summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/bpf-cgroup.h25
-rw-r--r--include/linux/bpf.h52
-rw-r--r--include/linux/bpf_local_storage.h163
-rw-r--r--include/linux/bpf_lsm.h29
-rw-r--r--include/linux/bpf_types.h3
-rw-r--r--include/linux/btf.h3
-rw-r--r--include/linux/btf_ids.h51
-rw-r--r--include/linux/filter.h8
-rw-r--r--include/linux/if_tun.h19
-rw-r--r--include/linux/netdevice.h10
-rw-r--r--include/linux/rcupdate_trace.h9
-rw-r--r--include/linux/skmsg.h17
-rw-r--r--include/linux/tcp.h20
-rw-r--r--include/net/bpf_sk_storage.h14
-rw-r--r--include/net/inet_connection_sock.h2
-rw-r--r--include/net/request_sock.h9
-rw-r--r--include/net/sock.h4
-rw-r--r--include/net/tcp.h59
-rw-r--r--include/net/xdp_sock.h30
-rw-r--r--include/net/xdp_sock_drv.h122
-rw-r--r--include/net/xsk_buff_pool.h53
-rw-r--r--include/uapi/linux/bpf.h398
22 files changed, 967 insertions, 133 deletions
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 64f367044e25..2f98d2fce62e 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -279,6 +279,31 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \
BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_RECVMSG, NULL)
+/* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a
+ * fullsock and its parent fullsock cannot be traced by
+ * sk_to_full_sk().
+ *
+ * e.g. sock_ops->sk is a request_sock and it is under syncookie mode.
+ * Its listener-sk is not attached to the rsk_listener.
+ * In this case, the caller holds the listener-sk (unlocked),
+ * set its sock_ops->sk to req_sk, and call this SOCK_OPS"_SK" with
+ * the listener-sk such that the cgroup-bpf-progs of the
+ * listener-sk will be run.
+ *
+ * Regardless of syncookie mode or not,
+ * calling bpf_setsockopt on listener-sk will not make sense anyway,
+ * so passing 'sock_ops->sk == req_sk' to the bpf prog is appropriate here.
+ */
+#define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled) \
+ __ret = __cgroup_bpf_run_filter_sock_ops(sk, \
+ sock_ops, \
+ BPF_CGROUP_SOCK_OPS); \
+ __ret; \
+})
+
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \
({ \
int __ret = 0; \
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 55f694b63164..c6d9f2c444f4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -34,6 +34,8 @@ struct btf_type;
struct exception_table_entry;
struct seq_operations;
struct bpf_iter_aux_info;
+struct bpf_local_storage;
+struct bpf_local_storage_map;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
@@ -104,6 +106,25 @@ struct bpf_map_ops {
__poll_t (*map_poll)(struct bpf_map *map, struct file *filp,
struct poll_table_struct *pts);
+ /* Functions called by bpf_local_storage maps */
+ int (*map_local_storage_charge)(struct bpf_local_storage_map *smap,
+ void *owner, u32 size);
+ void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap,
+ void *owner, u32 size);
+ struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner);
+
+ /* map_meta_equal must be implemented for maps that can be
+ * used as an inner map. It is a runtime check to ensure
+ * an inner map can be inserted to an outer map.
+ *
+ * Some properties of the inner map has been used during the
+ * verification time. When inserting an inner map at the runtime,
+ * map_meta_equal has to ensure the inserting map has the same
+ * properties that the verifier has used earlier.
+ */
+ bool (*map_meta_equal)(const struct bpf_map *meta0,
+ const struct bpf_map *meta1);
+
/* BTF name and id of struct allocated by map_alloc */
const char * const map_btf_name;
int *map_btf_id;
@@ -227,6 +248,9 @@ int map_check_no_btf(const struct bpf_map *map,
const struct btf_type *key_type,
const struct btf_type *value_type);
+bool bpf_map_meta_equal(const struct bpf_map *meta0,
+ const struct bpf_map *meta1);
+
extern const struct bpf_map_ops bpf_map_offload_ops;
/* function argument constraints */
@@ -309,6 +333,7 @@ struct bpf_func_proto {
* for this argument.
*/
int *ret_btf_id; /* return value btf_id */
+ bool (*allowed)(const struct bpf_prog *prog);
};
/* bpf_context is intentionally undefined structure. Pointer to bpf_context is
@@ -514,6 +539,8 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
/* these two functions are called from generated trampoline */
u64 notrace __bpf_prog_enter(void);
void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
+void notrace __bpf_prog_enter_sleepable(void);
+void notrace __bpf_prog_exit_sleepable(void);
struct bpf_ksym {
unsigned long start;
@@ -709,6 +736,7 @@ struct bpf_prog_aux {
bool offload_requested;
bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
bool func_proto_unreliable;
+ bool sleepable;
enum bpf_tramp_prog_type trampoline_prog_type;
struct bpf_trampoline *trampoline;
struct hlist_node tramp_hlist;
@@ -1218,12 +1246,18 @@ typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog,
union bpf_iter_link_info *linfo,
struct bpf_iter_aux_info *aux);
typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux);
+typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux,
+ struct seq_file *seq);
+typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux,
+ struct bpf_link_info *info);
#define BPF_ITER_CTX_ARG_MAX 2
struct bpf_iter_reg {
const char *target;
bpf_iter_attach_target_t attach_target;
bpf_iter_detach_target_t detach_target;
+ bpf_iter_show_fdinfo_t show_fdinfo;
+ bpf_iter_fill_link_info_t fill_link_info;
u32 ctx_arg_info_size;
struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
const struct bpf_iter_seq_info *seq_info;
@@ -1250,6 +1284,10 @@ int bpf_iter_new_fd(struct bpf_link *link);
bool bpf_link_is_iter(struct bpf_link *link);
struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop);
int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx);
+void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux,
+ struct seq_file *seq);
+int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux,
+ struct bpf_link_info *info);
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);
@@ -1340,6 +1378,8 @@ int btf_struct_access(struct bpf_verifier_log *log,
const struct btf_type *t, int off, int size,
enum bpf_access_type atype,
u32 *next_btf_id);
+bool btf_struct_ids_match(struct bpf_verifier_log *log,
+ int off, u32 id, u32 need_type_id);
int btf_resolve_helper_id(struct bpf_verifier_log *log,
const struct bpf_func_proto *fn, int);
@@ -1358,6 +1398,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
struct btf *btf, const struct btf_type *t);
struct bpf_prog *bpf_prog_by_id(u32 id);
+struct bpf_link *bpf_link_by_id(u32 id);
const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
#else /* !CONFIG_BPF_SYSCALL */
@@ -1637,6 +1678,7 @@ 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);
+int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
void sock_map_unhash(struct sock *sk);
void sock_map_close(struct sock *sk, long timeout);
#else
@@ -1658,6 +1700,12 @@ static inline int sock_map_prog_detach(const union bpf_attr *attr,
{
return -EOPNOTSUPP;
}
+
+static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value,
+ u64 flags)
+{
+ return -EOPNOTSUPP;
+}
#endif /* CONFIG_BPF_STREAM_PARSER */
#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
@@ -1736,6 +1784,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
+extern const struct bpf_func_proto bpf_copy_from_user_proto;
const struct bpf_func_proto *bpf_tracing_func_proto(
enum bpf_func_id func_id, const struct bpf_prog *prog);
@@ -1850,4 +1899,7 @@ enum bpf_text_poke_type {
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *addr1, void *addr2);
+struct btf_id_set;
+bool btf_id_set_contains(struct btf_id_set *set, u32 id);
+
#endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
new file mode 100644
index 000000000000..b2c9463f36a1
--- /dev/null
+++ b/include/linux/bpf_local_storage.h
@@ -0,0 +1,163 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2019 Facebook
+ * Copyright 2020 Google LLC.
