diff options
author | Jakub Kicinski <kuba@kernel.org> | 2023-04-13 16:11:22 -0700 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2023-04-13 16:43:38 -0700 |
commit | c2865b1122595e69e7df52d01f7f02338b8babca (patch) | |
tree | e1bfb26b2d31ce0bf590cabafc8e3a0ff1bece4c /net | |
parent | 800e68c44ffe71f9715f745b38fd1af6910b3773 (diff) | |
parent | 8c5c2a4898e3d6bad86e29d471e023c8a19ba799 (diff) |
Daniel Borkmann says:
====================
pull-request: bpf-next 2023-04-13
We've added 260 non-merge commits during the last 36 day(s) which contain
a total of 356 files changed, 21786 insertions(+), 11275 deletions(-).
The main changes are:
1) Rework BPF verifier log behavior and implement it as a rotating log
by default with the option to retain old-style fixed log behavior,
from Andrii Nakryiko.
2) Adds support for using {FOU,GUE} encap with an ipip device operating
in collect_md mode and add a set of BPF kfuncs for controlling encap
params, from Christian Ehrig.
3) Allow BPF programs to detect at load time whether a particular kfunc
exists or not, and also add support for this in light skeleton,
from Alexei Starovoitov.
4) Optimize hashmap lookups when key size is multiple of 4,
from Anton Protopopov.
5) Enable RCU semantics for task BPF kptrs and allow referenced kptr
tasks to be stored in BPF maps, from David Vernet.
6) Add support for stashing local BPF kptr into a map value via
bpf_kptr_xchg(). This is useful e.g. for rbtree node creation
for new cgroups, from Dave Marchevsky.
7) Fix BTF handling of is_int_ptr to skip modifiers to work around
tracing issues where a program cannot be attached, from Feng Zhou.
8) Migrate a big portion of test_verifier unit tests over to
test_progs -a verifier_* via inline asm to ease {read,debug}ability,
from Eduard Zingerman.
9) Several updates to the instruction-set.rst documentation
which is subject to future IETF standardization
(https://lwn.net/Articles/926882/), from Dave Thaler.
10) Fix BPF verifier in the __reg_bound_offset's 64->32 tnum sub-register
known bits information propagation, from Daniel Borkmann.
11) Add skb bitfield compaction work related to BPF with the overall goal
to make more of the sk_buff bits optional, from Jakub Kicinski.
12) BPF selftest cleanups for build id extraction which stand on its own
from the upcoming integration work of build id into struct file object,
from Jiri Olsa.
13) Add fixes and optimizations for xsk descriptor validation and several
selftest improvements for xsk sockets, from Kal Conley.
14) Add BPF links for struct_ops and enable switching implementations
of BPF TCP cong-ctls under a given name by replacing backing
struct_ops map, from Kui-Feng Lee.
15) Remove a misleading BPF verifier env->bypass_spec_v1 check on variable
offset stack read as earlier Spectre checks cover this,
from Luis Gerhorst.
16) Fix issues in copy_from_user_nofault() for BPF and other tracers
to resemble copy_from_user_nmi() from safety PoV, from Florian Lehner
and Alexei Starovoitov.
17) Add --json-summary option to test_progs in order for CI tooling to
ease parsing of test results, from Manu Bretelle.
18) Batch of improvements and refactoring to prep for upcoming
bpf_local_storage conversion to bpf_mem_cache_{alloc,free} allocator,
from Martin KaFai Lau.
19) Improve bpftool's visual program dump which produces the control
flow graph in a DOT format by adding C source inline annotations,
from Quentin Monnet.
20) Fix attaching fentry/fexit/fmod_ret/lsm to modules by extracting
the module name from BTF of the target and searching kallsyms of
the correct module, from Viktor Malik.
21) Improve BPF verifier handling of '<const> <cond> <non_const>'
to better detect whether in particular jmp32 branches are taken,
from Yonghong Song.
22) Allow BPF TCP cong-ctls to write app_limited of struct tcp_sock.
A built-in cc or one from a kernel module is already able to write
to app_limited, from Yixin Shen.
