -717,7 +717,8 @@ int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari);
int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari);
-int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar);
+int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar,
+ bool map_wc);
void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar);
void mlx5_health_cleanup(struct mlx5_core_dev *dev);
int mlx5_health_init(struct mlx5_core_dev *dev);
@@ -796,37 +797,6 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
int size_in, void *data_out, int size_out,
u16 reg_num, int arg, int write);
-int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
-int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
- int ptys_size, int proto_mask, u8 local_port);
-int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev,
- u32 *proto_cap, int proto_mask);
-int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev,
- u32 *proto_admin, int proto_mask);
-int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
- u8 *link_width_oper, u8 local_port);
-int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev,
- u8 *proto_oper, int proto_mask,
- u8 local_port);
-int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin,
- int proto_mask);
-int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
- enum mlx5_port_status status);
-int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
- enum mlx5_port_status *status);
-
-int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port);
-void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port);
-void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu,
- u8 port);
-
-int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
- u8 *vl_hw_cap, u8 local_port);
-
-int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause);
-int mlx5_query_port_pause(struct mlx5_core_dev *dev,
- u32 *rx_pause, u32 *tx_pause);
-
int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 9b8a02b7880f..e52730e01ed6 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -166,6 +166,8 @@ enum {
MLX5_CMD_OP_SET_L2_TABLE_ENTRY = 0x829,
MLX5_CMD_OP_QUERY_L2_TABLE_ENTRY = 0x82a,
MLX5_CMD_OP_DELETE_L2_TABLE_ENTRY = 0x82b,
+ MLX5_CMD_OP_SET_WOL_ROL = 0x830,
+ MLX5_CMD_OP_QUERY_WOL_ROL = 0x831,
MLX5_CMD_OP_CREATE_TIR = 0x900,
MLX5_CMD_OP_MODIFY_TIR = 0x901,
MLX5_CMD_OP_DESTROY_TIR = 0x902,
@@ -730,7 +732,19 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 reserved_at_1bf[0x3];
u8 log_max_msg[0x5];
- u8 reserved_at_1c7[0x18];
+ u8 reserved_at_1c7[0x4];
+ u8 max_tc[0x4];
+ u8 reserved_at_1cf[0x6];
+ u8 rol_s[0x1];
+ u8 rol_g[0x1];
+ u8 reserved_at_1d7[0x1];
+ u8 wol_s[0x1];
+ u8 wol_g[0x1];
+ u8 wol_a[0x1];
+ u8 wol_b[0x1];
+ u8 wol_m[0x1];
+ u8 wol_u[0x1];
+ u8 wol_p[0x1];
u8 stat_rate_support[0x10];
u8 reserved_at_1ef[0xc];
@@ -6911,6 +6925,54 @@ struct mlx5_ifc_mtt_bits {
u8 rd_en[0x1];
};
+struct mlx5_ifc_query_wol_rol_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x10];
+ u8 rol_mode[0x8];
+ u8 wol_mode[0x8];
+
+ u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_query_wol_rol_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_set_wol_rol_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_set_wol_rol_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 rol_mode_valid[0x1];
+ u8 wol_mode_valid[0x1];
+ u8 reserved_at_42[0xe];
+ u8 rol_mode[0x8];
+ u8 wol_mode[0x8];
+
+ u8 reserved_at_60[0x20];
+};
+
enum {
MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER = 0x0,
MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED = 0x1,
@@ -7102,4 +7164,49 @@ struct mlx5_ifc_modify_flow_table_in_bits {
u8 reserved_at_100[0x100];
};
+struct mlx5_ifc_ets_tcn_config_reg_bits {
+ u8 g[0x1];
+ u8 b[0x1];
+ u8 r[0x1];
+ u8 reserved_at_3[0x9];
+ u8 group[0x4];
+ u8 reserved_at_10[0x9];
+ u8 bw_allocation[0x7];
+
+ u8 reserved_at_20[0xc];
+ u8 max_bw_units[0x4];
+ u8 reserved_at_30[0x8];
+ u8 max_bw_value[0x8];
+};
+
+struct mlx5_ifc_ets_global_config_reg_bits {
+ u8 reserved_at_0[0x2];
+ u8 r[0x1];
+ u8 reserved_at_3[0x1d];
+
+ u8 reserved_at_20[0xc];
+ u8 max_bw_units[0x4];
+ u8 reserved_at_30[0x8];
+ u8 max_bw_value[0x8];
+};
+
+struct mlx5_ifc_qetc_reg_bits {
+ u8 reserved_at_0[0x8];
+ u8 port_number[0x8];
+ u8 reserved_at_10[0x30];
+
+ struct mlx5_ifc_ets_tcn_config_reg_bits tc_configuration[0x8];
+ struct mlx5_ifc_ets_global_config_reg_bits global_configuration;
+};
+
+struct mlx5_ifc_qtct_reg_bits {
+ u8 reserved_at_0[0x8];
+ u8 port_number[0x8];
+ u8 reserved_at_10[0xd];
+ u8 prio[0x3];
+
+ u8 reserved_at_20[0x1d];
+ u8 tclass[0x3];
+};
+
#endif /* MLX5_IFC_H */
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
new file mode 100644
index 000000000000..a1d145abd4eb
--- /dev/null
+++ b/include/linux/mlx5/port.h
@@ -0,0 +1,87 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __MLX5_PORT_H__
+#define __MLX5_PORT_H__
+
+#include <linux/mlx5/driver.h>
+
+int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
+int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
+ int ptys_size, int proto_mask, u8 local_port);
+int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev,
+ u32 *proto_cap, int proto_mask);
+int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev,
+ u32 *proto_admin, int proto_mask);
+int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
+ u8 *link_width_oper, u8 local_port);
+int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev,
+ u8 *proto_oper, int proto_mask,
+ u8 local_port);
+int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin,
+ int proto_mask);
+int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
+ enum mlx5_port_status status);
+int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
+ enum mlx5_port_status *status);
+
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port);
+void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port);
+void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu,
+ u8 port);
+
+int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
+ u8 *vl_hw_cap, u8 local_port);
+
+int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause);
+int mlx5_query_port_pause(struct mlx5_core_dev *dev,
+ u32 *rx_pause, u32 *tx_pause);
+
+int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx);
+int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx,
+ u8 *pfc_en_rx);
+
+int mlx5_max_tc(struct mlx5_core_dev *mdev);
+
+int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc);
+int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group);
+int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw);
+int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
+ u8 *max_bw_value,
+ u8 *max_bw_unit);
+int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
+ u8 *max_bw_value,
+ u8 *max_bw_unit);
+int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode);
+int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode);
+
+#endif /* __MLX5_PORT_H__ */
diff --git a/include/linux/net.h b/include/linux/net.h
index 0b4ac7da583a..49175e4ced11 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -215,6 +215,7 @@ int __sock_create(struct net *net, int family, int type, int proto,
int sock_create(int family, int type, int proto, struct socket **res);
int sock_create_kern(struct net *net, int family, int type, int proto, struct socket **res);
int sock_create_lite(int family, int type, int proto, struct socket **res);
+struct socket *sock_alloc(void);
void sock_release(struct socket *sock);
int sock_sendmsg(struct socket *sock, struct msghdr *msg);
int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index d9654f0eecb3..a734bf43d190 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -67,6 +67,8 @@ enum {
NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */
NETIF_F_BUSY_POLL_BIT, /* Busy poll */
+ NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */
+
/*
* Add your fresh new feature above and remember to update
* netdev_features_strings[] in net/core/ethtool.c and maybe
@@ -124,6 +126,7 @@ enum {
#define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX)
#define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD)
#define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL)
+#define NETIF_F_HW_TC __NETIF_F(HW_TC)
#define for_each_netdev_feature(mask_addr, bit) \
for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5440b7b705eb..be693b34662f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -51,6 +51,7 @@
#include <linux/neighbour.h>
#include <uapi/linux/netdevice.h>
#include <uapi/linux/if_bonding.h>
+#include <uapi/linux/pkt_cls.h>
struct netpoll_info;
struct device;
@@ -267,6 +268,7 @@ struct header_ops {
void (*cache_update)(struct hh_cache *hh,
const struct net_device *dev,
const unsigned char *haddr);
+ bool (*validate)(const char *ll_header, unsigned int len);
};
/* These flag bits are private to the generic network queueing
@@ -778,6 +780,27 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a,
typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
struct sk_buff *skb);
+/* These structures hold the attributes of qdisc and classifiers
+ * that are being passed to the netdevice through the setup_tc op.
+ */
+enum {
+ TC_SETUP_MQPRIO,
+ TC_SETUP_CLSU32,
+ TC_SETUP_CLSFLOWER,
+};
+
+struct tc_cls_u32_offload;
+
+struct tc_to_netdev {
+ unsigned int type;
+ union {
+ u8 tc;
+ struct tc_cls_u32_offload *cls_u32;
+ struct tc_cls_flower_offload *cls_flower;
+ };
+};
+
+
/*
* This structure defines the management hooks for network devices.
* The following hooks can be defined; unless noted otherwise, they are
@@ -1073,6 +1096,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
* This function is used to get egress tunnel information for given skb.
* This is useful for retrieving outer tunnel header parameters while
* sampling packet.
+ * void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom);
+ * This function is used to specify the headroom that the skb must
+ * consider when allocation skb during packet reception. Setting
+ * appropriate rx headroom value allows avoiding skb head copy on
+ * forward. Setting a negative value reset the rx headroom to the
+ * default value.
*
*/
struct net_device_ops {
@@ -1150,7 +1179,10 @@ struct net_device_ops {
int (*ndo_set_vf_rss_query_en)(
struct net_device *dev,
int vf, bool setting);
- int (*ndo_setup_tc)(struct net_device *dev, u8 tc);
+ int (*ndo_setup_tc)(struct net_device *dev,
+ u32 handle,
+ __be16 protocol,
+ struct tc_to_netdev *tc);
#if IS_ENABLED(CONFIG_FCOE)
int (*ndo_fcoe_enable)(struct net_device *dev);
int (*ndo_fcoe_disable)(struct net_device *dev);
@@ -1255,6 +1287,8 @@ struct net_device_ops {
bool proto_down);
int (*ndo_fill_metadata_dst)(struct net_device *dev,
struct sk_buff *skb);
+ void (*ndo_set_rx_headroom)(struct net_device *dev,
+ int needed_headroom);
};
/**
@@ -1291,6 +1325,10 @@ struct net_device_ops {
* @IFF_OPENVSWITCH: device is a Open vSwitch master
* @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device
* @IFF_TEAM: device is a team device
+ * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured
+ * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external
+ * entity (i.e. the master device for bridged veth)
+ * @IFF_MACSEC: device is a MACsec device
*/
enum netdev_priv_flags {
IFF_802_1Q_VLAN = 1<<0,
@@ -1318,6 +1356,9 @@ enum netdev_priv_flags {
IFF_OPENVSWITCH = 1<<22,
IFF_L3MDEV_SLAVE = 1<<23,
IFF_TEAM = 1<<24,
+ IFF_RXFH_CONFIGURED = 1<<25,
+ IFF_PHONY_HEADROOM = 1<<26,
+ IFF_MACSEC = 1<<27,
};
#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN
@@ -1345,6 +1386,8 @@ enum netdev_priv_flags {
#define IFF_OPENVSWITCH IFF_OPENVSWITCH
#define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE
#define IFF_TEAM IFF_TEAM
+#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED
+#define IFF_MACSEC IFF_MACSEC
/**
* struct net_device - The DEVICE structure.
@@ -1397,6 +1440,8 @@ enum netdev_priv_flags {
* do not use this in drivers
* @tx_dropped: Dropped packets by core network,
* do not use this in drivers
+ * @rx_nohandler: nohandler dropped packets by core network on
+ * inactive devices, do not use this in drivers
*
* @wireless_handlers: List of functions to handle Wireless Extensions,
* instead of ioctl,
@@ -1420,8 +1465,7 @@ enum netdev_priv_flags {
* @dma: DMA channel
* @mtu: Interface MTU value
* @type: Interface hardware type
- * @hard_header_len: Hardware header length, which means that this is the
- * minimum size of a packet.
+ * @hard_header_len: Maximum hardware header length.
*
* @needed_headroom: Extra headroom the hardware may need, but not in all
* cases can this be guaranteed
@@ -1611,6 +1655,7 @@ struct net_device {
atomic_long_t rx_dropped;
atomic_long_t tx_dropped;
+ atomic_long_t rx_nohandler;
#ifdef CONFIG_WIRELESS_EXT
const struct iw_handler_def * wireless_handlers;
@@ -1908,6 +1953,26 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
struct sk_buff *skb,
void *accel_priv);
+/* returns the headroom that the master device needs to take in account
+ * when forwarding to this dev
+ */
+static inline unsigned netdev_get_fwd_headroom(struct net_device *dev)
+{
+ return dev->priv_flags & IFF_PHONY_HEADROOM ? 0 : dev->needed_headroom;
+}
+
+static inline void netdev_set_rx_headroom(struct net_device *dev, int new_hr)
+{
+ if (dev->netdev_ops->ndo_set_rx_headroom)
+ dev->netdev_ops->ndo_set_rx_headroom(dev, new_hr);
+}
+
+/* set the device rx headroom to the dev's default */
+static inline void netdev_reset_rx_headroom(struct net_device *dev)
+{
+ netdev_set_rx_headroom(dev, -1);
+}
+
/*
* Net namespace inlines
*/
@@ -2627,6 +2692,24 @@ static inline int dev_parse_header(const struct sk_buff *skb,
return dev->header_ops->parse(skb, haddr);
}
+/* ll_header must have at least hard_header_len allocated */
+static inline bool dev_validate_header(const struct net_device *dev,
+ char *ll_header, int len)
+{
+ if (likely(len >= dev->hard_header_len))
+ return true;
+
+ if (capable(CAP_SYS_RAWIO)) {
+ memset(ll_header + len, 0, dev->hard_header_len - len);
+ return true;
+ }
+
+ if (dev->header_ops && dev->header_ops->validate)
+ return dev->header_ops->validate(ll_header, len);
+
+ return false;
+}
+
typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
static inline int unregister_gifconf(unsigned int family)
@@ -3741,7 +3824,7 @@ void netdev_lower_state_changed(struct net_device *lower_dev,
/* RSS keys are 40 or 52 bytes long */
#define NETDEV_RSS_KEY_LEN 52
-extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN];
+extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly;
void netdev_rss_key_fill(void *buffer, size_t len);
int dev_get_nest_level(struct net_device *dev,
@@ -3965,6 +4048,11 @@ static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol,
skb->mac_len = mac_len;
}
+static inline bool netif_is_macsec(const struct net_device *dev)
+{
+ return dev->priv_flags & IFF_MACSEC;
+}
+
static inline bool netif_is_macvlan(const struct net_device *dev)
{
return dev->priv_flags & IFF_MACVLAN;
@@ -4045,6 +4133,11 @@ static inline bool netif_is_lag_port(const struct net_device *dev)
return netif_is_bond_slave(dev) || netif_is_team_port(dev);
}
+static inline bool netif_is_rxfh_configured(const struct net_device *dev)
+{
+ return dev->priv_flags & IFF_RXFH_CONFIGURED;
+}
+
/* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
static inline void netif_keep_dst(struct net_device *dev)
{
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 0ad556726181..9230f9aee896 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -141,22 +141,6 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg);
#ifdef HAVE_JUMP_LABEL
extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
-
-static inline bool nf_hook_list_active(struct list_head *hook_list,
- u_int8_t pf, unsigned int hook)
-{
- if (__builtin_constant_p(pf) &&
- __builtin_constant_p(hook))
- return static_key_false(&nf_hooks_needed[pf][hook]);
-
- return !list_empty(hook_list);
-}
-#else
-static inline bool nf_hook_list_active(struct list_head *hook_list,
- u_int8_t pf, unsigned int hook)
-{
- return !list_empty(hook_list);
-}
#endif
int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state);
@@ -177,9 +161,18 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
int (*okfn)(struct net *, struct sock *, struct sk_buff *),
int thresh)
{
- struct list_head *hook_list = &net->nf.hooks[pf][hook];
+ struct list_head *hook_list;
+
+#ifdef HAVE_JUMP_LABEL
+ if (__builtin_constant_p(pf) &&
+ __builtin_constant_p(hook) &&
+ !static_key_false(&nf_hooks_needed[pf][hook]))
+ return 1;
+#endif
+
+ hook_list = &net->nf.hooks[pf][hook];
- if (nf_hook_list_active(hook_list, pf, hook)) {
+ if (!list_empty(hook_list)) {
struct nf_hook_state state;
nf_hook_state_init(&state, hook_list, hook, thresh,
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index ba0d9789eb6e..1d82dd5e9a08 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -34,8 +34,6 @@ int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n);
int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n);
int nfnetlink_has_listeners(struct net *net, unsigned int group);
-struct sk_buff *nfnetlink_alloc_skb(struct net *net, unsigned int size,
- u32 dst_portid, gfp_t gfp_mask);
int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid,
unsigned int group, int echo, gfp_t flags);
int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error);
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index c5577410c25d..80a305b85323 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -200,6 +200,9 @@ struct xt_table {
u_int8_t af; /* address/protocol family */
int priority; /* hook order */
+ /* called when table is needed in the given netns */
+ int (*table_init)(struct net *net);
+
/* A unique name... */
const char name[XT_TABLE_MAXNAMELEN];
};
@@ -408,8 +411,7 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu)
return cnt;
}
-struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *);
-void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *);
+struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *);
#ifdef CONFIG_COMPAT
#include <net/compat.h>
diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h
index 6f074db2f23d..029b95e8924e 100644
--- a/include/linux/netfilter_arp/arp_tables.h
+++ b/include/linux/netfilter_arp/arp_tables.h
@@ -48,10 +48,11 @@ struct arpt_error {
}
extern void *arpt_alloc_initial_table(const struct xt_table *);
-extern struct xt_table *arpt_register_table(struct net *net,
- const struct xt_table *table,
- const struct arpt_replace *repl);
-extern void arpt_unregister_table(struct xt_table *table);
+int arpt_register_table(struct net *net, const struct xt_table *table,
+ const struct arpt_replace *repl,
+ const struct nf_hook_ops *ops, struct xt_table **res);
+void arpt_unregister_table(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops);
extern unsigned int arpt_do_table(struct sk_buff *skb,
const struct nf_hook_state *state,
struct xt_table *table);
diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h
index aa598f942c01..7bfc5893ec31 100644
--- a/include/linux/netfilter_ipv4/ip_tables.h
+++ b/include/linux/netfilter_ipv4/ip_tables.h
@@ -24,10 +24,11 @@
extern void ipt_init(void) __init;
-extern struct xt_table *ipt_register_table(struct net *net,
- const struct xt_table *table,
- const struct ipt_replace *repl);
-extern void ipt_unregister_table(struct net *net, struct xt_table *table);
+int ipt_register_table(struct net *net, const struct xt_table *table,
+ const struct ipt_replace *repl,
+ const struct nf_hook_ops *ops, struct xt_table **res);
+void ipt_unregister_table(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops);
/* Standard entry. */
struct ipt_standard {
diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h
index 0f76e5c674f9..b21c392d6012 100644
--- a/include/linux/netfilter_ipv6/ip6_tables.h
+++ b/include/linux/netfilter_ipv6/ip6_tables.h
@@ -25,10 +25,11 @@
extern void ip6t_init(void) __init;
extern void *ip6t_alloc_initial_table(const struct xt_table *);
-extern struct xt_table *ip6t_register_table(struct net *net,
- const struct xt_table *table,
- const struct ip6t_replace *repl);
-extern void ip6t_unregister_table(struct net *net, struct xt_table *table);
+int ip6t_register_table(struct net *net, const struct xt_table *table,
+ const struct ip6t_replace *repl,
+ const struct nf_hook_ops *ops, struct xt_table **res);
+void ip6t_unregister_table(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops);
extern unsigned int ip6t_do_table(struct sk_buff *skb,
const struct nf_hook_state *state,
struct xt_table *table);
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 0b41959aab9f..da14ab61f363 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -69,16 +69,6 @@ extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group)
extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
extern int netlink_has_listeners(struct sock *sk, unsigned int group);
-extern struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size,
- unsigned int ldiff, u32 dst_portid,
- gfp_t gfp_mask);
-static inline struct sk_buff *
-netlink_alloc_skb(struct sock *ssk, unsigned int size, u32 dst_portid,
- gfp_t gfp_mask)
-{
- return __netlink_alloc_skb(ssk, size, 0, dst_portid, gfp_mask);
-}
-
extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid,
__u32 group, gfp_t allocation);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 79ec7bbf0155..78fda2a69ab8 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -966,11 +966,20 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs);
extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs);
+extern struct perf_callchain_entry *
+get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
+ bool crosstask, bool add_mark);
+extern int get_callchain_buffers(void);
+extern void put_callchain_buffers(void);
-static inline void perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
{
- if (entry->nr < PERF_MAX_STACK_DEPTH)
+ if (entry->nr < PERF_MAX_STACK_DEPTH) {
entry->ip[entry->nr++] = ip;
+ return 0;
+ } else {
+ return -1; /* no more room, stop walking the stack */
+ }
}
extern int sysctl_perf_event_paranoid;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index d6f3641e7933..2abd7918f64f 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -327,8 +327,6 @@ struct phy_c45_device_ids {
/* phy_device: An instance of a PHY
*
* drv: Pointer to the driver for this PHY instance
- * bus: Pointer to the bus this PHY is on
- * dev: driver model device structure for this PHY
* phy_id: UID for this device found during discovery
* c45_ids: 802.3-c45 Device Identifers if is_c45.
* is_c45: Set to true if this phy uses clause 45 addressing.
@@ -338,7 +336,6 @@ struct phy_c45_device_ids {
* suspended: Set to true if this phy has been suspended successfully.
* state: state of the PHY for management purposes
* dev_flags: Device-specific flags used by the PHY driver.
- * addr: Bus address of PHY
* link_timeout: The number of timer firings to wait before the
* giving up on the current attempt at acquiring a link
* irq: IRQ number of the PHY's interrupt (-1 if none)
diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h
index 2400d2ea4f34..1d41ec44e39d 100644
--- a/include/linux/phy_fixed.h
+++ b/include/linux/phy_fixed.h
@@ -19,7 +19,7 @@ extern struct phy_device *fixed_phy_register(unsigned int irq,
struct fixed_phy_status *status,
int link_gpio,
struct device_node *np);
-extern void fixed_phy_del(int phy_addr);
+extern void fixed_phy_unregister(struct phy_device *phydev);
extern int fixed_phy_set_link_update(struct phy_device *phydev,
int (*link_update)(struct net_device *,
struct fixed_phy_status *));
@@ -40,9 +40,8 @@ static inline struct phy_device *fixed_phy_register(unsigned int irq,
{
return ERR_PTR(-ENODEV);
}
-static inline int fixed_phy_del(int phy_addr)
+static inline void fixed_phy_unregister(struct phy_device *phydev)
{
- return -ENODEV;
}
static inline int fixed_phy_set_link_update(struct phy_device *phydev,
int (*link_update)(struct net_device *,
diff --git a/include/linux/platform_data/brcmfmac-sdio.h b/include/linux/platform_data/brcmfmac-sdio.h
deleted file mode 100644
index e75dcbf2b230..000000000000
--- a/include/linux/platform_data/brcmfmac-sdio.h
+++ /dev/null
@@ -1,135 +0,0 @@
-/*
- * Copyright (c) 2013 Broadcom Corporation
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
- * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION
- * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
- * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- */
-
-#ifndef _LINUX_BRCMFMAC_PLATFORM_H
-#define _LINUX_BRCMFMAC_PLATFORM_H
-
-/*
- * Platform specific driver functions and data. Through the platform specific
- * device data functions can be provided to help the brcmfmac driver to
- * operate with the device in combination with the used platform.
- *
- * Use the platform data in the following (similar) way:
- *
- *
-#include <brcmfmac_platform.h>
-
-
-static void brcmfmac_power_on(void)
-{
-}
-
-static void brcmfmac_power_off(void)
-{
-}
-
-static void brcmfmac_reset(void)
-{
-}
-
-static struct brcmfmac_sdio_platform_data brcmfmac_sdio_pdata = {
- .power_on = brcmfmac_power_on,
- .power_off = brcmfmac_power_off,
- .reset = brcmfmac_reset
-};
-
-static struct platform_device brcmfmac_device = {
- .name = BRCMFMAC_SDIO_PDATA_NAME,
- .id = PLATFORM_DEVID_NONE,
- .dev.platform_data = &brcmfmac_sdio_pdata
-};
-
-void __init brcmfmac_init_pdata(void)
-{
- brcmfmac_sdio_pdata.oob_irq_supported = true;
- brcmfmac_sdio_pdata.oob_irq_nr = gpio_to_irq(GPIO_BRCMF_SDIO_OOB);
- brcmfmac_sdio_pdata.oob_irq_flags = IORESOURCE_IRQ |
- IORESOURCE_IRQ_HIGHLEVEL;
- platform_device_register(&brcmfmac_device);
-}
- *
- *
- * Note: the brcmfmac can be loaded as module or be statically built-in into
- * the kernel. If built-in then do note that it uses module_init (and
- * module_exit) routines which equal device_initcall. So if you intend to
- * create a module with the platform specific data for the brcmfmac and have
- * it built-in to the kernel then use a higher initcall then device_initcall
- * (see init.h). If this is not done then brcmfmac will load without problems
- * but will not pickup the platform data.
- *
- * When the driver does not "detect" platform driver data then it will continue
- * without reporting anything and just assume there is no data needed. Which is
- * probably true for most platforms.
- *
- * Explanation of the platform_data fields:
- *
- * drive_strength: is the preferred drive_strength to be used for the SDIO
- * pins. If 0 then a default value will be used. This is the target drive
- * strength, the exact drive strength which will be used depends on the
- * capabilities of the device.
- *
- * oob_irq_supported: does the board have support for OOB interrupts. SDIO
- * in-band interrupts are relatively slow and for having less overhead on
- * interrupt processing an out of band interrupt can be used. If the HW
- * supports this then enable this by setting this field to true and configure
- * the oob related fields.
- *
- * oob_irq_nr, oob_irq_flags: the OOB interrupt information. The values are
- * used for registering the irq using request_irq function.
- *
- * broken_sg_support: flag for broken sg list support of SDIO host controller.
- * Set this to true if the SDIO host controller has higher align requirement
- * than 32 bytes for each scatterlist item.
- *
- * sd_head_align: alignment requirement for start of data buffer
- *
- * sd_sgentry_align: length alignment requirement for each sg entry
- *
- * power_on: This function is called by the brcmfmac when the module gets
- * loaded. This can be particularly useful for low power devices. The platform
- * spcific routine may for example decide to power up the complete device.
- * If there is no use-case for this function then provide NULL.
- *
- * power_off: This function is called by the brcmfmac when the module gets
- * unloaded. At this point the device can be powered down or otherwise be reset.
- * So if an actual power_off is not supported but reset is then reset the device
- * when this function gets called. This can be particularly useful for low power
- * devices. If there is no use-case for this function (either power-down or
- * reset) then provide NULL.
- *
- * reset: This function can get called if the device communication broke down.
- * This functionality is particularly useful in case of SDIO type devices. It is
- * possible to reset a dongle via sdio data interface, but it requires that
- * this is fully functional. This function is chip/module specific and this
- * function should return only after the complete reset has completed.
- */
-
-#define BRCMFMAC_SDIO_PDATA_NAME "brcmfmac_sdio"
-
-struct brcmfmac_sdio_platform_data {
- unsigned int drive_strength;
- bool oob_irq_supported;
- unsigned int oob_irq_nr;
- unsigned long oob_irq_flags;
- bool broken_sg_support;
- unsigned short sd_head_align;
- unsigned short sd_sgentry_align;
- void (*power_on)(void);
- void (*power_off)(void);
- void (*reset)(void);
-};
-
-#endif /* _LINUX_BRCMFMAC_PLATFORM_H */
diff --git a/include/linux/platform_data/brcmfmac.h b/include/linux/platform_data/brcmfmac.h
new file mode 100644
index 000000000000..1d30bf278231
--- /dev/null
+++ b/include/linux/platform_data/brcmfmac.h
@@ -0,0 +1,185 @@
+/*
+ * Copyright (c) 201 Broadcom Corporation
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
+ * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION
+ * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
+ * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef _LINUX_BRCMFMAC_PLATFORM_H
+#define _LINUX_BRCMFMAC_PLATFORM_H
+
+
+#define BRCMFMAC_PDATA_NAME "brcmfmac"
+
+#define BRCMFMAC_COUNTRY_BUF_SZ 4
+
+
+/*
+ * Platform specific driver functions and data. Through the platform specific
+ * device data functions and data can be provided to help the brcmfmac driver to
+ * operate with the device in combination with the used platform.
+ */
+
+
+/**
+ * Note: the brcmfmac can be loaded as module or be statically built-in into
+ * the kernel. If built-in then do note that it uses module_init (and
+ * module_exit) routines which equal device_initcall. So if you intend to
+ * create a module with the platform specific data for the brcmfmac and have
+ * it built-in to the kernel then use a higher initcall then device_initcall
+ * (see init.h). If this is not done then brcmfmac will load without problems
+ * but will not pickup the platform data.
+ *
+ * When the driver does not "detect" platform driver data then it will continue
+ * without reporting anything and just assume there is no data needed. Which is
+ * probably true for most platforms.
+ */
+
+/**
+ * enum brcmf_bus_type - Bus type identifier. Currently SDIO, USB and PCIE are
+ * supported.
+ */
+enum brcmf_bus_type {
+ BRCMF_BUSTYPE_SDIO,
+ BRCMF_BUSTYPE_USB,
+ BRCMF_BUSTYPE_PCIE
+};
+
+
+/**
+ * struct brcmfmac_sdio_pd - SDIO Device specific platform data.
+ *
+ * @txglomsz: SDIO txglom size. Use 0 if default of driver is to be
+ * used.
+ * @drive_strength: is the preferred drive_strength to be used for the SDIO
+ * pins. If 0 then a default value will be used. This is
+ * the target drive strength, the exact drive strength
+ * which will be used depends on the capabilities of the
+ * device.
+ * @oob_irq_supported: does the board have support for OOB interrupts. SDIO
+ * in-band interrupts are relatively slow and for having
+ * less overhead on interrupt processing an out of band
+ * interrupt can be used. If the HW supports this then
+ * enable this by setting this field to true and configure
+ * the oob related fields.
+ * @oob_irq_nr,
+ * @oob_irq_flags: the OOB interrupt information. The values are used for
+ * registering the irq using request_irq function.
+ * @broken_sg_support: flag for broken sg list support of SDIO host controller.
+ * Set this to true if the SDIO host controller has higher
+ * align requirement than 32 bytes for each scatterlist
+ * item.
+ * @sd_head_align: alignment requirement for start of data buffer.
+ * @sd_sgentry_align: length alignment requirement for each sg entry.
+ * @reset: This function can get called if the device communication
+ * broke down. This functionality is particularly useful in
+ * case of SDIO type devices. It is possible to reset a
+ * dongle via sdio data interface, but it requires that
+ * this is fully functional. This function is chip/module
+ * specific and this function should return only after the
+ * complete reset has completed.
+ */
+struct brcmfmac_sdio_pd {
+ int txglomsz;
+ unsigned int drive_strength;
+ bool oob_irq_supported;
+ unsigned int oob_irq_nr;
+ unsigned long oob_irq_flags;
+ bool broken_sg_support;
+ unsigned short sd_head_align;
+ unsigned short sd_sgentry_align;
+ void (*reset)(void);
+};
+
+/**
+ * struct brcmfmac_pd_cc_entry - Struct for translating user space country code
+ * (iso3166) to firmware country code and
+ * revision.
+ *
+ * @iso3166: iso3166 alpha 2 country code string.
+ * @cc: firmware country code string.
+ * @rev: firmware country code revision.
+ */
+struct brcmfmac_pd_cc_entry {
+ char iso3166[BRCMFMAC_COUNTRY_BUF_SZ];
+ char cc[BRCMFMAC_COUNTRY_BUF_SZ];
+ s32 rev;
+};
+
+/**
+ * struct brcmfmac_pd_cc - Struct for translating country codes as set by user
+ * space to a country code and rev which can be used by
+ * firmware.
+ *
+ * @table_size: number of entries in table (> 0)
+ * @table: array of 1 or more elements with translation information.
+ */
+struct brcmfmac_pd_cc {
+ int table_size;
+ struct brcmfmac_pd_cc_entry table[0];
+};
+
+/**
+ * struct brcmfmac_pd_device - Device specific platform data. (id/rev/bus_type)
+ * is the unique identifier of the device.
+ *
+ * @id: ID of the device for which this data is. In case of SDIO
+ * or PCIE this is the chipid as identified by chip.c In
+ * case of USB this is the chipid as identified by the
+ * device query.
+ * @rev: chip revision, see id.
+ * @bus_type: The type of bus. Some chipid/rev exist for different bus
+ * types. Each bus type has its own set of settings.
+ * @feature_disable: Bitmask of features to disable (override), See feature.c
+ * in brcmfmac for details.
+ * @country_codes: If available, pointer to struct for translating country
+ * codes.
+ * @bus: Bus specific (union) device settings. Currently only
+ * SDIO.
+ */
+struct brcmfmac_pd_device {
+ unsigned int id;
+ unsigned int rev;
+ enum brcmf_bus_type bus_type;
+ unsigned int feature_disable;
+ struct brcmfmac_pd_cc *country_codes;
+ union {
+ struct brcmfmac_sdio_pd sdio;
+ } bus;
+};
+
+/**
+ * struct brcmfmac_platform_data - BRCMFMAC specific platform data.