+ */
+
+#ifndef _BPF_LOCAL_STORAGE_H
+#define _BPF_LOCAL_STORAGE_H
+
+#include <linux/bpf.h>
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <uapi/linux/btf.h>
+
+#define BPF_LOCAL_STORAGE_CACHE_SIZE 16
+
+struct bpf_local_storage_map_bucket {
+ struct hlist_head list;
+ raw_spinlock_t lock;
+};
+
+/* Thp map is not the primary owner of a bpf_local_storage_elem.
+ * Instead, the container object (eg. sk->sk_bpf_storage) is.
+ *
+ * The map (bpf_local_storage_map) is for two purposes
+ * 1. Define the size of the "local storage". It is
+ * the map's value_size.
+ *
+ * 2. Maintain a list to keep track of all elems such
+ * that they can be cleaned up during the map destruction.
+ *
+ * When a bpf local storage is being looked up for a
+ * particular object, the "bpf_map" pointer is actually used
+ * as the "key" to search in the list of elem in
+ * the respective bpf_local_storage owned by the object.
+ *
+ * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer
+ * as the searching key.
+ */
+struct bpf_local_storage_map {
+ struct bpf_map map;
+ /* Lookup elem does not require accessing the map.
+ *
+ * Updating/Deleting requires a bucket lock to
+ * link/unlink the elem from the map. Having
+ * multiple buckets to improve contention.
+ */
+ struct bpf_local_storage_map_bucket *buckets;
+ u32 bucket_log;
+ u16 elem_size;
+ u16 cache_idx;
+};
+
+struct bpf_local_storage_data {
+ /* smap is used as the searching key when looking up
+ * from the object's bpf_local_storage.
+ *
+ * Put it in the same cacheline as the data to minimize
+ * the number of cachelines access during the cache hit case.
+ */
+ struct bpf_local_storage_map __rcu *smap;
+ u8 data[] __aligned(8);
+};
+
+/* Linked to bpf_local_storage and bpf_local_storage_map */
+struct bpf_local_storage_elem {
+ struct hlist_node map_node; /* Linked to bpf_local_storage_map */
+ struct hlist_node snode; /* Linked to bpf_local_storage */
+ struct bpf_local_storage __rcu *local_storage;
+ struct rcu_head rcu;
+ /* 8 bytes hole */
+ /* The data is stored in aother cacheline to minimize
+ * the number of cachelines access during a cache hit.
+ */
+ struct bpf_local_storage_data sdata ____cacheline_aligned;
+};
+
+struct bpf_local_storage {
+ struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE];
+ struct hlist_head list; /* List of bpf_local_storage_elem */
+ void *owner; /* The object that owns the above "list" of
+ * bpf_local_storage_elem.
+ */
+ struct rcu_head rcu;
+ raw_spinlock_t lock; /* Protect adding/removing from the "list" */
+};
+
+/* U16_MAX is much more than enough for sk local storage
+ * considering a tcp_sock is ~2k.
+ */
+#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE \
+ min_t(u32, \
+ (KMALLOC_MAX_SIZE - MAX_BPF_STACK - \
+ sizeof(struct bpf_local_storage_elem)), \
+ (U16_MAX - sizeof(struct bpf_local_storage_elem)))
+
+#define SELEM(_SDATA) \
+ container_of((_SDATA), struct bpf_local_storage_elem, sdata)
+#define SDATA(_SELEM) (&(_SELEM)->sdata)
+
+#define BPF_LOCAL_STORAGE_CACHE_SIZE 16
+
+struct bpf_local_storage_cache {
+ spinlock_t idx_lock;
+ u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE];
+};
+
+#define DEFINE_BPF_STORAGE_CACHE(name) \
+static struct bpf_local_storage_cache name = { \
+ .idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock), \
+}
+
+u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache);
+void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache,
+ u16 idx);
+
+/* Helper functions for bpf_local_storage */
+int bpf_local_storage_map_alloc_check(union bpf_attr *attr);
+
+struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr);
+
+struct bpf_local_storage_data *
+bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
+ struct bpf_local_storage_map *smap,
+ bool cacheit_lockit);
+
+void bpf_local_storage_map_free(struct bpf_local_storage_map *smap);
+
+int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+ const struct btf *btf,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type);
+
+void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
+ struct bpf_local_storage_elem *selem);
+
+bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
+ struct bpf_local_storage_elem *selem,
+ bool uncharge_omem);
+
+void bpf_selem_unlink(struct bpf_local_storage_elem *selem);
+
+void bpf_selem_link_map(struct bpf_local_storage_map *smap,
+ struct bpf_local_storage_elem *selem);
+
+void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem);
+
+struct bpf_local_storage_elem *
+bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value,
+ bool charge_mem);
+
+int
+bpf_local_storage_alloc(void *owner,
+ struct bpf_local_storage_map *smap,
+ struct bpf_local_storage_elem *first_selem);
+
+struct bpf_local_storage_data *
+bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
+ void *value, u64 map_flags);
+
+#endif /* _BPF_LOCAL_STORAGE_H */
diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h
index af74712af585..aaacb6aafc87 100644
--- a/include/linux/bpf_lsm.h
+++ b/include/linux/bpf_lsm.h
@@ -17,9 +17,28 @@
#include <linux/lsm_hook_defs.h>
#undef LSM_HOOK
+struct bpf_storage_blob {
+ struct bpf_local_storage __rcu *storage;
+};
+
+extern struct lsm_blob_sizes bpf_lsm_blob_sizes;
+
int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
const struct bpf_prog *prog);
+static inline struct bpf_storage_blob *bpf_inode(
+ const struct inode *inode)
+{
+ if (unlikely(!inode->i_security))
+ return NULL;
+
+ return inode->i_security + bpf_lsm_blob_sizes.lbs_inode;
+}
+
+extern const struct bpf_func_proto bpf_inode_storage_get_proto;
+extern const struct bpf_func_proto bpf_inode_storage_delete_proto;
+void bpf_inode_storage_free(struct inode *inode);
+
#else /* !CONFIG_BPF_LSM */
static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
@@ -28,6 +47,16 @@ static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
return -EOPNOTSUPP;
}
+static inline struct bpf_storage_blob *bpf_inode(
+ const struct inode *inode)
+{
+ return NULL;
+}
+
+static inline void bpf_inode_storage_free(struct inode *inode)
+{
+}
+
#endif /* CONFIG_BPF_LSM */
