bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
|
/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */
|
|
|
|
|
|
|
|
|
|
#ifndef _LINUX_SKMSG_H
|
|
|
|
|
#define _LINUX_SKMSG_H
|
|
|
|
|
|
|
|
|
|
#include <linux/bpf.h>
|
|
|
|
|
#include <linux/filter.h>
|
|
|
|
|
#include <linux/scatterlist.h>
|
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
|
|
|
|
|
|
#include <net/sock.h>
|
|
|
|
|
#include <net/tcp.h>
|
|
|
|
|
#include <net/strparser.h>
|
|
|
|
|
|
|
|
|
|
#define MAX_MSG_FRAGS MAX_SKB_FRAGS
|
|
|
|
|
|
|
|
|
|
enum __sk_action {
|
|
|
|
|
__SK_DROP = 0,
|
|
|
|
|
__SK_PASS,
|
|
|
|
|
__SK_REDIRECT,
|
|
|
|
|
__SK_NONE,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct sk_msg_sg {
|
|
|
|
|
u32 start;
|
|
|
|
|
u32 curr;
|
|
|
|
|
u32 end;
|
|
|
|
|
u32 size;
|
|
|
|
|
u32 copybreak;
|
|
|
|
|
bool copy[MAX_MSG_FRAGS];
|
2018-10-13 07:46:01 +07:00
|
|
|
/* The extra element is used for chaining the front and sections when
|
|
|
|
|
* the list becomes partitioned (e.g. end < start). The crypto APIs
|
|
|
|
|
* require the chaining.
|
|
|
|
|
*/
|
|
|
|
|
struct scatterlist data[MAX_MSG_FRAGS + 1];
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
};
|
|
|
|
|
|
2018-12-21 02:35:31 +07:00
|
|
|
/* UAPI in filter.c depends on struct sk_msg_sg being first element. */
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
struct sk_msg {
|
|
|
|
|
struct sk_msg_sg sg;
|
|
|
|
|
void *data;
|
|
|
|
|
void *data_end;
|
|
|
|
|
u32 apply_bytes;
|
|
|
|
|
u32 cork_bytes;
|
|
|
|
|
u32 flags;
|
|
|
|
|
struct sk_buff *skb;
|
|
|
|
|
struct sock *sk_redir;
|
|
|
|
|
struct sock *sk;
|
|
|
|
|
struct list_head list;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct sk_psock_progs {
|
|
|
|
|
struct bpf_prog *msg_parser;
|
|
|
|
|
struct bpf_prog *skb_parser;
|
|
|
|
|
struct bpf_prog *skb_verdict;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
enum sk_psock_state_bits {
|
|
|
|
|
SK_PSOCK_TX_ENABLED,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct sk_psock_link {
|
|
|
|
|
struct list_head list;
|
|
|
|
|
struct bpf_map *map;
|
|
|
|
|
void *link_raw;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct sk_psock_parser {
|
|
|
|
|
struct strparser strp;
|
|
|
|
|
bool enabled;
|
|
|
|
|
void (*saved_data_ready)(struct sock *sk);
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct sk_psock_work_state {
|
|
|
|
|
struct sk_buff *skb;
|
|
|
|
|
u32 len;
|
|
|
|
|
u32 off;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct sk_psock {
|
|
|
|
|
struct sock *sk;
|
|
|
|
|
struct sock *sk_redir;
|
|
|
|
|
u32 apply_bytes;
|
|
|
|
|
u32 cork_bytes;
|
|
|
|
|
u32 eval;
|
|
|
|
|
struct sk_msg *cork;
|
|
|
|
|
struct sk_psock_progs progs;
|
|
|
|
|
struct sk_psock_parser parser;
|
|
|
|
|
struct sk_buff_head ingress_skb;
|
|
|
|
|
struct list_head ingress_msg;
|
|
|
|
|
unsigned long state;
|
|
|
|
|
struct list_head link;
|
|
|
|
|
spinlock_t link_lock;
|
|
|
|
|
refcount_t refcnt;
|
|
|
|
|
void (*saved_unhash)(struct sock *sk);
|
|
|
|
|
void (*saved_close)(struct sock *sk, long timeout);
|
|
|
|
|
void (*saved_write_space)(struct sock *sk);
|
|
|
|
|
struct proto *sk_proto;
|
|
|
|
|
struct sk_psock_work_state work_state;
|
|
|
|
|
struct work_struct work;
|
|
|
|
|
union {
|
|
|
|
|
struct rcu_head rcu;
|
|
|
|
|