+ *
+ * @power_on: This function is called by the brcmfmac driver when the module
+ * gets loaded. This can be particularly useful for low power
+ * devices. The platform spcific routine may for example decide to
+ * power up the complete device. If there is no use-case for this
+ * function then provide NULL.
+ * @power_off: This function is called by the brcmfmac when the module gets
+ * unloaded. At this point the devices can be powered down or
+ * otherwise be reset. So if an actual power_off is not supported
+ * but reset is supported by the devices then reset the devices
+ * when this function gets called. This can be particularly useful
+ * for low power devices. If there is no use-case for this
+ * function then provide NULL.
+ */
+struct brcmfmac_platform_data {
+ void (*power_on)(void);
+ void (*power_off)(void);
+ char *fw_alternative_path;
+ int device_count;
+ struct brcmfmac_pd_device devices[0];
+};
+
+
+#endif /* _LINUX_BRCMFMAC_PLATFORM_H */
diff --git a/include/linux/platform_data/microread.h b/include/linux/platform_data/microread.h
deleted file mode 100644
index ca13992089b8..000000000000
--- a/include/linux/platform_data/microread.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Driver include for the Inside Secure microread NFC Chip.
- *
- * Copyright (C) 2011 Tieto Poland
- * Copyright (C) 2012 Intel Corporation. All rights reserved.
- *
- * 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 published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#ifndef _MICROREAD_H
-#define _MICROREAD_H
-
-#include <linux/i2c.h>
-
-#define MICROREAD_DRIVER_NAME "microread"
-
-/* board config platform data for microread */
-struct microread_nfc_platform_data {
- unsigned int rst_gpio;
- unsigned int irq_gpio;
- unsigned int ioh_gpio;
-};
-
-#endif /* _MICROREAD_H */
diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h
index 1d1ba2c5ee7a..53ecb37ae563 100644
--- a/include/linux/qed/common_hsi.h
+++ b/include/linux/qed/common_hsi.h
@@ -11,9 +11,11 @@
#define CORE_SPQE_PAGE_SIZE_BYTES 4096
+#define X_FINAL_CLEANUP_AGG_INT 1
+
#define FW_MAJOR_VERSION 8
-#define FW_MINOR_VERSION 4
-#define FW_REVISION_VERSION 2
+#define FW_MINOR_VERSION 7
+#define FW_REVISION_VERSION 3
#define FW_ENGINEERING_VERSION 0
/***********************/
@@ -152,6 +154,9 @@
/* number of queues in a PF queue group */
#define QM_PF_QUEUE_GROUP_SIZE 8
+/* the size of a single queue element in bytes */
+#define QM_PQ_ELEMENT_SIZE 4
+
/* base number of Tx PQs in the CM PQ representation.
* should be used when storing PQ IDs in CM PQ registers and context
*/
@@ -285,6 +290,16 @@
#define PXP_NUM_ILT_RECORDS_K2 11000
#define MAX_NUM_ILT_RECORDS MAX(PXP_NUM_ILT_RECORDS_BB, PXP_NUM_ILT_RECORDS_K2)
+#define SDM_COMP_TYPE_NONE 0
+#define SDM_COMP_TYPE_WAKE_THREAD 1
+#define SDM_COMP_TYPE_AGG_INT 2
+#define SDM_COMP_TYPE_CM 3
+#define SDM_COMP_TYPE_LOADER 4
+#define SDM_COMP_TYPE_PXP 5
+#define SDM_COMP_TYPE_INDICATE_ERROR 6
+#define SDM_COMP_TYPE_RELEASE_THREAD 7
+#define SDM_COMP_TYPE_RAM 8
+
/******************/
/* PBF CONSTANTS */
/******************/
@@ -335,7 +350,7 @@ struct event_ring_entry {
/* Multi function mode */
enum mf_mode {
- SF,
+ ERROR_MODE /* Unsupported mode */,
MF_OVLAN,
MF_NPAR,
MAX_MF_MODE
@@ -606,4 +621,19 @@ struct status_block {
#define STATUS_BLOCK_ZERO_PAD3_SHIFT 24
};
+struct tunnel_parsing_flags {
+ u8 flags;
+#define TUNNEL_PARSING_FLAGS_TYPE_MASK 0x3
+#define TUNNEL_PARSING_FLAGS_TYPE_SHIFT 0
+#define TUNNEL_PARSING_FLAGS_TENNANT_ID_EXIST_MASK 0x1
+#define TUNNEL_PARSING_FLAGS_TENNANT_ID_EXIST_SHIFT 2
+#define TUNNEL_PARSING_FLAGS_NEXT_PROTOCOL_MASK 0x3
+#define TUNNEL_PARSING_FLAGS_NEXT_PROTOCOL_SHIFT 3
+#define TUNNEL_PARSING_FLAGS_FIRSTHDRIPMATCH_MASK 0x1
+#define TUNNEL_PARSING_FLAGS_FIRSTHDRIPMATCH_SHIFT 5
+#define TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_MASK 0x1
+#define TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_SHIFT 6
+#define TUNNEL_PARSING_FLAGS_IPV4_OPTIONS_MASK 0x1
+#define TUNNEL_PARSING_FLAGS_IPV4_OPTIONS_SHIFT 7
+};
#endif /* __COMMON_HSI__ */
diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h
index 320b3373ac1d..092cb0c1afcb 100644
--- a/include/linux/qed/eth_common.h
+++ b/include/linux/qed/eth_common.h
@@ -17,10 +17,8 @@
#define ETH_MAX_RAMROD_PER_CON 8
#define ETH_TX_BD_PAGE_SIZE_BYTES 4096
#define ETH_RX_BD_PAGE_SIZE_BYTES 4096
-#define ETH_RX_SGE_PAGE_SIZE_BYTES 4096
#define ETH_RX_CQE_PAGE_SIZE_BYTES 4096
#define ETH_RX_NUM_NEXT_PAGE_BDS 2
-#define ETH_RX_NUM_NEXT_PAGE_SGES 2
#define ETH_TX_MIN_BDS_PER_NON_LSO_PKT 1
#define ETH_TX_MAX_BDS_PER_NON_LSO_PACKET 18
@@ -34,7 +32,8 @@
#define ETH_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS
-#define ETH_REG_CQE_PBL_SIZE 3
+/* Maximum number of buffers, used for RX packet placement */
+#define ETH_RX_MAX_BUFF_PER_PKT 5
/* num of MAC/VLAN filters */
#define ETH_NUM_MAC_FILTERS 512
@@ -54,9 +53,9 @@
/* TPA constants */
#define ETH_TPA_MAX_AGGS_NUM 64
-#define ETH_TPA_CQE_START_SGL_SIZE 3
-#define ETH_TPA_CQE_CONT_SGL_SIZE 6
-#define ETH_TPA_CQE_END_SGL_SIZE 4
+#define ETH_TPA_CQE_START_LEN_LIST_SIZE ETH_RX_MAX_BUFF_PER_PKT
+#define ETH_TPA_CQE_CONT_LEN_LIST_SIZE 6
+#define ETH_TPA_CQE_END_LEN_LIST_SIZE 4
/* Queue Zone sizes */
#define TSTORM_QZONE_SIZE 0
@@ -74,18 +73,18 @@ struct coalescing_timeset {
struct eth_tx_1st_bd_flags {
u8 bitfields;
+#define ETH_TX_1ST_BD_FLAGS_START_BD_MASK 0x1
+#define ETH_TX_1ST_BD_FLAGS_START_BD_SHIFT 0
#define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_MASK 0x1
-#define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_SHIFT 0
+#define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_SHIFT 1
#define ETH_TX_1ST_BD_FLAGS_IP_CSUM_MASK 0x1
-#define ETH_TX_1ST_BD_FLAGS_IP_CSUM_SHIFT 1
+#define ETH_TX_1ST_BD_FLAGS_IP_CSUM_SHIFT 2
#define ETH_TX_1ST_BD_FLAGS_L4_CSUM_MASK 0x1
-#define ETH_TX_1ST_BD_FLAGS_L4_CSUM_SHIFT 2
+#define ETH_TX_1ST_BD_FLAGS_L4_CSUM_SHIFT 3
#define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_MASK 0x1
-#define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_SHIFT 3
+#define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_SHIFT 4
#define ETH_TX_1ST_BD_FLAGS_LSO_MASK 0x1
-#define ETH_TX_1ST_BD_FLAGS_LSO_SHIFT 4
-#define ETH_TX_1ST_BD_FLAGS_START_BD_MASK 0x1
-#define ETH_TX_1ST_BD_FLAGS_START_BD_SHIFT 5
+#define ETH_TX_1ST_BD_FLAGS_LSO_SHIFT 5
#define ETH_TX_1ST_BD_FLAGS_TUNN_IP_CSUM_MASK 0x1
#define ETH_TX_1ST_BD_FLAGS_TUNN_IP_CSUM_SHIFT 6
#define ETH_TX_1ST_BD_FLAGS_TUNN_L4_CSUM_MASK 0x1
@@ -97,38 +96,44 @@ struct eth_tx_data_1st_bd {
__le16 vlan;
u8 nbds;
struct eth_tx_1st_bd_flags bd_flags;
- __le16 fw_use_only;
+ __le16 bitfields;
+#define ETH_TX_DATA_1ST_BD_TUNN_CFG_OVERRIDE_MASK 0x1
+#define ETH_TX_DATA_1ST_BD_TUNN_CFG_OVERRIDE_SHIFT 0
+#define ETH_TX_DATA_1ST_BD_RESERVED0_MASK 0x1
+#define ETH_TX_DATA_1ST_BD_RESERVED0_SHIFT 1
+#define ETH_TX_DATA_1ST_BD_FW_USE_ONLY_MASK 0x3FFF
+#define ETH_TX_DATA_1ST_BD_FW_USE_ONLY_SHIFT 2
};
/* The parsing information data for the second tx bd of a given packet. */
struct eth_tx_data_2nd_bd {
__le16 tunn_ip_size;
- __le16 bitfields;
-#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_MASK 0x1FFF
-#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_SHIFT 0
-#define ETH_TX_DATA_2ND_BD_RESERVED0_MASK 0x7
-#define ETH_TX_DATA_2ND_BD_RESERVED0_SHIFT 13
- __le16 bitfields2;
+ __le16 bitfields1;
#define ETH_TX_DATA_2ND_BD_TUNN_INNER_L2_HDR_SIZE_W_MASK 0xF
#define ETH_TX_DATA_2ND_BD_TUNN_INNER_L2_HDR_SIZE_W_SHIFT 0
#define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_MASK 0x3
#define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_SHIFT 4
#define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_MASK 0x3
#define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_SHIFT 6
+#define ETH_TX_DATA_2ND_BD_START_BD_MASK 0x1
+#define ETH_TX_DATA_2ND_BD_START_BD_SHIFT 8
#define ETH_TX_DATA_2ND_BD_TUNN_TYPE_MASK 0x3
-#define ETH_TX_DATA_2ND_BD_TUNN_TYPE_SHIFT 8
+#define ETH_TX_DATA_2ND_BD_TUNN_TYPE_SHIFT 9
#define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_MASK 0x1
-#define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_SHIFT 10
+#define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_SHIFT 11
#define ETH_TX_DATA_2ND_BD_IPV6_EXT_MASK 0x1
-#define ETH_TX_DATA_2ND_BD_IPV6_EXT_SHIFT 11
+#define ETH_TX_DATA_2ND_BD_IPV6_EXT_SHIFT 12
#define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_MASK 0x1
-#define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_SHIFT 12
+#define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_SHIFT 13
#define ETH_TX_DATA_2ND_BD_L4_UDP_MASK 0x1
-#define ETH_TX_DATA_2ND_BD_L4_UDP_SHIFT 13
+#define ETH_TX_DATA_2ND_BD_L4_UDP_SHIFT 14
#define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_MASK 0x1
-#define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_SHIFT 14
-#define ETH_TX_DATA_2ND_BD_RESERVED1_MASK 0x1
-#define ETH_TX_DATA_2ND_BD_RESERVED1_SHIFT 15
+#define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_SHIFT 15
+ __le16 bitfields2;
+#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_MASK 0x1FFF
+#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_SHIFT 0
+#define ETH_TX_DATA_2ND_BD_RESERVED0_MASK 0x7
+#define ETH_TX_DATA_2ND_BD_RESERVED0_SHIFT 13
};
/* Regular ETH Rx FP CQE. */
@@ -145,11 +150,68 @@ struct eth_fast_path_rx_reg_cqe {
struct parsing_and_err_flags pars_flags;
__le16 vlan_tag;
__le32 rss_hash;
- __le16 len_on_bd;
+ __le16 len_on_first_bd;
u8 placement_offset;
- u8 reserved;
- __le16 pbl[ETH_REG_CQE_PBL_SIZE];
- u8 reserved1[10];
+ struct tunnel_parsing_flags tunnel_pars_flags;
+ u8 bd_num;
+ u8 reserved[7];
+ u32 fw_debug;
+ u8 reserved1[3];
+ u8 flags;
+#define ETH_FAST_PATH_RX_REG_CQE_VALID_MASK 0x1
+#define ETH_FAST_PATH_RX_REG_CQE_VALID_SHIFT 0
+#define ETH_FAST_PATH_RX_REG_CQE_VALID_TOGGLE_MASK 0x1
+#define ETH_FAST_PATH_RX_REG_CQE_VALID_TOGGLE_SHIFT 1
+#define ETH_FAST_PATH_RX_REG_CQE_RESERVED2_MASK 0x3F
+#define ETH_FAST_PATH_RX_REG_CQE_RESERVED2_SHIFT 2
+};
+
+/* TPA-continue ETH Rx FP CQE. */
+struct eth_fast_path_rx_tpa_cont_cqe {
+ u8 type;
+ u8 tpa_agg_index;
+ __le16 len_list[ETH_TPA_CQE_CONT_LEN_LIST_SIZE];
+ u8 reserved[5];
+ u8 reserved1;
+ __le16 reserved2[ETH_TPA_CQE_CONT_LEN_LIST_SIZE];
+};
+
+/* TPA-end ETH Rx FP CQE. */
+struct eth_fast_path_rx_tpa_end_cqe {
+ u8 type;
+ u8 tpa_agg_index;
+ __le16 total_packet_len;
+ u8 num_of_bds;
+ u8 end_reason;
+ __le16 num_of_coalesced_segs;
+ __le32 ts_delta;
+ __le16 len_list[ETH_TPA_CQE_END_LEN_LIST_SIZE];
+ u8 reserved1[3];
+ u8 reserved2;
+ __le16 reserved3[ETH_TPA_CQE_END_LEN_LIST_SIZE];
+};
+
+/* TPA-start ETH Rx FP CQE. */
+struct eth_fast_path_rx_tpa_start_cqe {
+ u8 type;
+ u8 bitfields;
+#define ETH_FAST_PATH_RX_TPA_START_CQE_RSS_HASH_TYPE_MASK 0x7
+#define ETH_FAST_PATH_RX_TPA_START_CQE_RSS_HASH_TYPE_SHIFT 0
+#define ETH_FAST_PATH_RX_TPA_START_CQE_TC_MASK 0xF
+#define ETH_FAST_PATH_RX_TPA_START_CQE_TC_SHIFT 3
+#define ETH_FAST_PATH_RX_TPA_START_CQE_RESERVED0_MASK 0x1
+#define ETH_FAST_PATH_RX_TPA_START_CQE_RESERVED0_SHIFT 7
+ __le16 seg_len;
+ struct parsing_and_err_flags pars_flags;
+ __le16 vlan_tag;
+ __le32 rss_hash;
+ __le16 len_on_first_bd;
+ u8 placement_offset;
+ struct tunnel_parsing_flags tunnel_pars_flags;
+ u8 tpa_agg_index;
+ u8 header_len;
+ __le16 ext_bd_len_list[ETH_TPA_CQE_START_LEN_LIST_SIZE];
+ u32 fw_debug;
};
/* The L4 pseudo checksum mode for Ethernet */
@@ -168,13 +230,26 @@ struct eth_slow_path_rx_cqe {
u8 type;
u8 ramrod_cmd_id;
u8 error_flag;
- u8 reserved[27];
+ u8 reserved[25];
__le16 echo;
+ u8 reserved1;
+ u8 flags;
+/* for PMD mode - valid indication */
+#define ETH_SLOW_PATH_RX_CQE_VALID_MASK 0x1
+#define ETH_SLOW_PATH_RX_CQE_VALID_SHIFT 0
+/* for PMD mode - valid toggle indication */
+#define ETH_SLOW_PATH_RX_CQE_VALID_TOGGLE_MASK 0x1
+#define ETH_SLOW_PATH_RX_CQE_VALID_TOGGLE_SHIFT 1
+#define ETH_SLOW_PATH_RX_CQE_RESERVED2_MASK 0x3F
+#define ETH_SLOW_PATH_RX_CQE_RESERVED2_SHIFT 2
};
/* union for all ETH Rx CQE types */
union eth_rx_cqe {
struct eth_fast_path_rx_reg_cqe fast_path_regular;
+ struct eth_fast_path_rx_tpa_start_cqe fast_path_tpa_start;
+ struct eth_fast_path_rx_tpa_cont_cqe fast_path_tpa_cont;
+ struct eth_fast_path_rx_tpa_end_cqe fast_path_tpa_end;
struct eth_slow_path_rx_cqe slow_path;
};
@@ -183,15 +258,18 @@ enum eth_rx_cqe_type {
ETH_RX_CQE_TYPE_UNUSED,
ETH_RX_CQE_TYPE_REGULAR,
ETH_RX_CQE_TYPE_SLOW_PATH,
+ ETH_RX_CQE_TYPE_TPA_START,
+ ETH_RX_CQE_TYPE_TPA_CONT,
+ ETH_RX_CQE_TYPE_TPA_END,
MAX_ETH_RX_CQE_TYPE
};
/* ETH Rx producers data */
struct eth_rx_prod_data {
__le16 bd_prod;
- __le16 sge_prod;
__le16 cqe_prod;
__le16 reserved;
+ __le16 reserved1;
};
/* The first tx bd of a given packet */
@@ -211,12 +289,17 @@ struct eth_tx_2nd_bd {
/* The parsing information data for the third tx bd of a given packet. */
struct eth_tx_data_3rd_bd {
__le16 lso_mss;
- u8 bitfields;
+ __le16 bitfields;
#define ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_MASK 0xF
#define ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_SHIFT 0
#define ETH_TX_DATA_3RD_BD_HDR_NBD_MASK 0xF
#define ETH_TX_DATA_3RD_BD_HDR_NBD_SHIFT 4
- u8 resereved0[3];
+#define ETH_TX_DATA_3RD_BD_START_BD_MASK 0x1
+#define ETH_TX_DATA_3RD_BD_START_BD_SHIFT 8
+#define ETH_TX_DATA_3RD_BD_RESERVED0_MASK 0x7F
+#define ETH_TX_DATA_3RD_BD_RESERVED0_SHIFT 9
+ u8 tunn_l4_hdr_start_offset_w;
+ u8 tunn_hdr_size_w;
};
/* The third tx bd of a given packet */
@@ -226,12 +309,24 @@ struct eth_tx_3rd_bd {
struct eth_tx_data_3rd_bd data;
};
+/* Complementary information for the regular tx bd of a given packet. */
+struct eth_tx_data_bd {
+ __le16 reserved0;
+ __le16 bitfields;
+#define ETH_TX_DATA_BD_RESERVED1_MASK 0xFF
+#define ETH_TX_DATA_BD_RESERVED1_SHIFT 0
+#define ETH_TX_DATA_BD_START_BD_MASK 0x1
+#define ETH_TX_DATA_BD_START_BD_SHIFT 8
+#define ETH_TX_DATA_BD_RESERVED2_MASK 0x7F
+#define ETH_TX_DATA_BD_RESERVED2_SHIFT 9
+ __le16 reserved3;
+};
+
/* The common non-special TX BD ring element */
struct eth_tx_bd {
struct regpair addr;
__le16 nbytes;
- __le16 reserved0;
- __le32 reserved1;
+ struct eth_tx_data_bd data;
};
union eth_tx_bd_types {
diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index 41b9049b57e2..5f8fcaaa6504 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -19,6 +19,10 @@
/* dma_addr_t manip */
#define DMA_LO_LE(x) cpu_to_le32(lower_32_bits(x))
#define DMA_HI_LE(x) cpu_to_le32(upper_32_bits(x))
+#define DMA_REGPAIR_LE(x, val) do { \
+ (x).hi = DMA_HI_LE((val)); \
+ (x).lo = DMA_LO_LE((val)); \
+ } while (0)
#define HILO_GEN(hi, lo, type) ((((type)(hi)) << 32) + (lo))
#define HILO_DMA(hi, lo) HILO_GEN(hi, lo, dma_addr_t)
diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h
index 81ab178e31c1..e1d69834a11f 100644
--- a/include/linux/qed/qed_eth_if.h
+++ b/include/linux/qed/qed_eth_if.h
@@ -33,10 +33,20 @@ struct qed_update_vport_params {
u8 vport_id;
u8 update_vport_active_flg;
u8 vport_active_flg;
+ u8 update_accept_any_vlan_flg;
+ u8 accept_any_vlan;
u8 update_rss_flg;
struct qed_update_vport_rss_params rss_params;
};
+struct qed_start_vport_params {
+ bool remove_inner_vlan;
+ bool gro_enable;
+ bool drop_ttl0;
+ u8 vport_id;
+ u16 mtu;
+};
+
struct qed_stop_rxq_params {
u8 rss_id;
u8 rx_queue_id;
@@ -116,9 +126,7 @@ struct qed_eth_ops {
void *cookie);
int (*vport_start)(struct qed_dev *cdev,
- u8 vport_id, u16 mtu,
- u8 drop_ttl0_flg,
- u8 inner_vlan_removal_en_flg);
+ struct qed_start_vport_params *params);
int (*vport_stop)(struct qed_dev *cdev,
u8 vport_id);
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index d4a32e878180..1f7599c77cd4 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -80,7 +80,7 @@ struct qed_dev_info {
u8 num_hwfns;
u8 hw_mac[ETH_ALEN];
- bool is_mf;
+ bool is_mf_default;
/* FW version */
u16 fw_major;
@@ -360,6 +360,12 @@ enum DP_MODULE {
/* to be added...up to 0x8000000 */
};
+enum qed_mf_mode {
+ QED_MF_DEFAULT,
+ QED_MF_OVLAN,
+ QED_MF_NPAR,
+};
+
struct qed_eth_stats {
u64 no_buff_discards;
u64 packet_too_big_discard;
@@ -440,6 +446,12 @@ struct qed_eth_stats {
#define RX_PI 0
#define TX_PI(tc) (RX_PI + 1 + tc)
+struct qed_sb_cnt_info {
+ int sb_cnt;
+ int sb_iov_cnt;
+ int sb_free_blk;
+};
+
static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info)
{
u32 prod = 0;
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 14ec1652daf4..17d4f849c65e 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -319,6 +319,27 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
})
/**
+ * list_next_or_null_rcu - get the first element from a list
+ * @head: the head for the list.
+ * @ptr: the list head to take the next element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_head within the struct.
+ *
+ * Note that if the ptr is at the end of the list, NULL is returned.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_next_or_null_rcu(head, ptr, type, member) \
+({ \
+ struct list_head *__head = (head); \
+ struct list_head *__ptr = (ptr); \
+ struct list_head *__next = READ_ONCE(__ptr->next); \
+ likely(__next != __head) ? list_entry_rcu(__next, type, \
+ member) : NULL; \
+})
+
+/**
* list_for_each_entry_rcu - iterate over rcu list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
diff --git a/include/linux/rfkill-gpio.h b/include/linux/rfkill-gpio.h
deleted file mode 100644
index 20bcb55498cd..000000000000
--- a/include/linux/rfkill-gpio.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Copyright (c) 2011, NVIDIA Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
- */
-
-
-#ifndef __RFKILL_GPIO_H
-#define __RFKILL_GPIO_H
-
-#include <linux/types.h>
-#include <linux/rfkill.h>
-
-/**
- * struct rfkill_gpio_platform_data - platform data for rfkill gpio device.
- * for unused gpio's, the expected value is -1.
- * @name: name for the gpio rf kill instance
- */
-
-struct rfkill_gpio_platform_data {
- char *name;
- enum rfkill_type type;
-};
-
-#endif /* __RFKILL_GPIO_H */
diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h
index d9010789b4e8..e6a0031d1b1f 100644
--- a/include/linux/rfkill.h
+++ b/include/linux/rfkill.h
@@ -104,7 +104,8 @@ int __must_check rfkill_register(struct rfkill *rfkill);
*
* Pause polling -- say transmitter is off for other reasons.
* NOTE: not necessary for suspend/resume -- in that case the
- * core stops polling anyway
+ * core stops polling anyway (but will also correctly handle
+ * the case of polling having been paused before suspend.)
*/
void rfkill_pause_polling(struct rfkill *rfkill);
@@ -212,6 +213,15 @@ void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw);
* @rfkill: rfkill struct to query
*/
bool rfkill_blocked(struct rfkill *rfkill);
+
+/**
+ * rfkill_find_type - Helpper for finding rfkill type by name
+ * @name: the name of the type
+ *
+ * Returns enum rfkill_type that conrresponds the name.
+ */
+enum rfkill_type rfkill_find_type(const char *name);
+
#else /* !RFKILL */
static inline struct rfkill * __must_check
rfkill_alloc(const char *name,
@@ -268,6 +278,12 @@ static inline bool rfkill_blocked(struct rfkill *rfkill)
{
return false;
}
+
+static inline enum rfkill_type rfkill_find_type(const char *name)
+{
+ return RFKILL_TYPE_ALL;
+}
+
#endif /* RFKILL || RFKILL_MODULE */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d3fcd4591ce4..15d0df943466 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1161,10 +1161,6 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from)
to->l4_hash = from->l4_hash;
};
-static inline void skb_sender_cpu_clear(struct sk_buff *skb)
-{
-}
-
#ifdef NET_SKBUFF_DATA_USES_OFFSET
static inline unsigned char *skb_end_pointer(const struct sk_buff *skb)
{
@@ -2186,6 +2182,11 @@ static inline int skb_checksum_start_offset(const struct sk_buff *skb)
return skb->csum_start - skb_headroom(skb);
}
+static inline unsigned char *skb_checksum_start(const struct sk_buff *skb)
+{
+ return skb->head + skb->csum_start;
+}
+
static inline int skb_transport_offset(const struct sk_buff *skb)
{
return skb_transport_header(skb) - skb->data;
@@ -2424,6 +2425,10 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi,
{
return __napi_alloc_skb(napi, length, GFP_ATOMIC);
}
+void napi_consume_skb(struct sk_buff *skb, int budget);
+
+void __kfree_skb_flush(void);
+void __kfree_skb_defer(struct sk_buff *skb);
/**
* __dev_alloc_pages - allocate page for network Rx
@@ -2646,6 +2651,13 @@ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len
skb_headroom(skb) + len <= skb->hdr_len;
}
+static inline int skb_try_make_writable(struct sk_buff *skb,
+ unsigned int write_len)
+{
+ return skb_cloned(skb) && !skb_clone_writable(skb, write_len) &&
+ pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+}
+
static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom,
int cloned)
{
@@ -3574,6 +3586,7 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
struct skb_gso_cb {
int mac_offset;
int encap_level;
+ __wsum csum;
__u16 csum_start;
};
#define SKB_SGO_CB_OFFSET 32
@@ -3600,6 +3613,16 @@ static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra)
return 0;
}
+static inline void gso_reset_checksum(struct sk_buff *skb, __wsum res)
+{
+ /* Do not update partial checksums if remote checksum is enabled. */
+ if (skb->remcsum_offload)
+ return;
+
+ SKB_GSO_CB(skb)->csum = res;
+ SKB_GSO_CB(skb)->csum_start = skb_checksum_start(skb) - skb->head;
+}
+
/* Compute the checksum for a gso segment. First compute the checksum value
* from the start of transport header to SKB_GSO_CB(skb)->csum_start, and
* then add in skb->csum (checksum from csum_start to end of packet).
@@ -3610,15 +3633,14 @@ static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra)
*/
static inline __sum16 gso_make_checksum(struct sk_buff *skb, __wsum res)
{
- int plen = SKB_GSO_CB(skb)->csum_start - skb_headroom(skb) -
- skb_transport_offset(skb);
- __wsum partial;
+ unsigned char *csum_start = skb_transport_header(skb);
+ int plen = (skb->head + SKB_GSO_CB(skb)->csum_start) - csum_start;
+ __wsum partial = SKB_GSO_CB(skb)->csum;
- partial = csum_partial(skb_transport_header(skb), plen, skb->csum);
- skb->csum = res;
- SKB_GSO_CB(skb)->csum_start -= plen;
+ SKB_GSO_CB(skb)->csum = res;
+ SKB_GSO_CB(skb)->csum_start = csum_start - skb->head;
- return csum_fold(partial);
+ return csum_fold(csum_partial(csum_start, plen, partial));
}
static inline bool skb_is_gso(const struct sk_buff *skb)
@@ -3708,5 +3730,30 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
return hdr_len + skb_gso_transport_seglen(skb);
}
+/* Local Checksum Offload.
+ * Compute outer checksum based on the assumption that the
+ * inner checksum will be offloaded later.
+ * See Documentation/networking/checksum-offloads.txt for
+ * explanation of how this works.
+ * Fill in outer checksum adjustment (e.g. with sum of outer
+ * pseudo-header) before calling.
+ * Also ensure that inner checksum is in linear data area.
+ */
+static inline __wsum lco_csum(struct sk_buff *skb)
+{
+ unsigned char *csum_start = skb_checksum_start(skb);
+ unsigned char *l4_hdr = skb_transport_header(skb);
+ __wsum partial;
+
+ /* Start with complement of inner checksum adjustment */
+ partial = ~csum_unfold(*(__force __sum16 *)(csum_start +
+ skb->csum_offset));
+
+ /* Add in checksum of our headers (incl. outer checksum
+ * adjustment filled in by caller) and return result.
+ */
+ return csum_partial(l4_hdr, csum_start - l4_hdr, partial);
+}
+
#endif /* __KERNEL__ */
#endif /* _LINUX_SKBUFF_H */
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 5bf59c8493b7..73bf6c6a833b 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -200,7 +200,9 @@ struct ucred {
#define AF_ALG 38 /* Algorithm sockets */
#define AF_NFC 39 /* NFC sockets */
#define AF_VSOCK 40 /* vSockets */
-#define AF_MAX 41 /* For now.. */
+#define AF_KCM 41 /* Kernel Connection Multiplexor*/
+
+#define AF_MAX 42 /* For now.. */
/* Protocol families, same as address families. */
#define PF_UNSPEC AF_UNSPEC
@@ -246,6 +248,7 @@ struct ucred {
#define PF_ALG AF_ALG
#define PF_NFC AF_NFC
#define PF_VSOCK AF_VSOCK
+#define PF_KCM AF_KCM
#define PF_MAX AF_MAX
/* Maximum queue length specifiable by listen. */
@@ -274,6 +277,7 @@ struct ucred {
#define MSG_MORE 0x8000 /* Sender will send more */
#define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */
#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */
+#define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */
#define MSG_EOF MSG_FIN
#define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */
@@ -322,6 +326,7 @@ struct ucred {
#define SOL_CAIF 278
#define SOL_ALG 279
#define SOL_NFC 280
+#define SOL_KCM 281
/* IPX options */
#define IPX_TYPE 1
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 881a79d52467..4bcf5a61aada 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -90,7 +90,21 @@ struct stmmac_dma_cfg {
int pbl;
int fixed_burst;
int mixed_burst;
- int burst_len;
+ bool aal;
+};
+
+#define AXI_BLEN 7
+struct stmmac_axi {
+ bool axi_lpi_en;
+ bool axi_xit_frm;
+ u32 axi_wr_osr_lmt;
+ u32 axi_rd_osr_lmt;
+ bool axi_kbbe;
+ bool axi_axi_all;
+ u32 axi_blen[AXI_BLEN];
+ bool axi_fb;
+ bool axi_mb;
+ bool axi_rb;
};
struct plat_stmmacenet_data {
@@ -123,5 +137,6 @@ struct plat_stmmacenet_data {
int (*init)(struct platform_device *pdev, void *priv);
void (*exit)(struct platform_device *pdev, void *priv);
void *bsp_priv;
+ struct stmmac_axi *axi;
};
#endif
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index b386361ba3e8..7be9b1242354 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -29,9 +29,14 @@ static inline struct tcphdr *tcp_hdr(const struct sk_buff *skb)
return (struct tcphdr *)skb_transport_header(skb);
}
+static inline unsigned int __tcp_hdrlen(const struct tcphdr *th)
+{
+ return th->doff * 4;
+}
+
static inline unsigned int tcp_hdrlen(const struct sk_buff *skb)
{
- return tcp_hdr(skb)->doff * 4;
+ return __tcp_hdrlen(tcp_hdr(skb));
}
static inline struct tcphdr *inner_tcp_hdr(const struct sk_buff *skb)
@@ -153,6 +158,9 @@ struct tcp_sock {
u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn
* total number of segments in.
*/
+ u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn
+ * total number of data segments in.
+ */
u32 rcv_nxt; /* What we want to receive next */
u32 copied_seq; /* Head of yet unread data */
u32 rcv_wup; /* rcv_nxt on last window update sent */
@@ -160,6 +168,9 @@ struct tcp_sock {
u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut
* The total number of segments sent.
*/
+ u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut
+ * total number of data segments sent.
+ */
u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked
* sum(delta(snd_una)), or how many bytes
* were acked.