#endif /* _LINUX_BPF_LSM_H */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index a52a5688418e..2e6f568377f1 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -107,6 +107,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)
#endif
+#ifdef CONFIG_BPF_LSM
+BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops)
+#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
#if defined(CONFIG_XDP_SOCKETS)
BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 8b81fbb4497c..a9af5e7a7ece 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -64,8 +64,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf,
u32 id, u32 *res_id);
const struct btf_type *
btf_resolve_size(const struct btf *btf, const struct btf_type *type,
- u32 *type_size, const struct btf_type **elem_type,
- u32 *total_nelems);
+ u32 *type_size);
#define for_each_member(i, struct_type, member) \
for (i = 0, member = btf_type_member(struct_type); \
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 4867d549e3c1..210b086188a3 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -3,6 +3,11 @@
#ifndef _LINUX_BTF_IDS_H
#define _LINUX_BTF_IDS_H
+struct btf_id_set {
+ u32 cnt;
+ u32 ids[];
+};
+
#ifdef CONFIG_DEBUG_INFO_BTF
#include <linux/compiler.h> /* for __PASTE */
@@ -62,7 +67,7 @@ asm( \
".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
"." #scope " " #name "; \n" \
#name ":; \n" \
-".popsection; \n"); \
+".popsection; \n");
#define BTF_ID_LIST(name) \
__BTF_ID_LIST(name, local) \
@@ -88,12 +93,56 @@ asm( \
".zero 4 \n" \
".popsection; \n");
+/*
+ * The BTF_SET_START/END macros pair defines sorted list of
+ * BTF IDs plus its members count, with following layout:
+ *
+ * BTF_SET_START(list)
+ * BTF_ID(type1, name1)
+ * BTF_ID(type2, name2)
+ * BTF_SET_END(list)
+ *
+ * __BTF_ID__set__list:
+ * .zero 4
+ * list:
+ * __BTF_ID__type1__name1__3:
+ * .zero 4
+ * __BTF_ID__type2__name2__4:
+ * .zero 4
+ *
+ */
+#define __BTF_SET_START(name, scope) \
+asm( \
+".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
+"." #scope " __BTF_ID__set__" #name "; \n" \
+"__BTF_ID__set__" #name ":; \n" \
+".zero 4 \n" \
+".popsection; \n");
+
+#define BTF_SET_START(name) \
+__BTF_ID_LIST(name, local) \
+__BTF_SET_START(name, local)
+
+#define BTF_SET_START_GLOBAL(name) \
+__BTF_ID_LIST(name, globl) \
+__BTF_SET_START(name, globl)
+
+#define BTF_SET_END(name) \
+asm( \
+".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
+".size __BTF_ID__set__" #name ", .-" #name " \n" \
+".popsection; \n"); \
+extern struct btf_id_set name;
+
#else
#define BTF_ID_LIST(name) static u32 name[5];
#define BTF_ID(prefix, name)
#define BTF_ID_UNUSED
#define BTF_ID_LIST_GLOBAL(name) u32 name[1];
+#define BTF_SET_START(name) static struct btf_id_set name = { 0 };
+#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
+#define BTF_SET_END(name)
#endif /* CONFIG_DEBUG_INFO_BTF */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0a355b005bf4..995625950cc1 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1236,13 +1236,17 @@ struct bpf_sock_addr_kern {
struct bpf_sock_ops_kern {
struct sock *sk;
- u32 op;
union {
u32 args[4];
u32 reply;
u32 replylong[4];
};
- u32 is_fullsock;
+ struct sk_buff *syn_skb;
+ struct sk_buff *skb;
+ void *skb_data_end;
+ u8 op;
+ u8 is_fullsock;
+ u8 remaining_opt_len;
u64 temp; /* temp and everything after is not
* initialized to 0 before calling
* the BPF program. New fields that
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 5bda8cf457b6..2a7660843444 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -27,9 +27,18 @@ struct tun_xdp_hdr {
#if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE)
struct socket *tun_get_socket(struct file *);
struct ptr_ring *tun_get_tx_ring(struct file *file);
-bool tun_is_xdp_frame(void *ptr);
-void *tun_xdp_to_ptr(void *ptr);
-void *tun_ptr_to_xdp(void *ptr);
+static inline bool tun_is_xdp_frame(void *ptr)
+{
+ return (unsigned long)ptr & TUN_XDP_FLAG;
+}
+static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp)
+{
+ return (void *)((unsigned long)xdp | TUN_XDP_FLAG);
+}
+static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr)
+{
+ return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG);
+}
void tun_ptr_free(void *ptr);
#else
#include <linux/err.h>
@@ -48,11 +57,11 @@ static inline bool tun_is_xdp_frame(void *ptr)
{
return false;
}
-static inline void *tun_xdp_to_ptr(void *ptr)
+static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp)
{
return NULL;
}
-static inline void *tun_ptr_to_xdp(void *ptr)
+static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr)
{
return NULL;
}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c0b512e6a02b..7f9fcfd15942 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -618,7 +618,7 @@ struct netdev_queue {
/* Subordinate device that the queue has been assigned to */
struct net_device *sb_dev;
#ifdef CONFIG_XDP_SOCKETS
- struct xdp_umem *umem;
+ struct xsk_buff_pool *pool;
#endif
/*
* write-mostly part
@@ -755,7 +755,7 @@ struct netdev_rx_queue {
struct net_device *dev;
struct xdp_rxq_info xdp_rxq;
#ifdef CONFIG_XDP_SOCKETS
- struct xdp_umem *umem;
+ struct xsk_buff_pool *pool;
#endif
} ____cacheline_aligned_in_smp;
@@ -883,7 +883,7 @@ enum bpf_netdev_command {
/* BPF program for offload callbacks, invoked at program load time. */
BPF_OFFLOAD_MAP_ALLOC,
BPF_OFFLOAD_MAP_FREE,
- XDP_SETUP_XSK_UMEM,
+ XDP_SETUP_XSK_POOL,
};
struct bpf_prog_offload_ops;
@@ -917,9 +917,9 @@ struct netdev_bpf {
struct {
struct bpf_offloaded_map *offmap;
};
- /* XDP_SETUP_XSK_UMEM */
+ /* XDP_SETUP_XSK_POOL */
struct {
- struct xdp_umem *umem;
+ struct xsk_buff_pool *pool;
u16 queue_id;
} xsk;
};
diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index d9015aac78c6..aaaac8ac927c 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -82,7 +82,14 @@ static inline void rcu_read_unlock_trace(void)
void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
void synchronize_rcu_tasks_trace(void);
void rcu_barrier_tasks_trace(void);
-
+#else
+/*
+ * The BPF JIT forms these addresses even when it doesn't call these
+ * functions, so provide definitions that result in runtime errors.
