summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-07-11 04:16:22 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-07-11 04:16:22 +0300
commit5a764898afec0bc097003e8c3e727792289f76d6 (patch)
tree5e5ffde9c63913705b2869046458af8bd485c16e /include
parent9321f1aaf63e74ec3884347490e4ebb039f01b6e (diff)
parent1195c7cebb95081d809f81a27b21829573cbd4a8 (diff)
downloadlinux-5a764898afec0bc097003e8c3e727792289f76d6.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from David Miller: 1) Restore previous behavior of CAP_SYS_ADMIN wrt loading networking BPF programs, from Maciej Żenczykowski. 2) Fix dropped broadcasts in mac80211 code, from Seevalamuthu Mariappan. 3) Slay memory leak in nl80211 bss color attribute parsing code, from Luca Coelho. 4) Get route from skb properly in ip_route_use_hint(), from Miaohe Lin. 5) Don't allow anything other than ARPHRD_ETHER in llc code, from Eric Dumazet. 6) xsk code dips too deeply into DMA mapping implementation internals. Add dma_need_sync and use it. From Christoph Hellwig 7) Enforce power-of-2 for BPF ringbuf sizes. From Andrii Nakryiko. 8) Check for disallowed attributes when loading flow dissector BPF programs. From Lorenz Bauer. 9) Correct packet injection to L3 tunnel devices via AF_PACKET, from Jason A. Donenfeld. 10) Don't advertise checksum offload on ipa devices that don't support it. From Alex Elder. 11) Resolve several issues in TCP MD5 signature support. Missing memory barriers, bogus options emitted when using syncookies, and failure to allow md5 key changes in established states. All from Eric Dumazet. 12) Fix interface leak in hsr code, from Taehee Yoo. 13) VF reset fixes in hns3 driver, from Huazhong Tan. 14) Make loopback work again with ipv6 anycast, from David Ahern. 15) Fix TX starvation under high load in fec driver, from Tobias Waldekranz. 16) MLD2 payload lengths not checked properly in bridge multicast code, from Linus Lüssing. 17) Packet scheduler code that wants to find the inner protocol currently only works for one level of VLAN encapsulation. Allow Q-in-Q situations to work properly here, from Toke Høiland-Jørgensen. 18) Fix route leak in l2tp, from Xin Long. 19) Resolve conflict between the sk->sk_user_data usage of bpf reuseport support and various protocols. From Martin KaFai Lau. 20) Fix socket cgroup v2 reference counting in some situations, from Cong Wang. 21) Cure memory leak in mlx5 connection tracking offload support, from Eli Britstein. * git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (146 commits) mlxsw: pci: Fix use-after-free in case of failed devlink reload mlxsw: spectrum_router: Remove inappropriate usage of WARN_ON() net: macb: fix call to pm_runtime in the suspend/resume functions net: macb: fix macb_suspend() by removing call to netif_carrier_off() net: macb: fix macb_get/set_wol() when moving to phylink net: macb: mark device wake capable when "magic-packet" property present net: macb: fix wakeup test in runtime suspend/resume routines bnxt_en: fix NULL dereference in case SR-IOV configuration fails libbpf: Fix libbpf hashmap on (I)LP32 architectures net/mlx5e: CT: Fix memory leak in cleanup net/mlx5e: Fix port buffers cell size value net/mlx5e: Fix 50G per lane indication net/mlx5e: Fix CPU mapping after function reload to avoid aRFS RX crash net/mlx5e: Fix VXLAN configuration restore after function reload net/mlx5e: Fix usage of rcu-protected pointer net/mxl5e: Verify that rpriv is not NULL net/mlx5: E-Switch, Fix vlan or qos setting in legacy mode net/mlx5: Fix eeprom support for SFP module cgroup: Fix sock_cgroup_data on big-endian. selftests: bpf: Fix detach from sockmap tests ...