@@ -256,6 +267,7 @@ struct tcp_sock {
u32 prr_delivered; /* Number of newly delivered packets to
* receiver in Recovery. */
u32 prr_out; /* Total number of pkts sent during Recovery. */
+ u32 delivered; /* Total data packets delivered incl. rexmits */
u32 rcv_wnd; /* Current receiver window */
u32 write_seq; /* Tail(+1) of data held in tcp send buffer */
diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h
index 2f6a3f2233ed..da3a77d25fcb 100644
--- a/include/net/6lowpan.h
+++ b/include/net/6lowpan.h
@@ -75,6 +75,8 @@
#define LOWPAN_IPHC_MAX_HC_BUF_LEN (sizeof(struct ipv6hdr) + \
LOWPAN_IPHC_MAX_HEADER_LEN + \
LOWPAN_NHC_MAX_HDR_LEN)
+/* SCI/DCI is 4 bit width, so we have maximum 16 entries */
+#define LOWPAN_IPHC_CTX_TABLE_SIZE (1 << 4)
#define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */
#define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */
@@ -98,9 +100,39 @@ enum lowpan_lltypes {
LOWPAN_LLTYPE_IEEE802154,
};
+enum lowpan_iphc_ctx_flags {
+ LOWPAN_IPHC_CTX_FLAG_ACTIVE,
+ LOWPAN_IPHC_CTX_FLAG_COMPRESSION,
+};
+
+struct lowpan_iphc_ctx {
+ u8 id;
+ struct in6_addr pfx;
+ u8 plen;
+ unsigned long flags;
+};
+
+struct lowpan_iphc_ctx_table {
+ spinlock_t lock;
+ const struct lowpan_iphc_ctx_ops *ops;
+ struct lowpan_iphc_ctx table[LOWPAN_IPHC_CTX_TABLE_SIZE];
+};
+
+static inline bool lowpan_iphc_ctx_is_active(const struct lowpan_iphc_ctx *ctx)
+{
+ return test_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE, &ctx->flags);
+}
+
+static inline bool
+lowpan_iphc_ctx_is_compression(const struct lowpan_iphc_ctx *ctx)
+{
+ return test_bit(LOWPAN_IPHC_CTX_FLAG_COMPRESSION, &ctx->flags);
+}
+
struct lowpan_priv {
enum lowpan_lltypes lltype;
struct dentry *iface_debugfs;
+ struct lowpan_iphc_ctx_table ctx;
/* must be last */
u8 priv[0] __aligned(sizeof(void *));
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 9d446f136607..2a19fe111c78 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -7,6 +7,8 @@
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
struct tcf_common {
struct hlist_node tcfc_head;
@@ -65,11 +67,6 @@ static inline int tcf_hashinfo_init(struct tcf_hashinfo *hf, unsigned int mask)
return 0;
}
-static inline void tcf_hashinfo_destroy(struct tcf_hashinfo *hf)
-{
- kfree(hf->htab);
-}
-
/* Update lastuse only if needed, to avoid dirtying a cache line.
* We use a temp variable to avoid fetching jiffies twice.
*/
@@ -81,42 +78,76 @@ static inline void tcf_lastuse_update(struct tcf_t *tm)
tm->lastuse = now;
}
-#ifdef CONFIG_NET_CLS_ACT
-
-#define ACT_P_CREATED 1
-#define ACT_P_DELETED 1
-
struct tc_action {
void *priv;
const struct tc_action_ops *ops;
__u32 type; /* for backward compat(TCA_OLD_COMPAT) */
__u32 order;
struct list_head list;
+ struct tcf_hashinfo *hinfo;
};
+#ifdef CONFIG_NET_CLS_ACT
+
+#define ACT_P_CREATED 1
+#define ACT_P_DELETED 1
+
struct tc_action_ops {
struct list_head head;
- struct tcf_hashinfo *hinfo;
char kind[IFNAMSIZ];
__u32 type; /* TBD to match kind */
struct module *owner;
int (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *);
int (*dump)(struct sk_buff *, struct tc_action *, int, int);
void (*cleanup)(struct tc_action *, int bind);
- int (*lookup)(struct tc_action *, u32);
+ int (*lookup)(struct net *, struct tc_action *, u32);
int (*init)(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action *act, int ovr,
int bind);
- int (*walk)(struct sk_buff *, struct netlink_callback *, int, struct tc_action *);
+ int (*walk)(struct net *, struct sk_buff *,
+ struct netlink_callback *, int, struct tc_action *);
+};
+
+struct tc_action_net {
+ struct tcf_hashinfo *hinfo;
+ const struct tc_action_ops *ops;
};
-int tcf_hash_search(struct tc_action *a, u32 index);
-u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo);
-int tcf_hash_check(u32 index, struct tc_action *a, int bind);
-int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
- int size, int bind, bool cpustats);
+static inline
+int tc_action_net_init(struct tc_action_net *tn, const struct tc_action_ops *ops,
+ unsigned int mask)
+{
+ int err = 0;
+
+ tn->hinfo = kmalloc(sizeof(*tn->hinfo), GFP_KERNEL);
+ if (!tn->hinfo)
+ return -ENOMEM;
+ tn->ops = ops;
+ err = tcf_hashinfo_init(tn->hinfo, mask);
+ if (err)
+ kfree(tn->hinfo);
+ return err;
+}
+
+void tcf_hashinfo_destroy(const struct tc_action_ops *ops,
+ struct tcf_hashinfo *hinfo);
+
+static inline void tc_action_net_exit(struct tc_action_net *tn)
+{
+ tcf_hashinfo_destroy(tn->ops, tn->hinfo);
+}
+
+int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
+ struct netlink_callback *cb, int type,
+ struct tc_action *a);
+int tcf_hash_search(struct tc_action_net *tn, struct tc_action *a, u32 index);
+u32 tcf_hash_new_index(struct tc_action_net *tn);
+int tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a,
+ int bind);
+int tcf_hash_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
+ struct tc_action *a, int size, int bind, bool cpustats);
void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
-void tcf_hash_insert(struct tc_action *a);
+void tcf_hash_insert(struct tc_action_net *tn, struct tc_action *a);
int __tcf_hash_release(struct tc_action *a, bool bind, bool strict);
@@ -125,8 +156,8 @@ static inline int tcf_hash_release(struct tc_action *a, bool bind)
return __tcf_hash_release(a, bind, false);
}
-int tcf_register_action(struct tc_action_ops *a, unsigned int mask);
-int tcf_unregister_action(struct tc_action_ops *a);
+int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
+int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops);
int tcf_action_destroy(struct list_head *actions, int bind);
int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions,
struct tcf_result *res);
@@ -140,5 +171,16 @@ int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
+
+#define tc_no_actions(_exts) \
+ (list_empty(&(_exts)->actions))
+
+#define tc_for_each_action(_a, _exts) \
+ list_for_each_entry(a, &(_exts)->actions, list)
+#else /* CONFIG_NET_CLS_ACT */
+
+#define tc_no_actions(_exts) true
+#define tc_for_each_action(_a, _exts) while (0)
+
#endif /* CONFIG_NET_CLS_ACT */
#endif
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 47f52d3cd8df..730d856683e5 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -87,6 +87,8 @@ int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
u32 banned_flags);
int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
u32 banned_flags);
+int ipv4_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
+ bool match_wildcard);
int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
bool match_wildcard);
void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr);
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 339ea57be423..5d38d980b89d 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -233,6 +233,7 @@ enum {
HCI_SC_ENABLED,
HCI_SC_ONLY,
HCI_PRIVACY,
+ HCI_LIMITED_PRIVACY,
HCI_RPA_EXPIRED,
HCI_RPA_RESOLVING,
HCI_HS_ENABLED,
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d4f82edb5cff..dc71473462ac 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -25,6 +25,7 @@
#ifndef __HCI_CORE_H
#define __HCI_CORE_H
+#include <linux/leds.h>
#include <net/bluetooth/hci.h>
#include <net/bluetooth/hci_sock.h>
@@ -396,6 +397,8 @@ struct hci_dev {
struct delayed_work rpa_expired;
bdaddr_t rpa;
+ struct led_trigger *power_led;
+
int (*open)(struct hci_dev *hdev);
int (*close)(struct hci_dev *hdev);
int (*flush)(struct hci_dev *hdev);
diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h
index f1fbc3b11962..f358ad5e4214 100644
--- a/include/net/bond_3ad.h
+++ b/include/net/bond_3ad.h
@@ -306,5 +306,6 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
struct slave *slave);
int bond_3ad_set_carrier(struct bonding *bond);
void bond_3ad_update_lacp_rate(struct bonding *bond);
+void bond_3ad_update_ad_actor_settings(struct bonding *bond);
#endif /* _NET_BOND_3AD_H */
diff --git a/include/net/bonding.h b/include/net/bonding.h
index ee6c52053aa3..791800ddd6d9 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -215,6 +215,7 @@ struct bonding {
* ALB mode (6) - to sync the use and modifications of its hash table
*/
spinlock_t mode_lock;
+ spinlock_t stats_lock;
u8 send_peer_notif;
u8 igmp_retrans;
#ifdef CONFIG_PROC_FS
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 9bcaaf7cd15a..9e1b24c29f0c 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -712,6 +712,8 @@ struct cfg80211_acl_data {
* @p2p_opp_ps: P2P opportunistic PS
* @acl: ACL configuration used by the drivers which has support for
* MAC address based access control
+ * @pbss: If set, start as a PCP instead of AP. Relevant for DMG
+ * networks.
*/
struct cfg80211_ap_settings {
struct cfg80211_chan_def chandef;
@@ -730,6 +732,7 @@ struct cfg80211_ap_settings {
u8 p2p_ctwindow;
bool p2p_opp_ps;
const struct cfg80211_acl_data *acl;
+ bool pbss;
};
/**
@@ -1888,6 +1891,8 @@ struct cfg80211_ibss_params {
* @ht_capa_mask: The bits of ht_capa which are to be used.
* @vht_capa: VHT Capability overrides
* @vht_capa_mask: The bits of vht_capa which are to be used.
+ * @pbss: if set, connect to a PCP instead of AP. Valid for DMG
+ * networks.
*/
struct cfg80211_connect_params {
struct ieee80211_channel *channel;
@@ -1910,6 +1915,7 @@ struct cfg80211_connect_params {
struct ieee80211_ht_cap ht_capa_mask;
struct ieee80211_vht_cap vht_capa;
struct ieee80211_vht_cap vht_capa_mask;
+ bool pbss;
};
/**
@@ -3489,6 +3495,7 @@ struct cfg80211_cached_keys;
* registered for unexpected class 3 frames (AP mode)
* @conn: (private) cfg80211 software SME connection state machine data
* @connect_keys: (private) keys to set after connection is established
+ * @conn_bss_type: connecting/connected BSS type
* @ibss_fixed: (private) IBSS is using fixed BSSID
* @ibss_dfs_possible: (private) IBSS may change to a DFS channel
* @event_list: (private) list for internal event processing
@@ -3519,6 +3526,7 @@ struct wireless_dev {
u8 ssid_len, mesh_id_len, mesh_id_up_len;
struct cfg80211_conn *conn;
struct cfg80211_cached_keys *connect_keys;
+ enum ieee80211_bss_type conn_bss_type;
struct list_head event_list;
spinlock_t event_lock;
diff --git a/include/net/checksum.h b/include/net/checksum.h
index 10a16b5bd1c7..5c30891e84e5 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -88,8 +88,11 @@ static inline __wsum
csum_block_add(__wsum csum, __wsum csum2, int offset)
{
u32 sum = (__force u32)csum2;
- if (offset&1)
- sum = ((sum&0xFF00FF)<<8)+((sum>>8)&0xFF00FF);
+
+ /* rotate sum to align it with a 16b boundary */
+ if (offset & 1)
+ sum = ror32(sum, 8);
+
return csum_add(csum, (__force __wsum)sum);
}
@@ -102,10 +105,7 @@ csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len)
static inline __wsum
csum_block_sub(__wsum csum, __wsum csum2, int offset)
{
- u32 sum = (__force u32)csum2;
- if (offset&1)
- sum = ((sum&0xFF00FF)<<8)+((sum>>8)&0xFF00FF);
- return csum_sub(csum, (__force __wsum)sum);
+ return csum_block_add(csum, ~csum2, offset);
}
static inline __wsum csum_unfold(__sum16 n)
@@ -120,6 +120,11 @@ static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum)
#define CSUM_MANGLED_0 ((__force __sum16)0xffff)
+static inline void csum_replace_by_diff(__sum16 *sum, __wsum diff)
+{
+ *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum)));
+}
+
static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to)
{
__wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from);
diff --git a/include/net/codel.h b/include/net/codel.h
index 267e70210061..d168aca115cc 100644
--- a/include/net/codel.h
+++ b/include/net/codel.h
@@ -162,12 +162,14 @@ struct codel_vars {
* struct codel_stats - contains codel shared variables and stats
* @maxpacket: largest packet we've seen so far
* @drop_count: temp count of dropped packets in dequeue()
+ * @drop_len: bytes of dropped packets in dequeue()
* ecn_mark: number of packets we ECN marked instead of dropping
* ce_mark: number of packets CE marked because sojourn time was above ce_threshold
*/
struct codel_stats {
u32 maxpacket;
u32 drop_count;
+ u32 drop_len;
u32 ecn_mark;
u32 ce_mark;
};
@@ -308,6 +310,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
vars->rec_inv_sqrt);
goto end;
}
+ stats->drop_len += qdisc_pkt_len(skb);
qdisc_drop(skb, sch);
stats->drop_count++;
skb = dequeue_func(vars, sch);
@@ -330,6 +333,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
if (params->ecn && INET_ECN_set_ce(skb)) {
stats->ecn_mark++;
} else {
+ stats->drop_len += qdisc_pkt_len(skb);
qdisc_drop(skb, sch);
stats->drop_count++;
diff --git a/include/net/devlink.h b/include/net/devlink.h
new file mode 100644
index 000000000000..c37d257891d6
--- /dev/null
+++ b/include/net/devlink.h
@@ -0,0 +1,140 @@
+/*
+ * include/net/devlink.h - Network physical device Netlink interface
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef _NET_DEVLINK_H_
+#define _NET_DEVLINK_H_
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/gfp.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <net/net_namespace.h>
+#include <uapi/linux/devlink.h>
+
+struct devlink_ops;
+
+struct devlink {
+ struct list_head list;
+ struct list_head port_list;
+ const struct devlink_ops *ops;
+ struct device *dev;
+ possible_net_t _net;
+ char priv[0] __aligned(NETDEV_ALIGN);
+};
+
+struct devlink_port {
+ struct list_head list;
+ struct devlink *devlink;
+ unsigned index;
+ bool registered;
+ enum devlink_port_type type;
+ enum devlink_port_type desired_type;
+ void *type_dev;
+ bool split;
+ u32 split_group;
+};
+
+struct devlink_ops {
+ size_t priv_size;
+ int (*port_type_set)(struct devlink_port *devlink_port,
+ enum devlink_port_type port_type);
+ int (*port_split)(struct devlink *devlink, unsigned int port_index,
+ unsigned int count);
+ int (*port_unsplit)(struct devlink *devlink, unsigned int port_index);
+};
+
+static inline void *devlink_priv(struct devlink *devlink)
+{
+ BUG_ON(!devlink);
+ return &devlink->priv;
+}
+
+static inline struct devlink *priv_to_devlink(void *priv)
+{
+ BUG_ON(!priv);
+ return container_of(priv, struct devlink, priv);
+}
+
+struct ib_device;
+
+#if IS_ENABLED(CONFIG_NET_DEVLINK)
+
+struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size);
+int devlink_register(struct devlink *devlink, struct device *dev);
+void devlink_unregister(struct devlink *devlink);
+void devlink_free(struct devlink *devlink);
+int devlink_port_register(struct devlink *devlink,
+ struct devlink_port *devlink_port,
+ unsigned int port_index);
+void devlink_port_unregister(struct devlink_port *devlink_port);
+void devlink_port_type_eth_set(struct devlink_port *devlink_port,
+ struct net_device *netdev);
+void devlink_port_type_ib_set(struct devlink_port *devlink_port,
+ struct ib_device *ibdev);
+void devlink_port_type_clear(struct devlink_port *devlink_port);
+void devlink_port_split_set(struct devlink_port *devlink_port,
+ u32 split_group);
+
+#else
+
+static inline struct devlink *devlink_alloc(const struct devlink_ops *ops,
+ size_t priv_size)
+{
+ return kzalloc(sizeof(struct devlink) + priv_size, GFP_KERNEL);
+}
+
+static inline int devlink_register(struct devlink *devlink, struct device *dev)
+{
+ return 0;
+}
+
+static inline void devlink_unregister(struct devlink *devlink)
+{
+}
+
+static inline void devlink_free(struct devlink *devlink)
+{
+ kfree(devlink);
+}
+
+static inline int devlink_port_register(struct devlink *devlink,
+ struct devlink_port *devlink_port,
+ unsigned int port_index)
+{
+ return 0;
+}
+
+static inline void devlink_port_unregister(struct devlink_port *devlink_port)
+{
+}
+
+static inline void devlink_port_type_eth_set(struct devlink_port *devlink_port,
+ struct net_device *netdev)
+{
+}
+
+static inline void devlink_port_type_ib_set(struct devlink_port *devlink_port,
+ struct ib_device *ibdev)
+{
+}
+
+static inline void devlink_port_type_clear(struct devlink_port *devlink_port)
+{
+}
+
+static inline void devlink_port_split_set(struct devlink_port *devlink_port,
+ u32 split_group)
+{
+}
+
+#endif
+
+#endif /* _NET_DEVLINK_H_ */
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 26a0e86e611e..6463bb2863ac 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -296,16 +296,17 @@ struct dsa_switch_driver {
/*
* Bridge integration
*/
- int (*port_join_bridge)(struct dsa_switch *ds, int port,
- u32 br_port_mask);
- int (*port_leave_bridge)(struct dsa_switch *ds, int port,
- u32 br_port_mask);
+ int (*port_bridge_join)(struct dsa_switch *ds, int port,
+ struct net_device *bridge);
+ void (*port_bridge_leave)(struct dsa_switch *ds, int port);
int (*port_stp_update)(struct dsa_switch *ds, int port,
u8 state);
/*
* VLAN support
*/
+ int (*port_vlan_filtering)(struct dsa_switch *ds, int port,
+ bool vlan_filtering);
int (*port_vlan_prepare)(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_vlan *vlan,
struct switchdev_trans *trans);
@@ -314,9 +315,9 @@ struct dsa_switch_driver {
struct switchdev_trans *trans);
int (*port_vlan_del)(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_vlan *vlan);
- int (*port_pvid_get)(struct dsa_switch *ds, int port, u16 *pvid);
- int (*vlan_getnext)(struct dsa_switch *ds, u16 *vid,
- unsigned long *ports, unsigned long *untagged);
+ int (*port_vlan_dump)(struct dsa_switch *ds, int port,
+ struct switchdev_obj_port_vlan *vlan,
+ int (*cb)(struct switchdev_obj *obj));
/*
* Forwarding database
diff --git a/include/net/dst.h b/include/net/dst.h
index c7329dcd90cc..5c98443c1c9e 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -398,6 +398,18 @@ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
__skb_tunnel_rx(skb, dev, net);
}
+static inline u32 dst_tclassid(const struct sk_buff *skb)
+{
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ const struct dst_entry *dst;
+
+ dst = skb_dst(skb);
+ if (dst)
+ return dst->tclassid;
+#endif
+ return 0;
+}
+
int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb);
static inline int dst_discard(struct sk_buff *skb)
{
diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h
new file mode 100644
index 000000000000..151accae708b
--- /dev/null
+++ b/include/net/dst_cache.h
@@ -0,0 +1,97 @@
+#ifndef _NET_DST_CACHE_H
+#define _NET_DST_CACHE_H
+
+#include <linux/jiffies.h>
+#include <net/dst.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ip6_fib.h>
+#endif
+
+struct dst_cache {
+ struct dst_cache_pcpu __percpu *cache;
+ unsigned long reset_ts;
+};
+
+/**
+ * dst_cache_get - perform cache lookup
+ * @dst_cache: the cache
+ *
+ * The caller should use dst_cache_get_ip4() if it need to retrieve the
+ * source address to be used when xmitting to the cached dst.
+ * local BH must be disabled.
+ */
+struct dst_entry *dst_cache_get(struct dst_cache *dst_cache);
+
+/**
+ * dst_cache_get_ip4 - perform cache lookup and fetch ipv4 source address
+ * @dst_cache: the cache
+ * @saddr: return value for the retrieved source address
+ *
+ * local BH must be disabled.
+ */
+struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr);
+
+/**
+ * dst_cache_set_ip4 - store the ipv4 dst into the cache
+ * @dst_cache: the cache
+ * @dst: the entry to be cached
+ * @saddr: the source address to be stored inside the cache
+ *
+ * local BH must be disabled.
+ */
+void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst,
+ __be32 saddr);
+
+#if IS_ENABLED(CONFIG_IPV6)
+
+/**
+ * dst_cache_set_ip6 - store the ipv6 dst into the cache
+ * @dst_cache: the cache
+ * @dst: the entry to be cached
+ * @saddr: the source address to be stored inside the cache
+ *
+ * local BH must be disabled.
+ */
+void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
+ const struct in6_addr *addr);
+
+/**
+ * dst_cache_get_ip6 - perform cache lookup and fetch ipv6 source address
+ * @dst_cache: the cache
+ * @saddr: return value for the retrieved source address
+ *
+ * local BH must be disabled.
+ */
+struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache,
+ struct in6_addr *saddr);
+#endif
+
+/**
+ * dst_cache_reset - invalidate the cache contents
+ * @dst_cache: the cache
+ *
+ * This do not free the cached dst to avoid races and contentions.
+ * the dst will be freed on later cache lookup.
+ */
+static inline void dst_cache_reset(struct dst_cache *dst_cache)
+{
+ dst_cache->reset_ts = jiffies;
+}
+
+/**
+ * dst_cache_init - initialize the cache, allocating the required storage
+ * @dst_cache: the cache
+ * @gfp: allocation flags
+ */
+int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp);
+
+/**
+ * dst_cache_destroy - empty the cache and free the allocated storage
+ * @dst_cache: the cache
+ *
+ * No synchronization is enforced: it must be called only when the cache
+ * is unsed.
+ */
+void dst_cache_destroy(struct dst_cache *dst_cache);
+
+#endif
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 30a56ab2ccfb..5db9f5910428 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -62,6 +62,7 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a,
sizeof(a->u.tun_info) + a->u.tun_info.options_len);
}
+void metadata_dst_free(struct metadata_dst *);
struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags);
@@ -125,7 +126,7 @@ static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb,
ip_tunnel_key_init(&tun_dst->u.tun_info.key,
iph->saddr, iph->daddr, iph->tos, iph->ttl,
- 0, 0, tunnel_id, flags);
+ 0, 0, 0, tunnel_id, flags);
return tun_dst;
}
@@ -151,8 +152,11 @@ static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb,
info->key.u.ipv6.src = ip6h->saddr;
info->key.u.ipv6.dst = ip6h->daddr;
+
info->key.tos = ipv6_get_dsfield(ip6h);
info->key.ttl = ip6h->hop_limit;
+ info->key.label = ip6_flowlabel(ip6h);
+
return tun_dst;
}
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 8c8548cf5888..d3d60dccd19f 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -184,4 +184,17 @@ static inline bool flow_keys_have_l4(struct flow_keys *keys)
u32 flow_hash_from_keys(struct flow_keys *keys);
+static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector,
+ enum flow_dissector_key_id key_id)
+{
+ return flow_dissector->used_keys & (1 << key_id);
+}
+
+static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissector,
+ enum flow_dissector_key_id key_id,
+ void *target_container)
+{
+ return ((char *)target_container) + flow_dissector->offset[key_id];
+}
+
#endif
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 43c0e771f417..8d4608ce8716 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -83,7 +83,6 @@ struct genl_family {
* @attrs: netlink attributes
* @_net: network namespace
* @user_ptr: user pointers
- * @dst_sk: destination socket
*/
struct genl_info {
u32 snd_seq;
@@ -94,7 +93,6 @@ struct genl_info {
struct nlattr ** attrs;
possible_net_t _net;
void * user_ptr[2];
- struct sock * dst_sk;
};
static inline struct net *genl_info_net(struct genl_info *info)
@@ -188,8 +186,6 @@ int genl_unregister_family(struct genl_family *family);
void genl_notify(struct genl_family *family, struct sk_buff *skb,
struct genl_info *info, u32 group, gfp_t flags);
-struct sk_buff *genlmsg_new_unicast(size_t payload, struct genl_info *info,
- gfp_t flags);
void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq,
struct genl_family *family, int flags, u8 cmd);
diff --git a/include/net/hwbm.h b/include/net/hwbm.h
new file mode 100644
index 000000000000..47d08662501b
--- /dev/null
+++ b/include/net/hwbm.h
@@ -0,0 +1,28 @@
+#ifndef _HWBM_H
+#define _HWBM_H
+
+struct hwbm_pool {
+ /* Capacity of the pool */
+ int size;
+ /* Size of the buffers managed */
+ int frag_size;
+ /* Number of buffers currently used by this pool */
+ int buf_num;
+ /* constructor called during alocation */
+ int (*construct)(struct hwbm_pool *bm_pool, void *buf);
+ /* protect acces to the buffer counter*/
+ spinlock_t lock;
+ /* private data */
+ void *priv;
+};
+#ifdef CONFIG_HWBM
+void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf);
+int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp);
+int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp);
+#else
+void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) {}
+int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) { return 0; }
+int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp)
+{ return 0; }
+#endif /* CONFIG_HWBM */
+#endif /* _HWBM_H */
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 7ff588ca6817..28332bdac333 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -53,6 +53,7 @@ struct sock *__inet6_lookup_established(struct net *net,
struct sock *inet6_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb, int doff,
const struct in6_addr *saddr,
const __be16 sport,
const struct in6_addr *daddr,
@@ -60,6 +61,7 @@ struct sock *inet6_lookup_listener(struct net *net,
static inline struct sock *__inet6_lookup(struct net *net,
struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb, int doff,
const struct in6_addr *saddr,
const __be16 sport,
const struct in6_addr *daddr,
@@ -71,12 +73,12 @@ static inline struct sock *__inet6_lookup(struct net *net,
if (sk)
return sk;
- return inet6_lookup_listener(net, hashinfo, saddr, sport,
+ return inet6_lookup_listener(net, hashinfo, skb, doff, saddr, sport,
daddr, hnum, dif);
}
static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
- struct sk_buff *skb,
+ struct sk_buff *skb, int doff,
const __be16 sport,
const __be16 dport,
int iif)
@@ -86,16 +88,19 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
if (sk)
return sk;
- return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo,
- &ipv6_hdr(skb)->saddr, sport,
+ return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
+ doff, &ipv6_hdr(skb)->saddr, sport,
&ipv6_hdr(skb)->daddr, ntohs(dport),
iif);
}
struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb, int doff,
const struct in6_addr *saddr, const __be16 sport,
const struct in6_addr *daddr, const __be16 dport,
const int dif);
+
+int inet6_hash(struct sock *sk);
#endif /* IS_ENABLED(CONFIG_IPV6) */
#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif) \
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 12aac0fd6ee7..909972aa3acd 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -13,6 +13,7 @@ struct netns_frags {
int timeout;
int high_thresh;
int low_thresh;
+ int max_dist;
};
/**
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index de2e3ade6102..50f635c2c536 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -207,12 +207,16 @@ void inet_hashinfo_init(struct inet_hashinfo *h);
bool inet_ehash_insert(struct sock *sk, struct sock *osk);
bool inet_ehash_nolisten(struct sock *sk, struct sock *osk);
-void __inet_hash(struct sock *sk, struct sock *osk);
-void inet_hash(struct sock *sk);
+int __inet_hash(struct sock *sk, struct sock *osk,
+ int (*saddr_same)(const struct sock *sk1,
+ const struct sock *sk2,
+ bool match_wildcard));
+int inet_hash(struct sock *sk);
void inet_unhash(struct sock *sk);
struct sock *__inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb, int doff,
const __be32 saddr, const __be16 sport,
const __be32 daddr,
const unsigned short hnum,
@@ -220,10 +224,11 @@ struct sock *__inet_lookup_listener(struct net *net,
static inline struct sock *inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb, int doff,
__be32 saddr, __be16 sport,
__be32 daddr, __be16 dport, int dif)
{
- return __inet_lookup_listener(net, hashinfo, saddr, sport,
+ return __inet_lookup_listener(net, hashinfo, skb, doff, saddr, sport,
daddr, ntohs(dport), dif);
}
@@ -299,6 +304,7 @@ static inline struct sock *
static inline struct sock *__inet_lookup(struct net *net,
struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb, int doff,
const __be32 saddr, const __be16 sport,
const __be32 daddr, const __be16 dport,
const int dif)
@@ -307,12 +313,13 @@ static inline struct sock *__inet_lookup(struct net *net,
struct sock *sk = __inet_lookup_established(net, hashinfo,
saddr, sport, daddr, hnum, dif);
- return sk ? : __inet_lookup_listener(net, hashinfo, saddr, sport,
- daddr, hnum, dif);
+ return sk ? : __inet_lookup_listener(net, hashinfo, skb, doff, saddr,
+ sport, daddr, hnum, dif);
}
static inline struct sock *inet_lookup(struct net *net,
struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb, int doff,
const __be32 saddr, const __be16 sport,
const __be32 daddr, const __be16 dport,
const int dif)
@@ -320,7 +327,8 @@ static inline struct sock *inet_lookup(struct net *net,
struct sock *sk;
local_bh_disable();
- sk = __inet_lookup(net, hashinfo, saddr, sport, daddr, dport, dif);
+ sk = __inet_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
+ dport, dif);
local_bh_enable();
return sk;
@@ -328,6 +336,7 @@ static inline struct sock *inet_lookup(struct net *net,
static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
struct sk_buff *skb,
+ int doff,
const __be16 sport,
const __be16 dport)
{
@@ -337,8 +346,8 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
if (sk)
return sk;
else
- return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo,
- iph->saddr, sport,
+ return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
+ doff, iph->saddr, sport,
iph->daddr, dport, inet_iif(skb));
}
diff --git a/include/net/ip.h b/include/net/ip.h
index 1a98f1ca1638..fad74d323bd6 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -240,17 +240,13 @@ static inline int inet_is_local_reserved_port(struct net *net, int port)
}
#endif
+__be32 inet_current_timestamp(void);
+
/* From inetpeer.c */
extern int inet_peer_threshold;
extern int inet_peer_minttl;
extern int inet_peer_maxttl;
-/* From ip_input.c */
-extern int sysctl_ip_early_demux;
-
-/* From ip_output.c */
-extern int sysctl_ip_dynaddr;
-
void ipfrag_init(void);
void ip_static_sysctl_init(void);
diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h
index 1a49b73f7f6e..cca840584c88 100644
--- a/include/net/ip6_checksum.h
+++ b/include/net/ip6_checksum.h
@@ -37,8 +37,7 @@
#ifndef _HAVE_ARCH_IPV6_CSUM
__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
const struct in6_addr *daddr,
- __u32 len, unsigned short proto,
- __wsum csum);
+ __u32 len, __u8 proto, __wsum csum);
#endif
static inline __wsum ip6_compute_pseudo(struct sk_buff *skb, int proto)
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 0d0ce0b2d870..499a707765ea 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -6,6 +6,7 @@
#include <linux/if_tunnel.h>
#include <linux/ip6_tunnel.h>
#include <net/ip_tunnels.h>
+#include <net/dst_cache.h>
#define IP6TUNNEL_ERR_TIMEO (30*HZ)
@@ -33,12 +34,6 @@ struct __ip6_tnl_parm {
__be32 o_key;
};
-struct ip6_tnl_dst {
- seqlock_t lock;
- struct dst_entry __rcu *dst;
- u32 cookie;
-};
-
/* IPv6 tunnel */
struct ip6_tnl {
struct ip6_tnl __rcu *next; /* next tunnel in list */
@@ -46,7 +41,7 @@ struct ip6_tnl {
struct net *net; /* netns for packet i/o */
struct __ip6_tnl_parm parms; /* tunnel configuration parameters */
struct flowi fl; /* flowi template for xmit */
- struct ip6_tnl_dst __percpu *dst_cache; /* cached dst */
+ struct dst_cache dst_cache; /* cached dst */
int err_count;
unsigned long err_time;
@@ -66,11 +61,6 @@ struct ipv6_tlv_tnl_enc_lim {
__u8 encap_limit; /* tunnel encapsulation limit */
} __packed;
-struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t);
-int ip6_tnl_dst_init(struct ip6_tnl *t);
-void ip6_tnl_dst_destroy(struct ip6_tnl *t);
-void ip6_tnl_dst_reset(struct ip6_tnl *t);
-void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst);
int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
const struct in6_addr *raddr);
int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index dda9abf6b89c..c35dda9ec991 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -7,12 +7,15 @@
#include <linux/socket.h>
#include <linux/types.h>
#include <linux/u64_stats_sync.h>
+#include <linux/bitops.h>
+
#include <net/dsfield.h>
#include <net/gro_cells.h>
#include <net/inet_ecn.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/lwtunnel.h>
+#include <net/dst_cache.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
@@ -47,6 +50,7 @@ struct ip_tunnel_key {
__be16 tun_flags;
u8 tos; /* TOS for IPv4, TC for IPv6 */
u8 ttl; /* TTL for IPv4, HL for IPv6 */
+ __be32 label; /* Flow Label for IPv6 */
__be16 tp_src;
__be16 tp_dst;
};
@@ -55,8 +59,16 @@ struct ip_tunnel_key {
#define IP_TUNNEL_INFO_TX 0x01 /* represents tx tunnel parameters */
#define IP_TUNNEL_INFO_IPV6 0x02 /* key contains IPv6 addresses */
+/* Maximum tunnel options length. */
+#define IP_TUNNEL_OPTS_MAX \
+ GENMASK((FIELD_SIZEOF(struct ip_tunnel_info, \
+ options_len) * BITS_PER_BYTE) - 1, 0)
+
struct ip_tunnel_info {
struct ip_tunnel_key key;
+#ifdef CONFIG_DST_CACHE
+ struct dst_cache dst_cache;
+#endif
u8 options_len;
u8 mode;
};
@@ -85,11 +97,6 @@ struct ip_tunnel_prl_entry {
struct rcu_head rcu_head;
};
-struct ip_tunnel_dst {
- struct dst_entry __rcu *dst;
- __be32 saddr;
-};
-
struct metadata_dst;
struct ip_tunnel {
@@ -108,7 +115,7 @@ struct ip_tunnel {
int tun_hlen; /* Precalculated header length */
int mlink;
- struct ip_tunnel_dst __percpu *dst_cache;
+ struct dst_cache dst_cache;
struct ip_tunnel_parm parms;
@@ -141,6 +148,7 @@ struct ip_tunnel {
#define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400)
#define TUNNEL_GENEVE_OPT __cpu_to_be16(0x0800)
#define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000)
+#define TUNNEL_NOCACHE __cpu_to_be16(0x2000)
#define TUNNEL_OPTIONS_PRESENT (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT)
@@ -181,7 +189,7 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
__be32 saddr, __be32 daddr,
- u8 tos, u8 ttl,
+ u8 tos, u8 ttl, __be32 label,
__be16 tp_src, __be16 tp_dst,
__be64 tun_id, __be16 tun_flags)
{
@@ -192,6 +200,7 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
0, IP_TUNNEL_KEY_IPV4_PAD_LEN);
key->tos = tos;
key->ttl = ttl;
+ key->label = label;
key->tun_flags = tun_flags;
/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
@@ -207,6 +216,20 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
0, sizeof(*key) - IP_TUNNEL_KEY_SIZE);
}
+static inline bool
+ip_tunnel_dst_cache_usable(const struct sk_buff *skb,
+ const struct ip_tunnel_info *info)
+{
+ if (skb->mark)
+ return false;
+ if (!info)
+ return true;
+ if (info->key.tun_flags & TUNNEL_NOCACHE)
+ return false;
+
+ return true;
+}
+
static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info
*tun_info)
{
@@ -248,7 +271,6 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p);
void ip_tunnel_setup(struct net_device *dev, int net_id);
-void ip_tunnel_dst_reset_all(struct ip_tunnel *t);
int ip_tunnel_encap_setup(struct ip_tunnel *t,
struct ip_tunnel_encap *ipencap);
@@ -273,15 +295,15 @@ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
return INET_ECN_encapsulate(tos, inner);
}
-int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto);
+int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto,
+ bool xnet);
void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, u8 proto,
u8 tos, u8 ttl, __be16 df, bool xnet);
struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
gfp_t flags);
-struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum,
- int gso_type_mask);
+struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask);
static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
{
@@ -356,6 +378,17 @@ static inline void ip_tunnel_unneed_metadata(void)
{
}
+static inline void ip_tunnel_info_opts_get(void *to,
+ const struct ip_tunnel_info *info)
+{
+}
+
+static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
+ const void *from, int len)
+{
+ info->options_len = 0;
+}
+
#endif /* CONFIG_INET */
#endif /* __NET_IP_TUNNELS_H */
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 0816c872b689..a6cc576fd467 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1588,6 +1588,23 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
}
#endif /* CONFIG_IP_VS_NFCT */
+/* Really using conntrack? */
+static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp,
+ struct sk_buff *skb)
+{
+#ifdef CONFIG_IP_VS_NFCT
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+
+ if (!(cp->flags & IP_VS_CONN_F_NFCT))
+ return false;
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct && !nf_ct_is_untracked(ct))
+ return true;
+#endif
+ return false;
+}
+
static inline int
ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
{
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 6570f379aba2..f3c9857c645d 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -259,8 +259,12 @@ static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
rcu_read_lock();
opt = rcu_dereference(np->opt);
- if (opt && !atomic_inc_not_zero(&opt->refcnt))
- opt = NULL;
+ if (opt) {
+ if (!atomic_inc_not_zero(&opt->refcnt))
+ opt = NULL;
+ else
+ opt = rcu_pointer_handoff(opt);
+ }
rcu_read_unlock();
return opt;
}
diff --git a/include/net/kcm.h b/include/net/kcm.h
new file mode 100644
index 000000000000..2840b5825dcc
--- /dev/null
+++ b/include/net/kcm.h
@@ -0,0 +1,226 @@
+/*
+ * Kernel Connection Multiplexor
+ *
+ * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
+ *
+ * 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 published by the Free Software Foundation.