struct work_struct gc;
|
|
|
|
|
};
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
|
|
|
|
|
int elem_first_coalesce);
|
2018-10-13 07:45:59 +07:00
|
|
|
int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src,
|
|
|
|
|
u32 off, u32 len);
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len);
|
|
|
|
|
int sk_msg_free(struct sock *sk, struct sk_msg *msg);
|
|
|
|
|
int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg);
|
|
|
|
|
void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes);
|
|
|
|
|
void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg,
|
|
|
|
|
u32 bytes);
|
|
|
|
|
|
|
|
|
|
void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes);
|
2018-10-13 07:46:01 +07:00
|
|
|
void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes);
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
|
|
|
|
|
int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
|
|
|
|
|
struct sk_msg *msg, u32 bytes);
|
|
|
|
|
int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
|
|
|
|
|
struct sk_msg *msg, u32 bytes);
|
|
|
|
|
|
|
|
|
|
static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
|
|
|
|
|
{
|
|
|
|
|
WARN_ON(i == msg->sg.end && bytes);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes)
|
|
|
|
|
{
|
|
|
|
|
if (psock->apply_bytes) {
|
|
|
|
|
if (psock->apply_bytes < bytes)
|
|
|
|
|
psock->apply_bytes = 0;
|
|
|
|
|
else
|
|
|
|
|
psock->apply_bytes -= bytes;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2019-11-05 06:36:57 +07:00
|
|
|
static inline u32 sk_msg_iter_dist(u32 start, u32 end)
|
|
|
|
|
{
|
|
|
|
|
return end >= start ? end - start : end + (MAX_MSG_FRAGS - start);
|
|
|
|
|
}
|
|
|
|
|
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
#define sk_msg_iter_var_prev(var) \
|
|
|
|
|
do { \
|
|
|
|
|
if (var == 0) \
|
|
|
|
|
var = MAX_MSG_FRAGS - 1; \
|
|
|
|
|
else \
|
|
|
|
|
var--; \
|
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
|
|
#define sk_msg_iter_var_next(var) \
|
|
|
|
|
do { \
|
|
|
|
|
var++; \
|
|
|
|
|
if (var == MAX_MSG_FRAGS) \
|
|
|
|
|
var = 0; \
|
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
|
|
#define sk_msg_iter_prev(msg, which) \
|
|
|
|
|
sk_msg_iter_var_prev(msg->sg.which)
|
|
|
|
|
|
|
|
|
|
#define sk_msg_iter_next(msg, which) \
|
|
|
|
|
sk_msg_iter_var_next(msg->sg.which)
|
|
|
|
|
|
|
|
|
|
static inline void sk_msg_clear_meta(struct sk_msg *msg)
|
|
|
|
|
{
|
|
|
|
|
memset(&msg->sg, 0, offsetofend(struct sk_msg_sg, copy));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_msg_init(struct sk_msg *msg)
|
|
|
|
|
{
|
2018-10-13 07:46:01 +07:00
|
|
|
BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != MAX_MSG_FRAGS);
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
memset(msg, 0, sizeof(*msg));
|
2018-10-13 07:46:01 +07:00
|
|
|
sg_init_marker(msg->sg.data, MAX_MSG_FRAGS);
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
|
|
|
|
|
int which, u32 size)
|
|
|
|
|
{
|
|
|
|
|
dst->sg.data[which] = src->sg.data[which];
|
|
|
|
|
dst->sg.data[which].length = size;
|
2018-10-17 00:36:01 +07:00
|
|
|
dst->sg.size += size;
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
src->sg.data[which].length -= size;
|
|
|
|
|
src->sg.data[which].offset += size;
|
|
|
|
|
}
|
|
|
|
|
|
2018-10-13 07:46:01 +07:00
|
|
|
