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 03:45:58 +03:00
|
|
|
/* 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
|
2019-11-27 23:16:41 +03:00
|
|
|
#define NR_MSG_FRAG_IDS (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 03:45:58 +03:00
|
|
|
|
|
|
|
|
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;
|
2019-10-07 07:09:27 +03:00
|
|
|
unsigned long copy;
|
2019-11-27 23:16:41 +03:00
|
|
|
/* The extra two elements:
|
|
|
|
|
* 1) used for chaining the front and sections when the list becomes
|
|
|
|
|
* partitioned (e.g. end < start). The crypto APIs require the
|
|
|
|
|
* chaining;
|
|
|
|
|
* 2) to chain tailer SG entries after the message.
|
2018-10-13 03:46:01 +03:00
|
|
|
*/
|
2019-11-27 23:16:41 +03:00
|
|
|
struct scatterlist data[MAX_MSG_FRAGS + 2];
|
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 03:45:58 +03:00
|
|
|
};
|
2019-11-27 23:16:41 +03:00
|
|
|
static_assert(BITS_PER_LONG >= NR_MSG_FRAG_IDS);
|
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 03:45:58 +03:00
|
|
|
|
2018-12-20 22:35:31 +03:00
|
|
|
/* 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 03:45:58 +03:00
|
|
|
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;
|
2021-02-23 21:49:30 +03:00
|
|
|
struct bpf_prog *stream_parser;
|
|
|
|
|
struct bpf_prog *stream_verdict;
|
2021-03-31 05:32:30 +03:00
|
|
|
struct bpf_prog *skb_verdict;
|
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 03:45:58 +03:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
enum sk_psock_state_bits {
|
|
|
|
|
SK_PSOCK_TX_ENABLED,
|
2023-08-04 10:37:38 +03:00
|
|
|
SK_PSOCK_RX_STRP_ENABLED,
|
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 03:45:58 +03:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct sk_psock_link {
|
|
|
|
|
struct list_head list;
|
|
|
|
|
struct bpf_map *map;
|
|
|
|
|
void *link_raw;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct sk_psock_work_state {
|
|
|
|
|
u32 len;
|
|
|
|
|
u32 off;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct sk_psock {
|
|
|
|
|
struct sock *sk;
|
|
|
|
|
struct sock *sk_redir;
|
|
|
|
|
u32 apply_bytes;
|
|
|
|
|
u32 cork_bytes;
|
|
|
|
|
u32 eval;
|
2022-11-29 13:40:39 +03:00
|
|
|
bool redir_ingress; /* undefined if sk_redir is null */
|
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 03:45:58 +03:00
|
|
|
struct sk_msg *cork;
|
|
|
|
|
struct sk_psock_progs progs;
|
2021-02-23 21:49:27 +03:00
|
|
|
#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
|
|
|
|
|
struct strparser strp;
|
|
|
|
|
#endif
|
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 03:45:58 +03:00
|
|
|
struct sk_buff_head ingress_skb;
|
|
|
|
|
struct list_head ingress_msg;
|
2021-03-31 05:32:23 +03:00
|
|
|
spinlock_t ingress_lock;
|
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 03:45:58 +03:00
|
|
|
unsigned long state;
|
|
|
|
|
struct list_head link;
|
|
|
|
|
spinlock_t link_lock;
|
|
|
|
|
refcount_t refcnt;
|
|
|
|
|
void (*saved_unhash)(struct sock *sk);
|
2022-05-24 10:53:11 +03:00
|
|
|
void (*saved_destroy)(struct sock *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 03:45:58 +03:00
|
|
|
void (*saved_close)(struct sock *sk, long timeout);
|
|
|
|
|
void (*saved_write_space)(struct sock *sk);
|
2021-02-23 21:49:27 +03:00
|
|
|
void (*saved_data_ready)(struct sock *sk);
|
2021-04-07 06:21:11 +03:00
|
|
|
int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock,
|
|
|
|
|
bool restore);
|
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 03:45:58 +03:00
|
|
|
struct proto *sk_proto;
|
2021-03-31 05:32:25 +03:00
|
|
|
struct mutex work_mutex;
|
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 03:45:58 +03:00
|
|
|
struct sk_psock_work_state work_state;
|
bpf, sockmap: Convert schedule_work into delayed_work
[ Upstream commit 29173d07f79883ac94f5570294f98af3d4287382 ]
Sk_buffs are fed into sockmap verdict programs either from a strparser
(when the user might want to decide how framing of skb is done by attaching
another parser program) or directly through tcp_read_sock. The
tcp_read_sock is the preferred method for performance when the BPF logic is
a stream parser.
The flow for Cilium's common use case with a stream parser is,
tcp_read_sock()
sk_psock_verdict_recv
ret = bpf_prog_run_pin_on_cpu()
sk_psock_verdict_apply(sock, skb, ret)
// if system is under memory pressure or app is slow we may
// need to queue skb. Do this queuing through ingress_skb and
// then kick timer to wake up handler
skb_queue_tail(ingress_skb, skb)
schedule_work(work);
The work queue is wired up to sk_psock_backlog(). This will then walk the
ingress_skb skb list that holds our sk_buffs that could not be handled,
but should be OK to run at some later point. However, its possible that
the workqueue doing this work still hits an error when sending the skb.
When this happens the skbuff is requeued on a temporary 'state' struct
kept with the workqueue. This is necessary because its possible to
partially send an skbuff before hitting an error and we need to know how
and where to restart when the workqueue runs next.
Now for the trouble, we don't rekick the workqueue. This can cause a
stall where the skbuff we just cached on the state variable might never
be sent. This happens when its the last packet in a flow and no further
packets come along that would cause the system to kick the workqueue from
that side.