+ */
+
+#ifndef __NET_KCM_H_
+#define __NET_KCM_H_
+
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <uapi/linux/kcm.h>
+
+extern unsigned int kcm_net_id;
+
+#define KCM_STATS_ADD(stat, count) ((stat) += (count))
+#define KCM_STATS_INCR(stat) ((stat)++)
+
+struct kcm_psock_stats {
+ unsigned long long rx_msgs;
+ unsigned long long rx_bytes;
+ unsigned long long tx_msgs;
+ unsigned long long tx_bytes;
+ unsigned int rx_aborts;
+ unsigned int rx_mem_fail;
+ unsigned int rx_need_more_hdr;
+ unsigned int rx_msg_too_big;
+ unsigned int rx_msg_timeouts;
+ unsigned int rx_bad_hdr_len;
+ unsigned long long reserved;
+ unsigned long long unreserved;
+ unsigned int tx_aborts;
+};
+
+struct kcm_mux_stats {
+ unsigned long long rx_msgs;
+ unsigned long long rx_bytes;
+ unsigned long long tx_msgs;
+ unsigned long long tx_bytes;
+ unsigned int rx_ready_drops;
+ unsigned int tx_retries;
+ unsigned int psock_attach;
+ unsigned int psock_unattach_rsvd;
+ unsigned int psock_unattach;
+};
+
+struct kcm_stats {
+ unsigned long long rx_msgs;
+ unsigned long long rx_bytes;
+ unsigned long long tx_msgs;
+ unsigned long long tx_bytes;
+};
+
+struct kcm_tx_msg {
+ unsigned int sent;
+ unsigned int fragidx;
+ unsigned int frag_offset;
+ unsigned int msg_flags;
+ struct sk_buff *frag_skb;
+ struct sk_buff *last_skb;
+};
+
+struct kcm_rx_msg {
+ int full_len;
+ int accum_len;
+ int offset;
+ int early_eaten;
+};
+
+/* Socket structure for KCM client sockets */
+struct kcm_sock {
+ struct sock sk;
+ struct kcm_mux *mux;
+ struct list_head kcm_sock_list;
+ int index;
+ u32 done : 1;
+ struct work_struct done_work;
+
+ struct kcm_stats stats;
+
+ /* Transmit */
+ struct kcm_psock *tx_psock;
+ struct work_struct tx_work;
+ struct list_head wait_psock_list;
+ struct sk_buff *seq_skb;
+
+ /* Don't use bit fields here, these are set under different locks */
+ bool tx_wait;
+ bool tx_wait_more;
+
+ /* Receive */
+ struct kcm_psock *rx_psock;
+ struct list_head wait_rx_list; /* KCMs waiting for receiving */
+ bool rx_wait;
+ u32 rx_disabled : 1;
+};
+
+struct bpf_prog;
+
+/* Structure for an attached lower socket */
+struct kcm_psock {
+ struct sock *sk;
+ struct kcm_mux *mux;
+ int index;
+
+ u32 tx_stopped : 1;
+ u32 rx_stopped : 1;
+ u32 done : 1;
+ u32 unattaching : 1;
+
+ void (*save_state_change)(struct sock *sk);
+ void (*save_data_ready)(struct sock *sk);
+ void (*save_write_space)(struct sock *sk);
+
+ struct list_head psock_list;
+
+ struct kcm_psock_stats stats;
+
+ /* Receive */
+ struct sk_buff *rx_skb_head;
+ struct sk_buff **rx_skb_nextp;
+ struct sk_buff *ready_rx_msg;
+ struct list_head psock_ready_list;
+ struct work_struct rx_work;
+ struct delayed_work rx_delayed_work;
+ struct bpf_prog *bpf_prog;
+ struct kcm_sock *rx_kcm;
+ unsigned long long saved_rx_bytes;
+ unsigned long long saved_rx_msgs;
+ struct timer_list rx_msg_timer;
+ unsigned int rx_need_bytes;
+
+ /* Transmit */
+ struct kcm_sock *tx_kcm;
+ struct list_head psock_avail_list;
+ unsigned long long saved_tx_bytes;
+ unsigned long long saved_tx_msgs;
+};
+
+/* Per net MUX list */
+struct kcm_net {
+ struct mutex mutex;
+ struct kcm_psock_stats aggregate_psock_stats;
+ struct kcm_mux_stats aggregate_mux_stats;
+ struct list_head mux_list;
+ int count;
+};
+
+/* Structure for a MUX */
+struct kcm_mux {
+ struct list_head kcm_mux_list;
+ struct rcu_head rcu;
+ struct kcm_net *knet;
+
+ struct list_head kcm_socks; /* All KCM sockets on MUX */
+ int kcm_socks_cnt; /* Total KCM socket count for MUX */
+ struct list_head psocks; /* List of all psocks on MUX */
+ int psocks_cnt; /* Total attached sockets */
+
+ struct kcm_mux_stats stats;
+ struct kcm_psock_stats aggregate_psock_stats;
+
+ /* Receive */
+ spinlock_t rx_lock ____cacheline_aligned_in_smp;
+ struct list_head kcm_rx_waiters; /* KCMs waiting for receiving */
+ struct list_head psocks_ready; /* List of psocks with a msg ready */
+ struct sk_buff_head rx_hold_queue;
+
+ /* Transmit */
+ spinlock_t lock ____cacheline_aligned_in_smp; /* TX and mux locking */
+ struct list_head psocks_avail; /* List of available psocks */
+ struct list_head kcm_tx_waiters; /* KCMs waiting for a TX psock */
+};
+
+#ifdef CONFIG_PROC_FS
+int kcm_proc_init(void);
+void kcm_proc_exit(void);
+#else
+static inline int kcm_proc_init(void) { return 0; }
+static inline void kcm_proc_exit(void) { }
+#endif
+
+static inline void aggregate_psock_stats(struct kcm_psock_stats *stats,
+ struct kcm_psock_stats *agg_stats)
+{
+ /* Save psock statistics in the mux when psock is being unattached. */
+
+#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat)
+ SAVE_PSOCK_STATS(rx_msgs);
+ SAVE_PSOCK_STATS(rx_bytes);
+ SAVE_PSOCK_STATS(rx_aborts);
+ SAVE_PSOCK_STATS(rx_mem_fail);
+ SAVE_PSOCK_STATS(rx_need_more_hdr);
+ SAVE_PSOCK_STATS(rx_msg_too_big);
+ SAVE_PSOCK_STATS(rx_msg_timeouts);
+ SAVE_PSOCK_STATS(rx_bad_hdr_len);
+ SAVE_PSOCK_STATS(tx_msgs);
+ SAVE_PSOCK_STATS(tx_bytes);
+ SAVE_PSOCK_STATS(reserved);
+ SAVE_PSOCK_STATS(unreserved);
+ SAVE_PSOCK_STATS(tx_aborts);
+#undef SAVE_PSOCK_STATS
+}
+
+static inline void aggregate_mux_stats(struct kcm_mux_stats *stats,
+ struct kcm_mux_stats *agg_stats)
+{
+ /* Save psock statistics in the mux when psock is being unattached. */
+
+#define SAVE_MUX_STATS(_stat) (agg_stats->_stat += stats->_stat)
+ SAVE_MUX_STATS(rx_msgs);
+ SAVE_MUX_STATS(rx_bytes);
+ SAVE_MUX_STATS(tx_msgs);
+ SAVE_MUX_STATS(tx_bytes);
+ SAVE_MUX_STATS(rx_ready_drops);
+ SAVE_MUX_STATS(psock_attach);
+ SAVE_MUX_STATS(psock_unattach_rsvd);
+ SAVE_MUX_STATS(psock_unattach);
+#undef SAVE_MUX_STATS
+}
+
+#endif /* __NET_KCM_H_ */
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index 5567d46b3cff..c43a9c73de5e 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -39,7 +39,7 @@ struct l3mdev_ops {
#ifdef CONFIG_NET_L3_MASTER_DEV
-int l3mdev_master_ifindex_rcu(struct net_device *dev);
+int l3mdev_master_ifindex_rcu(const struct net_device *dev);
static inline int l3mdev_master_ifindex(struct net_device *dev)
{
int ifindex;
@@ -179,7 +179,7 @@ struct dst_entry *l3mdev_rt6_dst_by_oif(struct net *net,
#else
-static inline int l3mdev_master_ifindex_rcu(struct net_device *dev)
+static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev)
{
return 0;
}
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 66350ce3e955..e9f116e29c22 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -170,6 +170,8 @@ static inline int lwtunnel_input(struct sk_buff *skb)
return -EOPNOTSUPP;
}
-#endif
+#endif /* CONFIG_LWTUNNEL */
+
+#define MODULE_ALIAS_RTNL_LWT(encap_type) MODULE_ALIAS("rtnl-lwt-" __stringify(encap_type))
#endif /* __NET_LWTUNNEL_H */
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 7c30faff245f..0c09da34b67a 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -5,7 +5,7 @@
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
- * Copyright (C) 2015 Intel Deutschland GmbH
+ * Copyright (C) 2015 - 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
@@ -298,6 +298,7 @@ struct ieee80211_vif_chanctx_switch {
* note that this is only called when it changes after the channel
* context had been assigned.
* @BSS_CHANGED_OCB: OCB join status changed
+ * @BSS_CHANGED_MU_GROUPS: VHT MU-MIMO group id or user position changed
*/
enum ieee80211_bss_change {
BSS_CHANGED_ASSOC = 1<<0,
@@ -323,6 +324,7 @@ enum ieee80211_bss_change {
BSS_CHANGED_BEACON_INFO = 1<<20,
BSS_CHANGED_BANDWIDTH = 1<<21,
BSS_CHANGED_OCB = 1<<22,
+ BSS_CHANGED_MU_GROUPS = 1<<23,
/* when adding here, make sure to change ieee80211_reconfig */
};
@@ -436,6 +438,19 @@ struct ieee80211_event {
};
/**
+ * struct ieee80211_mu_group_data - STA's VHT MU-MIMO group data
+ *
+ * This structure describes the group id data of VHT MU-MIMO
+ *
+ * @membership: 64 bits array - a bit is set if station is member of the group
+ * @position: 2 bits per group id indicating the position in the group
+ */
+struct ieee80211_mu_group_data {
+ u8 membership[WLAN_MEMBERSHIP_LEN];
+ u8 position[WLAN_USER_POSITION_LEN];
+};
+
+/**
* struct ieee80211_bss_conf - holds the BSS's changing parameters
*
* This structure keeps information about a BSS (and an association
@@ -477,6 +492,7 @@ struct ieee80211_event {
* @enable_beacon: whether beaconing should be enabled or not
* @chandef: Channel definition for this BSS -- the hardware might be
* configured a higher bandwidth than this BSS uses, for example.
+ * @mu_group: VHT MU-MIMO group membership data
* @ht_operation_mode: HT operation mode like in &struct ieee80211_ht_operation.
* This field is only valid when the channel is a wide HT/VHT channel.
* Note that with TDLS this can be the case (channel is HT, protection must
@@ -535,6 +551,7 @@ struct ieee80211_bss_conf {
s32 cqm_rssi_thold;
u32 cqm_rssi_hyst;
struct cfg80211_chan_def chandef;
+ struct ieee80211_mu_group_data mu_group;
__be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN];
int arp_addr_cnt;
bool qos;
@@ -691,12 +708,14 @@ enum mac80211_tx_info_flags {
* protocol frame (e.g. EAP)
* @IEEE80211_TX_CTRL_PS_RESPONSE: This frame is a response to a poll
* frame (PS-Poll or uAPSD).
+ * @IEEE80211_TX_CTRL_RATE_INJECT: This frame is injected with rate information
*
* These flags are used in tx_info->control.flags.
*/
enum mac80211_tx_control_flags {
IEEE80211_TX_CTRL_PORT_CTRL_PROTO = BIT(0),
IEEE80211_TX_CTRL_PS_RESPONSE = BIT(1),
+ IEEE80211_TX_CTRL_RATE_INJECT = BIT(2),
};
/*
@@ -993,6 +1012,8 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
* @RX_FLAG_MACTIME_END: The timestamp passed in the RX status (@mactime
* field) is valid and contains the time the last symbol of the MPDU
* (including FCS) was received.
+ * @RX_FLAG_MACTIME_PLCP_START: The timestamp passed in the RX status (@mactime
+ * field) is valid and contains the time the SYNC preamble was received.
* @RX_FLAG_SHORTPRE: Short preamble was used for this frame
* @RX_FLAG_HT: HT MCS was used and rate_idx is MCS index
* @RX_FLAG_VHT: VHT MCS was used and rate_index is MCS index
@@ -1014,6 +1035,14 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
* @RX_FLAG_AMPDU_DELIM_CRC_KNOWN: The delimiter CRC field is known (the CRC
* is stored in the @ampdu_delimiter_crc field)
* @RX_FLAG_LDPC: LDPC was used
+ * @RX_FLAG_ONLY_MONITOR: Report frame only to monitor interfaces without
+ * processing it in any regular way.
+ * This is useful if drivers offload some frames but still want to report
+ * them for sniffing purposes.
+ * @RX_FLAG_SKIP_MONITOR: Process and report frame to all interfaces except
+ * monitor interfaces.
+ * This is useful if drivers offload some frames but still want to report
+ * them for sniffing purposes.
* @RX_FLAG_STBC_MASK: STBC 2 bit bitmask. 1 - Nss=1, 2 - Nss=2, 3 - Nss=3
* @RX_FLAG_10MHZ: 10 MHz (half channel) was used
* @RX_FLAG_5MHZ: 5 MHz (quarter channel) was used
@@ -1033,6 +1062,7 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
enum mac80211_rx_flags {
RX_FLAG_MMIC_ERROR = BIT(0),
RX_FLAG_DECRYPTED = BIT(1),
+ RX_FLAG_MACTIME_PLCP_START = BIT(2),
RX_FLAG_MMIC_STRIPPED = BIT(3),
RX_FLAG_IV_STRIPPED = BIT(4),
RX_FLAG_FAILED_FCS_CRC = BIT(5),
@@ -1046,7 +1076,7 @@ enum mac80211_rx_flags {
RX_FLAG_HT_GF = BIT(13),
RX_FLAG_AMPDU_DETAILS = BIT(14),
RX_FLAG_PN_VALIDATED = BIT(15),
- /* bit 16 free */
+ RX_FLAG_DUP_VALIDATED = BIT(16),
RX_FLAG_AMPDU_LAST_KNOWN = BIT(17),
RX_FLAG_AMPDU_IS_LAST = BIT(18),
RX_FLAG_AMPDU_DELIM_CRC_ERROR = BIT(19),
@@ -1054,6 +1084,8 @@ enum mac80211_rx_flags {
RX_FLAG_MACTIME_END = BIT(21),
RX_FLAG_VHT = BIT(22),
RX_FLAG_LDPC = BIT(23),
+ RX_FLAG_ONLY_MONITOR = BIT(24),
+ RX_FLAG_SKIP_MONITOR = BIT(25),
RX_FLAG_STBC_MASK = BIT(26) | BIT(27),
RX_FLAG_10MHZ = BIT(28),
RX_FLAG_5MHZ = BIT(29),
@@ -1072,6 +1104,7 @@ enum mac80211_rx_flags {
* @RX_VHT_FLAG_160MHZ: 160 MHz was used
* @RX_VHT_FLAG_BF: packet was beamformed
*/
+
enum mac80211_rx_vht_flags {
RX_VHT_FLAG_80MHZ = BIT(0),
RX_VHT_FLAG_160MHZ = BIT(1),
@@ -1091,6 +1124,8 @@ enum mac80211_rx_vht_flags {
* it but can store it and pass it back to the driver for synchronisation
* @band: the active band when this frame was received
* @freq: frequency the radio was tuned to when receiving this frame, in MHz
+ * This field must be set for management frames, but isn't strictly needed
+ * for data (other) frames - for those it only affects radiotap reporting.
* @signal: signal strength when receiving this frame, either in dBm, in dB or
* unspecified depending on the hardware capabilities flags
* @IEEE80211_HW_SIGNAL_*
@@ -1347,6 +1382,7 @@ enum ieee80211_vif_flags {
* @csa_active: marks whether a channel switch is going on. Internally it is
* write-protected by sdata_lock and local->mtx so holding either is fine
* for read access.
+ * @mu_mimo_owner: indicates interface owns MU-MIMO capability
* @driver_flags: flags/capabilities the driver has for this interface,
* these need to be set (or cleared) when the interface is added
* or, if supported by the driver, the interface type is changed
@@ -1373,6 +1409,7 @@ struct ieee80211_vif {
u8 addr[ETH_ALEN];
bool p2p;
bool csa_active;
+ bool mu_mimo_owner;
u8 cab_queue;
u8 hw_queue[IEEE80211_NUM_ACS];
@@ -1486,9 +1523,8 @@ enum ieee80211_key_flags {
* wants to be given when a frame is transmitted and needs to be
* encrypted in hardware.
* @cipher: The key's cipher suite selector.
- * @tx_pn: PN used for TX on non-TKIP keys, may be used by the driver
- * as well if it needs to do software PN assignment by itself
- * (e.g. due to TSO)
+ * @tx_pn: PN used for TX keys, may be used by the driver as well if it
+ * needs to do software PN assignment by itself (e.g. due to TSO)
* @flags: key flags, see &enum ieee80211_key_flags.
* @keyidx: the key index (0-3)
* @keylen: key material length
@@ -1514,6 +1550,9 @@ struct ieee80211_key_conf {
#define IEEE80211_MAX_PN_LEN 16
+#define TKIP_PN_TO_IV16(pn) ((u16)(pn & 0xffff))
+#define TKIP_PN_TO_IV32(pn) ((u32)((pn >> 16) & 0xffffffff))
+
/**
* struct ieee80211_key_seq - key sequence counter
*
@@ -1684,6 +1723,18 @@ struct ieee80211_sta_rates {
* @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only
* valid if the STA is a TDLS peer in the first place.
* @mfp: indicates whether the STA uses management frame protection or not.
+ * @max_amsdu_subframes: indicates the maximal number of MSDUs in a single
+ * A-MSDU. Taken from the Extended Capabilities element. 0 means
+ * unlimited.
+ * @max_amsdu_len: indicates the maximal length of an A-MSDU in bytes. This
+ * field is always valid for packets with a VHT preamble. For packets
+ * with a HT preamble, additional limits apply:
+ * + If the skb is transmitted as part of a BA agreement, the
+ * A-MSDU maximal size is min(max_amsdu_len, 4065) bytes.
+ * + If the skb is not part of a BA aggreement, the A-MSDU maximal
+ * size is min(max_amsdu_len, 7935) bytes.
+ * Both additional HT limits must be enforced by the low level driver.
+ * This is defined by the spec (IEEE 802.11-2012 section 8.3.2.2 NOTE 2).
* @txq: per-TID data TX queues (if driver uses the TXQ abstraction)
*/
struct ieee80211_sta {
@@ -1702,6 +1753,8 @@ struct ieee80211_sta {
bool tdls;
bool tdls_initiator;
bool mfp;
+ u8 max_amsdu_subframes;
+ u16 max_amsdu_len;
struct ieee80211_txq *txq[IEEE80211_NUM_TIDS];
@@ -1910,6 +1963,11 @@ struct ieee80211_txq {
* by just its MAC address; this prevents, for example, the same station
* from connecting to two virtual AP interfaces at the same time.
*
+ * @IEEE80211_HW_SUPPORTS_REORDERING_BUFFER: Hardware (or driver) manages the
+ * reordering buffer internally, guaranteeing mac80211 receives frames in
+ * order and does not need to manage its own reorder buffer or BA session
+ * timeout.
+ *
* @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
*/
enum ieee80211_hw_flags {
@@ -1946,6 +2004,7 @@ enum ieee80211_hw_flags {
IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU,
IEEE80211_HW_BEACON_TX_STATUS,
IEEE80211_HW_NEEDS_UNIQUE_STA_ADDR,
+ IEEE80211_HW_SUPPORTS_REORDERING_BUFFER,
/* keep last, obviously */
NUM_IEEE80211_HW_FLAGS
@@ -2167,7 +2226,7 @@ static inline void SET_IEEE80211_DEV(struct ieee80211_hw *hw, struct device *dev
* @hw: the &struct ieee80211_hw to set the MAC address for
* @addr: the address to set
*/
-static inline void SET_IEEE80211_PERM_ADDR(struct ieee80211_hw *hw, u8 *addr)
+static inline void SET_IEEE80211_PERM_ADDR(struct ieee80211_hw *hw, const u8 *addr)
{
memcpy(hw->wiphy->perm_addr, addr, ETH_ALEN);
}
@@ -2684,6 +2743,33 @@ enum ieee80211_ampdu_mlme_action {
};
/**
+ * struct ieee80211_ampdu_params - AMPDU action parameters
+ *
+ * @action: the ampdu action, value from %ieee80211_ampdu_mlme_action.
+ * @sta: peer of this AMPDU session
+ * @tid: tid of the BA session
+ * @ssn: start sequence number of the session. TX/RX_STOP can pass 0. When
+ * action is set to %IEEE80211_AMPDU_RX_START the driver passes back the
+ * actual ssn value used to start the session and writes the value here.
+ * @buf_size: reorder buffer size (number of subframes). Valid only when the
+ * action is set to %IEEE80211_AMPDU_RX_START or
+ * %IEEE80211_AMPDU_TX_OPERATIONAL
+ * @amsdu: indicates the peer's ability to receive A-MSDU within A-MPDU.
+ * valid when the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL
+ * @timeout: BA session timeout. Valid only when the action is set to
+ * %IEEE80211_AMPDU_RX_START
+ */
+struct ieee80211_ampdu_params {
+ enum ieee80211_ampdu_mlme_action action;
+ struct ieee80211_sta *sta;
+ u16 tid;
+ u16 ssn;
+ u8 buf_size;
+ bool amsdu;
+ u16 timeout;
+};
+
+/**
* enum ieee80211_frame_release_type - frame release reason
* @IEEE80211_FRAME_RELEASE_PSPOLL: frame released for PS-Poll
* @IEEE80211_FRAME_RELEASE_UAPSD: frame(s) released due to
@@ -3027,13 +3113,9 @@ enum ieee80211_reconfig_type {
* @ampdu_action: Perform a certain A-MPDU action
* The RA/TID combination determines the destination and TID we want
* the ampdu action to be performed for. The action is defined through
- * ieee80211_ampdu_mlme_action. Starting sequence number (@ssn)
- * is the first frame we expect to perform the action on. Notice
- * that TX/RX_STOP can pass NULL for this parameter.
- * The @buf_size parameter is only valid when the action is set to
- * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's reorder
- * buffer size (number of subframes) for this session -- the driver
- * may neither send aggregates containing more subframes than this
+ * ieee80211_ampdu_mlme_action.
+ * When the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL the driver
+ * may neither send aggregates containing more subframes than @buf_size
* nor send aggregates in a way that lost frames would exceed the
* buffer size. If just limiting the aggregate size, this would be
* possible with a buf_size of 8:
@@ -3044,9 +3126,6 @@ enum ieee80211_reconfig_type {
* buffer size of 8. Correct ways to retransmit #1 would be:
* - TX: 1 or 18 or 81
* Even "189" would be wrong since 1 could be lost again.
- * The @amsdu parameter is valid when the action is set to
- * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's ability
- * to receive A-MSDU within A-MPDU.
*
* Returns a negative error code on failure.
* The callback can sleep.
@@ -3388,9 +3467,7 @@ struct ieee80211_ops {
int (*tx_last_beacon)(struct ieee80211_hw *hw);
int (*ampdu_action)(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
- enum ieee80211_ampdu_mlme_action action,
- struct ieee80211_sta *sta, u16 tid, u16 *ssn,
- u8 buf_size, bool amsdu);
+ struct ieee80211_ampdu_params *params);
int (*get_survey)(struct ieee80211_hw *hw, int idx,
struct survey_info *survey);
void (*rfkill_poll)(struct ieee80211_hw *hw);
@@ -4374,21 +4451,19 @@ void ieee80211_get_tkip_p2k(struct ieee80211_key_conf *keyconf,
struct sk_buff *skb, u8 *p2k);
/**
- * ieee80211_get_key_tx_seq - get key TX sequence counter
+ * ieee80211_tkip_add_iv - write TKIP IV and Ext. IV to pos
*
+ * @pos: start of crypto header
* @keyconf: the parameter passed with the set key
- * @seq: buffer to receive the sequence data
+ * @pn: PN to add
*
- * This function allows a driver to retrieve the current TX IV/PN
- * for the given key. It must not be called if IV generation is
- * offloaded to the device.
+ * Returns: pointer to the octet following IVs (i.e. beginning of
+ * the packet payload)
*
- * Note that this function may only be called when no TX processing
- * can be done concurrently, for example when queues are stopped
- * and the stop has been synchronized.
+ * This function writes the tkip IV value to pos (which should
+ * point to the crypto header)
*/
-void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf,
- struct ieee80211_key_seq *seq);
+u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key_conf *keyconf, u64 pn);
/**
* ieee80211_get_key_rx_seq - get key RX sequence counter
@@ -4410,23 +4485,6 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf,
int tid, struct ieee80211_key_seq *seq);
/**
- * ieee80211_set_key_tx_seq - set key TX sequence counter
- *
- * @keyconf: the parameter passed with the set key
- * @seq: new sequence data
- *
- * This function allows a driver to set the current TX IV/PNs for the
- * given key. This is useful when resuming from WoWLAN sleep and the
- * device may have transmitted frames using the PTK, e.g. replies to
- * ARP requests.
- *
- * Note that this function may only be called when no TX processing
- * can be done concurrently.
- */
-void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf,
- struct ieee80211_key_seq *seq);
-
-/**
* ieee80211_set_key_rx_seq - set key RX sequence counter
*
* @keyconf: the parameter passed with the set key
@@ -5121,6 +5179,24 @@ void ieee80211_stop_rx_ba_session(struct ieee80211_vif *vif, u16 ba_rx_bitmap,
const u8 *addr);
/**
+ * ieee80211_mark_rx_ba_filtered_frames - move RX BA window and mark filtered
+ * @pubsta: station struct
+ * @tid: the session's TID
+ * @ssn: starting sequence number of the bitmap, all frames before this are
+ * assumed to be out of the window after the call
+ * @filtered: bitmap of filtered frames, BIT(0) is the @ssn entry etc.
+ * @received_mpdus: number of received mpdus in firmware
+ *
+ * This function moves the BA window and releases all frames before @ssn, and
+ * marks frames marked in the bitmap as having been filtered. Afterwards, it
+ * checks if any frames in the window starting from @ssn can now be released
+ * (in case they were only waiting for frames that were filtered.)
+ */
+void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid,
+ u16 ssn, u64 filtered,
+ u16 received_mpdus);
+
+/**
* ieee80211_send_bar - send a BlockAckReq frame
*
* can be used to flush pending frames from the peer's aggregation reorder
@@ -5371,6 +5447,21 @@ ieee80211_vif_type_p2p(struct ieee80211_vif *vif)
return ieee80211_iftype_p2p(vif->type, vif->p2p);
}
+/**
+ * ieee80211_update_mu_groups - set the VHT MU-MIMO groud data
+ *
+ * @vif: the specified virtual interface
+ * @membership: 64 bits array - a bit is set if station is member of the group
+ * @position: 2 bits per group id indicating the position in the group
+ *
+ * Note: This function assumes that the given vif is valid and the position and
+ * membership data is of the correct size and are in the same byte order as the
+ * matching GroupId management frame.
+ * Calls to this function need to be serialized with RX path.
+ */
+void ieee80211_update_mu_groups(struct ieee80211_vif *vif,
+ const u8 *membership, const u8 *position);
+
void ieee80211_enable_rssi_reports(struct ieee80211_vif *vif,
int rssi_min_thold,
int rssi_max_thold);
@@ -5523,4 +5614,19 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid);
*/
struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
struct ieee80211_txq *txq);
+
+/**
+ * ieee80211_txq_get_depth - get pending frame/byte count of given txq
+ *
+ * The values are not guaranteed to be coherent with regard to each other, i.e.
+ * txq state can change half-way of this function and the caller may end up
+ * with "new" frame_cnt and "old" byte_cnt or vice-versa.