Diffstat (limited to 'include')
-rw-r--r--include/linux/bpf-netns.h5
-rw-r--r--include/linux/bpf.h13
-rw-r--r--include/linux/btf.h5
-rw-r--r--include/linux/cgroup-defs.h8
-rw-r--r--include/linux/cgroup.h4
-rw-r--r--include/linux/dma-direct.h1
-rw-r--r--include/linux/dma-mapping.h5
-rw-r--r--include/linux/ieee80211.h4
-rw-r--r--include/linux/if_vlan.h29
-rw-r--r--include/linux/mlx5/driver.h1
-rw-r--r--include/linux/mlx5/mlx5_ifc.h28
-rw-r--r--include/linux/skmsg.h13
-rw-r--r--include/net/dst.h10
-rw-r--r--include/net/flow_dissector.h3
-rw-r--r--include/net/genetlink.h10
-rw-r--r--include/net/inet_ecn.h25
-rw-r--r--include/net/ip_tunnels.h3
-rw-r--r--include/net/netns/bpf.h7
-rw-r--r--include/net/pkt_sched.h11
-rw-r--r--include/net/sock.h3
-rw-r--r--include/net/xsk_buff_pool.h6
-rw-r--r--include/uapi/linux/bpf.h41
22 files changed, 164 insertions, 71 deletions
diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h
index 4052d649f36d..47d5b0c708c9 100644
--- a/include/linux/bpf-netns.h
+++ b/include/linux/bpf-netns.h
@@ -33,7 +33,7 @@ int netns_bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr);
int netns_bpf_prog_attach(const union bpf_attr *attr,
struct bpf_prog *prog);
-int netns_bpf_prog_detach(const union bpf_attr *attr);
+int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
int netns_bpf_link_create(const union bpf_attr *attr,
struct bpf_prog *prog);
#else
@@ -49,7 +49,8 @@ static inline int netns_bpf_prog_attach(const union bpf_attr *attr,
return -EOPNOTSUPP;
}
-static inline int netns_bpf_prog_detach(const union bpf_attr *attr)
+static inline int netns_bpf_prog_detach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype)
{
return -EOPNOTSUPP;
}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 07052d44bca1..9750a1902ee5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1543,13 +1543,16 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
#if defined(CONFIG_BPF_STREAM_PARSER)
-int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which);
+int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
+ struct bpf_prog *old, u32 which);
int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
+int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
void sock_map_unhash(struct sock *sk);
void sock_map_close(struct sock *sk, long timeout);
#else
static inline int sock_map_prog_update(struct bpf_map *map,
- struct bpf_prog *prog, u32 which)
+ struct bpf_prog *prog,
+ struct bpf_prog *old, u32 which)
{
return -EOPNOTSUPP;
}
@@ -1559,6 +1562,12 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr,
{
return -EINVAL;
}
+
+static inline int sock_map_prog_detach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype)
+{
+ return -EOPNOTSUPP;
+}
#endif /* CONFIG_BPF_STREAM_PARSER */
#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 5c1ea99b480f..8b81fbb4497c 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -82,6 +82,11 @@ static inline bool btf_type_is_int(const struct btf_type *t)
return BTF_INFO_KIND(t->info) == BTF_KIND_INT;
}
+static inline bool btf_type_is_small_int(const struct btf_type *t)
+{
+ return btf_type_is_int(t) && t->size <= sizeof(u64);
+}
+
static inline bool btf_type_is_enum(const struct btf_type *t)
{
return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM;
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 52661155f85f..fee0b5547cd0 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -790,7 +790,9 @@ struct sock_cgroup_data {
union {
#ifdef __LITTLE_ENDIAN
struct {
- u8 is_data;
+ u8 is_data : 1;
+ u8 no_refcnt : 1;
+ u8 unused : 6;
u8 padding;
u16 prioidx;
u32 classid;
@@ -800,7 +802,9 @@ struct sock_cgroup_data {
u32 classid;
u16 prioidx;
u8 padding;
- u8 is_data;
+ u8 unused : 6;
+ u8 no_refcnt : 1;
+ u8 is_data : 1;
} __packed;
#endif
u64 val;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 4598e4da6b1b..618838c48313 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -822,6 +822,7 @@ extern spinlock_t cgroup_sk_update_lock;
void cgroup_sk_alloc_disable(void);
void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
+void cgroup_sk_clone(struct sock_cgroup_data *skcd);
void cgroup_sk_free(struct sock_cgroup_data *skcd);
static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
@@ -835,7 +836,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