+ */
+static inline void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func) { BUG(); }
+static inline void rcu_read_lock_trace(void) { BUG(); }
+static inline void rcu_read_unlock_trace(void) { BUG(); }
#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
#endif /* __LINUX_RCUPDATE_TRACE_H */
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 1e9ed840b9fc..3119928fc103 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -340,23 +340,6 @@ static inline void sk_psock_update_proto(struct sock *sk,
struct sk_psock *psock,
struct proto *ops)
{
- /* Initialize saved callbacks and original proto only once, since this
- * function may be called multiple times for a psock, e.g. when
- * psock->progs.msg_parser is updated.
- *
- * Since we've not installed the new proto, psock is not yet in use and
- * we can initialize it without synchronization.
- */
- if (!psock->sk_proto) {
- struct proto *orig = READ_ONCE(sk->sk_prot);
-
- psock->saved_unhash = orig->unhash;
- psock->saved_close = orig->close;
- psock->saved_write_space = sk->sk_write_space;
-
- psock->sk_proto = orig;
- }
-
/* Pairs with lockless read in sk_clone_lock() */
WRITE_ONCE(sk->sk_prot, ops);
}
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 14b62d7df942..56ff2952edaf 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -92,6 +92,8 @@ struct tcp_options_received {
smc_ok : 1, /* SMC seen on SYN packet */
snd_wscale : 4, /* Window scaling received from sender */
rcv_wscale : 4; /* Window scaling to send to receiver */
+ u8 saw_unknown:1, /* Received unknown option */
+ unused:7;
u8 num_sacks; /* Number of SACK blocks */
u16 user_mss; /* mss requested by user in ioctl */
u16 mss_clamp; /* Maximal mss, negotiated at connection setup */
@@ -237,14 +239,13 @@ struct tcp_sock {
repair : 1,
frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */
u8 repair_queue;
- u8 syn_data:1, /* SYN includes data */
+ u8 save_syn:2, /* Save headers of SYN packet */
+ syn_data:1, /* SYN includes data */
syn_fastopen:1, /* SYN includes Fast Open option */
syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
syn_fastopen_ch:1, /* Active TFO re-enabling probe */
syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
- save_syn:1, /* Save headers of SYN packet */
- is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
- syn_smc:1; /* SYN includes SMC */
+ is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
u32 tlp_high_seq; /* snd_nxt at the time of TLP */
u32 tcp_tx_delay; /* delay (in usec) added to TX packets */
@@ -391,6 +392,9 @@ struct tcp_sock {
#if IS_ENABLED(CONFIG_MPTCP)
bool is_mptcp;
#endif
+#if IS_ENABLED(CONFIG_SMC)
+ bool syn_smc; /* SYN includes SMC */
+#endif
#ifdef CONFIG_TCP_MD5SIG
/* TCP AF-Specific parts; only used by MD5 Signature support so far */
@@ -406,7 +410,7 @@ struct tcp_sock {
* socket. Used to retransmit SYNACKs etc.
*/
struct request_sock __rcu *fastopen_rsk;
- u32 *saved_syn;
+ struct saved_syn *saved_syn;
};
enum tsq_enum {
@@ -484,6 +488,12 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp)
tp->saved_syn = NULL;
}
+static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn)
+{
+ return saved_syn->mac_hdrlen + saved_syn->network_hdrlen +
+ saved_syn->tcp_hdrlen;
+}
+
struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
const struct sk_buff *orig_skb);
diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index 5036c94c0503..119f4c9c3a9c 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -3,13 +3,27 @@
#ifndef _BPF_SK_STORAGE_H
#define _BPF_SK_STORAGE_H
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <net/sock.h>
+#include <uapi/linux/sock_diag.h>
+#include <uapi/linux/btf.h>
+#include <linux/bpf_local_storage.h>
+
struct sock;
void bpf_sk_storage_free(struct sock *sk);
extern const struct bpf_func_proto bpf_sk_storage_get_proto;
extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
+extern const struct bpf_func_proto sk_storage_get_btf_proto;
+extern const struct bpf_func_proto sk_storage_delete_btf_proto;
+struct bpf_local_storage_elem;
struct bpf_sk_storage_diag;
struct sk_buff;
struct nlattr;
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index aa8893c68c50..c738abeb3265 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -86,6 +86,8 @@ struct inet_connection_sock {
struct timer_list icsk_retransmit_timer;
struct timer_list icsk_delack_timer;
__u32 icsk_rto;
+ __u32 icsk_rto_min;
+ __u32 icsk_delack_max;
__u32 icsk_pmtu_cookie;
const struct tcp_congestion_ops *icsk_ca_ops;
const struct inet_connection_sock_af_ops *icsk_af_ops;
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index b2eb8b4ba697..29e41ff3ec93 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -41,6 +41,13 @@ struct request_sock_ops {
int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req);
+struct saved_syn {
+ u32 mac_hdrlen;
+ u32 network_hdrlen;
+ u32 tcp_hdrlen;
+ u8 data[];
+};
+
/* struct request_sock - mini sock to represent a connection request
*/
struct request_sock {
@@ -60,7 +67,7 @@ struct request_sock {
struct timer_list rsk_timer;
const struct request_sock_ops *rsk_ops;
struct sock *sk;
- u32 *saved_syn;
+ struct saved_syn *saved_syn;
u32 secid;
u32 peer_secid;
};
diff --git a/include/net/sock.h b/include/net/sock.h
index b943731fa879..7dd3051551fb 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -246,7 +246,7 @@ struct sock_common {
/* public: */
};
-struct bpf_sk_storage;
+struct bpf_local_storage;
/**
* struct sock - network layer representation of sockets
@@ -517,7 +517,7 @@ struct sock {
void (*sk_destruct)(struct sock *sk);
struct sock_reuseport __rcu *sk_reuseport_cb;
#ifdef CONFIG_BPF_SYSCALL
- struct bpf_sk_storage __rcu *sk_bpf_storage;
+ struct bpf_local_storage __rcu *sk_bpf_storage;
#endif
struct rcu_head sk_rcu;
};
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0d11db6436c8..e85d564446c6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -394,7 +394,7 @@ void tcp_metrics_init(void);
bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
void tcp_close(struct sock *sk, long timeout);
void tcp_init_sock(struct sock *sk);
-void tcp_init_transfer(struct sock *sk, int bpf_op);
+void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb);
__poll_t tcp_poll(struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int tcp_getsockopt(struct sock *sk, int level, int optname,
@@ -455,7 +455,8 @@ enum tcp_synack_type {
struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
- enum tcp_synack_type synack_type);
+ enum tcp_synack_type synack_type,
+ struct sk_buff *syn_skb);
int tcp_disconnect(struct sock *sk, int flags);
void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
@@ -699,7 +700,7 @@ static inline void tcp_fast_path_check(struct sock *sk)
static inline u32 tcp_rto_min(struct sock *sk)
{
const struct dst_entry *dst = __sk_dst_get(sk);
- u32 rto_min = TCP_RTO_MIN;
+ u32 rto_min = inet_csk(sk)->icsk_rto_min;
if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
@@ -2025,7 +2026,8 @@ struct tcp_request_sock_ops {
int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl, struct request_sock *req,
struct tcp_fastopen_cookie *foc,
- enum tcp_synack_type synack_type);
+ enum tcp_synack_type synack_type,
+ struct sk_buff *syn_skb);
};
extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops;
@@ -2223,6 +2225,55 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
struct msghdr *msg, int len, int flags);
#endif /* CONFIG_NET_SOCK_MSG */
+#ifdef CONFIG_CGROUP_BPF
+/* Copy the listen sk's HDR_OPT_CB flags to its child.