+ *
+ * @txq: pointer obtained from station or virtual interface
+ * @frame_cnt: pointer to store frame count
+ * @byte_cnt: pointer to store byte count
+ */
+void ieee80211_txq_get_depth(struct ieee80211_txq *txq,
+ unsigned long *frame_cnt,
+ unsigned long *byte_cnt);
#endif /* MAC80211_H */
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index da574bbdc333..6cd7a70706a9 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -16,10 +16,10 @@
#ifndef NET_MAC802154_H
#define NET_MAC802154_H
+#include <asm/unaligned.h>
#include <net/af_ieee802154.h>
#include <linux/ieee802154.h>
#include <linux/skbuff.h>
-#include <linux/unaligned/memmove.h>
#include <net/cfg802154.h>
@@ -247,13 +247,14 @@ struct ieee802154_ops {
*/
static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb)
{
- /* return some invalid fc on failure */
- if (unlikely(skb->len < 2)) {
+ /* check if we can fc at skb_mac_header of sk buffer */
+ if (unlikely(!skb_mac_header_was_set(skb) ||
+ (skb_tail_pointer(skb) - skb_mac_header(skb)) < 2)) {
WARN_ON(1);
return cpu_to_le16(0);
}
- return (__force __le16)__get_unaligned_memmove16(skb_mac_header(skb));
+ return get_unaligned_le16(skb_mac_header(skb));
}
/**
@@ -263,7 +264,7 @@ static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb)
*/
static inline void ieee802154_be64_to_le64(void *le64_dst, const void *be64_src)
{
- __put_unaligned_memmove64(swab64p(be64_src), le64_dst);
+ put_unaligned_le64(get_unaligned_be64(be64_src), le64_dst);
}
/**
@@ -273,7 +274,7 @@ static inline void ieee802154_be64_to_le64(void *le64_dst, const void *be64_src)
*/
static inline void ieee802154_le64_to_be64(void *be64_dst, const void *le64_src)
{
- __put_unaligned_memmove64(swab64p(le64_src), be64_dst);
+ put_unaligned_be64(get_unaligned_le64(le64_src), be64_dst);
}
/**
@@ -283,7 +284,7 @@ static inline void ieee802154_le64_to_be64(void *be64_dst, const void *le64_src)
*/
static inline void ieee802154_le16_to_be16(void *be16_dst, const void *le16_src)
{
- __put_unaligned_memmove16(swab16p(le16_src), be16_dst);
+ put_unaligned_be16(get_unaligned_le16(le16_src), be16_dst);
}
/**
diff --git a/include/net/netfilter/nft_masq.h b/include/net/netfilter/nft_masq.h
index e2a518b60e19..a3f3c11b2526 100644
--- a/include/net/netfilter/nft_masq.h
+++ b/include/net/netfilter/nft_masq.h
@@ -2,7 +2,9 @@
#define _NFT_MASQ_H_
struct nft_masq {
- u32 flags;
+ u32 flags;
+ enum nft_registers sreg_proto_min:8;
+ enum nft_registers sreg_proto_max:8;
};
extern const struct nla_policy nft_masq_policy[];
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 2b7907a35568..a69cde3ce460 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -80,9 +80,13 @@ struct netns_ipv4 {
int sysctl_tcp_ecn;
int sysctl_tcp_ecn_fallback;
+ int sysctl_ip_default_ttl;
int sysctl_ip_no_pmtu_disc;
int sysctl_ip_fwd_use_pmtu;
int sysctl_ip_nonlocal_bind;
+ /* Shall we try to damage output packets if routing dev changes? */
+ int sysctl_ip_dynaddr;
+ int sysctl_ip_early_demux;
int sysctl_fwmark_reflect;
int sysctl_tcp_fwmark_accept;
@@ -98,6 +102,21 @@ struct netns_ipv4 {
int sysctl_tcp_keepalive_probes;
int sysctl_tcp_keepalive_intvl;
+ int sysctl_tcp_syn_retries;
+ int sysctl_tcp_synack_retries;
+ int sysctl_tcp_syncookies;
+ int sysctl_tcp_reordering;
+ int sysctl_tcp_retries1;
+ int sysctl_tcp_retries2;
+ int sysctl_tcp_orphan_retries;
+ int sysctl_tcp_fin_timeout;
+ unsigned int sysctl_tcp_notsent_lowat;
+
+ int sysctl_igmp_max_memberships;
+ int sysctl_igmp_max_msf;
+ int sysctl_igmp_llm_reports;
+ int sysctl_igmp_qrv;
+
struct ping_group_range ping_group_range;
atomic_t dev_addr_genid;
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index c0368db6df54..10d0848f5b8a 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -58,7 +58,10 @@ struct netns_ipv6 {
struct timer_list ip6_fib_timer;
struct hlist_head *fib_table_hash;
struct fib6_table *fib6_main_tbl;
+ struct list_head fib6_walkers;
struct dst_ops ip6_dst_ops;
+ rwlock_t fib6_walker_lock;
+ spinlock_t fib6_gc_lock;
unsigned int ip6_rt_gc_expire;
unsigned long ip6_rt_last_gc;
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h
index 68e509750caa..039cc29cb4a8 100644
--- a/include/net/phonet/phonet.h
+++ b/include/net/phonet/phonet.h
@@ -51,7 +51,7 @@ void pn_sock_init(void);
struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *sa);
void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb);
void phonet_get_local_port_range(int *min, int *max);
-void pn_sock_hash(struct sock *sk);
+int pn_sock_hash(struct sock *sk);
void pn_sock_unhash(struct sock *sk);
int pn_sock_get_port(struct sock *sk, unsigned short sport);
diff --git a/include/net/ping.h b/include/net/ping.h
index ac80cb45e630..5fd7cc244833 100644
--- a/include/net/ping.h
+++ b/include/net/ping.h
@@ -65,7 +65,7 @@ struct pingfakehdr {
};
int ping_get_port(struct sock *sk, unsigned short ident);
-void ping_hash(struct sock *sk);
+int ping_hash(struct sock *sk);
void ping_unhash(struct sock *sk);
int ping_init_sock(struct sock *sk);
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index bc49967e1a68..caa5e18636df 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -358,4 +358,69 @@ tcf_match_indev(struct sk_buff *skb, int ifindex)
}
#endif /* CONFIG_NET_CLS_IND */
+struct tc_cls_u32_knode {
+ struct tcf_exts *exts;
+ struct tc_u32_sel *sel;
+ u32 handle;
+ u32 val;
+ u32 mask;
+ u32 link_handle;
+ u8 fshift;
+};
+
+struct tc_cls_u32_hnode {
+ u32 handle;
+ u32 prio;
+ unsigned int divisor;
+};
+
+enum tc_clsu32_command {
+ TC_CLSU32_NEW_KNODE,
+ TC_CLSU32_REPLACE_KNODE,
+ TC_CLSU32_DELETE_KNODE,
+ TC_CLSU32_NEW_HNODE,
+ TC_CLSU32_REPLACE_HNODE,
+ TC_CLSU32_DELETE_HNODE,
+};
+
+struct tc_cls_u32_offload {
+ /* knode values */
+ enum tc_clsu32_command command;
+ union {
+ struct tc_cls_u32_knode knode;
+ struct tc_cls_u32_hnode hnode;
+ };
+};
+
+/* tca flags definitions */
+#define TCA_CLS_FLAGS_SKIP_HW 1
+
+static inline bool tc_should_offload(struct net_device *dev, u32 flags)
+{
+ if (!(dev->features & NETIF_F_HW_TC))
+ return false;
+
+ if (flags & TCA_CLS_FLAGS_SKIP_HW)
+ return false;
+
+ if (!dev->netdev_ops->ndo_setup_tc)
+ return false;
+
+ return true;
+}
+
+enum tc_fl_command {
+ TC_CLSFLOWER_REPLACE,
+ TC_CLSFLOWER_DESTROY,
+};
+
+struct tc_cls_flower_offload {
+ enum tc_fl_command command;
+ unsigned long cookie;
+ struct flow_dissector *dissector;
+ struct fl_flow_key *mask;
+ struct fl_flow_key *key;
+ struct tcf_exts *exts;
+};
+
#endif
diff --git a/include/net/raw.h b/include/net/raw.h
index 6a40c6562dd2..3e789008394d 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -57,7 +57,7 @@ int raw_seq_open(struct inode *ino, struct file *file,
#endif
-void raw_hash_sk(struct sock *sk);
+int raw_hash_sk(struct sock *sk);
void raw_unhash_sk(struct sock *sk);
struct raw_sock {
diff --git a/include/net/route.h b/include/net/route.h
index a3b9ef74a389..9b0a523bb428 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -329,14 +329,13 @@ static inline int inet_iif(const struct sk_buff *skb)
return skb->skb_iif;
}
-extern int sysctl_ip_default_ttl;
-
static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
{
int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
+ struct net *net = dev_net(dst->dev);
if (hoplimit == 0)
- hoplimit = sysctl_ip_default_ttl;
+ hoplimit = net->ipv4.sysctl_ip_default_ttl;
return hoplimit;
}
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 636a362a0e03..46e55f0202a6 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -345,6 +345,12 @@ extern struct Qdisc_ops pfifo_fast_ops;
extern struct Qdisc_ops mq_qdisc_ops;
extern struct Qdisc_ops noqueue_qdisc_ops;
extern const struct Qdisc_ops *default_qdisc_ops;
+static inline const struct Qdisc_ops *
+get_default_qdisc_ops(const struct net_device *dev, int ntx)
+{
+ return ntx < dev->real_num_tx_queues ?
+ default_qdisc_ops : &pfifo_fast_ops;
+}
struct Qdisc_class_common {
u32 classid;
@@ -396,7 +402,8 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
struct Qdisc *qdisc);
void qdisc_reset(struct Qdisc *qdisc);
void qdisc_destroy(struct Qdisc *qdisc);
-void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n);
+void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
+ unsigned int len);
struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
const struct Qdisc_ops *ops);
struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
@@ -707,6 +714,23 @@ static inline void qdisc_reset_queue(struct Qdisc *sch)
sch->qstats.backlog = 0;
}
+static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
+ struct Qdisc **pold)
+{
+ struct Qdisc *old;
+
+ sch_tree_lock(sch);
+ old = *pold;
+ *pold = new;
+ if (old != NULL) {
+ qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog);
+ qdisc_reset(old);
+ }
+ sch_tree_unlock(sch);
+
+ return old;
+}
+
static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch,
struct sk_buff_head *list)
{
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 487ef34bbd63..efc01743b9d6 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -201,7 +201,7 @@ struct sctp_chunk *sctp_make_cwr(const struct sctp_association *,
struct sctp_chunk * sctp_make_datafrag_empty(struct sctp_association *,
const struct sctp_sndrcvinfo *sinfo,
int len, const __u8 flags,
- __u16 ssn);
+ __u16 ssn, gfp_t gfp);
struct sctp_chunk *sctp_make_ecne(const struct sctp_association *,
const __u32);
struct sctp_chunk *sctp_make_sack(const struct sctp_association *);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 5a57409da37b..e2ac0620d4be 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -535,7 +535,6 @@ struct sctp_datamsg {
struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *,
struct sctp_sndrcvinfo *,
struct iov_iter *);
-void sctp_datamsg_free(struct sctp_datamsg *);
void sctp_datamsg_put(struct sctp_datamsg *);
void sctp_chunk_fail(struct sctp_chunk *, int error);
int sctp_chunk_abandoned(struct sctp_chunk *);
@@ -656,7 +655,7 @@ void sctp_chunk_free(struct sctp_chunk *);
void *sctp_addto_chunk(struct sctp_chunk *, int len, const void *data);
struct sctp_chunk *sctp_chunkify(struct sk_buff *,
const struct sctp_association *,
- struct sock *);
+ struct sock *, gfp_t gfp);
void sctp_init_addrs(struct sctp_chunk *, union sctp_addr *,
union sctp_addr *);
const union sctp_addr *sctp_source(const struct sctp_chunk *chunk);
@@ -718,10 +717,10 @@ struct sctp_packet *sctp_packet_init(struct sctp_packet *,
__u16 sport, __u16 dport);
struct sctp_packet *sctp_packet_config(struct sctp_packet *, __u32 vtag, int);
sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *,
- struct sctp_chunk *, int);
+ struct sctp_chunk *, int, gfp_t);
sctp_xmit_t sctp_packet_append_chunk(struct sctp_packet *,
struct sctp_chunk *);
-int sctp_packet_transmit(struct sctp_packet *);
+int sctp_packet_transmit(struct sctp_packet *, gfp_t);
void sctp_packet_free(struct sctp_packet *);
static inline int sctp_packet_empty(struct sctp_packet *packet)
@@ -1054,7 +1053,7 @@ struct sctp_outq {
void sctp_outq_init(struct sctp_association *, struct sctp_outq *);
void sctp_outq_teardown(struct sctp_outq *);
void sctp_outq_free(struct sctp_outq*);
-int sctp_outq_tail(struct sctp_outq *, struct sctp_chunk *chunk);
+int sctp_outq_tail(struct sctp_outq *, struct sctp_chunk *chunk, gfp_t);
int sctp_outq_sack(struct sctp_outq *, struct sctp_chunk *);
int sctp_outq_is_empty(const struct sctp_outq *);
void sctp_outq_restart(struct sctp_outq *);
@@ -1062,7 +1061,7 @@ void sctp_outq_restart(struct sctp_outq *);
void sctp_retransmit(struct sctp_outq *, struct sctp_transport *,
sctp_retransmit_reason_t);
void sctp_retransmit_mark(struct sctp_outq *, struct sctp_transport *, __u8);
-int sctp_outq_uncork(struct sctp_outq *);
+int sctp_outq_uncork(struct sctp_outq *, gfp_t gfp);
/* Uncork and flush an outqueue. */
static inline void sctp_outq_cork(struct sctp_outq *q)
{
diff --git a/include/net/sock.h b/include/net/sock.h
index f5ea148853e2..255d3e03727b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -984,7 +984,7 @@ struct proto {
void (*release_cb)(struct sock *sk);
/* Keeping track of sk's, looking them up, and port selection methods. */
- void (*hash)(struct sock *sk);
+ int (*hash)(struct sock *sk);
void (*unhash)(struct sock *sk);
void (*rehash)(struct sock *sk);
int (*get_port)(struct sock *sk, unsigned short snum);
@@ -1194,10 +1194,10 @@ static inline void sock_prot_inuse_add(struct net *net, struct proto *prot,
/* With per-bucket locks this operation is not-atomic, so that
* this version is not worse.
*/
-static inline void __sk_prot_rehash(struct sock *sk)
+static inline int __sk_prot_rehash(struct sock *sk)
{
sk->sk_prot->unhash(sk);
- sk->sk_prot->hash(sk);
+ return sk->sk_prot->hash(sk);
}
void sk_prot_clear_portaddr_nulls(struct sock *sk, int size);
diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h
index 592a6bc02b0b..93c520b83d10 100644
--- a/include/net/tc_act/tc_gact.h
+++ b/include/net/tc_act/tc_gact.h
@@ -2,6 +2,7 @@
#define __NET_TC_GACT_H
#include <net/act_api.h>
+#include <linux/tc_act/tc_gact.h>
struct tcf_gact {
struct tcf_common common;
@@ -15,4 +16,19 @@ struct tcf_gact {
#define to_gact(a) \
container_of(a->priv, struct tcf_gact, common)
+static inline bool is_tcf_gact_shot(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ struct tcf_gact *gact;
+
+ if (a->ops && a->ops->type != TCA_ACT_GACT)
+ return false;
+
+ gact = a->priv;
+ if (gact->tcf_action == TC_ACT_SHOT)
+ return true;
+
+#endif
+ return false;
+}
#endif /* __NET_TC_GACT_H */
diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h
new file mode 100644
index 000000000000..dc9a09aefb33
--- /dev/null
+++ b/include/net/tc_act/tc_ife.h
@@ -0,0 +1,61 @@
+#ifndef __NET_TC_IFE_H
+#define __NET_TC_IFE_H
+
+#include <net/act_api.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/module.h>
+
+#define IFE_METAHDRLEN 2
+struct tcf_ife_info {
+ struct tcf_common common;
+ u8 eth_dst[ETH_ALEN];
+ u8 eth_src[ETH_ALEN];
+ u16 eth_type;
+ u16 flags;
+ /* list of metaids allowed */
+ struct list_head metalist;
+};
+#define to_ife(a) \
+ container_of(a->priv, struct tcf_ife_info, common)
+
+struct tcf_meta_info {
+ const struct tcf_meta_ops *ops;
+ void *metaval;
+ u16 metaid;
+ struct list_head metalist;
+};
+
+struct tcf_meta_ops {
+ u16 metaid; /*Maintainer provided ID */
+ u16 metatype; /*netlink attribute type (look at net/netlink.h) */
+ const char *name;
+ const char *synopsis;
+ struct list_head list;
+ int (*check_presence)(struct sk_buff *, struct tcf_meta_info *);
+ int (*encode)(struct sk_buff *, void *, struct tcf_meta_info *);
+ int (*decode)(struct sk_buff *, void *, u16 len);
+ int (*get)(struct sk_buff *skb, struct tcf_meta_info *mi);
+ int (*alloc)(struct tcf_meta_info *, void *);
+ void (*release)(struct tcf_meta_info *);
+ int (*validate)(void *val, int len);
+ struct module *owner;
+};
+
+#define MODULE_ALIAS_IFE_META(metan) MODULE_ALIAS("ifemeta" __stringify_1(metan))
+
+int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi);
+int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi);
+int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
+ const void *dval);
+int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval);
+int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval);
+int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi);
+int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi);
+int ife_validate_meta_u32(void *val, int len);
+int ife_validate_meta_u16(void *val, int len);
+void ife_release_meta_gen(struct tcf_meta_info *mi);
+int register_ife_op(struct tcf_meta_ops *mops);
+int unregister_ife_op(struct tcf_meta_ops *mops);
+
+#endif /* __NET_TC_IFE_H */
diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h
index 0df9a0db4a8e..b496d5ad7d42 100644
--- a/include/net/tc_act/tc_skbedit.h
+++ b/include/net/tc_act/tc_skbedit.h
@@ -20,6 +20,7 @@
#define __NET_TC_SKBEDIT_H
#include <net/act_api.h>
+#include <linux/tc_act/tc_skbedit.h>
struct tcf_skbedit {
struct tcf_common common;
@@ -32,4 +33,19 @@ struct tcf_skbedit {
#define to_skbedit(a) \
container_of(a->priv, struct tcf_skbedit, common)
+/* Return true iff action is mark */
+static inline bool is_tcf_skbedit_mark(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ if (a->ops && a->ops->type == TCA_ACT_SKBEDIT)
+ return to_skbedit(a)->flags == SKBEDIT_F_MARK;
+#endif
+ return false;
+}
+
+static inline u32 tcf_skbedit_mark(const struct tc_action *a)
+{
+ return to_skbedit(a)->mark;
+}
+
#endif /* __NET_TC_SKBEDIT_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b04bc989ad6c..b91370f61be6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -238,13 +238,6 @@ extern struct inet_timewait_death_row tcp_death_row;
extern int sysctl_tcp_timestamps;
extern int sysctl_tcp_window_scaling;
extern int sysctl_tcp_sack;
-extern int sysctl_tcp_fin_timeout;
-extern int sysctl_tcp_syn_retries;
-extern int sysctl_tcp_synack_retries;
-extern int sysctl_tcp_retries1;
-extern int sysctl_tcp_retries2;
-extern int sysctl_tcp_orphan_retries;
-extern int sysctl_tcp_syncookies;
extern int sysctl_tcp_fastopen;
extern int sysctl_tcp_retrans_collapse;
extern int sysctl_tcp_stdurg;
@@ -273,7 +266,6 @@ extern int sysctl_tcp_thin_dupack;
extern int sysctl_tcp_early_retrans;
extern int sysctl_tcp_limit_output_bytes;
extern int sysctl_tcp_challenge_ack_limit;
-extern unsigned int sysctl_tcp_notsent_lowat;
extern int sysctl_tcp_min_tso_segs;
extern int sysctl_tcp_min_rtt_wlen;
extern int sysctl_tcp_autocorking;
@@ -567,6 +559,7 @@ void tcp_rearm_rto(struct sock *sk);
void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);
void tcp_reset(struct sock *sk);
void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb);
+void tcp_fin(struct sock *sk);
/* tcp_timer.c */
void tcp_init_xmit_timers(struct sock *);
@@ -962,9 +955,11 @@ static inline void tcp_enable_fack(struct tcp_sock *tp)
*/
static inline void tcp_enable_early_retrans(struct tcp_sock *tp)
{
+ struct net *net = sock_net((struct sock *)tp);
+
tp->do_early_retrans = sysctl_tcp_early_retrans &&
sysctl_tcp_early_retrans < 4 && !sysctl_tcp_thin_dupack &&
- sysctl_tcp_reordering == 3;
+ net->ipv4.sysctl_tcp_reordering == 3;
}
static inline void tcp_disable_early_retrans(struct tcp_sock *tp)
@@ -1251,7 +1246,7 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)
static inline int tcp_fin_time(const struct sock *sk)
{
- int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout;
+ int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout;
const int rto = inet_csk(sk)->icsk_rto;
if (fin_timeout < (rto << 2) - (rto >> 1))
@@ -1433,6 +1428,7 @@ void tcp_free_fastopen_req(struct tcp_sock *tp);
extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
int tcp_fastopen_reset_cipher(void *key, unsigned int len);
+void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
@@ -1681,7 +1677,8 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
{
- return tp->notsent_lowat ?: sysctl_tcp_notsent_lowat;
+ struct net *net = sock_net((struct sock *)tp);
+ return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat;
}
static inline bool tcp_stream_memory_free(const struct sock *sk)
@@ -1815,4 +1812,38 @@ static inline void skb_set_tcp_pure_ack(struct sk_buff *skb)
skb->truesize = 2;
}
+static inline int tcp_inq(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ int answ;
+
+ if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
+ answ = 0;
+ } else if (sock_flag(sk, SOCK_URGINLINE) ||
+ !tp->urg_data ||
+ before(tp->urg_seq, tp->copied_seq) ||
+ !before(tp->urg_seq, tp->rcv_nxt)) {
+
+ answ = tp->rcv_nxt - tp->copied_seq;
+
+ /* Subtract 1, if FIN was received */
+ if (answ && sock_flag(sk, SOCK_DONE))
+ answ--;
+ } else {
+ answ = tp->urg_seq - tp->copied_seq;
+ }
+
+ return answ;
+}
+
+static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb)
+{
+ u16 segs_in;
+
+ segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs);
+ tp->segs_in += segs_in;
+ if (skb->len > tcp_hdrlen(skb))
+ tp->data_segs_in += segs_in;
+}
+
#endif /* _TCP_H */
diff --git a/include/net/udp.h b/include/net/udp.h
index 2842541e28e7..92927f729ac8 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -177,9 +177,10 @@ static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
}
/* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
-static inline void udp_lib_hash(struct sock *sk)
+static inline int udp_lib_hash(struct sock *sk)
{
BUG();
+ return 0;
}
void udp_lib_unhash(struct sock *sk);
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index cca2ad3082c3..b83114077cee 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -88,8 +88,8 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb,
struct net_device *dev, struct in6_addr *saddr,
struct in6_addr *daddr,
- __u8 prio, __u8 ttl, __be16 src_port,
- __be16 dst_port, bool nocheck);
+ __u8 prio, __u8 ttl, __be32 label,
+ __be16 src_port, __be16 dst_port, bool nocheck);
#endif
void udp_tunnel_sock_release(struct socket *sock);
@@ -103,7 +103,7 @@ static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb,
{
int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
- return iptunnel_handle_offloads(skb, udp_csum, type);
+ return iptunnel_handle_offloads(skb, type);
}
static inline void udp_tunnel_gro_complete(struct sk_buff *skb, int nhoff)
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 0fb86442544b..a763c96ecde4 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -9,17 +9,71 @@
#include <linux/udp.h>
#include <net/dst_metadata.h>
+/* VXLAN protocol (RFC 7348) header:
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |R|R|R|R|I|R|R|R| Reserved |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | VXLAN Network Identifier (VNI) | Reserved |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * I = VXLAN Network Identifier (VNI) present.
+ */
+struct vxlanhdr {
+ __be32 vx_flags;
+ __be32 vx_vni;
+};
+
+/* VXLAN header flags. */
+#define VXLAN_HF_VNI cpu_to_be32(BIT(27))
+
+#define VXLAN_N_VID (1u << 24)
+#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
+#define VXLAN_VNI_MASK cpu_to_be32(VXLAN_VID_MASK << 8)
+#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
+
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
+#define FDB_HASH_BITS 8
+#define FDB_HASH_SIZE (1<<FDB_HASH_BITS)
+
+/* Remote checksum offload for VXLAN (VXLAN_F_REMCSUM_[RT]X):
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |R|R|R|R|I|R|R|R|R|R|C| Reserved |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | VXLAN Network Identifier (VNI) |O| Csum start |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * C = Remote checksum offload bit. When set indicates that the
+ * remote checksum offload data is present.
+ *
+ * O = Offset bit. Indicates the checksum offset relative to
+ * checksum start.
+ *
+ * Csum start = Checksum start divided by two.
+ *
+ * http://tools.ietf.org/html/draft-herbert-vxlan-rco
+ */
+
+/* VXLAN-RCO header flags. */
+#define VXLAN_HF_RCO cpu_to_be32(BIT(21))
+
+/* Remote checksum offload header option */
+#define VXLAN_RCO_MASK cpu_to_be32(0x7f) /* Last byte of vni field */
+#define VXLAN_RCO_UDP cpu_to_be32(0x80) /* Indicate UDP RCO (TCP when not set *) */
+#define VXLAN_RCO_SHIFT 1 /* Left shift of start */
+#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1)
+#define VXLAN_MAX_REMCSUM_START (0x7f << VXLAN_RCO_SHIFT)
/*
- * VXLAN Group Based Policy Extension:
+ * VXLAN Group Based Policy Extension (VXLAN_F_GBP):
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * |1|-|-|-|1|-|-|-|R|D|R|R|A|R|R|R| Group Policy ID |
+ * |G|R|R|R|I|R|R|R|R|D|R|R|A|R|R|R| Group Policy ID |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | VXLAN Network Identifier (VNI) | Reserved |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
+ * G = Group Policy ID present.
+ *
* D = Don't Learn bit. When set, this bit indicates that the egress
* VTEP MUST NOT learn the source address of the encapsulated frame.
*
@@ -27,18 +81,18 @@
* this packet. Policies MUST NOT be applied by devices when the
* A bit is set.
*
- * [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy
+ * https://tools.ietf.org/html/draft-smith-vxlan-group-policy
*/
struct vxlanhdr_gbp {
- __u8 vx_flags;
+ u8 vx_flags;
#ifdef __LITTLE_ENDIAN_BITFIELD
- __u8 reserved_flags1:3,
+ u8 reserved_flags1:3,
policy_applied:1,
reserved_flags2:2,
dont_learn:1,
reserved_flags3:1;
#elif defined(__BIG_ENDIAN_BITFIELD)
- __u8 reserved_flags1:1,
+ u8 reserved_flags1:1,
dont_learn:1,
reserved_flags2:2,
policy_applied:1,
@@ -50,7 +104,10 @@ struct vxlanhdr_gbp {
__be32 vx_vni;
};
-#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | 0xFFFFFF)
+/* VXLAN-GBP header flags. */
+#define VXLAN_HF_GBP cpu_to_be32(BIT(31))
+
+#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | cpu_to_be32(0xFFFFFF))
/* skb->mark mapping
*
@@ -62,44 +119,6 @@ struct vxlanhdr_gbp {
#define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16)
#define VXLAN_GBP_ID_MASK (0xFFFF)
-/* VXLAN protocol header:
- * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * |G|R|R|R|I|R|R|C| Reserved |
- * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * | VXLAN Network Identifier (VNI) | Reserved |
- * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- *
- * G = 1 Group Policy (VXLAN-GBP)
- * I = 1 VXLAN Network Identifier (VNI) present
- * C = 1 Remote checksum offload (RCO)
- */
-struct vxlanhdr {
- __be32 vx_flags;
- __be32 vx_vni;
-};
-
-/* VXLAN header flags. */
-#define VXLAN_HF_RCO BIT(21)
-#define VXLAN_HF_VNI BIT(27)
-#define VXLAN_HF_GBP BIT(31)
-
-/* Remote checksum offload header option */
-#define VXLAN_RCO_MASK 0x7f /* Last byte of vni field */
-#define VXLAN_RCO_UDP 0x80 /* Indicate UDP RCO (TCP when not set *) */
-#define VXLAN_RCO_SHIFT 1 /* Left shift of start */
-#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1)
-#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT)
-
-#define VXLAN_N_VID (1u << 24)
-#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
-#define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8)
-#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
-
-#define VNI_HASH_BITS 10
-#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
-#define FDB_HASH_BITS 8
-#define FDB_HASH_SIZE (1<<FDB_HASH_BITS)
-
struct vxlan_metadata {
u32 gbp;
};
@@ -125,23 +144,25 @@ union vxlan_addr {
struct vxlan_rdst {
union vxlan_addr remote_ip;
__be16 remote_port;
- u32 remote_vni;
+ __be32 remote_vni;
u32 remote_ifindex;
struct list_head list;
struct rcu_head rcu;
+ struct dst_cache dst_cache;
};
struct vxlan_config {
union vxlan_addr remote_ip;
union vxlan_addr saddr;
- u32 vni;
+ __be32 vni;
int remote_ifindex;
int mtu;
__be16 dst_port;
- __u16 port_min;
- __u16 port_max;
- __u8 tos;
- __u8 ttl;
+ u16 port_min;
+ u16 port_max;
+ u8 tos;
+ u8 ttl;
+ __be32 label;
u32 flags;
unsigned long age_interval;
unsigned int addrmax;
@@ -177,7 +198,7 @@ struct vxlan_dev {
#define VXLAN_F_L2MISS 0x08
#define VXLAN_F_L3MISS 0x10
#define VXLAN_F_IPV6 0x20
-#define VXLAN_F_UDP_CSUM 0x40
+#define VXLAN_F_UDP_ZERO_CSUM_TX 0x40
#define VXLAN_F_UDP_ZERO_CSUM6_TX 0x80
#define VXLAN_F_UDP_ZERO_CSUM6_RX 0x100
#define VXLAN_F_REMCSUM_TX 0x200
@@ -242,6 +263,68 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
/* IPv6 header + UDP + VXLAN + Ethernet header */
#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)
+static inline struct vxlanhdr *vxlan_hdr(struct sk_buff *skb)
+{
+ return (struct vxlanhdr *)(udp_hdr(skb) + 1);
+}
+
+static inline __be32 vxlan_vni(__be32 vni_field)
+{
+#if defined(__BIG_ENDIAN)
+ return vni_field >> 8;
+#else
+ return (vni_field & VXLAN_VNI_MASK) << 8;
+#endif
+}
+
+static inline __be32 vxlan_vni_field(__be32 vni)
+{
+#if defined(__BIG_ENDIAN)
+ return vni << 8;
+#else
+ return vni >> 8;
+#endif
+}
+
+static inline __be32 vxlan_tun_id_to_vni(__be64 tun_id)
+{
+#if defined(__BIG_ENDIAN)
+ return tun_id;
+#else
+ return tun_id >> 32;
+#endif
+}
+
+static inline __be64 vxlan_vni_to_tun_id(__be32 vni)
+{
+#if defined(__BIG_ENDIAN)
+ return (__be64)vni;
+#else
+ return (__be64)vni << 32;
+#endif
+}
+
+static inline size_t vxlan_rco_start(__be32 vni_field)
+{
+ return be32_to_cpu(vni_field & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT;
+}
+
+static inline size_t vxlan_rco_offset(__be32 vni_field)
+{
+ return (vni_field & VXLAN_RCO_UDP) ?