*/
v = READ_ONCE(skcd->val);
- if (v & 1)
+ if (v & 3)
return &cgrp_dfl_root.cgrp;
return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
@@ -847,6 +848,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
#else /* CONFIG_CGROUP_DATA */
static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
+static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {}
static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
#endif /* CONFIG_CGROUP_DATA */
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index cdfa400f89b3..5184735a0fe8 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -85,4 +85,5 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size,
unsigned long attrs);
int dma_direct_supported(struct device *dev, u64 mask);
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
#endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 78f677cf45ab..a33ed3954ed4 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -461,6 +461,7 @@ int dma_set_mask(struct device *dev, u64 mask);
int dma_set_coherent_mask(struct device *dev, u64 mask);
u64 dma_get_required_mask(struct device *dev);
size_t dma_max_mapping_size(struct device *dev);
+bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
unsigned long dma_get_merge_boundary(struct device *dev);
#else /* CONFIG_HAS_DMA */
static inline dma_addr_t dma_map_page_attrs(struct device *dev,
@@ -571,6 +572,10 @@ static inline size_t dma_max_mapping_size(struct device *dev)
{
return 0;
}
+static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+ return false;
+}
static inline unsigned long dma_get_merge_boundary(struct device *dev)
{
return 0;
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index fe15f831841b..9f732499ea88 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -3333,13 +3333,17 @@ struct ieee80211_multiple_bssid_configuration {
#define WLAN_AKM_SUITE_TDLS SUITE(0x000FAC, 7)
#define WLAN_AKM_SUITE_SAE SUITE(0x000FAC, 8)
#define WLAN_AKM_SUITE_FT_OVER_SAE SUITE(0x000FAC, 9)
+#define WLAN_AKM_SUITE_AP_PEER_KEY SUITE(0x000FAC, 10)
#define WLAN_AKM_SUITE_8021X_SUITE_B SUITE(0x000FAC, 11)
#define WLAN_AKM_SUITE_8021X_SUITE_B_192 SUITE(0x000FAC, 12)
+#define WLAN_AKM_SUITE_FT_8021X_SHA384 SUITE(0x000FAC, 13)
#define WLAN_AKM_SUITE_FILS_SHA256 SUITE(0x000FAC, 14)
#define WLAN_AKM_SUITE_FILS_SHA384 SUITE(0x000FAC, 15)
#define WLAN_AKM_SUITE_FT_FILS_SHA256 SUITE(0x000FAC, 16)
#define WLAN_AKM_SUITE_FT_FILS_SHA384 SUITE(0x000FAC, 17)
#define WLAN_AKM_SUITE_OWE SUITE(0x000FAC, 18)
+#define WLAN_AKM_SUITE_FT_PSK_SHA384 SUITE(0x000FAC, 19)
+#define WLAN_AKM_SUITE_PSK_SHA384 SUITE(0x000FAC, 20)
#define WLAN_MAX_KEY_LEN 32
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index b05e855f1ddd..41a518336673 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -25,6 +25,8 @@
#define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */
#define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */
+#define VLAN_MAX_DEPTH 8 /* Max. number of nested VLAN tags parsed */
+
/*
* struct vlan_hdr - vlan header
* @h_vlan_TCI: priority and VLAN ID
@@ -577,10 +579,10 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
* Returns the EtherType of the packet, regardless of whether it is
* vlan encapsulated (normal or hardware accelerated) or not.
*/
-static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
+static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
int *depth)
{
- unsigned int vlan_depth = skb->mac_len;
+ unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH;
/* if type is 802.1Q/AD then the header should already be
* present at mac_len - VLAN_HLEN (if mac_len > 0), or at
@@ -595,13 +597,12 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
vlan_depth = ETH_HLEN;
}
do {
- struct vlan_hdr *vh;
+ struct vlan_hdr vhdr, *vh;
- if (unlikely(!pskb_may_pull(skb,
- vlan_depth + VLAN_HLEN)))
+ vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr);
+ if (unlikely(!vh || !--parse_depth))
return 0;
- vh = (struct vlan_hdr *)(skb->data + vlan_depth);
type = vh->h_vlan_encapsulated_proto;
vlan_depth += VLAN_HLEN;
} while (eth_type_vlan(type));
@@ -620,11 +621,25 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
* Returns the EtherType of the packet, regardless of whether it is
* vlan encapsulated (normal or hardware accelerated) or not.