Conflicts:
Documentation/bpf/bpf_devel_QA.rst
b7abcd9c656b ("bpf, doc: Link to submitting-patches.rst for general patch submission info")
0f10f647f455 ("bpf, docs: Use internal linking for link to netdev subsystem doc")
https://lore.kernel.org/all/20230307095812.236eb1be@canb.auug.org.au/
include/net/ip_tunnels.h
bc9d003dc48c3 ("ip_tunnel: Preserve pointer const in ip_tunnel_info_opts")
ac931d4cdec3d ("ipip,ip_tunnel,sit: Add FOU support for externally controlled ipip devices")
https://lore.kernel.org/all/20230413161235.4093777-1-broonie@kernel.org/
net/bpf/test_run.c
e5995bc7e2ba ("bpf, test_run: fix crashes due to XDP frame overwriting/corruption")
294635a8165a ("bpf, test_run: fix &xdp_frame misplacement for LIVE_FRAMES")
https://lore.kernel.org/all/20230320102619.05b80a98@canb.auug.org.au/
====================
Link: https://lore.kernel.org/r/20230413191525.7295-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
-rw-r--r-- | net/bpf/bpf_dummy_struct_ops.c | 14 | ||||
-rw-r--r-- | net/bpf/test_run.c | 34 | ||||
-rw-r--r-- | net/core/bpf_sk_storage.c | 24 | ||||
-rw-r--r-- | net/core/filter.c | 29 | ||||
-rw-r--r-- | net/core/sock_map.c | 8 | ||||
-rw-r--r-- | net/core/xdp.c | 19 | ||||
-rw-r--r-- | net/ipv4/Makefile | 2 | ||||
-rw-r--r-- | net/ipv4/bpf_tcp_ca.c | 23 | ||||
-rw-r--r-- | net/ipv4/fou_bpf.c | 119 | ||||
-rw-r--r-- | net/ipv4/fou_core.c | 5 | ||||
-rw-r--r-- | net/ipv4/ip_tunnel.c | 22 | ||||
-rw-r--r-- | net/ipv4/ipip.c | 1 | ||||
-rw-r--r-- | net/ipv4/tcp_cong.c | 66 | ||||
-rw-r--r-- | net/ipv6/sit.c | 2 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_bpf.c | 5 | ||||
-rw-r--r-- | net/xdp/xsk.c | 9 | ||||
-rw-r--r-- | net/xdp/xsk_queue.h | 19 | ||||
-rw-r--r-- | net/xdp/xskmap.c | 8 |
18 files changed, 299 insertions, 110 deletions
diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index ff4f89a2b02a..5918d1b32e19 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -173,14 +173,11 @@ static int bpf_dummy_ops_check_member(const struct btf_type *t, static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) + int off, int size) { const struct btf_type *state; const struct btf_type *t; s32 type_id; - int err; type_id = btf_find_by_name_kind(reg->btf, "bpf_dummy_ops_state", BTF_KIND_STRUCT); @@ -194,11 +191,12 @@ static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log, return -EACCES; } - err = btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); - if (err < 0) - return err; + if (off + size > sizeof(struct bpf_dummy_ops_state)) { + bpf_log(log, "write access at off %d with size %d\n", off, size); + return -EACCES; + } - return atype == BPF_READ ? err : NOT_INIT; + return NOT_INIT; } static const struct bpf_verifier_ops bpf_dummy_verifier_ops = { diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index d350f31c7a3d..0b9bd9b39990 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -215,6 +215,16 @@ static void xdp_test_run_teardown(struct xdp_test_data *xdp) kfree(xdp->skbs); } +static bool frame_was_changed(const struct xdp_page_head *head) +{ + /* xdp_scrub_frame() zeroes the data pointer, flags is the last field, + * i.e. has the highest chances to be overwritten. If those two are + * untouched, it's most likely safe to skip the context reset. + */ + return head->frame->data != head->orig_ctx.data || + head->frame->flags != head->orig_ctx.flags; +} + static bool ctx_was_changed(struct xdp_page_head *head) { return head->orig_ctx.data != head->ctx.data || @@ -224,7 +234,7 @@ static bool ctx_was_changed(struct xdp_page_head *head) static void reset_ctx(struct xdp_page_head *head) { - if (likely(!ctx_was_changed(head))) + if (likely(!frame_was_changed(head) && !ctx_was_changed(head))) return; head->ctx.data = head->orig_ctx.data; @@ -538,6 +548,11 @@ int noinline bpf_fentry_test8(struct bpf_fentry_test_t *arg) return (long)arg->a; } +__bpf_kfunc u32 bpf_fentry_test9(u32 *a) +{ + return *a; +} + __bpf_kfunc int bpf_modify_return_test(int a, int *b) { *b += 1; @@ -567,6 +582,11 @@ long noinline bpf_kfunc_call_test4(signed char a, short b, int c, long d) return (long)a + (long)b + (long)c + d; } +int noinline bpf_fentry_shadow_test(int a) +{ + return a + 1; +} + struct prog_test_member1 { int a; }; @@ -598,6 +618,11 @@ bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) return &prog_test_struct; } +__bpf_kfunc void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p) +{ + WARN_ON_ONCE(1); +} + __bpf_kfunc struct prog_test_member * bpf_kfunc_call_memb_acquire(void) { @@ -607,9 +632,6 @@ bpf_kfunc_call_memb_acquire(void) __bpf_kfunc void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) { - if (!p) - return; - refcount_dec(&p->cnt); } @@ -795,6 +817,7 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2) BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS | KF_RCU) BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE) BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset) BTF_SET8_END(test_sk_check_kfunc_ids) static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, @@ -844,7 +867,8 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 || bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111 || bpf_fentry_test7((struct bpf_fentry_test_t *)0) != 0 || - bpf_fentry_test8(&arg) != 0) + bpf_fentry_test8(&arg) != 0 || + bpf_fentry_test9(&retval) != 0) goto out; break; case BPF_MODIFY_RETURN: diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 7a36353dbc22..d4172534dfa8 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -40,7 +40,7 @@ static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map) if (!sdata) return -ENOENT; - bpf_selem_unlink(SELEM(sdata), true); + bpf_selem_unlink(SELEM(sdata), false); return 0; } @@ -49,7 +49,6 @@ static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map) void bpf_sk_storage_free(struct sock *sk) { struct bpf_local_storage *sk_storage; - bool free_sk_storage = false; rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); @@ -58,13 +57,8 @@ void bpf_sk_storage_free(struct sock *sk) return; } - raw_spin_lock_bh(&sk_storage->lock); - free_sk_storage = bpf_local_storage_unlink_nolock(sk_storage); - raw_spin_unlock_bh(&sk_storage->lock); + bpf_local_storage_destroy(sk_storage); rcu_read_unlock(); - - if (free_sk_storage) - kfree_rcu(sk_storage, rcu); } static void bpf_sk_storage_map_free(struct bpf_map *map) @@ -74,7 +68,7 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) { - return bpf_local_storage_map_alloc(attr, &sk_cache); + return bpf_local_storage_map_alloc(attr, &sk_cache, false); } static int notsupp_get_next_key(struct bpf_map *map, void *key, @@ -100,8 +94,8 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) return ERR_PTR(err); } -static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static long bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct socket *sock; @@ -120,7 +114,7 @@ static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, return err; } -static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) +static long bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) { struct socket *sock; int fd, err; @@ -203,7 +197,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) } else { ret = bpf_local_storage_alloc(newsk, smap, copy_selem, GFP_ATOMIC); if (ret) { - kfree(copy_selem); + bpf_selem_free(copy_selem, smap, true); atomic_sub(smap->elem_size, &newsk->sk_omem_alloc); bpf_map_put(map); @@ -418,7 +412,7 @@ const struct bpf_func_proto bpf_sk_storage_get_tracing_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, @@ -430,7 +424,7 @@ const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], .allowed = bpf_sk_storage_tracing_allowed, }; diff --git a/net/core/filter.c b/net/core/filter.c index a8c8fd96c822..df0df59814ae 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5002,7 +5002,7 @@ const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto = { .func = bpf_get_socket_ptr_cookie, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON | PTR_MAYBE_NULL, }; BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) @@ -8746,23 +8746,18 @@ EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock); int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag); + int off, int size); EXPORT_SYMBOL_GPL(nfct_btf_struct_access); static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag) + int off, int size) { int ret = -EACCES; - if (atype == BPF_READ) - return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); - mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) - ret = nfct_btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); + ret = nfct_btf_struct_access(log, reg, off, size); mutex_unlock(&nf_conn_btf_access_lock); return ret; @@ -8829,17 +8824,13 @@ EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); static int xdp_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag) + int off, int size) { int ret = -EACCES; - if (atype == BPF_READ) - return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); - mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) - ret = nfct_btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); + ret = nfct_btf_struct_access(log, reg, off, size); mutex_unlock(&nf_conn_btf_access_lock); return ret; @@ -9189,7 +9180,7 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, - PKT_VLAN_PRESENT_OFFSET); + SKB_BF_MONO_TC_OFFSET); *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_MONO_DELIVERY_TIME_MASK, 2); *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC); @@ -9236,7 +9227,7 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, /* AX is needed because src_reg and dst_reg could be the same */ __u8 tmp_reg = BPF_REG_AX; - *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, PKT_VLAN_PRESENT_OFFSET); + *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK); *insn++ = BPF_JMP32_IMM(BPF_JNE, tmp_reg, @@ -9271,14 +9262,14 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, if (!prog->tstamp_type_access) { __u8 tmp_reg = BPF_REG_AX; - *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, PKT_VLAN_PRESENT_OFFSET); + *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); /* Writing __sk_buff->tstamp as ingress, goto <clear> */ *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); /* goto <store> */ *insn++ = BPF_JMP_A(2); /* <clear>: mono_delivery_time */ *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_MONO_DELIVERY_TIME_MASK); - *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, PKT_VLAN_PRESENT_OFFSET); + *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET); } #endif diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 9b854e236d23..7c189c2e2fbf 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -437,7 +437,7 @@ static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk, __sock_map_delete(stab, sk, link_raw); } -static int sock_map_delete_elem(struct bpf_map *map, void *key) +static long sock_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); u32 i = *(u32 *)key; @@ -587,8 +587,8 @@ out: return ret; } -static int sock_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static long sock_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) { struct sock *sk = (struct sock *)value; int ret; @@ -925,7 +925,7 @@ static void sock_hash_delete_from_link(struct bpf_map *map, struct sock *sk, raw_spin_unlock_bh(&bucket->lock); } -static int sock_hash_delete_elem(struct bpf_map *map, void *key) +static long sock_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u32 hash, key_size = map->key_size; diff --git a/net/core/xdp.c b/net/core/xdp.c index fb85aca81961..41e5ca8643ec 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -531,21 +531,6 @@ out: } EXPORT_SYMBOL_GPL(xdp_return_buff); -/* Only called for MEM_TYPE_PAGE_POOL see xdp.h */ -void __xdp_release_frame(void *data, struct xdp_mem_info *mem) -{ - struct xdp_mem_allocator *xa; - struct page *page; - - rcu_read_lock(); - xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); - page = virt_to_head_page(data); - if (xa) - page_pool_release_page(xa->page_pool, page); - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(__xdp_release_frame); - void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { @@ -658,8 +643,8 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, * - RX ring dev queue index (skb_record_rx_queue) */ - /* Until page_pool get SKB return path, release DMA here */ - xdp_release_frame(xdpf); + if (xdpf->mem.type == MEM_TYPE_PAGE_POOL) + skb_mark_for_recycle(skb); /* Allow SKB to reuse area used by xdp_frame */ xdp_scrub_frame(xdpf); diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 880277c9fd07..b18ba8ef93ad 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -26,7 +26,7 @@ obj-$(CONFIG_IP_MROUTE) += ipmr.o obj-$(CONFIG_IP_MROUTE_COMMON) += ipmr_base.o obj-$(CONFIG_NET_IPIP) += ipip.o gre-y := gre_demux.o -fou-y := fou_core.o fou_nl.o +fou-y := fou_core.o fou_nl.o fou_bpf.o obj-$(CONFIG_NET_FOU) += fou.o obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o obj-$(CONFIG_NET_IPGRE) += ip_gre.o diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 13fc0c185cd9..4406d796cc2f 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -72,15 +72,11 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag) + int off, int size) { const struct btf_type *t; size_t end; - if (atype == BPF_READ) - return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); - t = btf_type_by_id(reg->btf, reg->btf_id); if (t != tcp_sock_type) { bpf_log(log, "only read is supported\n"); @@ -113,6 +109,9 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, case