+ *
+ * During 3-Way-HandShake, the synack is usually sent from
+ * the listen sk with the HDR_OPT_CB flags set so that
+ * bpf-prog will be called to write the BPF hdr option.
+ *
+ * In fastopen, the child sk is used to send synack instead
+ * of the listen sk. Thus, inheriting the HDR_OPT_CB flags
+ * from the listen sk gives the bpf-prog a chance to write
+ * BPF hdr option in the synack pkt during fastopen.
+ *
+ * Both fastopen and non-fastopen child will inherit the
+ * HDR_OPT_CB flags to keep the bpf-prog having a consistent
+ * behavior when deciding to clear this cb flags (or not)
+ * during the PASSIVE_ESTABLISHED_CB.
+ *
+ * In the future, other cb flags could be inherited here also.
+ */
+static inline void bpf_skops_init_child(const struct sock *sk,
+ struct sock *child)
+{
+ tcp_sk(child)->bpf_sock_ops_cb_flags =
+ tcp_sk(sk)->bpf_sock_ops_cb_flags &
+ (BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG |
+ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG |
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG);
+}
+
+static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
+ struct sk_buff *skb,
+ unsigned int end_offset)
+{
+ skops->skb = skb;
+ skops->skb_data_end = skb->data + end_offset;
+}
+#else
+static inline void bpf_skops_init_child(const struct sock *sk,
+ struct sock *child)
+{
+}
+
+static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
+ struct sk_buff *skb,
+ unsigned int end_offset)
+{
+}
+#endif
+
/* Call BPF_SOCK_OPS program that returns an int. If the return value
* is < 0, then the BPF op failed (for example if the loaded BPF
* program does not support the chosen operation or there is no BPF
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index c9d87cc40c11..1a9559c0cbdd 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -18,25 +18,19 @@ struct xsk_queue;
struct xdp_buff;
struct xdp_umem {
- struct xsk_queue *fq;
- struct xsk_queue *cq;
- struct xsk_buff_pool *pool;
+ void *addrs;
u64 size;
u32 headroom;
u32 chunk_size;
+ u32 chunks;
+ u32 npgs;
struct user_struct *user;
refcount_t users;
- struct work_struct work;
- struct page **pgs;
- u32 npgs;
- u16 queue_id;
- u8 need_wakeup;
u8 flags;
- int id;
- struct net_device *dev;
bool zc;
- spinlock_t xsk_tx_list_lock;
- struct list_head xsk_tx_list;
+ struct page **pgs;
+ int id;
+ struct list_head xsk_dma_list;
};
struct xsk_map {
@@ -48,10 +42,11 @@ struct xsk_map {
struct xdp_sock {
/* struct sock must be the first member of struct xdp_sock */
struct sock sk;
- struct xsk_queue *rx;
+ struct xsk_queue *rx ____cacheline_aligned_in_smp;
struct net_device *dev;
struct xdp_umem *umem;
struct list_head flush_node;
+ struct xsk_buff_pool *pool;
u16 queue_id;
bool zc;
enum {
@@ -59,10 +54,9 @@ struct xdp_sock {
XSK_BOUND,
XSK_UNBOUND,
} state;
- /* Protects multiple processes in the control path */
- struct mutex mutex;
+
struct xsk_queue *tx ____cacheline_aligned_in_smp;
- struct list_head list;
+ struct list_head tx_list;
/* Mutual exclusion of NAPI TX thread and sendmsg error paths
* in the SKB destructor callback.