*/
-static inline __be16 vlan_get_protocol(struct sk_buff *skb)
+static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
{
return __vlan_get_protocol(skb, skb->protocol, NULL);
}
+/* A getter for the SKB protocol field which will handle VLAN tags consistently
+ * whether VLAN acceleration is enabled or not.
+ */
+static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
+{
+ if (!skip_vlan)
+ /* VLAN acceleration strips the VLAN header from the skb and
+ * moves it to skb->vlan_proto
+ */
+ return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol;
+
+ return vlan_get_protocol(skb);
+}
+
static inline void vlan_set_encap_proto(struct sk_buff *skb,
struct vlan_hdr *vhdr)
{
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 13c0e4556eda..1e6ca716635a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -147,6 +147,7 @@ enum {
MLX5_REG_MCDA = 0x9063,
MLX5_REG_MCAM = 0x907f,
MLX5_REG_MIRC = 0x9162,
+ MLX5_REG_SBCAM = 0xB01F,
MLX5_REG_RESOURCE_DUMP = 0xC000,
};
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ca1887dd0423..073b79eacc99 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -9960,6 +9960,34 @@ struct mlx5_ifc_pptb_reg_bits {
u8 untagged_buff[0x4];
};
+struct mlx5_ifc_sbcam_reg_bits {
+ u8 reserved_at_0[0x8];
+ u8 feature_group[0x8];
+ u8 reserved_at_10[0x8];
+ u8 access_reg_group[0x8];
+
+ u8 reserved_at_20[0x20];
+
+ u8 sb_access_reg_cap_mask[4][0x20];
+
+ u8 reserved_at_c0[0x80];
+
+ u8 sb_feature_cap_mask[4][0x20];
+
+ u8 reserved_at_1c0[0x40];
+
+ u8 cap_total_buffer_size[0x20];
+
+ u8 cap_cell_size[0x10];
+ u8 cap_max_pg_buffers[0x8];
+ u8 cap_num_pool_supported[0x8];
+
+ u8 reserved_at_240[0x8];
+ u8 cap_sbsr_stat_size[0x8];
+ u8 cap_max_tclass_data[0x8];
+ u8 cap_max_cpu_ingress_tclass_sb[0x8];
+};
+
struct mlx5_ifc_pbmc_reg_bits {
u8 reserved_at_0[0x8];
u8 local_port[0x8];
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 08674cd14d5a..1e9ed840b9fc 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -430,6 +430,19 @@ static inline void psock_set_prog(struct bpf_prog **pprog,
bpf_prog_put(prog);
}
+static inline int psock_replace_prog(struct bpf_prog **pprog,
+ struct bpf_prog *prog,
+ struct bpf_prog *old)
+{
+ if (cmpxchg(pprog, old, prog) != old)
+ return -ENOENT;
+
+ if (old)
+ bpf_prog_put(old);
+
+ return 0;
+}
+
static inline void psock_progs_drop(struct sk_psock_progs *progs)
{
psock_set_prog(&progs->msg_parser, NULL);
diff --git a/include/net/dst.h b/include/net/dst.h
index 07adfacd8088..852d8fb36ab7 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -400,7 +400,15 @@ static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, co
static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst,
struct sk_buff *skb)
{
- struct neighbour *n = dst->ops->neigh_lookup(dst, skb, NULL);
+ struct neighbour *n = NULL;
+
+ /* The packets from tunnel devices (eg bareudp) may have only
+ * metadata in the dst pointer of skb. Hence a pointer check of
+ * neigh_lookup is needed.
+ */
+ if (dst->ops->neigh_lookup)
+ n = dst->ops->neigh_lookup(dst, skb, NULL);
+
return IS_ERR(n) ? NULL : n;
}
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index a7eba43fe4e4..4b6e36288ddd 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -372,7 +372,8 @@ flow_dissector_init_keys(struct flow_dissector_key_control *key_control,
}
#ifdef CONFIG_BPF_SYSCALL
-int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog);
+int flow_dissector_bpf_prog_attach_check(struct net *net,
+ struct bpf_prog *prog);
#endif /* CONFIG_BPF_SYSCALL */
#endif
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 74950663bb00..6e5f1e1aa822 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -35,13 +35,6 @@ struct genl_info;
* do additional, common, filtering and return an error
* @post_doit: called after an operation's doit callback, it may
* undo operations done by pre_doit, for example release locks
- * @mcast_bind: a socket bound to the given multicast group (which
- * is given as the offset into the groups array)
- * @mcast_unbind: a socket was unbound from the given multicast group.
