diff options
author | Alexei Starovoitov <ast@kernel.org> | 2022-09-11 03:27:33 +0300 |
---|---|---|
committer | Alexei Starovoitov <ast@kernel.org> | 2022-09-11 03:27:33 +0300 |
commit | b8c62fe2025af081ea738a615c58d79d815f260f (patch) | |
tree | 772801bba2c6592be345947e6e5d165fdef6d2f5 /net/core/filter.c | |
parent | 57c92f11a215717bf90880828b7a23c736c3c0d9 (diff) | |
parent | e2d75e954c0a277b8fa0ddf666ddd4f9b73195f7 (diff) | |
download | linux-b8c62fe2025af081ea738a615c58d79d815f260f.tar.xz |
Merge branch 'Support direct writes to nf_conn:mark'
Daniel Xu says:
====================
Support direct writes to nf_conn:mark from TC and XDP prog types. This
is useful when applications want to store per-connection metadata. This
is also particularly useful for applications that run both bpf and
iptables/nftables because the latter can trivially access this metadata.
One example use case would be if a bpf prog is responsible for advanced
packet classification and iptables/nftables is later used for routing
due to pre-existing/legacy code.
Past discussion:
- v4: https://lore.kernel.org/bpf/cover.1661192455.git.dxu@dxuuu.xyz/
- v3: https://lore.kernel.org/bpf/cover.1660951028.git.dxu@dxuuu.xyz/
- v2: https://lore.kernel.org/bpf/CAP01T74Sgn354dXGiFWFryu4vg+o8b9s9La1d9zEbC4LGvH4qg@mail.gmail.com/T/
- v1: https://lore.kernel.org/bpf/cover.1660592020.git.dxu@dxuuu.xyz/
Changes since v4:
- Use exported function pointer + mutex to handle CONFIG_NF_CONNTRACK=m
case
Changes since v3:
- Use a mutex to protect module load/unload critical section
Changes since v2:
- Remove use of NOT_INIT for btf_struct_access write path
- Disallow nf_conn writing when nf_conntrack module not loaded
- Support writing to nf_conn___init:mark
Changes since v1:
- Add unimplemented stub for when !CONFIG_BPF_SYSCALL
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'net/core/filter.c')
-rw-r--r-- | net/core/filter.c | 54 |
1 files changed, 54 insertions, 0 deletions
diff --git a/net/core/filter.c b/net/core/filter.c index e872f45399b0..4b2be211bcbe 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -18,6 +18,7 @@ */ #include <linux/atomic.h> +#include <linux/bpf_verifier.h> #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> @@ -8604,6 +8605,36 @@ static bool tc_cls_act_is_valid_access(int off, int size, return bpf_skb_is_valid_access(off, size, type, prog, info); } +DEFINE_MUTEX(nf_conn_btf_access_lock); +EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock); + +int (*nfct_bsa)(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, u32 *next_btf_id, + enum bpf_type_flag *flag); +EXPORT_SYMBOL_GPL(nfct_bsa); + +static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, + const struct btf_type *t, int off, + int size, enum bpf_access_type atype, + u32 *next_btf_id, + enum bpf_type_flag *flag) +{ + int ret = -EACCES; + + if (atype == BPF_READ) + return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, + flag); + + mutex_lock(&nf_conn_btf_access_lock); + if (nfct_bsa) + ret = nfct_bsa(log, btf, t, off, size, atype, next_btf_id, flag); + mutex_unlock(&nf_conn_btf_access_lock); + + return ret; +} + static bool __is_valid_xdp_access(int off, int size) { if (off < 0 || off >= sizeof(struct xdp_md)) @@ -8663,6 +8694,27 @@ void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); +static int xdp_btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, + const struct btf_type *t, int off, + int size, enum bpf_access_type atype, + u32 *next_btf_id, + enum bpf_type_flag *flag) +{ + int ret = -EACCES; + + if (atype == BPF_READ) + return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, + flag); + + mutex_lock(&nf_conn_btf_access_lock); + if (nfct_bsa) + ret = nfct_bsa(log, btf, t, off, size, atype, next_btf_id, flag); + mutex_unlock(&nf_conn_btf_access_lock); + + return ret; +} + static bool sock_addr_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, @@ -10557,6 +10609,7 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, .gen_ld_abs = bpf_gen_ld_abs, + .btf_struct_access = tc_cls_act_btf_struct_access, }; const struct bpf_prog_ops tc_cls_act_prog_ops = { @@ -10568,6 +10621,7 @@ const struct bpf_verifier_ops xdp_verifier_ops = { .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, .gen_prologue = bpf_noop_prologue, + .btf_struct_access = xdp_btf_struct_access, }; const struct bpf_prog_ops xdp_prog_ops = { |