*/
@@ -77,6 +71,10 @@ struct xdp_sock {
struct list_head map_list;
/* Protects map_list */
spinlock_t map_list_lock;
+ /* Protects multiple processes in the control path */
+ struct mutex mutex;
+ struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */
+ struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
};
#ifdef CONFIG_XDP_SOCKETS
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index ccf848f7efa4..5b1ee8a9976d 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -11,47 +11,50 @@
#ifdef CONFIG_XDP_SOCKETS
-void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
-bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc);
-void xsk_umem_consume_tx_done(struct xdp_umem *umem);
-struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id);
-void xsk_set_rx_need_wakeup(struct xdp_umem *umem);
-void xsk_set_tx_need_wakeup(struct xdp_umem *umem);
-void xsk_clear_rx_need_wakeup(struct xdp_umem *umem);
-void xsk_clear_tx_need_wakeup(struct xdp_umem *umem);
-bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem);
+void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
+bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
+void xsk_tx_release(struct xsk_buff_pool *pool);
+struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
+ u16 queue_id);
+void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool);
+bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool);
-static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
{
- return XDP_PACKET_HEADROOM + umem->headroom;
+ return XDP_PACKET_HEADROOM + pool->headroom;
}
-static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
{
- return umem->chunk_size;
+ return pool->chunk_size;
}
-static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
{
- return xsk_umem_get_chunk_size(umem) - xsk_umem_get_headroom(umem);
+ return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool);
}
-static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem,
+static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
struct xdp_rxq_info *rxq)
{
- xp_set_rxq_info(umem->pool, rxq);
+ xp_set_rxq_info(pool, rxq);
}
-static inline void xsk_buff_dma_unmap(struct xdp_umem *umem,
+static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
unsigned long attrs)
{
- xp_dma_unmap(umem->pool, attrs);
+ xp_dma_unmap(pool, attrs);
}
-static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev,
- unsigned long attrs)
+static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
+ struct device *dev, unsigned long attrs)
{
- return xp_dma_map(umem->pool, dev, attrs, umem->pgs, umem->npgs);
+ struct xdp_umem *umem = pool->umem;
+
+ return xp_dma_map(pool, dev, attrs, umem->pgs, umem->npgs);
}
static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp)
@@ -68,14 +71,14 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
return xp_get_frame_dma(xskb);
}
-static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem)
+static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
{
- return xp_alloc(umem->pool);
+ return xp_alloc(pool);
}
-static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count)
+static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
{
- return xp_can_alloc(umem->pool, count);
+ return xp_can_alloc(pool, count);
}
static inline void xsk_buff_free(struct xdp_buff *xdp)
@@ -85,100 +88,104 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
xp_free(xskb);
}
-static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr)
+static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
+ u64 addr)
{
- return xp_raw_get_dma(umem->pool, addr);
+ return xp_raw_get_dma(pool, addr);
}
-static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr)
+static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
{
- return xp_raw_get_data(umem->pool, addr);
+ return xp_raw_get_data(pool, addr);
}
-static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
+static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
{
struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+ if (!pool->dma_need_sync)
+ return;
+
xp_dma_sync_for_cpu(xskb);
}
-static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem,
+static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
dma_addr_t dma,
size_t size)
{
- xp_dma_sync_for_device(umem->pool, dma, size);
+ xp_dma_sync_for_device(pool, dma, size);
}
#else
-static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
+static inline void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries)
{
}
-static inline bool xsk_umem_consume_tx(struct xdp_umem *umem,
- struct xdp_desc *desc)
+static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool,
+ struct xdp_desc *desc)
{
return false;
}
-static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem)
+static inline void xsk_tx_release(struct xsk_buff_pool *pool)
{
}
-static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
- u16 queue_id)
+static inline struct xsk_buff_pool *
+xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id)
{
return NULL;
}
-static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
{
}
-static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
{
}
-static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool)
{
}
-static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
{
}
-static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
+static inline bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
{
return false;
}
-static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
{
return 0;
}
-static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
{
return 0;
}
-static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
{
return 0;
}
-static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem,
+static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
struct xdp_rxq_info *rxq)
{
}
-static inline void xsk_buff_dma_unmap(struct xdp_umem *umem,
+static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
unsigned long attrs)
{
}
-static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev,
- unsigned long attrs)
+static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
+ struct device *dev, unsigned long attrs)
{
return 0;
}
@@ -193,12 +200,12 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
return 0;
}
-static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem)
+static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
{
return NULL;
}
-static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count)
+static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
{
return false;
}
@@ -207,21 +214,22 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
{
}
-static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr)
+static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
+ u64 addr)
{
return 0;
}
-static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr)
+static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
{
return NULL;
}
-static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
+static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
{
}
-static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem,
+static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
dma_addr_t dma,
size_t size)
{
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 6842990e2712..0140d086dc84 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -13,6 +13,8 @@ struct xsk_buff_pool;
struct xdp_rxq_info;
struct xsk_queue;
struct xdp_desc;
+struct xdp_umem;
+struct xdp_sock;
struct device;
struct page;
@@ -26,34 +28,68 @@ struct xdp_buff_xsk {
struct list_head free_list_node;
};
+struct xsk_dma_map {
+ dma_addr_t *dma_pages;
+ struct device *dev;
+ struct net_device *netdev;
+ refcount_t users;
+ struct list_head list; /* Protected by the RTNL_LOCK */
+ u32 dma_pages_cnt;
+ bool dma_need_sync;
+};
+
struct xsk_buff_pool {
- struct xsk_queue *fq;
+ /* Members only used in the control path first. */
+ struct device *dev;
+ struct net_device *netdev;
+ struct list_head xsk_tx_list;
+ /* Protects modifications to the xsk_tx_list */
+ spinlock_t xsk_tx_list_lock;
+ refcount_t users;
+ struct xdp_umem *umem;
+ struct work_struct work;
struct list_head free_list;
+ u32 heads_cnt;
+ u16 queue_id;
+
+ /* Data path members as close to free_heads at the end as possible. */
+ struct xsk_queue *fq ____cacheline_aligned_in_smp;
+ struct xsk_queue *cq;
+ /* For performance reasons, each buff pool has its own array of dma_pages
+ * even when they are identical.
+ */
dma_addr_t *dma_pages;
struct xdp_buff_xsk *heads;
u64 chunk_mask;
u64 addrs_cnt;
u32 free_list_cnt;
u32 dma_pages_cnt;
- u32 heads_cnt;
u32 free_heads_cnt;
u32 headroom;
u32 chunk_size;
u32 frame_len;
+ u8 cached_need_wakeup;
+ bool uses_need_wakeup;
bool dma_need_sync;
bool unaligned;
void *addrs;
- struct device *dev;
struct xdp_buff_xsk *free_heads[];
};
/* AF_XDP core. */
-struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
- u32 chunk_size, u32 headroom, u64 size,
- bool unaligned);
-void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq);
+struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
+ struct xdp_umem *umem);
+int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
+ u16 queue_id, u16 flags);
+int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
+ struct net_device *dev, u16 queue_id);
void xp_destroy(struct xsk_buff_pool *pool);
void xp_release(struct xdp_buff_xsk *xskb);
+void xp_get_pool(struct xsk_buff_pool *pool);
+void xp_put_pool(struct xsk_buff_pool *pool);
+void xp_clear_dev(struct xsk_buff_pool *pool);
+void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
+void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
/* AF_XDP, and XDP core. */
void xp_free(struct xdp_buff_xsk *xskb);
@@ -80,9 +116,6 @@ 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->dma_need_sync)
- return;
-
xp_dma_sync_for_cpu_slow(xskb);
}
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b6238b2209b7..8dda13880957 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -155,6 +155,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_DEVMAP_HASH,
BPF_MAP_TYPE_STRUCT_OPS,
BPF_MAP_TYPE_RINGBUF,
+ BPF_MAP_TYPE_INODE_STORAGE,
};
/* Note that tracing related programs such as
@@ -345,6 +346,14 @@ enum bpf_link_type {
/* The verifier internal test flag. Behavior is undefined */
#define BPF_F_TEST_STATE_FREQ (1U << 3)
+/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will
+ * restrict map and helper usage for such programs. Sleepable BPF programs can
+ * only be attached to hooks where kernel execution context allows sleeping.
+ * Such programs are allowed to use helpers that may sleep like
+ * bpf_copy_from_user().
+ */
+#define BPF_F_SLEEPABLE (1U << 4)
+
/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
* two extensions:
*
@@ -2807,7 +2816,7 @@ union bpf_attr {
*
* **-ERANGE** if resulting value was out of range.