- * Note that unbind() will not be called symmetrically if the
- * generic netlink family is removed while there are still open
- * sockets.
- * @attrbuf: buffer to store parsed attributes (private)
* @mcgrps: multicast groups used by this family
* @n_mcgrps: number of multicast groups
* @mcgrp_offset: starting number of multicast group IDs in this family
@@ -64,9 +57,6 @@ struct genl_family {
void (*post_doit)(const struct genl_ops *ops,
struct sk_buff *skb,
struct genl_info *info);
- int (*mcast_bind)(struct net *net, int group);
- void (*mcast_unbind)(struct net *net, int group);
- struct nlattr ** attrbuf; /* private */
const struct genl_ops * ops;
const struct genl_multicast_group *mcgrps;
unsigned int n_ops;
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index 0f0d1efe06dd..e1eaf1780288 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -4,6 +4,7 @@
#include <linux/ip.h>
#include <linux/skbuff.h>
+#include <linux/if_vlan.h>
#include <net/inet_sock.h>
#include <net/dsfield.h>
@@ -172,7 +173,7 @@ static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
static inline int INET_ECN_set_ce(struct sk_buff *skb)
{
- switch (skb->protocol) {
+ switch (skb_protocol(skb, true)) {
case cpu_to_be16(ETH_P_IP):
if (skb_network_header(skb) + sizeof(struct iphdr) <=
skb_tail_pointer(skb))
@@ -191,7 +192,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
static inline int INET_ECN_set_ect1(struct sk_buff *skb)
{
- switch (skb->protocol) {
+ switch (skb_protocol(skb, true)) {
case cpu_to_be16(ETH_P_IP):
if (skb_network_header(skb) + sizeof(struct iphdr) <=
skb_tail_pointer(skb))
@@ -272,12 +273,16 @@ static inline int IP_ECN_decapsulate(const struct iphdr *oiph,
{
__u8 inner;
- if (skb->protocol == htons(ETH_P_IP))
+ switch (skb_protocol(skb, true)) {
+ case htons(ETH_P_IP):
inner = ip_hdr(skb)->tos;
- else if (skb->protocol == htons(ETH_P_IPV6))
+ break;
+ case htons(ETH_P_IPV6):
inner = ipv6_get_dsfield(ipv6_hdr(skb));
- else
+ break;
+ default:
return 0;
+ }
return INET_ECN_decapsulate(skb, oiph->tos, inner);
}
@@ -287,12 +292,16 @@ static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h,
{
__u8 inner;
- if (skb->protocol == htons(ETH_P_IP))
+ switch (skb_protocol(skb, true)) {
+ case htons(ETH_P_IP):
inner = ip_hdr(skb)->tos;
- else if (skb->protocol == htons(ETH_P_IPV6))
+ break;
+ case htons(ETH_P_IPV6):
inner = ipv6_get_dsfield(ipv6_hdr(skb));
- else
+ break;
+ default:
return 0;
+ }
return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner);
}
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 076e5d7db7d3..36025dea7612 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -290,6 +290,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p, __u32 fwmark);
void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);
+extern const struct header_ops ip_tunnel_header_ops;
+__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb);
+
struct ip_tunnel_encap_ops {
size_t (*encap_hlen)(struct ip_tunnel_encap *e);
int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
diff --git a/include/net/netns/bpf.h b/include/net/netns/bpf.h
index a8dce2a380c8..0ca6a1b87185 100644
--- a/include/net/netns/bpf.h
+++ b/include/net/netns/bpf.h
@@ -9,10 +9,13 @@
#include <linux/bpf-netns.h>
struct bpf_prog;
+struct bpf_prog_array;
struct netns_bpf {
- struct bpf_prog __rcu *progs[MAX_NETNS_BPF_ATTACH_TYPE];
- struct bpf_link *links[MAX_NETNS_BPF_ATTACH_TYPE];
+ /* Array of programs to run compiled from progs or links */
+ struct bpf_prog_array __rcu *run_array[MAX_NETNS_BPF_ATTACH_TYPE];
+ struct bpf_prog *progs[MAX_NETNS_BPF_ATTACH_TYPE];
+ struct list_head links[MAX_NETNS_BPF_ATTACH_TYPE];
};
#endif /* __NETNS_BPF_H__ */
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 9092e697059e..ac8c890a2657 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -136,17 +136,6 @@ static inline void qdisc_run(struct Qdisc *q)
}
}
-static inline __be16 tc_skb_protocol(const struct sk_buff *skb)
-{
- /* We need to take extra care in case the skb came via
- * vlan accelerated path. In that case, use skb->vlan_proto
- * as the original vlan header was already stripped.