static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src)
|
|
|
|
|
{
|
|
|
|
|
memcpy(dst, src, sizeof(*src));
|
|
|
|
|
sk_msg_init(src);
|
|
|
|
|
}
|
|
|
|
|
|
2018-10-17 01:07:59 +07:00
|
|
|
static inline bool sk_msg_full(const struct sk_msg *msg)
|
|
|
|
|
{
|
|
|
|
|
return (msg->sg.end == msg->sg.start) && msg->sg.size;
|
|
|
|
|
}
|
|
|
|
|
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
static inline u32 sk_msg_elem_used(const struct sk_msg *msg)
|
|
|
|
|
{
|
2018-10-17 01:07:59 +07:00
|
|
|
if (sk_msg_full(msg))
|
|
|
|
|
return MAX_MSG_FRAGS;
|
|
|
|
|
|
2019-11-05 06:36:57 +07:00
|
|
|
return sk_msg_iter_dist(msg->sg.start, msg->sg.end);
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which)
|
|
|
|
|
{
|
|
|
|
|
return &msg->sg.data[which];
|
|
|
|
|
}
|
|
|
|
|
|
bpf: sk_msg program helper bpf_msg_push_data
This allows user to push data into a msg using sk_msg program types.
The format is as follows,
bpf_msg_push_data(msg, offset, len, flags)
this will insert 'len' bytes at offset 'offset'. For example to
prepend 10 bytes at the front of the message the user can,
bpf_msg_push_data(msg, 0, 10, 0);
This will invalidate data bounds so BPF user will have to then recheck
data bounds after calling this. After this the msg size will have been
updated and the user is free to write into the added bytes. We allow
any offset/len as long as it is within the (data, data_end) range.
However, a copy will be required if the ring is full and its possible
for the helper to fail with ENOMEM or EINVAL errors which need to be
handled by the BPF program.
This can be used similar to XDP metadata to pass data between sk_msg
layer and lower layers.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-10-20 09:56:49 +07:00
|
|
|
static inline struct scatterlist sk_msg_elem_cpy(struct sk_msg *msg, int which)
|
|
|
|
|
{
|
|
|
|
|
return msg->sg.data[which];
|
|
|
|
|
}
|
|
|
|
|
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
static inline struct page *sk_msg_page(struct sk_msg *msg, int which)
|
|
|
|
|
{
|
|
|
|
|
return sg_page(sk_msg_elem(msg, which));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline bool sk_msg_to_ingress(const struct sk_msg *msg)
|
|
|
|
|
{
|
|
|
|
|
return msg->flags & BPF_F_INGRESS;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_msg_compute_data_pointers(struct sk_msg *msg)
|
|
|
|
|
{
|
|
|
|
|
struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start);
|
|
|
|
|
|
|
|
|
|
if (msg->sg.copy[msg->sg.start]) {
|
|
|
|
|
msg->data = NULL;
|
|
|
|
|
msg->data_end = NULL;
|
|
|
|
|
} else {
|
|
|
|
|
msg->data = sg_virt(sge);
|
|
|
|
|
msg->data_end = msg->data + sge->length;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page,
|
|
|
|
|
u32 len, u32 offset)
|
|
|
|
|
{
|
|
|
|
|
struct scatterlist *sge;
|
|
|
|
|
|
|
|
|
|
get_page(page);
|
|
|
|
|
sge = sk_msg_elem(msg, msg->sg.end);
|
|
|
|
|
sg_set_page(sge, page, len, offset);
|
|
|
|
|
sg_unmark_end(sge);
|
|
|
|
|
|
|
|
|
|
msg->sg.copy[msg->sg.end] = true;
|
|
|
|
|
msg->sg.size += len;
|
|
|
|
|
sk_msg_iter_next(msg, end);
|
|
|
|
|
}
|
|
|
|
|
|
2018-10-13 07:46:01 +07:00
|
|
|
static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state)
|
|
|
|
|
{
|
|
|
|
|
do {
|
|
|
|
|
msg->sg.copy[i] = copy_state;
|
|
|
|
|
sk_msg_iter_var_next(i);
|
|
|
|
|
if (i == msg->sg.end)
|
|