*
- * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags)
+ * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags)
* Description
* Get a bpf-local-storage from a *sk*.
*
@@ -2823,6 +2832,9 @@ union bpf_attr {
* "type". The bpf-local-storage "type" (i.e. the *map*) is
* searched against all bpf-local-storages residing at *sk*.
*
+ * *sk* is a kernel **struct sock** pointer for LSM program.
+ * *sk* is a **struct bpf_sock** pointer for other program types.
+ *
* An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be
* used such that a new bpf-local-storage will be
* created if one does not exist. *value* can be used
@@ -2835,7 +2847,7 @@ union bpf_attr {
* **NULL** if not found or there was an error in adding
* a new bpf-local-storage.
*
- * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk)
+ * long bpf_sk_storage_delete(struct bpf_map *map, void *sk)
* Description
* Delete a bpf-local-storage from a *sk*.
* Return
@@ -3395,6 +3407,175 @@ union bpf_attr {
* A non-negative value equal to or less than *size* on success,
* or a negative error in case of failure.
*
+ * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
+ * Description
+ * Load header option. Support reading a particular TCP header
+ * option for bpf program (BPF_PROG_TYPE_SOCK_OPS).
+ *
+ * If *flags* is 0, it will search the option from the
+ * sock_ops->skb_data. The comment in "struct bpf_sock_ops"
+ * has details on what skb_data contains under different
+ * sock_ops->op.
+ *
+ * The first byte of the *searchby_res* specifies the
+ * kind that it wants to search.
+ *
+ * If the searching kind is an experimental kind
+ * (i.e. 253 or 254 according to RFC6994). It also
+ * needs to specify the "magic" which is either
+ * 2 bytes or 4 bytes. It then also needs to
+ * specify the size of the magic by using
+ * the 2nd byte which is "kind-length" of a TCP
+ * header option and the "kind-length" also
+ * includes the first 2 bytes "kind" and "kind-length"
+ * itself as a normal TCP header option also does.
+ *
+ * For example, to search experimental kind 254 with
+ * 2 byte magic 0xeB9F, the searchby_res should be
+ * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ].
+ *
+ * To search for the standard window scale option (3),
+ * the searchby_res should be [ 3, 0, 0, .... 0 ].
+ * Note, kind-length must be 0 for regular option.
+ *
+ * Searching for No-Op (0) and End-of-Option-List (1) are
+ * not supported.
+ *
+ * *len* must be at least 2 bytes which is the minimal size
+ * of a header option.
+ *
+ * Supported flags:
+ * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the
+ * saved_syn packet or the just-received syn packet.
+ *
+ * Return
+ * >0 when found, the header option is copied to *searchby_res*.
+ * The return value is the total length copied.
+ *
+ * **-EINVAL** If param is invalid
+ *
+ * **-ENOMSG** The option is not found
+ *
+ * **-ENOENT** No syn packet available when
+ * **BPF_LOAD_HDR_OPT_TCP_SYN** is used
+ *
+ * **-ENOSPC** Not enough space. Only *len* number of
+ * bytes are copied.
+ *
+ * **-EFAULT** Cannot parse the header options in the packet
+ *
+ * **-EPERM** This helper cannot be used under the
+ * current sock_ops->op.
+ *
+ * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags)
+ * Description
+ * Store header option. The data will be copied
+ * from buffer *from* with length *len* to the TCP header.
+ *
+ * The buffer *from* should have the whole option that
+ * includes the kind, kind-length, and the actual
+ * option data. The *len* must be at least kind-length
+ * long. The kind-length does not have to be 4 byte
+ * aligned. The kernel will take care of the padding
+ * and setting the 4 bytes aligned value to th->doff.
+ *
+ * This helper will check for duplicated option
+ * by searching the same option in the outgoing skb.
+ *
+ * This helper can only be called during
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *
+ * Return
+ * 0 on success, or negative error in case of failure:
+ *
+ * **-EINVAL** If param is invalid
+ *
+ * **-ENOSPC** Not enough space in the header.
+ * Nothing has been written
+ *
+ * **-EEXIST** The option has already existed
+ *
+ * **-EFAULT** Cannot parse the existing header options
+ *
+ * **-EPERM** This helper cannot be used under the
+ * current sock_ops->op.
+ *
+ * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags)
+ * Description
+ * Reserve *len* bytes for the bpf header option. The
+ * space will be used by bpf_store_hdr_opt() later in
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *
+ * If bpf_reserve_hdr_opt() is called multiple times,
+ * the total number of bytes will be reserved.
+ *
+ * This helper can only be called during
+ * BPF_SOCK_OPS_HDR_OPT_LEN_CB.
+ *
+ * Return
+ * 0 on success, or negative error in case of failure:
+ *
+ * **-EINVAL** if param is invalid
+ *
+ * **-ENOSPC** Not enough space in the header.
+ *
+ * **-EPERM** This helper cannot be used under the
+ * current sock_ops->op.
+ *
+ * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from an *inode*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *inode* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this
+ * helper enforces the key must be an inode and the map must also
+ * be a **BPF_MAP_TYPE_INODE_STORAGE**.
+ *
+ * Underneath, the value is stored locally at *inode* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf_local_storage residing at *inode*.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * int bpf_inode_storage_delete(struct bpf_map *map, void *inode)
+ * Description
+ * Delete a bpf_local_storage from an *inode*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * long bpf_d_path(struct path *path, char *buf, u32 sz)
+ * Description
+ * Return full path for given 'struct path' object, which
+ * needs to be the kernel BTF 'path' object. The path is
+ * returned in the provided buffer 'buf' of size 'sz' and
+ * is zero terminated.
+ *
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
+ * Description
+ * Read *size* bytes from user space address *user_ptr* and store
+ * the data in *dst*. This is a wrapper of copy_from_user().
+ * Return
+ * 0 on success, or a negative error in case of failure.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -3539,6 +3720,13 @@ union bpf_attr {
FN(skc_to_tcp_request_sock), \
FN(skc_to_udp6_sock), \
FN(get_task_stack), \
+ FN(load_hdr_opt), \
+ FN(store_hdr_opt), \
+ FN(reserve_hdr_opt), \
+ FN(inode_storage_get), \
+ FN(inode_storage_delete), \
+ FN(d_path), \
+ FN(copy_from_user), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -3648,9 +3836,13 @@ enum {
BPF_F_SYSCTL_BASE_NAME = (1ULL << 0),
};
-/* BPF_FUNC_sk_storage_get flags */
+/* BPF_FUNC_<kernel_obj>_storage_get flags */
enum {
- BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0),
+ BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0),
+ /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility
+ * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead.