- */
- if (skb_vlan_tag_present(skb))
- return skb->vlan_proto;
- return skb->protocol;
-}
-
/* Calculate maximal size of packet seen by hard_start_xmit
routine of this device.
*/
diff --git a/include/net/sock.h b/include/net/sock.h
index 3428619faae4..1183507df95b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -533,7 +533,8 @@ enum sk_pacing {
* be copied.
*/
#define SK_USER_DATA_NOCOPY 1UL
-#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY)
+#define SK_USER_DATA_BPF 2UL /* Managed by BPF */
+#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF)
/**
* sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index a4ff226505c9..6842990e2712 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -40,7 +40,7 @@ struct xsk_buff_pool {
u32 headroom;
u32 chunk_size;
u32 frame_len;
- bool cheap_dma;
+ bool dma_need_sync;
bool unaligned;
void *addrs;
struct device *dev;
@@ -80,7 +80,7 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb)
void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb);
static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb)
{
- if (xskb->pool->cheap_dma)
+ if (!xskb->pool->dma_need_sync)
return;
xp_dma_sync_for_cpu_slow(xskb);
@@ -91,7 +91,7 @@ void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma,
static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool,
dma_addr_t dma, size_t size)
{
- if (pool->cheap_dma)
+ if (!pool->dma_need_sync)
return;
xp_dma_sync_for_device_slow(pool, dma, size);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 974a71342aea..8bd33050b7bb 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3171,13 +3171,12 @@ union bpf_attr {
* int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
* Description
* Copy *size* bytes from *data* into a ring buffer *ringbuf*.
- * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
- * new data availability is sent.
- * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
- * new data availability is sent unconditionally.
+ * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * of new data availability is sent.
+ * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * of new data availability is sent unconditionally.
* Return
- * 0, on success;
- * < 0, on error.
+ * 0 on success, or a negative error in case of failure.
*
* void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags)
* Description
@@ -3189,20 +3188,20 @@ union bpf_attr {
* void bpf_ringbuf_submit(void *data, u64 flags)
* Description
* Submit reserved ring buffer sample, pointed to by *data*.
- * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
- * new data availability is sent.
- * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
- * new data availability is sent unconditionally.
+ * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * of new data availability is sent.
+ * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * of new data availability is sent unconditionally.
* Return
* Nothing. Always succeeds.
*
* void bpf_ringbuf_discard(void *data, u64 flags)
* Description
* Discard reserved ring buffer sample, pointed to by *data*.
- * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
- * new data availability is sent.
- * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
- * new data availability is sent unconditionally.
+ * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * of new data availability is sent.
+ * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * of new data availability is sent unconditionally.
* Return
* Nothing. Always succeeds.
*
@@ -3210,16 +3209,18 @@ union bpf_attr {
* Description
* Query various characteristics of provided ring buffer. What
* exactly is queries is determined by *flags*:
- * - BPF_RB_AVAIL_DATA - amount of data not yet consumed;
- * - BPF_RB_RING_SIZE - the size of ring buffer;
- * - BPF_RB_CONS_POS - consumer position (can wrap around);
- * - BPF_RB_PROD_POS - producer(s) position (can wrap around);
- * Data returned is just a momentary snapshots of actual values
+ *
+ * * **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed.
+ * * **BPF_RB_RING_SIZE**: The size of ring buffer.
+ * * **BPF_RB_CONS_POS**: Consumer position (can wrap around).
+ * * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around).
+ *
+ * Data returned is just a momentary snapshot of actual values
* and could be inaccurate, so this facility should be used to
* power heuristics and for reporting, not to make 100% correct
* calculation.
* Return
- * Requested value, or 0, if flags are not recognized.
+ * Requested value, or 0, if *flags* are not recognized.
*
* int bpf_csum_level(struct sk_buff *skb, u64 level)
* Description