+ offsetof(struct udphdr, check) :
+ offsetof(struct tcphdr, check);
+}
+
+static inline __be32 vxlan_compute_rco(unsigned int start, unsigned int offset)
+{
+ __be32 vni_field = cpu_to_be32(start >> VXLAN_RCO_SHIFT);
+
+ if (offset == offsetof(struct udphdr, check))
+ vni_field |= VXLAN_RCO_UDP;
+ return vni_field;
+}
+
#if IS_ENABLED(CONFIG_VXLAN)
void vxlan_get_rx_port(struct net_device *netdev);
#else
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index c34c9002460c..931a47ba4571 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -262,24 +262,22 @@ static inline enum ib_mtu iboe_get_mtu(int mtu)
static inline int iboe_get_rate(struct net_device *dev)
{
- struct ethtool_cmd cmd;
- u32 speed;
+ struct ethtool_link_ksettings cmd;
int err;
rtnl_lock();
- err = __ethtool_get_settings(dev, &cmd);
+ err = __ethtool_get_link_ksettings(dev, &cmd);
rtnl_unlock();
if (err)
return IB_RATE_PORT_CURRENT;
- speed = ethtool_cmd_speed(&cmd);
- if (speed >= 40000)
+ if (cmd.base.speed >= 40000)
return IB_RATE_40_GBPS;
- else if (speed >= 30000)
+ else if (cmd.base.speed >= 30000)
return IB_RATE_30_GBPS;
- else if (speed >= 20000)
+ else if (cmd.base.speed >= 20000)
return IB_RATE_20_GBPS;
- else if (speed >= 10000)
+ else if (cmd.base.speed >= 10000)
return IB_RATE_10_GBPS;
else
return IB_RATE_PORT_CURRENT;
diff --git a/include/rxrpc/packet.h b/include/rxrpc/packet.h
index 4dce116bfd80..9ebab3a8cf0a 100644
--- a/include/rxrpc/packet.h
+++ b/include/rxrpc/packet.h
@@ -22,7 +22,7 @@ typedef __be32 rxrpc_serial_net_t; /* on-the-wire Rx message serial number */
* on-the-wire Rx packet header
* - all multibyte fields should be in network byte order
*/
-struct rxrpc_header {
+struct rxrpc_wire_header {
__be32 epoch; /* client boot timestamp */
__be32 cid; /* connection and channel ID */
@@ -68,10 +68,19 @@ struct rxrpc_header {
} __packed;
-#define __rxrpc_header_off(X) offsetof(struct rxrpc_header,X)
-
extern const char *rxrpc_pkts[];
+#define RXRPC_SUPPORTED_PACKET_TYPES ( \
+ (1 << RXRPC_PACKET_TYPE_DATA) | \
+ (1 << RXRPC_PACKET_TYPE_ACK) | \
+ (1 << RXRPC_PACKET_TYPE_BUSY) | \
+ (1 << RXRPC_PACKET_TYPE_ABORT) | \
+ (1 << RXRPC_PACKET_TYPE_ACKALL) | \
+ (1 << RXRPC_PACKET_TYPE_CHALLENGE) | \
+ (1 << RXRPC_PACKET_TYPE_RESPONSE) | \
+ /*(1 << RXRPC_PACKET_TYPE_DEBUG) | */ \
+ (1 << RXRPC_PACKET_TYPE_VERSION))
+
/*****************************************************************************/
/*
* jumbo packet secondary header
diff --git a/include/trace/events/sunvnet.h b/include/trace/events/sunvnet.h
new file mode 100644
index 000000000000..eb080b267e55
--- /dev/null
+++ b/include/trace/events/sunvnet.h
@@ -0,0 +1,139 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sunvnet
+
+#if !defined(_TRACE_SUNVNET_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SUNVNET_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(vnet_rx_one,
+
+ TP_PROTO(int lsid, int rsid, int index, int needs_ack),
+
+ TP_ARGS(lsid, rsid, index, needs_ack),
+
+ TP_STRUCT__entry(
+ __field(int, lsid)
+ __field(int, rsid)
+ __field(int, index)
+ __field(int, needs_ack)
+ ),
+
+ TP_fast_assign(
+ __entry->lsid = lsid;
+ __entry->rsid = rsid;
+ __entry->index = index;
+ __entry->needs_ack = needs_ack;
+ ),
+
+ TP_printk("(%x:%x) walk_rx_one index %d; needs_ack %d",
+ __entry->lsid, __entry->rsid,
+ __entry->index, __entry->needs_ack)
+);
+
+DECLARE_EVENT_CLASS(vnet_tx_stopped_ack_template,
+
+ TP_PROTO(int lsid, int rsid, int ack_end, int npkts),
+
+ TP_ARGS(lsid, rsid, ack_end, npkts),
+
+ TP_STRUCT__entry(
+ __field(int, lsid)
+ __field(int, rsid)
+ __field(int, ack_end)
+ __field(int, npkts)
+ ),
+
+ TP_fast_assign(
+ __entry->lsid = lsid;
+ __entry->rsid = rsid;
+ __entry->ack_end = ack_end;
+ __entry->npkts = npkts;
+ ),
+
+ TP_printk("(%x:%x) stopped ack for %d; npkts %d",
+ __entry->lsid, __entry->rsid,
+ __entry->ack_end, __entry->npkts)
+);
+DEFINE_EVENT(vnet_tx_stopped_ack_template, vnet_tx_send_stopped_ack,
+ TP_PROTO(int lsid, int rsid, int ack_end, int npkts),
+ TP_ARGS(lsid, rsid, ack_end, npkts));
+DEFINE_EVENT(vnet_tx_stopped_ack_template, vnet_tx_defer_stopped_ack,
+ TP_PROTO(int lsid, int rsid, int ack_end, int npkts),
+ TP_ARGS(lsid, rsid, ack_end, npkts));
+DEFINE_EVENT(vnet_tx_stopped_ack_template, vnet_tx_pending_stopped_ack,
+ TP_PROTO(int lsid, int rsid, int ack_end, int npkts),
+ TP_ARGS(lsid, rsid, ack_end, npkts));
+
+TRACE_EVENT(vnet_rx_stopped_ack,
+
+ TP_PROTO(int lsid, int rsid, int end),
+
+ TP_ARGS(lsid, rsid, end),
+
+ TP_STRUCT__entry(
+ __field(int, lsid)
+ __field(int, rsid)
+ __field(int, end)
+ ),
+
+ TP_fast_assign(
+ __entry->lsid = lsid;
+ __entry->rsid = rsid;
+ __entry->end = end;
+ ),
+
+ TP_printk("(%x:%x) stopped ack for index %d",
+ __entry->lsid, __entry->rsid, __entry->end)
+);
+
+TRACE_EVENT(vnet_tx_trigger,
+
+ TP_PROTO(int lsid, int rsid, int start, int err),
+
+ TP_ARGS(lsid, rsid, start, err),
+
+ TP_STRUCT__entry(
+ __field(int, lsid)
+ __field(int, rsid)
+ __field(int, start)
+ __field(int, err)
+ ),
+
+ TP_fast_assign(
+ __entry->lsid = lsid;
+ __entry->rsid = rsid;
+ __entry->start = start;
+ __entry->err = err;
+ ),
+
+ TP_printk("(%x:%x) Tx trigger for %d sent with err %d %s",
+ __entry->lsid, __entry->rsid, __entry->start,
+ __entry->err, __entry->err > 0 ? "(ok)" : " ")
+);
+
+TRACE_EVENT(vnet_skip_tx_trigger,
+
+ TP_PROTO(int lsid, int rsid, int last),
+
+ TP_ARGS(lsid, rsid, last),
+
+ TP_STRUCT__entry(
+ __field(int, lsid)
+ __field(int, rsid)
+ __field(int, last)
+ ),
+
+ TP_fast_assign(
+ __entry->lsid = lsid;
+ __entry->rsid = rsid;
+ __entry->last = last;
+ ),
+
+ TP_printk("(%x:%x) Skip Tx trigger. Last trigger sent was %d",
+ __entry->lsid, __entry->rsid, __entry->last)
+);
+#endif /* _TRACE_SOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index fb8a41668382..67d632f1743d 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -90,4 +90,6 @@
#define SO_ATTACH_REUSEPORT_CBPF 51
#define SO_ATTACH_REUSEPORT_EBPF 52
+#define SO_CNX_ADVICE 53
+
#endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 5c9ae6a9b7f5..0495884defc1 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -174,6 +174,7 @@ header-y += if_hippi.h
header-y += if_infiniband.h
header-y += if_link.h
header-y += if_ltalk.h
+header-y += if_macsec.h
header-y += if_packet.h
header-y += if_phonet.h
header-y += if_plip.h
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5df4881dea7b..924f537183fd 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -81,6 +81,9 @@ enum bpf_map_type {
BPF_MAP_TYPE_ARRAY,
BPF_MAP_TYPE_PROG_ARRAY,
BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+ BPF_MAP_TYPE_PERCPU_HASH,
+ BPF_MAP_TYPE_PERCPU_ARRAY,
+ BPF_MAP_TYPE_STACK_TRACE,
};
enum bpf_prog_type {
@@ -98,12 +101,15 @@ enum bpf_prog_type {
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
#define BPF_EXIST 2 /* update existing element */
+#define BPF_F_NO_PREALLOC (1U << 0)
+
union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */
__u32 map_type; /* one of enum bpf_map_type */
__u32 key_size; /* size of key in bytes */
__u32 value_size; /* size of value in bytes */
__u32 max_entries; /* max number of entries in a map */
+ __u32 map_flags; /* prealloc or not */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -270,6 +276,42 @@ enum bpf_func_id {
*/
BPF_FUNC_perf_event_output,
BPF_FUNC_skb_load_bytes,
+
+ /**
+ * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id
+ * @ctx: struct pt_regs*
+ * @map: pointer to stack_trace map
+ * @flags: bits 0-7 - numer of stack frames to skip
+ * bit 8 - collect user stack instead of kernel
+ * bit 9 - compare stacks by hash only
+ * bit 10 - if two different stacks hash into the same stackid
+ * discard old
+ * other bits - reserved
+ * Return: >= 0 stackid on success or negative error
+ */
+ BPF_FUNC_get_stackid,
+
+ /**
+ * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff
+ * @from: raw from buffer
+ * @from_size: length of from buffer
+ * @to: raw to buffer
+ * @to_size: length of to buffer
+ * @seed: optional seed
+ * Return: csum result
+ */
+ BPF_FUNC_csum_diff,
+
+ /**
+ * bpf_skb_[gs]et_tunnel_opt(skb, opt, size)
+ * retrieve or populate tunnel options metadata
+ * @skb: pointer to skb
+ * @opt: pointer to raw tunnel option data
+ * @size: size of @opt
+ * Return: 0 on success for set, option size for get
+ */
+ BPF_FUNC_skb_get_tunnel_opt,
+ BPF_FUNC_skb_set_tunnel_opt,
__BPF_FUNC_MAX_ID,
};
@@ -277,6 +319,7 @@ enum bpf_func_id {
/* BPF_FUNC_skb_store_bytes flags. */
#define BPF_F_RECOMPUTE_CSUM (1ULL << 0)
+#define BPF_F_INVALIDATE_HASH (1ULL << 1)
/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags.
* First 4 bits are for passing the header field size.
@@ -285,6 +328,7 @@ enum bpf_func_id {
/* BPF_FUNC_l4_csum_replace flags. */
#define BPF_F_PSEUDO_HDR (1ULL << 4)
+#define BPF_F_MARK_MANGLED_0 (1ULL << 5)
/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
#define BPF_F_INGRESS (1ULL << 0)
@@ -292,8 +336,15 @@ enum bpf_func_id {
/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
#define BPF_F_TUNINFO_IPV6 (1ULL << 0)
+/* BPF_FUNC_get_stackid flags. */
+#define BPF_F_SKIP_FIELD_MASK 0xffULL
+#define BPF_F_USER_STACK (1ULL << 8)
+#define BPF_F_FAST_STACK_CMP (1ULL << 9)
+#define BPF_F_REUSE_STACKID (1ULL << 10)
+
/* BPF_FUNC_skb_set_tunnel_key flags. */
#define BPF_F_ZERO_CSUM_TX (1ULL << 1)
+#define BPF_F_DONT_FRAGMENT (1ULL << 2)
/* user accessible mirror of in-kernel sk_buff.
* new fields can only be added to the end of this structure
@@ -324,6 +375,7 @@ struct bpf_tunnel_key {
};
__u8 tunnel_tos;
__u8 tunnel_ttl;
+ __u32 tunnel_label;
};
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
new file mode 100644
index 000000000000..c9fee5781eb1
--- /dev/null
+++ b/include/uapi/linux/devlink.h
@@ -0,0 +1,72 @@
+/*
+ * include/uapi/linux/devlink.h - Network physical device Netlink interface
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_DEVLINK_H_
+#define _UAPI_LINUX_DEVLINK_H_
+
+#define DEVLINK_GENL_NAME "devlink"
+#define DEVLINK_GENL_VERSION 0x1
+#define DEVLINK_GENL_MCGRP_CONFIG_NAME "config"
+
+enum devlink_command {
+ /* don't change the order or add anything between, this is ABI! */
+ DEVLINK_CMD_UNSPEC,
+
+ DEVLINK_CMD_GET, /* can dump */
+ DEVLINK_CMD_SET,
+ DEVLINK_CMD_NEW,
+ DEVLINK_CMD_DEL,
+
+ DEVLINK_CMD_PORT_GET, /* can dump */
+ DEVLINK_CMD_PORT_SET,
+ DEVLINK_CMD_PORT_NEW,
+ DEVLINK_CMD_PORT_DEL,
+
+ DEVLINK_CMD_PORT_SPLIT,
+ DEVLINK_CMD_PORT_UNSPLIT,
+
+ /* add new commands above here */
+
+ __DEVLINK_CMD_MAX,
+ DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
+};
+
+enum devlink_port_type {
+ DEVLINK_PORT_TYPE_NOTSET,
+ DEVLINK_PORT_TYPE_AUTO,
+ DEVLINK_PORT_TYPE_ETH,
+ DEVLINK_PORT_TYPE_IB,
+};
+
+enum devlink_attr {
+ /* don't change the order or add anything between, this is ABI! */
+ DEVLINK_ATTR_UNSPEC,
+
+ /* bus name + dev name together are a handle for devlink entity */
+ DEVLINK_ATTR_BUS_NAME, /* string */
+ DEVLINK_ATTR_DEV_NAME, /* string */
+
+ DEVLINK_ATTR_PORT_INDEX, /* u32 */
+ DEVLINK_ATTR_PORT_TYPE, /* u16 */
+ DEVLINK_ATTR_PORT_DESIRED_TYPE, /* u16 */
+ DEVLINK_ATTR_PORT_NETDEV_IFINDEX, /* u32 */
+ DEVLINK_ATTR_PORT_NETDEV_NAME, /* string */
+ DEVLINK_ATTR_PORT_IBDEV_NAME, /* string */
+ DEVLINK_ATTR_PORT_SPLIT_COUNT, /* u32 */
+ DEVLINK_ATTR_PORT_SPLIT_GROUP, /* u32 */
+
+ /* add new attributes above here, update the policy in devlink.c */
+
+ __DEVLINK_ATTR_MAX,
+ DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1
+};
+
+#endif /* _UAPI_LINUX_DEVLINK_H_ */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 57fa39005e79..2835b07416b7 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -13,15 +13,21 @@
#ifndef _UAPI_LINUX_ETHTOOL_H
#define _UAPI_LINUX_ETHTOOL_H
+#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/if_ether.h>
+#ifndef __KERNEL__
+#include <limits.h> /* for INT_MAX */
+#endif
+
/* All structures exposed to userland should be defined such that they
* have the same layout for 32-bit and 64-bit userland.
*/
/**
- * struct ethtool_cmd - link control and status
+ * struct ethtool_cmd - DEPRECATED, link control and status
+ * This structure is DEPRECATED, please use struct ethtool_link_settings.
* @cmd: Command number = %ETHTOOL_GSET or %ETHTOOL_SSET
* @supported: Bitmask of %SUPPORTED_* flags for the link modes,
* physical connectors and other link features for which the
@@ -31,7 +37,7 @@
* physical connectors and other link features that are
* advertised through autonegotiation or enabled for
* auto-detection.
- * @speed: Low bits of the speed
+ * @speed: Low bits of the speed, 1Mb units, 0 to INT_MAX or SPEED_UNKNOWN
* @duplex: Duplex mode; one of %DUPLEX_*
* @port: Physical connector type; one of %PORT_*
* @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not
@@ -47,7 +53,7 @@
* obsoleted by &struct ethtool_coalesce. Read-only; deprecated.
* @maxrxpkt: Historically used to report RX IRQ coalescing; now
* obsoleted by &struct ethtool_coalesce. Read-only; deprecated.
- * @speed_hi: High bits of the speed
+ * @speed_hi: High bits of the speed, 1Mb units, 0 to INT_MAX or SPEED_UNKNOWN
* @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of
* %ETH_TP_MDI_*. If the status is unknown or not applicable, the
* value will be %ETH_TP_MDI_INVALID. Read-only.
@@ -748,6 +754,56 @@ struct ethtool_usrip4_spec {
__u8 proto;
};
+/**
+ * struct ethtool_tcpip6_spec - flow specification for TCP/IPv6 etc.
+ * @ip6src: Source host
+ * @ip6dst: Destination host
+ * @psrc: Source port
+ * @pdst: Destination port
+ * @tclass: Traffic Class
+ *
+ * This can be used to specify a TCP/IPv6, UDP/IPv6 or SCTP/IPv6 flow.
+ */
+struct ethtool_tcpip6_spec {
+ __be32 ip6src[4];
+ __be32 ip6dst[4];
+ __be16 psrc;
+ __be16 pdst;
+ __u8 tclass;
+};
+
+/**
+ * struct ethtool_ah_espip6_spec - flow specification for IPsec/IPv6
+ * @ip6src: Source host
+ * @ip6dst: Destination host
+ * @spi: Security parameters index
+ * @tclass: Traffic Class
+ *
+ * This can be used to specify an IPsec transport or tunnel over IPv6.
+ */
+struct ethtool_ah_espip6_spec {
+ __be32 ip6src[4];
+ __be32 ip6dst[4];
+ __be32 spi;
+ __u8 tclass;
+};
+
+/**
+ * struct ethtool_usrip6_spec - general flow specification for IPv6
+ * @ip6src: Source host
+ * @ip6dst: Destination host
+ * @l4_4_bytes: First 4 bytes of transport (layer 4) header
+ * @tclass: Traffic Class
+ * @l4_proto: Transport protocol number (nexthdr after any Extension Headers)
+ */
+struct ethtool_usrip6_spec {
+ __be32 ip6src[4];
+ __be32 ip6dst[4];
+ __be32 l4_4_bytes;
+ __u8 tclass;
+ __u8 l4_proto;
+};
+
union ethtool_flow_union {
struct ethtool_tcpip4_spec tcp_ip4_spec;
struct ethtool_tcpip4_spec udp_ip4_spec;
@@ -755,6 +811,12 @@ union ethtool_flow_union {
struct ethtool_ah_espip4_spec ah_ip4_spec;
struct ethtool_ah_espip4_spec esp_ip4_spec;
struct ethtool_usrip4_spec usr_ip4_spec;
+ struct ethtool_tcpip6_spec tcp_ip6_spec;
+ struct ethtool_tcpip6_spec udp_ip6_spec;
+ struct ethtool_tcpip6_spec sctp_ip6_spec;
+ struct ethtool_ah_espip6_spec ah_ip6_spec;
+ struct ethtool_ah_espip6_spec esp_ip6_spec;
+ struct ethtool_usrip6_spec usr_ip6_spec;
struct ethhdr ether_spec;
__u8 hdata[52];
};
@@ -1146,10 +1208,29 @@ enum ethtool_sfeatures_retval_bits {
#define ETHTOOL_F_WISH (1 << ETHTOOL_F_WISH__BIT)
#define ETHTOOL_F_COMPAT (1 << ETHTOOL_F_COMPAT__BIT)
+#define MAX_NUM_QUEUE 4096
+
+/**
+ * struct ethtool_per_queue_op - apply sub command to the queues in mask.
+ * @cmd: ETHTOOL_PERQUEUE
+ * @sub_command: the sub command which apply to each queues
+ * @queue_mask: Bitmap of the queues which sub command apply to
+ * @data: A complete command structure following for each of the queues addressed
+ */
+struct ethtool_per_queue_op {
+ __u32 cmd;
+ __u32 sub_command;
+ __u32 queue_mask[__KERNEL_DIV_ROUND_UP(MAX_NUM_QUEUE, 32)];
+ char data[];
+};
/* CMDs currently supported */
-#define ETHTOOL_GSET 0x00000001 /* Get settings. */
-#define ETHTOOL_SSET 0x00000002 /* Set settings. */
+#define ETHTOOL_GSET 0x00000001 /* DEPRECATED, Get settings.
+ * Please use ETHTOOL_GLINKSETTINGS
+ */
+#define ETHTOOL_SSET 0x00000002 /* DEPRECATED, Set settings.
+ * Please use ETHTOOL_SLINKSETTINGS
+ */
#define ETHTOOL_GDRVINFO 0x00000003 /* Get driver info. */
#define ETHTOOL_GREGS 0x00000004 /* Get NIC registers. */
#define ETHTOOL_GWOL 0x00000005 /* Get wake-on-lan options. */
@@ -1229,73 +1310,141 @@ enum ethtool_sfeatures_retval_bits {
#define ETHTOOL_STUNABLE 0x00000049 /* Set tunable configuration */
#define ETHTOOL_GPHYSTATS 0x0000004a /* get PHY-specific statistics */
+#define ETHTOOL_PERQUEUE 0x0000004b /* Set per queue options */
+
+#define ETHTOOL_GLINKSETTINGS 0x0000004c /* Get ethtool_link_settings */
+#define ETHTOOL_SLINKSETTINGS 0x0000004d /* Set ethtool_link_settings */
+
+
/* compatibility with older code */
#define SPARC_ETH_GSET ETHTOOL_GSET
#define SPARC_ETH_SSET ETHTOOL_SSET
-#define SUPPORTED_10baseT_Half (1 << 0)
-#define SUPPORTED_10baseT_Full (1 << 1)
-#define SUPPORTED_100baseT_Half (1 << 2)
-#define SUPPORTED_100baseT_Full (1 << 3)
-#define SUPPORTED_1000baseT_Half (1 << 4)
-#define SUPPORTED_1000baseT_Full (1 << 5)
-#define SUPPORTED_Autoneg (1 << 6)
-#define SUPPORTED_TP (1 << 7)
-#define SUPPORTED_AUI (1 << 8)
-#define SUPPORTED_MII (1 << 9)
-#define SUPPORTED_FIBRE (1 << 10)
-#define SUPPORTED_BNC (1 << 11)
-#define SUPPORTED_10000baseT_Full (1 << 12)
-#define SUPPORTED_Pause (1 << 13)
-#define SUPPORTED_Asym_Pause (1 << 14)
-#define SUPPORTED_2500baseX_Full (1 << 15)
-#define SUPPORTED_Backplane (1 << 16)
-#define SUPPORTED_1000baseKX_Full (1 << 17)
-#define SUPPORTED_10000baseKX4_Full (1 << 18)
-#define SUPPORTED_10000baseKR_Full (1 << 19)
-#define SUPPORTED_10000baseR_FEC (1 << 20)
-#define SUPPORTED_20000baseMLD2_Full (1 << 21)
-#define SUPPORTED_20000baseKR2_Full (1 << 22)
-#define SUPPORTED_40000baseKR4_Full (1 << 23)
-#define SUPPORTED_40000baseCR4_Full (1 << 24)
-#define SUPPORTED_40000baseSR4_Full (1 << 25)
-#define SUPPORTED_40000baseLR4_Full (1 << 26)
-#define SUPPORTED_56000baseKR4_Full (1 << 27)
-#define SUPPORTED_56000baseCR4_Full (1 << 28)
-#define SUPPORTED_56000baseSR4_Full (1 << 29)
-#define SUPPORTED_56000baseLR4_Full (1 << 30)
-
-#define ADVERTISED_10baseT_Half (1 << 0)
-#define ADVERTISED_10baseT_Full (1 << 1)
-#define ADVERTISED_100baseT_Half (1 << 2)
-#define ADVERTISED_100baseT_Full (1 << 3)
-#define ADVERTISED_1000baseT_Half (1 << 4)
-#define ADVERTISED_1000baseT_Full (1 << 5)
-#define ADVERTISED_Autoneg (1 << 6)
-#define ADVERTISED_TP (1 << 7)
-#define ADVERTISED_AUI (1 << 8)
-#define ADVERTISED_MII (1 << 9)
-#define ADVERTISED_FIBRE (1 << 10)
-#define ADVERTISED_BNC (1 << 11)
-#define ADVERTISED_10000baseT_Full (1 << 12)
-#define ADVERTISED_Pause (1 << 13)
-#define ADVERTISED_Asym_Pause (1 << 14)
-#define ADVERTISED_2500baseX_Full (1 << 15)
-#define ADVERTISED_Backplane (1 << 16)
-#define ADVERTISED_1000baseKX_Full (1 << 17)
-#define ADVERTISED_10000baseKX4_Full (1 << 18)
-#define ADVERTISED_10000baseKR_Full (1 << 19)
-#define ADVERTISED_10000baseR_FEC (1 << 20)
-#define ADVERTISED_20000baseMLD2_Full (1 << 21)
-#define ADVERTISED_20000baseKR2_Full (1 << 22)
-#define ADVERTISED_40000baseKR4_Full (1 << 23)
-#define ADVERTISED_40000baseCR4_Full (1 << 24)
-#define ADVERTISED_40000baseSR4_Full (1 << 25)
-#define ADVERTISED_40000baseLR4_Full (1 << 26)
-#define ADVERTISED_56000baseKR4_Full (1 << 27)
-#define ADVERTISED_56000baseCR4_Full (1 << 28)
-#define ADVERTISED_56000baseSR4_Full (1 << 29)
-#define ADVERTISED_56000baseLR4_Full (1 << 30)
+/* Link mode bit indices */
+enum ethtool_link_mode_bit_indices {
+ ETHTOOL_LINK_MODE_10baseT_Half_BIT = 0,
+ ETHTOOL_LINK_MODE_10baseT_Full_BIT = 1,
+ ETHTOOL_LINK_MODE_100baseT_Half_BIT = 2,
+ ETHTOOL_LINK_MODE_100baseT_Full_BIT = 3,
+ ETHTOOL_LINK_MODE_1000baseT_Half_BIT = 4,
+ ETHTOOL_LINK_MODE_1000baseT_Full_BIT = 5,
+ ETHTOOL_LINK_MODE_Autoneg_BIT = 6,
+ ETHTOOL_LINK_MODE_TP_BIT = 7,
+ ETHTOOL_LINK_MODE_AUI_BIT = 8,
+ ETHTOOL_LINK_MODE_MII_BIT = 9,
+ ETHTOOL_LINK_MODE_FIBRE_BIT = 10,
+ ETHTOOL_LINK_MODE_BNC_BIT = 11,
+ ETHTOOL_LINK_MODE_10000baseT_Full_BIT = 12,
+ ETHTOOL_LINK_MODE_Pause_BIT = 13,
+ ETHTOOL_LINK_MODE_Asym_Pause_BIT = 14,
+ ETHTOOL_LINK_MODE_2500baseX_Full_BIT = 15,
+ ETHTOOL_LINK_MODE_Backplane_BIT = 16,
+ ETHTOOL_LINK_MODE_1000baseKX_Full_BIT = 17,
+ ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT = 18,
+ ETHTOOL_LINK_MODE_10000baseKR_Full_BIT = 19,
+ ETHTOOL_LINK_MODE_10000baseR_FEC_BIT = 20,
+ ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT = 21,
+ ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT = 22,
+ ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT = 23,
+ ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT = 24,
+ ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT = 25,
+ ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT = 26,
+ ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT = 27,
+ ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT = 28,
+ ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT = 29,
+ ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT = 30,
+
+ /* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit
+ * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_*
+ * macro for bits > 31. The only way to use indices > 31 is to
+ * use the new ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API.
+ */
+
+ __ETHTOOL_LINK_MODE_LAST
+ = ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT,
+};
+
+#define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \
+ (1UL << (ETHTOOL_LINK_MODE_ ## base_name ## _BIT))
+
+/* DEPRECATED macros. Please migrate to
+ * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT
+ * define any new SUPPORTED_* macro for bits > 31.
+ */
+#define SUPPORTED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half)
+#define SUPPORTED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full)
+#define SUPPORTED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half)
+#define SUPPORTED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full)
+#define SUPPORTED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half)
+#define SUPPORTED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full)
+#define SUPPORTED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg)
+#define SUPPORTED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP)
+#define SUPPORTED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI)
+#define SUPPORTED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII)
+#define SUPPORTED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE)
+#define SUPPORTED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC)
+#define SUPPORTED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full)
+#define SUPPORTED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause)
+#define SUPPORTED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause)
+#define SUPPORTED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full)
+#define SUPPORTED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane)
+#define SUPPORTED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full)
+#define SUPPORTED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full)
+#define SUPPORTED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full)
+#define SUPPORTED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC)
+#define SUPPORTED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full)
+#define SUPPORTED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full)
+#define SUPPORTED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full)
+#define SUPPORTED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full)
+#define SUPPORTED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full)
+#define SUPPORTED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full)
+#define SUPPORTED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full)
+#define SUPPORTED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full)
+#define SUPPORTED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full)
+#define SUPPORTED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full)
+/* Please do not define any new SUPPORTED_* macro for bits > 31, see
+ * notice above.
+ */
+
+/*
+ * DEPRECATED macros. Please migrate to
+ * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT
+ * define any new ADERTISE_* macro for bits > 31.
+ */
+#define ADVERTISED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half)
+#define ADVERTISED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full)
+#define ADVERTISED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half)
+#define ADVERTISED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full)
+#define ADVERTISED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half)
+#define ADVERTISED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full)
+#define ADVERTISED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg)
+#define ADVERTISED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP)
+#define ADVERTISED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI)
+#define ADVERTISED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII)
+#define ADVERTISED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE)
+#define ADVERTISED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC)
+#define ADVERTISED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full)
+#define ADVERTISED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause)
+#define ADVERTISED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause)
+#define ADVERTISED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full)
+#define ADVERTISED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane)
+#define ADVERTISED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full)
+#define ADVERTISED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full)
+#define ADVERTISED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full)
+#define ADVERTISED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC)
+#define ADVERTISED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full)
+#define ADVERTISED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full)
+#define ADVERTISED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full)
+#define ADVERTISED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full)
+#define ADVERTISED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full)
+#define ADVERTISED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full)
+#define ADVERTISED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full)
+#define ADVERTISED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full)
+#define ADVERTISED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full)
+#define ADVERTISED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full)
+/* Please do not define any new ADVERTISED_* macro for bits > 31, see
+ * notice above.
+ */
/* The following are all involved in forcing a particular link
* mode for the device for setting things. When getting the
@@ -1303,7 +1452,7 @@ enum ethtool_sfeatures_retval_bits {
* it was forced up into this mode or autonegotiated.
*/
-/* The forced speed, 10Mb, 100Mb, gigabit, [2.5|5|10|20|25|40|50|56|100]GbE. */
+/* The forced speed, in units of 1Mb. All values 0 to INT_MAX are legal. */
#define SPEED_10 10
#define SPEED_100 100
#define SPEED_1000 1000
@@ -1319,11 +1468,28 @@ enum ethtool_sfeatures_retval_bits {
#define SPEED_UNKNOWN -1
+static inline int ethtool_validate_speed(__u32 speed)
+{
+ return speed <= INT_MAX || speed == SPEED_UNKNOWN;
+}
+
/* Duplex, half or full. */
#define DUPLEX_HALF 0x00
#define DUPLEX_FULL 0x01
#define DUPLEX_UNKNOWN 0xff
+static inline int ethtool_validate_duplex(__u8 duplex)
+{
+ switch (duplex) {
+ case DUPLEX_HALF:
+ case DUPLEX_FULL:
+ case DUPLEX_UNKNOWN:
+ return 1;
+ }
+
+ return 0;
+}
+
/* Which connector port. */
#define PORT_TP 0x00
#define PORT_AUI 0x01
@@ -1367,15 +1533,17 @@ enum ethtool_sfeatures_retval_bits {
#define UDP_V4_FLOW 0x02 /* hash or spec (udp_ip4_spec) */
#define SCTP_V4_FLOW 0x03 /* hash or spec (sctp_ip4_spec) */
#define AH_ESP_V4_FLOW 0x04 /* hash only */
-#define TCP_V6_FLOW 0x05 /* hash only */
-#define UDP_V6_FLOW 0x06 /* hash only */
-#define SCTP_V6_FLOW 0x07 /* hash only */
+#define TCP_V6_FLOW 0x05 /* hash or spec (tcp_ip6_spec; nfc only) */
+#define UDP_V6_FLOW 0x06 /* hash or spec (udp_ip6_spec; nfc only) */
+#define SCTP_V6_FLOW 0x07 /* hash or spec (sctp_ip6_spec; nfc only) */
#define AH_ESP_V6_FLOW 0x08 /* hash only */
#define AH_V4_FLOW 0x09 /* hash or spec (ah_ip4_spec) */
#define ESP_V4_FLOW 0x0a /* hash or spec (esp_ip4_spec) */
-#define AH_V6_FLOW 0x0b /* hash only */
-#define ESP_V6_FLOW 0x0c /* hash only */
-#define IP_USER_FLOW 0x0d /* spec only (usr_ip4_spec) */
+#define AH_V6_FLOW 0x0b /* hash or spec (ah_ip6_spec; nfc only) */
+#define ESP_V6_FLOW 0x0c /* hash or spec (esp_ip6_spec; nfc only) */
+#define IPV4_USER_FLOW 0x0d /* spec only (usr_ip4_spec) */
+#define IP_USER_FLOW IPV4_USER_FLOW
+#define IPV6_USER_FLOW 0x0e /* spec only (usr_ip6_spec; nfc only) */
#define IPV4_FLOW 0x10 /* hash only */
#define IPV6_FLOW 0x11 /* hash only */
#define ETHER_FLOW 0x12 /* spec only (ether_spec) */
@@ -1441,4 +1609,123 @@ enum ethtool_reset_flags {
};
#define ETH_RESET_SHARED_SHIFT 16
+
+/**
+ * struct ethtool_link_settings - link control and status
+ *
+ * IMPORTANT, Backward compatibility notice: When implementing new
+ * user-space tools, please first try %ETHTOOL_GLINKSETTINGS, and
+ * if it succeeds use %ETHTOOL_SLINKSETTINGS to change link
+ * settings; do not use %ETHTOOL_SSET if %ETHTOOL_GLINKSETTINGS
+ * succeeded: stick to %ETHTOOL_GLINKSETTINGS/%SLINKSETTINGS in
+ * that case. Conversely, if %ETHTOOL_GLINKSETTINGS fails, use
+ * %ETHTOOL_GSET to query and %ETHTOOL_SSET to change link
+ * settings; do not use %ETHTOOL_SLINKSETTINGS if
+ * %ETHTOOL_GLINKSETTINGS failed: stick to
+ * %ETHTOOL_GSET/%ETHTOOL_SSET in that case.
+ *
+ * @cmd: Command number = %ETHTOOL_GLINKSETTINGS or %ETHTOOL_SLINKSETTINGS
+ * @speed: Link speed (Mbps)
+ * @duplex: Duplex mode; one of %DUPLEX_*
+ * @port: Physical connector type; one of %PORT_*
+ * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not
+ * applicable. For clause 45 PHYs this is the PRTAD.
+ * @autoneg: Enable/disable autonegotiation and auto-detection;
+ * either %AUTONEG_DISABLE or %AUTONEG_ENABLE
+ * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO
+ * protocols supported by the interface; 0 if unknown.
+ * Read-only.
+ * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of
+ * %ETH_TP_MDI_*. If the status is unknown or not applicable, the
+ * value will be %ETH_TP_MDI_INVALID. Read-only.
+ * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of
+ * %ETH_TP_MDI_*. If MDI(-X) control is not implemented, reads
+ * yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected.
+ * When written successfully, the link should be renegotiated if
+ * necessary.
+ * @link_mode_masks_nwords: Number of 32-bit words for each of the
+ * supported, advertising, lp_advertising link mode bitmaps. For
+ * %ETHTOOL_GLINKSETTINGS: on entry, number of words passed by user
+ * (>= 0); on return, if handshake in progress, negative if
+ * request size unsupported by kernel: absolute value indicates
+ * kernel recommended size and cmd field is 0, as well as all the
+ * other fields; otherwise (handshake completed), strictly
+ * positive to indicate size used by kernel and cmd field is
+ * %ETHTOOL_GLINKSETTINGS, all other fields populated by driver. For
+ * %ETHTOOL_SLINKSETTINGS: must be valid on entry, ie. a positive
+ * value returned previously by %ETHTOOL_GLINKSETTINGS, otherwise
+ * refused. For drivers: ignore this field (use kernel's
+ * __ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will
+ * be overwritten by kernel.