offsetof(struct tcp_sock, ecn_flags): end = offsetofend(struct tcp_sock, ecn_flags); break; + case offsetof(struct tcp_sock, app_limited): + end = offsetofend(struct tcp_sock, app_limited); + break; default: bpf_log(log, "no write support to tcp_sock at off %d\n", off); return -EACCES; @@ -239,8 +238,6 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t, if (bpf_obj_name_cpy(tcp_ca->name, utcp_ca->name, sizeof(tcp_ca->name)) <= 0) return -EINVAL; - if (tcp_ca_find(utcp_ca->name)) - return -EEXIST; return 1; } @@ -266,13 +263,25 @@ static void bpf_tcp_ca_unreg(void *kdata) tcp_unregister_congestion_control(kdata); } +static int bpf_tcp_ca_update(void *kdata, void *old_kdata) +{ + return tcp_update_congestion_control(kdata, old_kdata); +} + +static int bpf_tcp_ca_validate(void *kdata) +{ + return tcp_validate_congestion_control(kdata); +} + struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, + .update = bpf_tcp_ca_update, .check_member = bpf_tcp_ca_check_member, .init_member = bpf_tcp_ca_init_member, .init = bpf_tcp_ca_init, + .validate = bpf_tcp_ca_validate, .name = "tcp_congestion_ops", }; diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c new file mode 100644 index 000000000000..3760a14b6b57 --- /dev/null +++ b/net/ipv4/fou_bpf.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Unstable Fou Helpers for TC-BPF hook + * + * These are called from SCHED_CLS BPF programs. Note that it is + * allowed to break compatibility for these functions since the interface they + * are exposed through to BPF programs is explicitly unstable. + */ + +#include <linux/bpf.h> +#include <linux/btf_ids.h> + +#include <net/dst_metadata.h> +#include <net/fou.h> + +struct bpf_fou_encap { + __be16 sport; + __be16 dport; +}; + +enum bpf_fou_encap_type { + FOU_BPF_ENCAP_FOU, + FOU_BPF_ENCAP_GUE, +}; + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in BTF"); + +/* bpf_skb_set_fou_encap - Set FOU encap parameters + * + * This function allows for using GUE or FOU encapsulation together with an + * ipip device in collect-metadata mode. + * + * It is meant to be used in BPF tc-hooks and after a call to the + * bpf_skb_set_tunnel_key helper, responsible for setting IP addresses. + * + * Parameters: + * @skb_ctx Pointer to ctx (__sk_buff) in TC program. Cannot be NULL + * @encap Pointer to a `struct bpf_fou_encap` storing UDP src and + * dst ports. If sport is set to 0 the kernel will auto-assign a + * port. This is similar to using `encap-sport auto`. + * Cannot be NULL + * @type Encapsulation type for the packet. Their definitions are + * specified in `enum bpf_fou_encap_type` + */ +__bpf_kfunc int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx, + struct bpf_fou_encap *encap, int type) +{ + struct sk_buff *skb = (struct sk_buff *)skb_ctx; + struct ip_tunnel_info *info = skb_tunnel_info(skb); + + if (unlikely(!encap)) + return -EINVAL; + + if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) + return -EINVAL; + + switch (type) { + case FOU_BPF_ENCAP_FOU: + info->encap.type = TUNNEL_ENCAP_FOU; + break; + case FOU_BPF_ENCAP_GUE: + info->encap.type = TUNNEL_ENCAP_GUE; + break; + default: + info->encap.type = TUNNEL_ENCAP_NONE; + } + + if (info->key.tun_flags & TUNNEL_CSUM) + info->encap.flags |= TUNNEL_ENCAP_FLAG_CSUM; + + info->encap.sport = encap->sport; + info->encap.dport = encap->dport; + + return 0; +} + +/* bpf_skb_get_fou_encap - Get FOU encap parameters + * + * This function allows for reading encap metadata from a packet received + * on an ipip device in collect-metadata mode. + * + * Parameters: + * @skb_ctx Pointer to ctx (__sk_buff) in TC program. Cannot be NULL + * @encap Pointer to a struct bpf_fou_encap storing UDP source and + * destination port. Cannot be NULL + */ +__bpf_kfunc int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx, + struct bpf_fou_encap *encap) +{ + struct sk_buff *skb = (struct sk_buff *)skb_ctx; + struct ip_tunnel_info *info = skb_tunnel_info(skb); + + if (unlikely(!info)) + return -EINVAL; + + encap->sport = info->encap.sport; + encap->dport = info->encap.dport; + + return 0; +} + +__diag_pop() + +BTF_SET8_START(fou_kfunc_set) +BTF_ID_FLAGS(func, bpf_skb_set_fou_encap) +BTF_ID_FLAGS(func, bpf_skb_get_fou_encap) +BTF_SET8_END(fou_kfunc_set) + +static const struct btf_kfunc_id_set fou_bpf_kfunc_set = { + .owner = THIS_MODULE, + .set = &fou_kfunc_set, +}; + +int register_fou_bpf(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, + &fou_bpf_kfunc_set); +} diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index