+ */
+ BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE,
};
/* BPF_FUNC_read_branch_records flags. */
@@ -4071,6 +4263,15 @@ struct bpf_link_info {
__u64 cgroup_id;
__u32 attach_type;
} cgroup;
+ struct {
+ __aligned_u64 target_name; /* in/out: target_name buffer ptr */
+ __u32 target_name_len; /* in/out: target_name buffer len */
+ union {
+ struct {
+ __u32 map_id;
+ } map;
+ };
+ } iter;
struct {
__u32 netns_ino;
__u32 attach_type;
@@ -4158,6 +4359,36 @@ struct bpf_sock_ops {
__u64 bytes_received;
__u64 bytes_acked;
__bpf_md_ptr(struct bpf_sock *, sk);
+ /* [skb_data, skb_data_end) covers the whole TCP header.
+ *
+ * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received
+ * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the
+ * header has not been written.
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have
+ * been written so far.
+ * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes
+ * the 3WHS.
+ * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes
+ * the 3WHS.
+ *
+ * bpf_load_hdr_opt() can also be used to read a particular option.
+ */
+ __bpf_md_ptr(void *, skb_data);
+ __bpf_md_ptr(void *, skb_data_end);
+ __u32 skb_len; /* The total length of a packet.
+ * It includes the header, options,
+ * and payload.
+ */
+ __u32 skb_tcp_flags; /* tcp_flags of the header. It provides
+ * an easy way to check for tcp_flags
+ * without parsing skb_data.
+ *
+ * In particular, the skb_tcp_flags
+ * will still be available in
+ * BPF_SOCK_OPS_HDR_OPT_LEN even though
+ * the outgoing header has not
+ * been written yet.
+ */
};
/* Definitions for bpf_sock_ops_cb_flags */
@@ -4166,8 +4397,51 @@ enum {
BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1),
BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2),
BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3),
+ /* Call bpf for all received TCP headers. The bpf prog will be
+ * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ * for the header option related helpers that will be useful
+ * to the bpf programs.
+ *
+ * It could be used at the client/active side (i.e. connect() side)
+ * when the server told it that the server was in syncookie
+ * mode and required the active side to resend the bpf-written
+ * options. The active side can keep writing the bpf-options until
+ * it received a valid packet from the server side to confirm
+ * the earlier packet (and options) has been received. The later
+ * example patch is using it like this at the active side when the
+ * server is in syncookie mode.
+ *
+ * The bpf prog will usually turn this off in the common cases.
+ */
+ BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4),
+ /* Call bpf when kernel has received a header option that
+ * the kernel cannot handle. The bpf prog will be called under
+ * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB.
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ * for the header option related helpers that will be useful
+ * to the bpf programs.
+ */
+ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5),
+ /* Call bpf when the kernel is writing header options for the
+ * outgoing packet. The bpf prog will first be called
+ * to reserve space in a skb under
+ * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then
+ * the bpf prog will be called to write the header option(s)
+ * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB
+ * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option
+ * related helpers that will be useful to the bpf programs.
+ *
+ * The kernel gets its chance to reserve space and write
+ * options first before the BPF program does.
+ */
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6),
/* Mask of all currently supported cb flags */
- BPF_SOCK_OPS_ALL_CB_FLAGS = 0xF,
+ BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F,
};
/* List of known BPF sock_ops operators.
@@ -4223,6 +4497,63 @@ enum {
*/
BPF_SOCK_OPS_RTT_CB, /* Called on every RTT.
*/
+ BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option.
+ * It will be called to handle
+ * the packets received at
+ * an already established
+ * connection.
+ *
+ * sock_ops->skb_data:
+ * Referring to the received skb.
+ * It covers the TCP header only.
+ *
+ * bpf_load_hdr_opt() can also
+ * be used to search for a
+ * particular option.
+ */
+ BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the
+ * header option later in
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ * Arg1: bool want_cookie. (in
+ * writing SYNACK only)
+ *
+ * sock_ops->skb_data:
+ * Not available because no header has
+ * been written yet.
+ *
+ * sock_ops->skb_tcp_flags:
+ * The tcp_flags of the
+ * outgoing skb. (e.g. SYN, ACK, FIN).
+ *
+ * bpf_reserve_hdr_opt() should
+ * be used to reserve space.
+ */
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options
+ * Arg1: bool want_cookie. (in
+ * writing SYNACK only)
+ *
+ * sock_ops->skb_data:
+ * Referring to the outgoing skb.
+ * It covers the TCP header
+ * that has already been written
+ * by the kernel and the
+ * earlier bpf-progs.
+ *
+ * sock_ops->skb_tcp_flags:
+ * The tcp_flags of the outgoing
+ * skb. (e.g. SYN, ACK, FIN).
+ *
+ * bpf_store_hdr_opt() should
+ * be used to write the
+ * option.
+ *
+ * bpf_load_hdr_opt() can also
+ * be used to search for a
+ * particular option that
+ * has already been written
+ * by the kernel or the
+ * earlier bpf-progs.
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
@@ -4250,6 +4581,63 @@ enum {
enum {
TCP_BPF_IW = 1001, /* Set TCP initial congestion window */
TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */
+ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */
+ TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */
+ /* Copy the SYN pkt to optval
+ *
+ * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the
+ * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit
+ * to only getting from the saved_syn. It can either get the
+ * syn packet from:
+ *
+ * 1. the just-received SYN packet (only available when writing the
+ * SYNACK). It will be useful when it is not necessary to
+ * save the SYN packet for latter use. It is also the only way
+ * to get the SYN during syncookie mode because the syn
+ * packet cannot be saved during syncookie.
+ *
+ * OR
+ *
+ * 2. the earlier saved syn which was done by
+ * bpf_setsockopt(TCP_SAVE_SYN).
+ *
+ * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the
+ * SYN packet is obtained.
+ *
+ * If the bpf-prog does not need the IP[46] header, the
+ * bpf-prog can avoid parsing the IP header by using
+ * TCP_BPF_SYN. Otherwise, the bpf-prog can get both
+ * IP[46] and TCP header by using TCP_BPF_SYN_IP.
+ *
+ * >0: Total number of bytes copied
+ * -ENOSPC: Not enough space in optval. Only optlen number of
+ * bytes is copied.
+ * -ENOENT: The SYN skb is not available now and the earlier SYN pkt
+ * is not saved by setsockopt(TCP_SAVE_SYN).
+ */
+ TCP_BPF_SYN = 1005, /* Copy the TCP header */
+ TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */
+ TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */
+};
+
+enum {
+ BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0),
+};
+
+/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ */
+enum {
+ BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the
+ * total option spaces
+ * required for an established
+ * sk in order to calculate the
+ * MSS. No skb is actually
+ * sent.
+ */
+ BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode
+ * when sending a SYN.
+ */
};
struct bpf_perf_event_value {
generated by cgit v1.2.3 (git 2.46.0) at 2026-01-27 03:52:43 +0000