+ * @supported: Bitmap with each bit meaning given by
+ * %ethtool_link_mode_bit_indices for the link modes, physical
+ * connectors and other link features for which the interface
+ * supports autonegotiation or auto-detection. Read-only.
+ * @advertising: Bitmap with each bit meaning given by
+ * %ethtool_link_mode_bit_indices for the link modes, physical
+ * connectors and other link features that are advertised through
+ * autonegotiation or enabled for auto-detection.
+ * @lp_advertising: Bitmap with each bit meaning given by
+ * %ethtool_link_mode_bit_indices for the link modes, and other
+ * link features that the link partner advertised through
+ * autonegotiation; 0 if unknown or not applicable. Read-only.
+ *
+ * If autonegotiation is disabled, the speed and @duplex represent the
+ * fixed link mode and are writable if the driver supports multiple
+ * link modes. If it is enabled then they are read-only; if the link
+ * is up they represent the negotiated link mode; if the link is down,
+ * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and
+ * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode.
+ *
+ * Some hardware interfaces may have multiple PHYs and/or physical
+ * connectors fitted or do not allow the driver to detect which are
+ * fitted. For these interfaces @port and/or @phy_address may be
+ * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE.
+ * Otherwise, attempts to write different values may be ignored or
+ * rejected.
+ *
+ * Deprecated %ethtool_cmd fields transceiver, maxtxpkt and maxrxpkt
+ * are not available in %ethtool_link_settings. Until all drivers are
+ * converted to ignore them or to the new %ethtool_link_settings API,
+ * for both queries and changes, users should always try
+ * %ETHTOOL_GLINKSETTINGS first, and if it fails with -ENOTSUPP stick
+ * only to %ETHTOOL_GSET and %ETHTOOL_SSET consistently. If it
+ * succeeds, then users should stick to %ETHTOOL_GLINKSETTINGS and
+ * %ETHTOOL_SLINKSETTINGS (which would support drivers implementing
+ * either %ethtool_cmd or %ethtool_link_settings).
+ *
+ * Users should assume that all fields not marked read-only are
+ * writable and subject to validation by the driver. They should use
+ * %ETHTOOL_GLINKSETTINGS to get the current values before making specific
+ * changes and then applying them with %ETHTOOL_SLINKSETTINGS.
+ *
+ * Drivers that implement %get_link_ksettings and/or
+ * %set_link_ksettings should ignore the @cmd
+ * and @link_mode_masks_nwords fields (any change to them overwritten
+ * by kernel), and rely only on kernel's internal
+ * %__ETHTOOL_LINK_MODE_MASK_NBITS and
+ * %ethtool_link_mode_mask_t. Drivers that implement
+ * %set_link_ksettings() should validate all fields other than @cmd
+ * and @link_mode_masks_nwords that are not described as read-only or
+ * deprecated, and must ignore all fields described as read-only.
+ */
+struct ethtool_link_settings {
+ __u32 cmd;
+ __u32 speed;
+ __u8 duplex;
+ __u8 port;
+ __u8 phy_address;
+ __u8 autoneg;
+ __u8 mdio_support;
+ __u8 eth_tp_mdix;
+ __u8 eth_tp_mdix_ctrl;
+ __s8 link_mode_masks_nwords;
+ __u32 reserved[8];
+ __u32 link_mode_masks[0];
+ /* layout of link_mode_masks fields:
+ * __u32 map_supported[link_mode_masks_nwords];
+ * __u32 map_advertising[link_mode_masks_nwords];
+ * __u32 map_lp_advertising[link_mode_masks_nwords];
+ */
+};
#endif /* _UAPI_LINUX_ETHTOOL_H */
diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h
index c3363ba1ae05..5512c90af7e3 100644
--- a/include/uapi/linux/genetlink.h
+++ b/include/uapi/linux/genetlink.h
@@ -21,6 +21,7 @@ struct genlmsghdr {
#define GENL_CMD_CAP_DO 0x02
#define GENL_CMD_CAP_DUMP 0x04
#define GENL_CMD_CAP_HASPOL 0x08
+#define GENL_UNS_ADMIN_PERM 0x10
/*
* List of reserved static generic netlink identifiers:
diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h
index 9cf2394f0bcf..f80277569f24 100644
--- a/include/uapi/linux/if.h
+++ b/include/uapi/linux/if.h
@@ -37,7 +37,7 @@
* are shared for all types of net_devices. The sysfs entries are available
* via /sys/class/net/<dev>/flags. Flags which can be toggled through sysfs
* are annotated below, note that only a few flags can be toggled and some
- * other flags are always always preserved from the original net_device flags
+ * other flags are always preserved from the original net_device flags
* even if you try to set them via sysfs. Flags which are always preserved
* are kept under the flag grouping @IFF_VOLATILE. Flags which are volatile
* are annotated below as such.
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 18db14477bdd..0536eefff9bf 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -137,11 +137,17 @@ struct bridge_vlan_info {
/* Bridge multicast database attributes
* [MDBA_MDB] = {
* [MDBA_MDB_ENTRY] = {
- * [MDBA_MDB_ENTRY_INFO]
+ * [MDBA_MDB_ENTRY_INFO] {
+ * struct br_mdb_entry
+ * [MDBA_MDB_EATTR attributes]
+ * }
* }
* }
* [MDBA_ROUTER] = {
- * [MDBA_ROUTER_PORT]
+ * [MDBA_ROUTER_PORT] = {
+ * u32 ifindex
+ * [MDBA_ROUTER_PATTR attributes]
+ * }
* }
*/
enum {
@@ -166,6 +172,22 @@ enum {
};
#define MDBA_MDB_ENTRY_MAX (__MDBA_MDB_ENTRY_MAX - 1)
+/* per mdb entry additional attributes */
+enum {
+ MDBA_MDB_EATTR_UNSPEC,
+ MDBA_MDB_EATTR_TIMER,
+ __MDBA_MDB_EATTR_MAX
+};
+#define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1)
+
+/* multicast router types */
+enum {
+ MDB_RTR_TYPE_DISABLED,
+ MDB_RTR_TYPE_TEMP_QUERY,
+ MDB_RTR_TYPE_PERM,
+ MDB_RTR_TYPE_TEMP
+};
+
enum {
MDBA_ROUTER_UNSPEC,
MDBA_ROUTER_PORT,
@@ -173,6 +195,15 @@ enum {
};
#define MDBA_ROUTER_MAX (__MDBA_ROUTER_MAX - 1)
+/* router port attributes */
+enum {
+ MDBA_ROUTER_PATTR_UNSPEC,
+ MDBA_ROUTER_PATTR_TIMER,
+ MDBA_ROUTER_PATTR_TYPE,
+ __MDBA_ROUTER_PATTR_MAX
+};
+#define MDBA_ROUTER_PATTR_MAX (__MDBA_ROUTER_PATTR_MAX - 1)
+
struct br_port_msg {
__u8 family;
__u32 ifindex;
@@ -183,6 +214,8 @@ struct br_mdb_entry {
#define MDB_TEMPORARY 0
#define MDB_PERMANENT 1
__u8 state;
+#define MDB_FLAGS_OFFLOAD (1 << 0)
+ __u8 flags;
__u16 vid;
struct {
union {
diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h
index ea9221b0331a..4a93051c578c 100644
--- a/include/uapi/linux/if_ether.h
+++ b/include/uapi/linux/if_ether.h
@@ -83,6 +83,7 @@
#define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */
#define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */
#define ETH_P_TIPC 0x88CA /* TIPC */
+#define ETH_P_MACSEC 0x88E5 /* 802.1ae MACsec */
#define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */
#define ETH_P_MVRP 0x88F5 /* 802.1Q MVRP */
#define ETH_P_1588 0x88F7 /* IEEE 1588 Timesync */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index a30b78090594..8e3f88fa5b59 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -35,6 +35,8 @@ struct rtnl_link_stats {
/* for cslip etc */
__u32 rx_compressed;
__u32 tx_compressed;
+
+ __u32 rx_nohandler; /* dropped, no handler found */
};
/* The main device statistics structure */
@@ -68,6 +70,8 @@ struct rtnl_link_stats64 {
/* for cslip etc */
__u64 rx_compressed;
__u64 tx_compressed;
+
+ __u64 rx_nohandler; /* dropped, no handler found */
};
/* The struct should be in sync with struct ifmap */
@@ -401,6 +405,43 @@ enum {
#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1)
+enum {
+ IFLA_VRF_PORT_UNSPEC,
+ IFLA_VRF_PORT_TABLE,
+ __IFLA_VRF_PORT_MAX
+};
+
+#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1)
+
+/* MACSEC section */
+enum {
+ IFLA_MACSEC_UNSPEC,
+ IFLA_MACSEC_SCI,
+ IFLA_MACSEC_PORT,
+ IFLA_MACSEC_ICV_LEN,
+ IFLA_MACSEC_CIPHER_SUITE,
+ IFLA_MACSEC_WINDOW,
+ IFLA_MACSEC_ENCODING_SA,
+ IFLA_MACSEC_ENCRYPT,
+ IFLA_MACSEC_PROTECT,
+ IFLA_MACSEC_INC_SCI,
+ IFLA_MACSEC_ES,
+ IFLA_MACSEC_SCB,
+ IFLA_MACSEC_REPLAY_PROTECT,
+ IFLA_MACSEC_VALIDATION,
+ __IFLA_MACSEC_MAX,
+};
+
+#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1)
+
+enum macsec_validation_type {
+ MACSEC_VALIDATE_DISABLED = 0,
+ MACSEC_VALIDATE_CHECK = 1,
+ MACSEC_VALIDATE_STRICT = 2,
+ __MACSEC_VALIDATE_END,
+ MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1,
+};
+
/* IPVLAN section */
enum {
IFLA_IPVLAN_UNSPEC,
@@ -444,6 +485,7 @@ enum {
IFLA_VXLAN_GBP,
IFLA_VXLAN_REMCSUM_NOPARTIAL,
IFLA_VXLAN_COLLECT_METADATA,
+ IFLA_VXLAN_LABEL,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
@@ -466,6 +508,7 @@ enum {
IFLA_GENEVE_UDP_CSUM,
IFLA_GENEVE_UDP_ZERO_CSUM6_TX,
IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
+ IFLA_GENEVE_LABEL,
__IFLA_GENEVE_MAX
};
#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h
new file mode 100644
index 000000000000..26b0d1e3e3e7
--- /dev/null
+++ b/include/uapi/linux/if_macsec.h
@@ -0,0 +1,161 @@
+/*
+ * include/uapi/linux/if_macsec.h - MACsec device
+ *
+ * Copyright (c) 2015 Sabrina Dubroca <sd@queasysnail.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _UAPI_MACSEC_H
+#define _UAPI_MACSEC_H
+
+#include <linux/types.h>
+
+#define MACSEC_GENL_NAME "macsec"
+#define MACSEC_GENL_VERSION 1
+
+#define MACSEC_MAX_KEY_LEN 128
+
+#define DEFAULT_CIPHER_ID 0x0080020001000001ULL
+#define DEFAULT_CIPHER_ALT 0x0080C20001000001ULL
+
+#define MACSEC_MIN_ICV_LEN 8
+#define MACSEC_MAX_ICV_LEN 32
+
+enum macsec_attrs {
+ MACSEC_ATTR_UNSPEC,
+ MACSEC_ATTR_IFINDEX, /* u32, ifindex of the MACsec netdevice */
+ MACSEC_ATTR_RXSC_CONFIG, /* config, nested macsec_rxsc_attrs */
+ MACSEC_ATTR_SA_CONFIG, /* config, nested macsec_sa_attrs */
+ MACSEC_ATTR_SECY, /* dump, nested macsec_secy_attrs */
+ MACSEC_ATTR_TXSA_LIST, /* dump, nested, macsec_sa_attrs for each TXSA */
+ MACSEC_ATTR_RXSC_LIST, /* dump, nested, macsec_rxsc_attrs for each RXSC */
+ MACSEC_ATTR_TXSC_STATS, /* dump, nested, macsec_txsc_stats_attr */
+ MACSEC_ATTR_SECY_STATS, /* dump, nested, macsec_secy_stats_attr */
+ __MACSEC_ATTR_END,
+ NUM_MACSEC_ATTR = __MACSEC_ATTR_END,
+ MACSEC_ATTR_MAX = __MACSEC_ATTR_END - 1,
+};
+
+enum macsec_secy_attrs {
+ MACSEC_SECY_ATTR_UNSPEC,
+ MACSEC_SECY_ATTR_SCI,
+ MACSEC_SECY_ATTR_ENCODING_SA,
+ MACSEC_SECY_ATTR_WINDOW,
+ MACSEC_SECY_ATTR_CIPHER_SUITE,
+ MACSEC_SECY_ATTR_ICV_LEN,
+ MACSEC_SECY_ATTR_PROTECT,
+ MACSEC_SECY_ATTR_REPLAY,
+ MACSEC_SECY_ATTR_OPER,
+ MACSEC_SECY_ATTR_VALIDATE,
+ MACSEC_SECY_ATTR_ENCRYPT,
+ MACSEC_SECY_ATTR_INC_SCI,
+ MACSEC_SECY_ATTR_ES,
+ MACSEC_SECY_ATTR_SCB,
+ __MACSEC_SECY_ATTR_END,
+ NUM_MACSEC_SECY_ATTR = __MACSEC_SECY_ATTR_END,
+ MACSEC_SECY_ATTR_MAX = __MACSEC_SECY_ATTR_END - 1,
+};
+
+enum macsec_rxsc_attrs {
+ MACSEC_RXSC_ATTR_UNSPEC,
+ MACSEC_RXSC_ATTR_SCI, /* config/dump, u64 */
+ MACSEC_RXSC_ATTR_ACTIVE, /* config/dump, u8 0..1 */
+ MACSEC_RXSC_ATTR_SA_LIST, /* dump, nested */
+ MACSEC_RXSC_ATTR_STATS, /* dump, nested, macsec_rxsc_stats_attr */
+ __MACSEC_RXSC_ATTR_END,
+ NUM_MACSEC_RXSC_ATTR = __MACSEC_RXSC_ATTR_END,
+ MACSEC_RXSC_ATTR_MAX = __MACSEC_RXSC_ATTR_END - 1,
+};
+
+enum macsec_sa_attrs {
+ MACSEC_SA_ATTR_UNSPEC,
+ MACSEC_SA_ATTR_AN, /* config/dump, u8 0..3 */
+ MACSEC_SA_ATTR_ACTIVE, /* config/dump, u8 0..1 */
+ MACSEC_SA_ATTR_PN, /* config/dump, u32 */
+ MACSEC_SA_ATTR_KEY, /* config, data */
+ MACSEC_SA_ATTR_KEYID, /* config/dump, u64 */
+ MACSEC_SA_ATTR_STATS, /* dump, nested, macsec_sa_stats_attr */
+ __MACSEC_SA_ATTR_END,
+ NUM_MACSEC_SA_ATTR = __MACSEC_SA_ATTR_END,
+ MACSEC_SA_ATTR_MAX = __MACSEC_SA_ATTR_END - 1,
+};
+
+enum macsec_nl_commands {
+ MACSEC_CMD_GET_TXSC,
+ MACSEC_CMD_ADD_RXSC,
+ MACSEC_CMD_DEL_RXSC,
+ MACSEC_CMD_UPD_RXSC,
+ MACSEC_CMD_ADD_TXSA,
+ MACSEC_CMD_DEL_TXSA,
+ MACSEC_CMD_UPD_TXSA,
+ MACSEC_CMD_ADD_RXSA,
+ MACSEC_CMD_DEL_RXSA,
+ MACSEC_CMD_UPD_RXSA,
+};
+
+/* u64 per-RXSC stats */
+enum macsec_rxsc_stats_attr {
+ MACSEC_RXSC_STATS_ATTR_UNSPEC,
+ MACSEC_RXSC_STATS_ATTR_IN_OCTETS_VALIDATED,
+ MACSEC_RXSC_STATS_ATTR_IN_OCTETS_DECRYPTED,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_UNCHECKED,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_DELAYED,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_OK,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_INVALID,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_LATE,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_NOT_VALID,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_NOT_USING_SA,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_UNUSED_SA,
+ __MACSEC_RXSC_STATS_ATTR_END,
+ NUM_MACSEC_RXSC_STATS_ATTR = __MACSEC_RXSC_STATS_ATTR_END,
+ MACSEC_RXSC_STATS_ATTR_MAX = __MACSEC_RXSC_STATS_ATTR_END - 1,
+};
+
+/* u32 per-{RX,TX}SA stats */
+enum macsec_sa_stats_attr {
+ MACSEC_SA_STATS_ATTR_UNSPEC,
+ MACSEC_SA_STATS_ATTR_IN_PKTS_OK,
+ MACSEC_SA_STATS_ATTR_IN_PKTS_INVALID,
+ MACSEC_SA_STATS_ATTR_IN_PKTS_NOT_VALID,
+ MACSEC_SA_STATS_ATTR_IN_PKTS_NOT_USING_SA,
+ MACSEC_SA_STATS_ATTR_IN_PKTS_UNUSED_SA,
+ MACSEC_SA_STATS_ATTR_OUT_PKTS_PROTECTED,
+ MACSEC_SA_STATS_ATTR_OUT_PKTS_ENCRYPTED,
+ __MACSEC_SA_STATS_ATTR_END,
+ NUM_MACSEC_SA_STATS_ATTR = __MACSEC_SA_STATS_ATTR_END,
+ MACSEC_SA_STATS_ATTR_MAX = __MACSEC_SA_STATS_ATTR_END - 1,
+};
+
+/* u64 per-TXSC stats */
+enum macsec_txsc_stats_attr {
+ MACSEC_TXSC_STATS_ATTR_UNSPEC,
+ MACSEC_TXSC_STATS_ATTR_OUT_PKTS_PROTECTED,
+ MACSEC_TXSC_STATS_ATTR_OUT_PKTS_ENCRYPTED,
+ MACSEC_TXSC_STATS_ATTR_OUT_OCTETS_PROTECTED,
+ MACSEC_TXSC_STATS_ATTR_OUT_OCTETS_ENCRYPTED,
+ __MACSEC_TXSC_STATS_ATTR_END,
+ NUM_MACSEC_TXSC_STATS_ATTR = __MACSEC_TXSC_STATS_ATTR_END,
+ MACSEC_TXSC_STATS_ATTR_MAX = __MACSEC_TXSC_STATS_ATTR_END - 1,
+};
+
+/* u64 per-SecY stats */
+enum macsec_secy_stats_attr {
+ MACSEC_SECY_STATS_ATTR_UNSPEC,
+ MACSEC_SECY_STATS_ATTR_OUT_PKTS_UNTAGGED,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_UNTAGGED,
+ MACSEC_SECY_STATS_ATTR_OUT_PKTS_TOO_LONG,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_NO_TAG,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_BAD_TAG,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_UNKNOWN_SCI,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_NO_SCI,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_OVERRUN,
+ __MACSEC_SECY_STATS_ATTR_END,
+ NUM_MACSEC_SECY_STATS_ATTR = __MACSEC_SECY_STATS_ATTR_END,
+ MACSEC_SECY_STATS_ATTR_MAX = __MACSEC_SECY_STATS_ATTR_END - 1,
+};
+
+#endif /* _UAPI_MACSEC_H */
diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h
index 08f894d2ddbd..f291569768dd 100644
--- a/include/uapi/linux/ip.h
+++ b/include/uapi/linux/ip.h
@@ -165,6 +165,8 @@ enum
IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL,
IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL,
IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN,
+ IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST,
+ IPV4_DEVCONF_DROP_GRATUITOUS_ARP,
__IPV4_DEVCONF_MAX
};
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 38b4fef20219..395876060f50 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -174,6 +174,9 @@ enum {
DEVCONF_USE_OIF_ADDRS_ONLY,
DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT,
DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN,
+ DEVCONF_DROP_UNICAST_IN_L2_MULTICAST,
+ DEVCONF_DROP_UNSOLICITED_NA,
+ DEVCONF_KEEP_ADDR_ON_DOWN,
DEVCONF_MAX
};
diff --git a/include/uapi/linux/kcm.h b/include/uapi/linux/kcm.h
new file mode 100644
index 000000000000..a5a530940b99
--- /dev/null
+++ b/include/uapi/linux/kcm.h
@@ -0,0 +1,40 @@
+/*
+ * Kernel Connection Multiplexor
+ *
+ * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
+ *
+ * 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 published by the Free Software Foundation.
+ *
+ * User API to clone KCM sockets and attach transport socket to a KCM
+ * multiplexor.
+ */
+
+#ifndef KCM_KERNEL_H
+#define KCM_KERNEL_H
+
+struct kcm_attach {
+ int fd;
+ int bpf_fd;
+};
+
+struct kcm_unattach {
+ int fd;
+};
+
+struct kcm_clone {
+ int fd;
+};
+
+#define SIOCKCMATTACH (SIOCPROTOPRIVATE + 0)
+#define SIOCKCMUNATTACH (SIOCPROTOPRIVATE + 1)
+#define SIOCKCMCLONE (SIOCPROTOPRIVATE + 2)
+
+#define KCMPROTO_CONNECTED 0
+
+/* Socket options */
+#define KCM_RECV_DISABLE 1
+
+#endif
+
diff --git a/include/uapi/linux/kernel.h b/include/uapi/linux/kernel.h
index 321e399457f5..466073f0ce46 100644
--- a/include/uapi/linux/kernel.h
+++ b/include/uapi/linux/kernel.h
@@ -9,5 +9,6 @@
#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
+#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
#endif /* _UAPI_LINUX_KERNEL_H */
diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h
index ce91215cf7e6..5062fb5751e1 100644
--- a/include/uapi/linux/mroute6.h
+++ b/include/uapi/linux/mroute6.h
@@ -1,6 +1,7 @@
#ifndef _UAPI__LINUX_MROUTE6_H
#define _UAPI__LINUX_MROUTE6_H
+#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/sockios.h>
@@ -46,14 +47,8 @@ typedef unsigned short mifi_t;
typedef __u32 if_mask;
#define NIFBITS (sizeof(if_mask) * 8) /* bits per mask */
-#if !defined(__KERNEL__)
-#if !defined(DIV_ROUND_UP)
-#define DIV_ROUND_UP(x,y) (((x) + ((y) - 1)) / (y))
-#endif
-#endif
-
typedef struct if_set {
- if_mask ifs_bits[DIV_ROUND_UP(IF_SETSIZE, NIFBITS)];
+ if_mask ifs_bits[__KERNEL_DIV_ROUND_UP(IF_SETSIZE, NIFBITS)];
} if_set;
#define IF_SET(n, p) ((p)->ifs_bits[(n)/NIFBITS] |= (1 << ((n) % NIFBITS)))
diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
index 23cbd34e4ac7..45dfad509c4d 100644
--- a/include/uapi/linux/netconf.h
+++ b/include/uapi/linux/netconf.h
@@ -19,6 +19,7 @@ enum {
__NETCONFA_MAX
};
#define NETCONFA_MAX (__NETCONFA_MAX - 1)
+#define NETCONFA_ALL -1
#define NETCONFA_IFINDEX_ALL -1
#define NETCONFA_IFINDEX_DEFAULT -2
diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
index 319f47128db8..6d074d14ee27 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_common.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -20,9 +20,15 @@ enum ip_conntrack_info {
IP_CT_ESTABLISHED_REPLY = IP_CT_ESTABLISHED + IP_CT_IS_REPLY,
IP_CT_RELATED_REPLY = IP_CT_RELATED + IP_CT_IS_REPLY,
- IP_CT_NEW_REPLY = IP_CT_NEW + IP_CT_IS_REPLY,
- /* Number of distinct IP_CT types (no NEW in reply dirn). */
- IP_CT_NUMBER = IP_CT_IS_REPLY * 2 - 1
+ /* No NEW in reply direction. */
+
+ /* Number of distinct IP_CT types. */
+ IP_CT_NUMBER,
+
+ /* only for userspace compatibility */
+#ifndef __KERNEL__
+ IP_CT_NEW_REPLY = IP_CT_NUMBER,
+#endif
};
#define NF_CT_STATE_INVALID_BIT (1 << 0)
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index be41ffc128b8..eeffde196f80 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -681,6 +681,7 @@ enum nft_exthdr_attributes {
* @NFT_META_IIFGROUP: packet input interface group
* @NFT_META_OIFGROUP: packet output interface group
* @NFT_META_CGROUP: socket control group (skb->sk->sk_classid)
+ * @NFT_META_PRANDOM: a 32bit pseudo-random number
*/
enum nft_meta_keys {
NFT_META_LEN,
@@ -707,6 +708,7 @@ enum nft_meta_keys {
NFT_META_IIFGROUP,
NFT_META_OIFGROUP,
NFT_META_CGROUP,
+ NFT_META_PRANDOM,
};
/**
@@ -949,10 +951,14 @@ enum nft_nat_attributes {
* enum nft_masq_attributes - nf_tables masquerade expression attributes
*
* @NFTA_MASQ_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32)
+ * @NFTA_MASQ_REG_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers)
+ * @NFTA_MASQ_REG_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers)
*/
enum nft_masq_attributes {
NFTA_MASQ_UNSPEC,
NFTA_MASQ_FLAGS,
+ NFTA_MASQ_REG_PROTO_MIN,
+ NFTA_MASQ_REG_PROTO_MAX,
__NFTA_MASQ_MAX
};
#define NFTA_MASQ_MAX (__NFTA_MASQ_MAX - 1)
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index f095155d8749..0dba4e4ed2be 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -107,8 +107,10 @@ struct nlmsgerr {
#define NETLINK_PKTINFO 3
#define NETLINK_BROADCAST_ERROR 4
#define NETLINK_NO_ENOBUFS 5
+#ifndef __KERNEL__
#define NETLINK_RX_RING 6
#define NETLINK_TX_RING 7
+#endif
#define NETLINK_LISTEN_ALL_NSID 8
#define NETLINK_LIST_MEMBERSHIPS 9
#define NETLINK_CAP_ACK 10
@@ -134,6 +136,7 @@ struct nl_mmap_hdr {
__u32 nm_gid;
};
+#ifndef __KERNEL__
enum nl_mmap_status {
NL_MMAP_STATUS_UNUSED,
NL_MMAP_STATUS_RESERVED,
@@ -145,6 +148,7 @@ enum nl_mmap_status {
#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO
#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT)
#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr))
+#endif
#define NET_MAJOR 36 /* Major 36 is reserved for networking */
diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
index f2159d30d1f5..d79399394b46 100644
--- a/include/uapi/linux/netlink_diag.h
+++ b/include/uapi/linux/netlink_diag.h
@@ -48,6 +48,8 @@ enum {
#define NDIAG_SHOW_MEMINFO 0x00000001 /* show memory info of a socket */
#define NDIAG_SHOW_GROUPS 0x00000002 /* show groups of a netlink socket */
+#ifndef __KERNEL__
#define NDIAG_SHOW_RING_CFG 0x00000004 /* show ring configuration */
+#endif
#endif
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 5b7b5ebe7ca8..5a30a7563633 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1727,6 +1727,8 @@ enum nl80211_commands {
* underlying device supports these minimal RRM features:
* %NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES,
* %NL80211_FEATURE_QUIET,
+ * Or, if global RRM is supported, see:
+ * %NL80211_EXT_FEATURE_RRM
* If this flag is used, driver must add the Power Capabilities IE to the
* association request. In addition, it must also set the RRM capability
* flag in the association request's Capability Info field.
@@ -1789,6 +1791,10 @@ enum nl80211_commands {
* thus it must not specify the number of iterations, only the interval
* between scans. The scan plans are executed sequentially.
* Each scan plan is a nested attribute of &enum nl80211_sched_scan_plan.
+ * @NL80211_ATTR_PBSS: flag attribute. If set it means operate
+ * in a PBSS. Specified in %NL80211_CMD_CONNECT to request
+ * connecting to a PCP, and in %NL80211_CMD_START_AP to start
+ * a PCP instead of AP. Relevant for DMG networks only.
*
* @NUM_NL80211_ATTR: total number of nl80211_attrs available
* @NL80211_ATTR_MAX: highest attribute number currently defined
@@ -2164,6 +2170,8 @@ enum nl80211_attrs {
NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS,
NL80211_ATTR_SCHED_SCAN_PLANS,
+ NL80211_ATTR_PBSS,
+
/* add attributes here, update the policy in nl80211.c */
__NL80211_ATTR_AFTER_LAST,
@@ -4396,12 +4404,18 @@ enum nl80211_feature_flags {
/**
* enum nl80211_ext_feature_index - bit index of extended features.
* @NL80211_EXT_FEATURE_VHT_IBSS: This driver supports IBSS with VHT datarates.
+ * @NL80211_EXT_FEATURE_RRM: This driver supports RRM. When featured, user can
+ * can request to use RRM (see %NL80211_ATTR_USE_RRM) with
+ * %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests, which will set
+ * the ASSOC_REQ_USE_RRM flag in the association request even if
+ * NL80211_FEATURE_QUIET is not advertized.
*
* @NUM_NL80211_EXT_FEATURES: number of extended features.
* @MAX_NL80211_EXT_FEATURES: highest extended feature index.
*/
enum nl80211_ext_feature_index {
NL80211_EXT_FEATURE_VHT_IBSS,
+ NL80211_EXT_FEATURE_RRM,
/* add new features before the definition below */
NUM_NL80211_EXT_FEATURES,
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index a27222d5b413..616d04761730 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -454,6 +454,14 @@ struct ovs_key_ct_labels {
#define OVS_CS_F_REPLY_DIR 0x08 /* Flow is in the reply direction. */
#define OVS_CS_F_INVALID 0x10 /* Could not track connection. */
#define OVS_CS_F_TRACKED 0x20 /* Conntrack has occurred. */
+#define OVS_CS_F_SRC_NAT 0x40 /* Packet's source address/port was
+ * mangled by NAT.
+ */
+#define OVS_CS_F_DST_NAT 0x80 /* Packet's destination address/port
+ * was mangled by NAT.
+ */
+
+#define OVS_CS_F_NAT_MASK (OVS_CS_F_SRC_NAT | OVS_CS_F_DST_NAT)
/**
* enum ovs_flow_attr - attributes for %OVS_FLOW_* commands.
@@ -632,6 +640,8 @@ struct ovs_action_hash {
* mask. For each bit set in the mask, the corresponding bit in the value is
* copied to the connection tracking label field in the connection.
* @OVS_CT_ATTR_HELPER: variable length string defining conntrack ALG.
+ * @OVS_CT_ATTR_NAT: Nested OVS_NAT_ATTR_* for performing L3 network address
+ * translation (NAT) on the packet.
*/
enum ovs_ct_attr {
OVS_CT_ATTR_UNSPEC,
@@ -641,12 +651,51 @@ enum ovs_ct_attr {
OVS_CT_ATTR_LABELS, /* labels to associate with this connection. */
OVS_CT_ATTR_HELPER, /* netlink helper to assist detection of
related connections. */
+ OVS_CT_ATTR_NAT, /* Nested OVS_NAT_ATTR_* */
__OVS_CT_ATTR_MAX
};
#define OVS_CT_ATTR_MAX (__OVS_CT_ATTR_MAX - 1)
/**
+ * enum ovs_nat_attr - Attributes for %OVS_CT_ATTR_NAT.
+ *
+ * @OVS_NAT_ATTR_SRC: Flag for Source NAT (mangle source address/port).
+ * @OVS_NAT_ATTR_DST: Flag for Destination NAT (mangle destination
+ * address/port). Only one of (@OVS_NAT_ATTR_SRC, @OVS_NAT_ATTR_DST) may be
+ * specified. Effective only for packets for ct_state NEW connections.
+ * Packets of committed connections are mangled by the NAT action according to
+ * the committed NAT type regardless of the flags specified. As a corollary, a
+ * NAT action without a NAT type flag will only mangle packets of committed
+ * connections. The following NAT attributes only apply for NEW
+ * (non-committed) connections, and they may be included only when the CT
+ * action has the @OVS_CT_ATTR_COMMIT flag and either @OVS_NAT_ATTR_SRC or
+ * @OVS_NAT_ATTR_DST is also included.
+ * @OVS_NAT_ATTR_IP_MIN: struct in_addr or struct in6_addr
+ * @OVS_NAT_ATTR_IP_MAX: struct in_addr or struct in6_addr
+ * @OVS_NAT_ATTR_PROTO_MIN: u16 L4 protocol specific lower boundary (port)
+ * @OVS_NAT_ATTR_PROTO_MAX: u16 L4 protocol specific upper boundary (port)
+ * @OVS_NAT_ATTR_PERSISTENT: Flag for persistent IP mapping across reboots
+ * @OVS_NAT_ATTR_PROTO_HASH: Flag for pseudo random L4 port mapping (MD5)
+ * @OVS_NAT_ATTR_PROTO_RANDOM: Flag for fully randomized L4 port mapping
+ */
+enum ovs_nat_attr {
+ OVS_NAT_ATTR_UNSPEC,
+ OVS_NAT_ATTR_SRC,
+ OVS_NAT_ATTR_DST,
+ OVS_NAT_ATTR_IP_MIN,
+ OVS_NAT_ATTR_IP_MAX,
+ OVS_NAT_ATTR_PROTO_MIN,
+ OVS_NAT_ATTR_PROTO_MAX,
+ OVS_NAT_ATTR_PERSISTENT,
+ OVS_NAT_ATTR_PROTO_HASH,
+ OVS_NAT_ATTR_PROTO_RANDOM,
+ __OVS_NAT_ATTR_MAX,
+};
+
+#define OVS_NAT_ATTR_MAX (__OVS_NAT_ATTR_MAX - 1)
+
+/**
* enum ovs_action_attr - Action types.