|
|
|
break;
|
|
|
|
|
} while (1);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start)
|
|
|
|
|
{
|
|
|
|
|
sk_msg_sg_copy(msg, start, true);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_msg_sg_copy_clear(struct sk_msg *msg, u32 start)
|
|
|
|
|
{
|
|
|
|
|
sk_msg_sg_copy(msg, start, false);
|
|
|
|
|
}
|
|
|
|
|
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
static inline struct sk_psock *sk_psock(const struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
return rcu_dereference_sk_user_data(sk);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_psock_queue_msg(struct sk_psock *psock,
|
|
|
|
|
struct sk_msg *msg)
|
|
|
|
|
{
|
|
|
|
|
list_add_tail(&msg->list, &psock->ingress_msg);
|
|
|
|
|
}
|
|
|
|
|
|
2018-10-13 07:46:01 +07:00
|
|
|
static inline bool sk_psock_queue_empty(const struct sk_psock *psock)
|
|
|
|
|
{
|
|
|
|
|
return psock ? list_empty(&psock->ingress_msg) : true;
|
|
|
|
|
}
|
|
|
|
|
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
static inline void sk_psock_report_error(struct sk_psock *psock, int err)
|
|
|
|
|
{
|
|
|
|
|
struct sock *sk = psock->sk;
|
|
|
|
|
|
|
|
|
|
sk->sk_err = err;
|
|
|
|
|
sk->sk_error_report(sk);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
struct sk_psock *sk_psock_init(struct sock *sk, int node);
|
|
|
|
|
|
|
|
|
|
int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock);
|
|
|
|
|
void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock);
|
|
|
|
|
void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock);
|
|
|
|
|
|
|
|
|
|
int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
|
|
|
|
|
struct sk_msg *msg);
|
|
|
|
|
|
|
|
|
|
static inline struct sk_psock_link *sk_psock_init_link(void)
|
|
|
|
|
{
|
|
|
|
|
return kzalloc(sizeof(struct sk_psock_link),
|
|
|
|
|
GFP_ATOMIC | __GFP_NOWARN);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_psock_free_link(struct sk_psock_link *link)
|
|
|
|
|
{
|
|
|
|
|
kfree(link);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock);
|
|
|
|
|
#if defined(CONFIG_BPF_STREAM_PARSER)
|
|
|
|
|
void sk_psock_unlink(struct sock *sk, struct sk_psock_link *link);
|
|
|
|
|
#else
|
|
|
|
|
static inline void sk_psock_unlink(struct sock *sk,
|
|
|
|
|
struct sk_psock_link *link)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
void __sk_psock_purge_ingress_msg(struct sk_psock *psock);
|
|
|
|
|
|
|
|
|
|
static inline void sk_psock_cork_free(struct sk_psock *psock)
|
|
|
|
|
{
|
|
|
|
|
if (psock->cork) {
|
|
|
|
|
sk_msg_free(psock->sk, psock->cork);
|
|
|
|
|
kfree(psock->cork);
|
|
|
|
|
psock->cork = NULL;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_psock_update_proto(struct sock *sk,
|
|
|
|
|
struct sk_psock *psock,
|
|
|
|
|
struct proto *ops)
|
|
|
|
|
{
|
|
|
|
|
psock->saved_unhash = sk->sk_prot->unhash;
|
|
|
|
|
psock->saved_close = sk->sk_prot->close;
|
|
|
|
|
psock->saved_write_space = sk->sk_write_space;
|
|
|
|
|
|
|
|
|
|
psock->sk_proto = sk->sk_prot;
|
|
|
|
|
sk->sk_prot = ops;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_psock_restore_proto(struct sock *sk,
|
|
|
|
|
struct sk_psock *psock)
|
|
|
|
|
{
|
2019-05-22 17:01:42 +07:00
|
|
|
sk->sk_write_space = psock->saved_write_space;
|
|
|
|
|
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
if (psock->sk_proto) {
|