cafec9b4eee0..0c41076e31ed 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -1236,10 +1236,15 @@ static int __init fou_init(void) if (ret < 0) goto unregister; + ret = register_fou_bpf(); + if (ret < 0) + goto kfunc_failed; + ret = ip_tunnel_encap_add_fou_ops(); if (ret == 0) return 0; +kfunc_failed: genl_unregister_family(&fou_nl_family); unregister: unregister_pernet_device(&fou_net_ops); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 2541083d49ad..beeae624c412 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -359,6 +359,20 @@ err_dev_set_mtu: return ERR_PTR(err); } +void ip_tunnel_md_udp_encap(struct sk_buff *skb, struct ip_tunnel_info *info) +{ + const struct iphdr *iph = ip_hdr(skb); + const struct udphdr *udph; + + if (iph->protocol != IPPROTO_UDP) + return; + + udph = (struct udphdr *)((__u8 *)iph + (iph->ihl << 2)); + info->encap.sport = udph->source; + info->encap.dport = udph->dest; +} +EXPORT_SYMBOL(ip_tunnel_md_udp_encap); + int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error) @@ -572,7 +586,11 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel_id_to_key32(key->tun_id), RT_TOS(tos), dev_net(dev), 0, skb->mark, skb_get_hash(skb), key->flow_flags); - if (tunnel->encap.type != TUNNEL_ENCAP_NONE) + + if (!tunnel_hlen) + tunnel_hlen = ip_encap_hlen(&tun_info->encap); + + if (ip_tunnel_encap(skb, &tun_info->encap, &proto, &fl4) < 0) goto tx_error; use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); @@ -732,7 +750,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, dev_net(dev), tunnel->parms.link, tunnel->fwmark, skb_get_hash(skb), 0); - if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) + if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) goto tx_error; if (connected && md) { diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index abea77759b7e..27b8f83c6ea2 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -241,6 +241,7 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) tun_dst = ip_tun_rx_dst(skb, 0, 0, 0); if (!tun_dst) return 0; + ip_tunnel_md_udp_encap(skb, &tun_dst->u.tun_info); } skb_reset_mac_header(skb); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index db8b4b488c31..1b34050a7538 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -75,14 +75,8 @@ struct tcp_congestion_ops *tcp_ca_find_key(u32 key) return NULL; } -/* - * Attach new congestion control algorithm to the list - * of available options. - */ -int tcp_register_congestion_control(struct tcp_congestion_ops *ca) +int tcp_validate_congestion_control(struct tcp_congestion_ops *ca) { - int ret = 0; - /* all algorithms must implement these */ if (!ca->ssthresh || !ca->undo_cwnd || !(ca->cong_avoid || ca->cong_control)) { @@ -90,6 +84,20 @@ int tcp_register_congestion_control(struct tcp_congestion_ops *ca) return -EINVAL; } + return 0; +} + +/* Attach new congestion control algorithm to the list + * of available options. + */ +int tcp_register_congestion_control(struct tcp_congestion_ops *ca) +{ + int ret; + + ret = tcp_validate_congestion_control(ca); + if (ret) + return ret; + ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); spin_lock(&tcp_cong_list_lock); @@ -130,6 +138,50 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca) } EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); +/* Replace a registered old ca with a new one. + * + * The new ca must have the same name as the old one, that has been + * registered. + */ +int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_congestion_ops *old_ca) +{ + struct tcp_congestion_ops *existing; + int ret; + + ret = tcp_validate_congestion_control(ca); + if (ret) + return ret; + + ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); + + spin_lock(&tcp_cong_list_lock); + existing = tcp_ca_find_key(old_ca->key); + if (ca->key == TCP_CA_UNSPEC || !existing || strcmp(existing->name, ca->name)) { + pr_notice("%s not registered or non-unique key\n", + ca->name); + ret = -EINVAL; + } else if (existing != old_ca) { + pr_notice("invalid old congestion control algorithm to replace\n"); + ret = -EINVAL; + } else { + /* Add the new one before removing the old one to keep + * one implementation available all the time. + */ + list_add_tail_rcu(&ca->list, &tcp_cong_list); + list_del_rcu(&existing->list); + pr_debug("%s updated\n", ca->name); + } + spin_unlock(&tcp_cong_list_lock); + + /* Wait for outstanding readers to complete before the + * module or struct_ops gets removed entirely. + */ + if (!ret) + synchronize_rcu(); + + return ret; +} + u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca) { const struct tcp_congestion_ops *ca; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 70d81bba5093..063560e2cb1a 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1024,7 +1024,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, ttl = iph6->hop_limit; tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); - if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) { + if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) { ip_rt_put(rt); goto tx_error; } diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index cd99e6dc1f35..3f821b7ba646 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -192,8 +192,7 @@ BTF_ID(struct, nf_conn___init) /* Check writes into `struct nf_conn` */ static int _nf_conntrack_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, - int off, int size, enum bpf_access_type atype, - u32 *next_btf_id, enum bpf_type_flag *flag) + int off, int size) { const struct btf_type *ncit, *nct, *t; size_t end; @@ -401,8 +400,6 @@ __bpf_kfunc struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) */ __bpf_kfunc void bpf_ct_release(struct nf_conn *nfct) { - if (!nfct) - return; nf_ct_put(nfct); } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 2ac58b282b5e..cc1e7f15fa73 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1301,9 +1301,10 @@ static int xsk_mmap(struct file *file, struct socket *sock, loff_t offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT; unsigned long size = vma->vm_end - vma->vm_start; struct xdp_sock *xs = xdp_sk(sock->sk); + int state = READ_ONCE(xs->state); struct xsk_queue *q = NULL; - if (READ_ONCE(xs->state) != XSK_READY) + if (state != XSK_READY && state != XSK_BOUND) return -EBUSY; if (offset == XDP_PGOFF_RX_RING) { @@ -1314,9 +1315,11 @@ static int xsk_mmap(struct file *file, struct socket *sock, /* Matches the smp_wmb() in XDP_UMEM_REG */ smp_rmb(); if (offset == XDP_UMEM_PGOFF_FILL_RING) - q = READ_ONCE(xs->fq_tmp); + q = state == XSK_READY ? READ_ONCE(xs->fq_tmp) : + READ_ONCE(xs->pool->fq); else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING) - q = READ_ONCE(xs->cq_tmp); + q = state == XSK_READY ? READ_ONCE(xs->cq_tmp) : + READ_ONCE(xs->pool->cq); } if (!q) diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index bfb2a7e50c26..6d40a77fccbe 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -133,16 +133,12 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 chunk, chunk_end; + u64 offset = desc->addr & (pool->chunk_size - 1); - chunk = xp_aligned_extract_addr(pool, desc->addr); - if (likely(desc->len)) { - chunk_end = xp_aligned_extract_addr(pool, desc->addr + desc->len - 1); - if (chunk != chunk_end) - return false; - } + if (offset + desc->len > pool->chunk_size) + return false; - if (chunk >= pool->addrs_cnt) + if (desc->addr >= pool->addrs_cnt) return false; if (desc->options) @@ -153,15 +149,12 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 addr, base_addr; - - base_addr = xp_unaligned_extract_addr(desc->addr); - addr = xp_unaligned_add_offset_to_addr(desc->addr); + u64 addr = xp_unaligned_add_offset_to_addr(desc->addr); if (desc->len > pool->chunk_size) return false; - if (base_addr >= pool->addrs_cnt || addr >= pool->addrs_cnt || + if (addr >= pool->addrs_cnt || addr + desc->len > pool->addrs_cnt || xp_desc_crosses_non_contig_pg(pool, addr, desc->len)) return false; diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 0c38d7175922..2c1427074a3b 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -162,8 +162,8 @@ static void *xsk_map_lookup_elem_sys_only(struct bpf_map *map, void *key) return ERR_PTR(-EOPNOTSUPP); } -static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long xsk_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) { struct xsk_map *m = container_of(map, struct xsk_map, map); struct xdp_sock __rcu **map_entry; @@ -223,7 +223,7 @@ out: return err; } -static int xsk_map_delete_elem(struct bpf_map *map, void *key) +static long xsk_map_delete_elem(struct bpf_map *map, void *key) { struct xsk_map *m = container_of(map, struct xsk_map, map); struct xdp_sock __rcu **map_entry; @@ -243,7 +243,7 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) return 0; } -static int xsk_map_redirect(struct bpf_map *map, u64 index, u64 flags) +static long xsk_map_redirect(struct bpf_map *map, u64 index, u64 flags) { return __bpf_xdp_redirect_map(map, index, flags, 0, __xsk_map_lookup_elem); |