*
* @OVS_ACTION_ATTR_OUTPUT: Output packet to port.
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 439873775d49..c43c5f78b9c4 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -172,6 +172,7 @@ enum {
TCA_U32_INDEV,
TCA_U32_PCNT,
TCA_U32_MARK,
+ TCA_U32_FLAGS,
__TCA_U32_MAX
};
@@ -416,6 +417,8 @@ enum {
TCA_FLOWER_KEY_TCP_DST, /* be16 */
TCA_FLOWER_KEY_UDP_SRC, /* be16 */
TCA_FLOWER_KEY_UDP_DST, /* be16 */
+
+ TCA_FLOWER_FLAGS,
__TCA_FLOWER_MAX,
};
diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h
index 058757f7a733..2e00dcebebd0 100644
--- a/include/uapi/linux/rfkill.h
+++ b/include/uapi/linux/rfkill.h
@@ -59,6 +59,8 @@ enum rfkill_type {
* @RFKILL_OP_DEL: a device was removed
* @RFKILL_OP_CHANGE: a device's state changed -- userspace changes one device
* @RFKILL_OP_CHANGE_ALL: userspace changes all devices (of a type, or all)
+ * into a state, also updating the default state used for devices that
+ * are hot-plugged later.
*/
enum rfkill_operation {
RFKILL_OP_ADD = 0,
diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h
new file mode 100644
index 000000000000..d648ff66586f
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_ife.h
@@ -0,0 +1,38 @@
+#ifndef __UAPI_TC_IFE_H
+#define __UAPI_TC_IFE_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_IFE 25
+/* Flag bits for now just encoding/decoding; mutually exclusive */
+#define IFE_ENCODE 1
+#define IFE_DECODE 0
+
+struct tc_ife {
+ tc_gen;
+ __u16 flags;
+};
+
+/*XXX: We need to encode the total number of bytes consumed */
+enum {
+ TCA_IFE_UNSPEC,
+ TCA_IFE_PARMS,
+ TCA_IFE_TM,
+ TCA_IFE_DMAC,
+ TCA_IFE_SMAC,
+ TCA_IFE_TYPE,
+ TCA_IFE_METALST,
+ __TCA_IFE_MAX
+};
+#define TCA_IFE_MAX (__TCA_IFE_MAX - 1)
+
+#define IFE_META_SKBMARK 1
+#define IFE_META_HASHID 2
+#define IFE_META_PRIO 3
+#define IFE_META_QMAP 4
+/*Can be overridden at runtime by module option*/
+#define __IFE_META_MAX 5
+#define IFE_META_MAX (__IFE_META_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 65a77b071e22..53e8e3fe6b1b 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -196,6 +196,11 @@ struct tcp_info {
__u64 tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */
__u32 tcpi_segs_out; /* RFC4898 tcpEStatsPerfSegsOut */
__u32 tcpi_segs_in; /* RFC4898 tcpEStatsPerfSegsIn */
+
+ __u32 tcpi_notsent_bytes;
+ __u32 tcpi_min_rtt;
+ __u32 tcpi_data_segs_in; /* RFC4898 tcpEStatsDataSegsIn */
+ __u32 tcpi_data_segs_out; /* RFC4898 tcpEStatsDataSegsOut */
};
/* for TCP_MD5SIG socket option */
diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h
index 252ffd4801ef..4f20dbc42910 100644
--- a/include/xen/interface/io/netif.h
+++ b/include/xen/interface/io/netif.h
@@ -1,16 +1,34 @@
/******************************************************************************
- * netif.h
+ * xen_netif.h
*
* Unified network-device I/O interface for Xen guest OSes.
*
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
* Copyright (c) 2003-2004, Keir Fraser
*/
-#ifndef __XEN_PUBLIC_IO_NETIF_H__
-#define __XEN_PUBLIC_IO_NETIF_H__
+#ifndef __XEN_PUBLIC_IO_XEN_NETIF_H__
+#define __XEN_PUBLIC_IO_XEN_NETIF_H__
-#include <xen/interface/io/ring.h>
-#include <xen/interface/grant_table.h>
+#include "ring.h"
+#include "../grant_table.h"
/*
* Older implementation of Xen network frontend / backend has an
@@ -38,10 +56,10 @@
* that it cannot safely queue packets (as it may not be kicked to send them).
*/
- /*
+/*
* "feature-split-event-channels" is introduced to separate guest TX
- * and RX notificaion. Backend either doesn't support this feature or
- * advertise it via xenstore as 0 (disabled) or 1 (enabled).
+ * and RX notification. Backend either doesn't support this feature or
+ * advertises it via xenstore as 0 (disabled) or 1 (enabled).
*
* To make use of this feature, frontend should allocate two event
* channels for TX and RX, advertise them to backend as
@@ -118,151 +136,804 @@
*/
/*
- * This is the 'wire' format for packets:
- * Request 1: xen_netif_tx_request -- XEN_NETTXF_* (any flags)
- * [Request 2: xen_netif_extra_info] (only if request 1 has XEN_NETTXF_extra_info)
- * [Request 3: xen_netif_extra_info] (only if request 2 has XEN_NETIF_EXTRA_MORE)
- * Request 4: xen_netif_tx_request -- XEN_NETTXF_more_data
- * Request 5: xen_netif_tx_request -- XEN_NETTXF_more_data
+ * "feature-multicast-control" and "feature-dynamic-multicast-control"
+ * advertise the capability to filter ethernet multicast packets in the
+ * backend. If the frontend wishes to take advantage of this feature then
+ * it may set "request-multicast-control". If the backend only advertises
+ * "feature-multicast-control" then "request-multicast-control" must be set
+ * before the frontend moves into the connected state. The backend will
+ * sample the value on this state transition and any subsequent change in
+ * value will have no effect. However, if the backend also advertises
+ * "feature-dynamic-multicast-control" then "request-multicast-control"
+ * may be set by the frontend at any time. In this case, the backend will
+ * watch the value and re-sample on watch events.
+ *
+ * If the sampled value of "request-multicast-control" is set then the
+ * backend transmit side should no longer flood multicast packets to the
+ * frontend, it should instead drop any multicast packet that does not
+ * match in a filter list.
+ * The list is amended by the frontend by sending dummy transmit requests
+ * containing XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL} extra-info fragments as
+ * specified below.
+ * Note that the filter list may be amended even if the sampled value of
+ * "request-multicast-control" is not set, however the filter should only
+ * be applied if it is set.
+ */
+
+/*
+ * Control ring
+ * ============
+ *
+ * Some features, such as hashing (detailed below), require a
+ * significant amount of out-of-band data to be passed from frontend to
+ * backend. Use of xenstore is not suitable for large quantities of data
+ * because of quota limitations and so a dedicated 'control ring' is used.
+ * The ability of the backend to use a control ring is advertised by
+ * setting:
+ *
+ * /local/domain/X/backend/<domid>/<vif>/feature-ctrl-ring = "1"
+ *
+ * The frontend provides a control ring to the backend by setting:
+ *
+ * /local/domain/<domid>/device/vif/<vif>/ctrl-ring-ref = <gref>
+ * /local/domain/<domid>/device/vif/<vif>/event-channel-ctrl = <port>
+ *
+ * where <gref> is the grant reference of the shared page used to
+ * implement the control ring and <port> is an event channel to be used
+ * as a mailbox interrupt. These keys must be set before the frontend
+ * moves into the connected state.
+ *
+ * The control ring uses a fixed request/response message size and is
+ * balanced (i.e. one request to one response), so operationally it is much
+ * the same as a transmit or receive ring.
+ * Note that there is no requirement that responses are issued in the same
+ * order as requests.
+ */
+
+/*
+ * Hash types
+ * ==========
+ *
+ * For the purposes of the definitions below, 'Packet[]' is an array of
+ * octets containing an IP packet without options, 'Array[X..Y]' means a
+ * sub-array of 'Array' containing bytes X thru Y inclusive, and '+' is
+ * used to indicate concatenation of arrays.
+ */
+
+/*
+ * A hash calculated over an IP version 4 header as follows:
+ *
+ * Buffer[0..8] = Packet[12..15] (source address) +
+ * Packet[16..19] (destination address)
+ *
+ * Result = Hash(Buffer, 8)
+ */
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV4 0
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV4 \
+ (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV4)
+
+/*
+ * A hash calculated over an IP version 4 header and TCP header as
+ * follows:
+ *
+ * Buffer[0..12] = Packet[12..15] (source address) +
+ * Packet[16..19] (destination address) +
+ * Packet[20..21] (source port) +
+ * Packet[22..23] (destination port)
+ *
+ * Result = Hash(Buffer, 12)
+ */
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP 1
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP \
+ (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV4_TCP)
+
+/*
+ * A hash calculated over an IP version 6 header as follows:
+ *
+ * Buffer[0..32] = Packet[8..23] (source address ) +
+ * Packet[24..39] (destination address)
+ *
+ * Result = Hash(Buffer, 32)
+ */
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV6 2
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV6 \
+ (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV6)
+
+/*
+ * A hash calculated over an IP version 6 header and TCP header as
+ * follows:
+ *
+ * Buffer[0..36] = Packet[8..23] (source address) +
+ * Packet[24..39] (destination address) +
+ * Packet[40..41] (source port) +
+ * Packet[42..43] (destination port)
+ *
+ * Result = Hash(Buffer, 36)
+ */
+#define _XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP 3
+#define XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP \
+ (1 << _XEN_NETIF_CTRL_HASH_TYPE_IPV6_TCP)
+
+/*
+ * Hash algorithms
+ * ===============
+ */
+
+#define XEN_NETIF_CTRL_HASH_ALGORITHM_NONE 0
+
+/*
+ * Toeplitz hash:
+ */
+
+#define XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ 1
+
+/*
+ * This algorithm uses a 'key' as well as the data buffer itself.
+ * (Buffer[] and Key[] are treated as shift-registers where the MSB of
+ * Buffer/Key[0] is considered 'left-most' and the LSB of Buffer/Key[N-1]
+ * is the 'right-most').
+ *
+ * Value = 0
+ * For number of bits in Buffer[]
+ * If (left-most bit of Buffer[] is 1)
+ * Value ^= left-most 32 bits of Key[]
+ * Key[] << 1
+ * Buffer[] << 1
+ *
+ * The code below is provided for convenience where an operating system
+ * does not already provide an implementation.
+ */
+#ifdef XEN_NETIF_DEFINE_TOEPLITZ
+static uint32_t xen_netif_toeplitz_hash(const uint8_t *key,
+ unsigned int keylen,
+ const uint8_t *buf, unsigned int buflen)
+{
+ unsigned int keyi, bufi;
+ uint64_t prefix = 0;
+ uint64_t hash = 0;
+
+ /* Pre-load prefix with the first 8 bytes of the key */
+ for (keyi = 0; keyi < 8; keyi++) {
+ prefix <<= 8;
+ prefix |= (keyi < keylen) ? key[keyi] : 0;
+ }
+
+ for (bufi = 0; bufi < buflen; bufi++) {
+ uint8_t byte = buf[bufi];
+ unsigned int bit;
+
+ for (bit = 0; bit < 8; bit++) {
+ if (byte & 0x80)
+ hash ^= prefix;
+ prefix <<= 1;
+ byte <<= 1;
+ }
+
+ /*
+ * 'prefix' has now been left-shifted by 8, so
+ * OR in the next byte.
+ */
+ prefix |= (keyi < keylen) ? key[keyi] : 0;
+ keyi++;
+ }
+
+ /* The valid part of the hash is in the upper 32 bits. */
+ return hash >> 32;
+}
+#endif /* XEN_NETIF_DEFINE_TOEPLITZ */
+
+/*
+ * Control requests (struct xen_netif_ctrl_request)
+ * ================================================
+ *
+ * All requests have the following format:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | type | data[0] |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | data[1] | data[2] |
+ * +-----+-----+-----+-----+-----------------------+
+ *
+ * id: the request identifier, echoed in response.
+ * type: the type of request (see below)
+ * data[]: any data associated with the request (determined by type)
+ */
+
+struct xen_netif_ctrl_request {
+ uint16_t id;
+ uint16_t type;
+
+#define XEN_NETIF_CTRL_TYPE_INVALID 0
+#define XEN_NETIF_CTRL_TYPE_GET_HASH_FLAGS 1
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_FLAGS 2
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_KEY 3
+#define XEN_NETIF_CTRL_TYPE_GET_HASH_MAPPING_SIZE 4
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE 5
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING 6
+#define XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM 7
+
+ uint32_t data[3];
+};
+
+/*
+ * Control responses (struct xen_netif_ctrl_response)
+ * ==================================================
+ *
+ * All responses have the following format:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | type | status |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | data |
+ * +-----+-----+-----+-----+
+ *
+ * id: the corresponding request identifier
+ * type: the type of the corresponding request
+ * status: the status of request processing
+ * data: any data associated with the response (determined by type and
+ * status)
+ */
+
+struct xen_netif_ctrl_response {
+ uint16_t id;
+ uint16_t type;
+ uint32_t status;
+
+#define XEN_NETIF_CTRL_STATUS_SUCCESS 0
+#define XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED 1
+#define XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER 2
+#define XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW 3
+
+ uint32_t data;
+};
+
+/*
+ * Control messages
+ * ================
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM
+ * --------------------------------------
+ *
+ * This is sent by the frontend to set the desired hash algorithm.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_HASH_ALGORITHM
+ * data[0] = a XEN_NETIF_CTRL_HASH_ALGORITHM_* value
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - The algorithm is not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ *
+ * NOTE: Setting data[0] to XEN_NETIF_CTRL_HASH_ALGORITHM_NONE disables
+ * hashing and the backend is free to choose how it steers packets
+ * to queues (which is the default behaviour).
+ *
+ * XEN_NETIF_CTRL_TYPE_GET_HASH_FLAGS
+ * ----------------------------------
+ *
+ * This is sent by the frontend to query the types of hash supported by
+ * the backend.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_GET_HASH_FLAGS
+ * data[0] = 0
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = supported hash types (if operation was successful)
+ *
+ * NOTE: A valid hash algorithm must be selected before this operation can
+ * succeed.
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_FLAGS
+ * ----------------------------------
+ *
+ * This is sent by the frontend to set the types of hash that the backend
+ * should calculate. (See above for hash type definitions).
+ * Note that the 'maximal' type of hash should always be chosen. For
+ * example, if the frontend sets both IPV4 and IPV4_TCP hash types then
+ * the latter hash type should be calculated for any TCP packet and the
+ * former only calculated for non-TCP packets.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_HASH_FLAGS
+ * data[0] = bitwise OR of XEN_NETIF_CTRL_HASH_TYPE_* values
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - One or more flag
+ * value is invalid or
+ * unsupported
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * NOTE: A valid hash algorithm must be selected before this operation can
+ * succeed.
+ * Also, setting data[0] to zero disables hashing and the backend
+ * is free to choose how it steers packets to queues.
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_KEY
+ * --------------------------------
+ *
+ * This is sent by the frontend to set the key of the hash if the algorithm
+ * requires it. (See hash algorithms above).
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_HASH_KEY
+ * data[0] = grant reference of page containing the key (assumed to
+ * start at beginning of grant)
+ * data[1] = size of key in octets
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Key size is invalid
+ * XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW - Key size is larger
+ * than the backend
+ * supports
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * NOTE: Any key octets not specified are assumed to be zero (the key
+ * is assumed to be empty by default) and specifying a new key
+ * invalidates any previous key, hence specifying a key size of
+ * zero will clear the key (which ensures that the calculated hash
+ * will always be zero).
+ * The maximum size of key is algorithm and backend specific, but
+ * is also limited by the single grant reference.
+ * The grant reference may be read-only and must remain valid until
+ * the response has been processed.
+ *
+ * XEN_NETIF_CTRL_TYPE_GET_HASH_MAPPING_SIZE
+ * -----------------------------------------
+ *
+ * This is sent by the frontend to query the maximum size of mapping
+ * table supported by the backend. The size is specified in terms of
+ * table entries.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_GET_HASH_MAPPING_SIZE
+ * data[0] = 0
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not supported
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = maximum number of entries allowed in the mapping table
+ * (if operation was successful) or zero if a mapping table is
+ * not supported (i.e. hash mapping is done only by modular
+ * arithmetic).
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE
+ * -------------------------------------
+ *
+ * This is sent by the frontend to set the actual size of the mapping
+ * table to be used by the backend. The size is specified in terms of
+ * table entries.
+ * Any previous table is invalidated by this message and any new table
+ * is assumed to be zero filled.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE
+ * data[0] = number of entries in mapping table
+ * data[1] = 0
+ * data[2] = 0
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Table size is invalid
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * NOTE: Setting data[0] to 0 means that hash mapping should be done
+ * using modular arithmetic.
+ *
+ * XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING
+ * ------------------------------------
+ *
+ * This is sent by the frontend to set the content of the table mapping
+ * hash value to queue number. The backend should calculate the hash from
+ * the packet header, use it as an index into the table (modulo the size
+ * of the table) and then steer the packet to the queue number found at
+ * that index.
+ *
+ * Request:
+ *
+ * type = XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING
+ * data[0] = grant reference of page containing the mapping (sub-)table
+ * (assumed to start at beginning of grant)
+ * data[1] = size of (sub-)table in entries
+ * data[2] = offset, in entries, of sub-table within overall table
+ *
+ * Response:
+ *
+ * status = XEN_NETIF_CTRL_STATUS_NOT_SUPPORTED - Operation not
+ * supported
+ * XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER - Table size or content
+ * is invalid
+ * XEN_NETIF_CTRL_STATUS_BUFFER_OVERFLOW - Table size is larger
+ * than the backend
+ * supports
+ * XEN_NETIF_CTRL_STATUS_SUCCESS - Operation successful
+ * data = 0
+ *
+ * NOTE: The overall table has the following format:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | mapping[0] | mapping[1] |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | . |
+ * | . |
+ * | . |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | mapping[N-2] | mapping[N-1] |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * where N is specified by a XEN_NETIF_CTRL_TYPE_SET_HASH_MAPPING_SIZE
+ * message and each mapping must specifies a queue between 0 and
+ * "multi-queue-num-queues" (see above).
+ * The backend may support a mapping table larger than can be
+ * mapped by a single grant reference. Thus sub-tables within a
+ * larger table can be individually set by sending multiple messages
+ * with differing offset values. Specifying a new sub-table does not
+ * invalidate any table data outside that range.
+ * The grant reference may be read-only and must remain valid until
+ * the response has been processed.
+ */
+
+DEFINE_RING_TYPES(xen_netif_ctrl,
+ struct xen_netif_ctrl_request,
+ struct xen_netif_ctrl_response);
+
+/*
+ * Guest transmit
+ * ==============
+ *
+ * This is the 'wire' format for transmit (frontend -> backend) packets:
+ *
+ * Fragment 1: xen_netif_tx_request_t - flags = XEN_NETTXF_*
+ * size = total packet size
+ * [Extra 1: xen_netif_extra_info_t] - (only if fragment 1 flags include
+ * XEN_NETTXF_extra_info)
+ * ...
+ * [Extra N: xen_netif_extra_info_t] - (only if extra N-1 flags include
+ * XEN_NETIF_EXTRA_MORE)
* ...
- * Request N: xen_netif_tx_request -- 0
+ * Fragment N: xen_netif_tx_request_t - (only if fragment N-1 flags include
+ * XEN_NETTXF_more_data - flags on preceding
+ * extras are not relevant here)
+ * flags = 0
+ * size = fragment size
+ *
+ * NOTE:
+ *
+ * This format slightly is different from that used for receive
+ * (backend -> frontend) packets. Specifically, in a multi-fragment
+ * packet the actual size of fragment 1 can only be determined by
+ * subtracting the sizes of fragments 2..N from the total packet size.
+ *
+ * Ring slot size is 12 octets, however not all request/response
+ * structs use the full size.
+ *
+ * tx request data (xen_netif_tx_request_t)
+ * ------------------------------------
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | grant ref | offset | flags |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | size |
+ * +-----+-----+-----+-----+
+ *
+ * grant ref: Reference to buffer page.
+ * offset: Offset within buffer page.
+ * flags: XEN_NETTXF_*.
+ * id: request identifier, echoed in response.
+ * size: packet size in bytes.
+ *
+ * tx response (xen_netif_tx_response_t)
+ * ---------------------------------
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | status | unused |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | unused |
+ * +-----+-----+-----+-----+
+ *
+ * id: reflects id in transmit request
+ * status: XEN_NETIF_RSP_*
+ *
+ * Guest receive
+ * =============
+ *
+ * This is the 'wire' format for receive (backend -> frontend) packets:
+ *
+ * Fragment 1: xen_netif_rx_request_t - flags = XEN_NETRXF_*
+ * size = fragment size
+ * [Extra 1: xen_netif_extra_info_t] - (only if fragment 1 flags include
+ * XEN_NETRXF_extra_info)
+ * ...
+ * [Extra N: xen_netif_extra_info_t] - (only if extra N-1 flags include
+ * XEN_NETIF_EXTRA_MORE)
+ * ...
+ * Fragment N: xen_netif_rx_request_t - (only if fragment N-1 flags include
+ * XEN_NETRXF_more_data - flags on preceding
+ * extras are not relevant here)
+ * flags = 0
+ * size = fragment size
+ *
+ * NOTE:
+ *
+ * This format slightly is different from that used for transmit
+ * (frontend -> backend) packets. Specifically, in a multi-fragment
+ * packet the size of the packet can only be determined by summing the
+ * sizes of fragments 1..N.
+ *
+ * Ring slot size is 8 octets.
+ *
+ * rx request (xen_netif_rx_request_t)
+ * -------------------------------
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | pad | gref |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * id: request identifier, echoed in response.
+ * gref: reference to incoming granted frame.
+ *
+ * rx response (xen_netif_rx_response_t)
+ * ---------------------------------
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | id | offset | flags | status |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * id: reflects id in receive request
+ * offset: offset in page of start of received packet
+ * flags: XEN_NETRXF_*
+ * status: -ve: XEN_NETIF_RSP_*; +ve: Rx'ed pkt size.
+ *
+ * NOTE: Historically, to support GSO on the frontend receive side, Linux
+ * netfront does not make use of the rx response id (because, as
+ * described below, extra info structures overlay the id field).
+ * Instead it assumes that responses always appear in the same ring
+ * slot as their corresponding request. Thus, to maintain
+ * compatibility, backends must make sure this is the case.
+ *
+ * Extra Info
+ * ==========
+ *
+ * Can be present if initial request or response has NET{T,R}XF_extra_info,
+ * or previous extra request has XEN_NETIF_EXTRA_MORE.
+ *
+ * The struct therefore needs to fit into either a tx or rx slot and
+ * is therefore limited to 8 octets.
+ *
+ * NOTE: Because extra info data overlays the usual request/response
+ * structures, there is no id information in the opposite direction.
+ * So, if an extra info overlays an rx response the frontend can
+ * assume that it is in the same ring slot as the request that was
+ * consumed to make the slot available, and the backend must ensure
+ * this assumption is true.
+ *
+ * extra info (xen_netif_extra_info_t)
+ * -------------------------------
+ *
+ * General format:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * |type |flags| type specific data |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * | padding for tx |
+ * +-----+-----+-----+-----+
+ *
+ * type: XEN_NETIF_EXTRA_TYPE_*
+ * flags: XEN_NETIF_EXTRA_FLAG_*
+ * padding for tx: present only in the tx case due to 8 octet limit
+ * from rx case. Not shown in type specific entries
+ * below.
+ *
+ * XEN_NETIF_EXTRA_TYPE_GSO:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * |type |flags| size |type | pad | features |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * type: Must be XEN_NETIF_EXTRA_TYPE_GSO
+ * flags: XEN_NETIF_EXTRA_FLAG_*
+ * size: Maximum payload size of each segment. For example,
+ * for TCP this is just the path MSS.
+ * type: XEN_NETIF_GSO_TYPE_*: This determines the protocol of
+ * the packet and any extra features required to segment the
+ * packet properly.
+ * features: EN_XEN_NETIF_GSO_FEAT_*: This specifies any extra GSO
+ * features required to process this packet, such as ECN
+ * support for TCPv4.
+ *
+ * XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}:
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * |type |flags| addr |
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * type: Must be XEN_NETIF_EXTRA_TYPE_MCAST_{ADD,DEL}
+ * flags: XEN_NETIF_EXTRA_FLAG_*
+ * addr: address to add/remove
+ *
+ * XEN_NETIF_EXTRA_TYPE_HASH:
+ *
+ * A backend that supports teoplitz hashing is assumed to accept
+ * this type of extra info in transmit packets.
+ * A frontend that enables hashing is assumed to accept
+ * this type of extra info in receive packets.
+ *
+ * 0 1 2 3 4 5 6 7 octet
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * |type |flags|htype| alg |LSB ---- value ---- MSB|
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ *
+ * type: Must be XEN_NETIF_EXTRA_TYPE_HASH
+ * flags: XEN_NETIF_EXTRA_FLAG_*
+ * htype: Hash type (one of _XEN_NETIF_CTRL_HASH_TYPE_* - see above)
+ * alg: The algorithm used to calculate the hash (one of
+ * XEN_NETIF_CTRL_HASH_TYPE_ALGORITHM_* - see above)
+ * value: Hash value
*/
/* Protocol checksum field is blank in the packet (hardware offload)? */
-#define _XEN_NETTXF_csum_blank (0)
-#define XEN_NETTXF_csum_blank (1U<<_XEN_NETTXF_csum_blank)
+#define _XEN_NETTXF_csum_blank (0)
+#define XEN_NETTXF_csum_blank (1U<<_XEN_NETTXF_csum_blank)
/* Packet data has been validated against protocol checksum. */
-#define _XEN_NETTXF_data_validated (1)
-#define XEN_NETTXF_data_validated (1U<<_XEN_NETTXF_data_validated)
+#define _XEN_NETTXF_data_validated (1)
+#define XEN_NETTXF_data_validated (1U<<_XEN_NETTXF_data_validated)
/* Packet continues in the next request descriptor. */
-#define _XEN_NETTXF_more_data (2)
-#define XEN_NETTXF_more_data (1U<<_XEN_NETTXF_more_data)
+#define _XEN_NETTXF_more_data (2)
+#define XEN_NETTXF_more_data (1U<<_XEN_NETTXF_more_data)
/* Packet to be followed by extra descriptor(s). */
-#define _XEN_NETTXF_extra_info (3)
-#define XEN_NETTXF_extra_info (1U<<_XEN_NETTXF_extra_info)
+#define _XEN_NETTXF_extra_info (3)
+#define XEN_NETTXF_extra_info (1U<<_XEN_NETTXF_extra_info)
#define XEN_NETIF_MAX_TX_SIZE 0xFFFF
struct xen_netif_tx_request {
- grant_ref_t gref; /* Reference to buffer page */
- uint16_t offset; /* Offset within buffer page */
- uint16_t flags; /* XEN_NETTXF_* */
- uint16_t id; /* Echoed in response message. */
- uint16_t size; /* Packet size in bytes. */
+ grant_ref_t gref;
+ uint16_t offset;
+ uint16_t flags;
+ uint16_t id;
+ uint16_t size;
};
/* Types of xen_netif_extra_info descriptors. */
-#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */
-#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */
-#define XEN_NETIF_EXTRA_TYPE_MCAST_ADD (2) /* u.mcast */
-#define XEN_NETIF_EXTRA_TYPE_MCAST_DEL (3) /* u.mcast */
-#define XEN_NETIF_EXTRA_TYPE_MAX (4)
+#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */
+#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */
+#define XEN_NETIF_EXTRA_TYPE_MCAST_ADD (2) /* u.mcast */
+#define XEN_NETIF_EXTRA_TYPE_MCAST_DEL (3) /* u.mcast */
+#define XEN_NETIF_EXTRA_TYPE_HASH (4) /* u.hash */
+#define XEN_NETIF_EXTRA_TYPE_MAX (5)
-/* xen_netif_extra_info flags. */
-#define _XEN_NETIF_EXTRA_FLAG_MORE (0)
-#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
+/* xen_netif_extra_info_t flags. */
+#define _XEN_NETIF_EXTRA_FLAG_MORE (0)
+#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
/* GSO types */
-#define XEN_NETIF_GSO_TYPE_NONE (0)
-#define XEN_NETIF_GSO_TYPE_TCPV4 (1)
-#define XEN_NETIF_GSO_TYPE_TCPV6 (2)
+#define XEN_NETIF_GSO_TYPE_NONE (0)
+#define XEN_NETIF_GSO_TYPE_TCPV4 (1)
+#define XEN_NETIF_GSO_TYPE_TCPV6 (2)
/*
- * This structure needs to fit within both netif_tx_request and
- * netif_rx_response for compatibility.
+ * This structure needs to fit within both xen_netif_tx_request_t and
+ * xen_netif_rx_response_t for compatibility.
*/
struct xen_netif_extra_info {
- uint8_t type; /* XEN_NETIF_EXTRA_TYPE_* */
- uint8_t flags; /* XEN_NETIF_EXTRA_FLAG_* */
-
+ uint8_t type;
+ uint8_t flags;
union {
struct {
- /*
- * Maximum payload size of each segment. For
- * example, for TCP this is just the path MSS.
- */
uint16_t size;
-
- /*
- * GSO type. This determines the protocol of
- * the packet and any extra features required
- * to segment the packet properly.
- */
- uint8_t type; /* XEN_NETIF_GSO_TYPE_* */
-
- /* Future expansion. */
+ uint8_t type;
uint8_t pad;
-
- /*
- * GSO features. This specifies any extra GSO
- * features required to process this packet,
- * such as ECN support for TCPv4.
- */
- uint16_t features; /* XEN_NETIF_GSO_FEAT_* */
+ uint16_t features;
} gso;
-
struct {
- uint8_t addr[6]; /* Address to add/remove. */
+ uint8_t addr[6];
} mcast;
-
+ struct {
+ uint8_t type;
+ uint8_t algorithm;
+ uint8_t value[4];
+ } hash;
uint16_t pad[3];
} u;
};
struct xen_netif_tx_response {
uint16_t id;
- int16_t status; /* XEN_NETIF_RSP_* */
+ int16_t status;
};
struct xen_netif_rx_request {
- uint16_t id; /* Echoed in response message. */
- grant_ref_t gref; /* Reference to incoming granted frame */
+ uint16_t id; /* Echoed in response message. */
+ uint16_t pad;
+ grant_ref_t gref;
};
/* Packet data has been validated against protocol checksum. */
-#define _XEN_NETRXF_data_validated (0)
-#define XEN_NETRXF_data_validated (1U<<_XEN_NETRXF_data_validated)
+#define _XEN_NETRXF_data_validated (0)
+#define XEN_NETRXF_data_validated (1U<<_XEN_NETRXF_data_validated)
/* Protocol checksum field is blank in the packet (hardware offload)? */
-#define _XEN_NETRXF_csum_blank (1)
-#define XEN_NETRXF_csum_blank (1U<<_XEN_NETRXF_csum_blank)
+#define _XEN_NETRXF_csum_blank (1)
+#define XEN_NETRXF_csum_blank (1U<<_XEN_NETRXF_csum_blank)
/* Packet continues in the next request descriptor. */
-#define _XEN_NETRXF_more_data (2)
-#define XEN_NETRXF_more_data (1U<<_XEN_NETRXF_more_data)
+#define _XEN_NETRXF_more_data (2)
+#define XEN_NETRXF_more_data (1U<<_XEN_NETRXF_more_data)
/* Packet to be followed by extra descriptor(s). */
-#define _XEN_NETRXF_extra_info (3)
-#define XEN_NETRXF_extra_info (1U<<_XEN_NETRXF_extra_info)
+#define _XEN_NETRXF_extra_info (3)
+#define XEN_NETRXF_extra_info (1U<<_XEN_NETRXF_extra_info)
-/* GSO Prefix descriptor. */
-#define _XEN_NETRXF_gso_prefix (4)
-#define XEN_NETRXF_gso_prefix (1U<<_XEN_NETRXF_gso_prefix)
+/* Packet has GSO prefix. Deprecated but included for compatibility */
+#define _XEN_NETRXF_gso_prefix (4)
+#define XEN_NETRXF_gso_prefix (1U<<_XEN_NETRXF_gso_prefix)
struct xen_netif_rx_response {
- uint16_t id;
- uint16_t offset; /* Offset in page of start of received packet */
- uint16_t flags; /* XEN_NETRXF_* */
- int16_t status; /* -ve: BLKIF_RSP_* ; +ve: Rx'ed pkt size. */
+ uint16_t id;
+ uint16_t offset;
+ uint16_t flags;
+ int16_t status;
};
/*
- * Generate netif ring structures and types.
+ * Generate xen_netif ring structures and types.
*/
-DEFINE_RING_TYPES(xen_netif_tx,
- struct xen_netif_tx_request,
+DEFINE_RING_TYPES(xen_netif_tx, struct xen_netif_tx_request,
struct xen_netif_tx_response);
-DEFINE_RING_TYPES(xen_netif_rx,
- struct xen_netif_rx_request,
+DEFINE_RING_TYPES(xen_netif_rx, struct xen_netif_rx_request,
struct xen_netif_rx_response);
-#define XEN_NETIF_RSP_DROPPED -2
-#define XEN_NETIF_RSP_ERROR -1
-#define XEN_NETIF_RSP_OKAY 0
-/* No response: used for auxiliary requests (e.g., xen_netif_extra_info). */
-#define XEN_NETIF_RSP_NULL 1
+#define XEN_NETIF_RSP_DROPPED -2
+#define XEN_NETIF_RSP_ERROR -1
+#define XEN_NETIF_RSP_OKAY 0
+/* No response: used for auxiliary requests (e.g., xen_netif_extra_info_t). */
+#define XEN_NETIF_RSP_NULL 1
#endif