2019-07-20 00:29:22 +07:00
|
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
|
bool has_ulp = !!icsk->icsk_ulp_data;
|
|
|
|
|
|
|
|
|
|
if (has_ulp)
|
|
|
|
|
tcp_update_ulp(sk, psock->sk_proto);
|
|
|
|
|
else
|
|
|
|
|
sk->sk_prot = psock->sk_proto;
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
psock->sk_proto = NULL;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_psock_set_state(struct sk_psock *psock,
|
|
|
|
|
enum sk_psock_state_bits bit)
|
|
|
|
|
{
|
|
|
|
|
set_bit(bit, &psock->state);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_psock_clear_state(struct sk_psock *psock,
|
|
|
|
|
enum sk_psock_state_bits bit)
|
|
|
|
|
{
|
|
|
|
|
clear_bit(bit, &psock->state);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline bool sk_psock_test_state(const struct sk_psock *psock,
|
|
|
|
|
enum sk_psock_state_bits bit)
|
|
|
|
|
{
|
|
|
|
|
return test_bit(bit, &psock->state);
|
|
|
|
|
}
|
|
|
|
|
|
2018-10-19 03:58:35 +07:00
|
|
|
static inline struct sk_psock *sk_psock_get_checked(struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
struct sk_psock *psock;
|
|
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
|
psock = sk_psock(sk);
|
|
|
|
|
if (psock) {
|
|
|
|
|
if (sk->sk_prot->recvmsg != tcp_bpf_recvmsg) {
|
|
|
|
|
psock = ERR_PTR(-EBUSY);
|
|
|
|
|
goto out;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (!refcount_inc_not_zero(&psock->refcnt))
|
|
|
|
|
psock = ERR_PTR(-EBUSY);
|
|
|
|
|
}
|
|
|
|
|
out:
|
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
return psock;
|
|
|
|
|
}
|
|
|
|
|
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
static inline struct sk_psock *sk_psock_get(struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
struct sk_psock *psock;
|
|
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
|
psock = sk_psock(sk);
|
|
|
|
|
if (psock && !refcount_inc_not_zero(&psock->refcnt))
|
|
|
|
|
psock = NULL;
|
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
return psock;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void sk_psock_stop(struct sock *sk, struct sk_psock *psock);
|
|
|
|
|
void sk_psock_destroy(struct rcu_head *rcu);
|
|
|
|
|
void sk_psock_drop(struct sock *sk, struct sk_psock *psock);
|
|
|
|
|
|
|
|
|
|
static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock)
|
|
|
|
|
{
|
|
|
|
|
if (refcount_dec_and_test(&psock->refcnt))
|
|
|
|
|
sk_psock_drop(sk, psock);
|
|
|
|
|
}
|
|
|
|
|
|
2018-12-21 02:35:33 +07:00
|
|
|
static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock)
|
|
|
|
|
{
|
|
|
|
|
if (psock->parser.enabled)
|
|
|
|
|
psock->parser.saved_data_ready(sk);
|
|
|
|
|
else
|
|
|
|
|
sk->sk_data_ready(sk);
|
|
|
|
|
}
|
|
|
|
|
|
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 07:45:58 +07:00
|
|
|
static inline void psock_set_prog(struct bpf_prog **pprog,
|
|
|
|
|
struct bpf_prog *prog)
|
|
|
|
|
{
|
|
|
|
|
prog = xchg(pprog, prog);
|
|
|
|
|
if (prog)
|
|
|
|
|
bpf_prog_put(prog);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void psock_progs_drop(struct sk_psock_progs *progs)
|
|
|
|
|
{
|
|
|
|
|
psock_set_prog(&progs->msg_parser, NULL);
|
|
|
|
|
psock_set_prog(&progs->skb_parser, NULL);
|
|
|
|
|
psock_set_prog(&progs->skb_verdict, NULL);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#endif /* _LINUX_SKMSG_H */
|