To fix we could do simple schedule_work(), but while under memory pressure
it makes sense to back off some instead of continue to retry repeatedly. So
instead to fix convert schedule_work to schedule_delayed_work and add
backoff logic to reschedule from backlog queue on errors. Its not obvious
though what a good backoff is so use '1'.
To test we observed some flakes whil running NGINX compliance test with
sockmap we attributed these failed test to this bug and subsequent issue.
>From on list discussion. This commit
bec217197b41("skmsg: Schedule psock work if the cached skb exists on the psock")
was intended to address similar race, but had a couple cases it missed.
Most obvious it only accounted for receiving traffic on the local socket
so if redirecting into another socket we could still get an sk_buff stuck
here. Next it missed the case where copied=0 in the recv() handler and
then we wouldn't kick the scheduler. Also its sub-optimal to require
userspace to kick the internal mechanisms of sockmap to wake it up and
copy data to user. It results in an extra syscall and requires the app
to actual handle the EAGAIN correctly.
Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: William Findlay <will@isovalent.com>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20230523025618.113937-3-john.fastabend@gmail.com
Stable-dep-of: 405df89dd52c ("bpf, sockmap: Improved check for empty queue")
Signed-off-by: Sasha Levin <sashal@kernel.org>
2023-05-23 05:56:06 +03:00
|
|
|
struct delayed_work work;
|
2021-03-31 05:32:26 +03:00
|
|
|
struct rcu_work rwork;
|
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 03:45:58 +03:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
|
|
|
|
|
int elem_first_coalesce);
|
2018-10-13 03:45:59 +03:00
|
|
|
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 03:45:58 +03:00
|
|
|
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 03:46:01 +03:00
|
|
|
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 03:45:58 +03:00
|
|
|
|
|
|
|
|
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);
|
2021-03-31 05:32:33 +03:00
|
|
|
int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
|
|
|
|
|
int len, int flags);
|
2021-10-08 23:33:04 +03:00
|
|
|
bool sk_msg_is_readable(struct sock *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 03:45:58 +03:00
|
|
|
|
|
|
|
|
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 02:36:57 +03:00
|
|
|
static inline u32 sk_msg_iter_dist(u32 start, u32 end)
|
|
|
|
|
{
|
2019-11-27 23:16:41 +03:00
|
|
|
return end >= start ? end - start : end + (NR_MSG_FRAG_IDS - start);
|
2019-11-05 02:36:57 +03:00
|
|
|
}
|
|
|
|
|
|
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 03:45:58 +03:00
|
|
|
#define sk_msg_iter_var_prev(var) \
|
|
|
|
|
do { \
|
|
|
|
|
if (var == 0) \
|
2019-11-27 23:16:41 +03:00
|
|
|
var = NR_MSG_FRAG_IDS - 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 03:45:58 +03:00
|
|
|
else \
|
|
|
|
|
var--; \
|
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
|
|
#define sk_msg_iter_var_next(var) \
|
|
|
|
|
do { \
|
|
|
|
|
var++; \
|
2019-11-27 23:16:41 +03:00
|
|
|
if (var == NR_MSG_FRAG_IDS) \
|
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 03:45:58 +03:00
|
|
|
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)
|
|
|
|
|
{
|
2019-11-27 23:16:41 +03:00
|
|
|
BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS);
|
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 03:45:58 +03:00
|
|
|
memset(msg, 0, sizeof(*msg));
|
2019-11-27 23:16:41 +03:00
|
|
|
sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS);
|
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 03:45:58 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
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;
|
2018-10-16 20:36:01 +03:00
|
|
|
dst->sg.size += size;
|
2020-05-04 20:21:44 +03:00
|
|
|
src->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 03:45:58 +03:00
|
|
|
src->sg.data[which].length -= size;
|
|
|
|
|
src->sg.data[which].offset += size;
|
|
|
|
|
}
|
|
|
|
|
|
2018-10-13 03:46:01 +03:00
|
|
|
static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src)
|
|
|
|
|
{
|
|
|
|
|
memcpy(dst, src, sizeof(*src));
|
|
|
|
|
sk_msg_init(src);
|
|
|
|
|
}
|
|
|
|
|
|
2018-10-16 21:07:59 +03:00
|
|
|
static inline bool sk_msg_full(const struct sk_msg *msg)
|
|
|
|
|
{
|
2019-11-27 23:16:41 +03:00
|
|
|
return sk_msg_iter_dist(msg->sg.start, msg->sg.end) == MAX_MSG_FRAGS;
|
2018-10-16 21:07:59 +03:00
|
|
|
}
|
|
|
|
|
|
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 03:45:58 +03:00
|
|
|
static inline u32 sk_msg_elem_used(const struct sk_msg *msg)
|
|
|
|
|
{
|
2019-11-05 02:36:57 +03:00
|
|
|
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 03:45:58 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
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 05:56:49 +03:00
|
|
|
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 03:45:58 +03:00
|
|
|
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);
|
|
|
|
|
|
2019-10-07 07:09:27 +03:00
|
|
|
if (test_bit(msg->sg.start, &msg->sg.copy)) {
|
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 03:45:58 +03:00
|
|
|
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);
|
|
|
|
|
|
2019-10-07 07:09:27 +03:00
|
|
|
__set_bit(msg->sg.end, &msg->sg.copy);
|
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 03:45:58 +03:00
|
|
|
msg->sg.size += len;
|
|
|
|
|
sk_msg_iter_next(msg, end);
|
|
|
|
|
}
|
|
|
|
|
|
2018-10-13 03:46:01 +03:00
|
|
|
static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state)
|
|
|
|
|
{
|
|
|
|
|
do {
|
2019-10-07 07:09:27 +03:00
|
|
|
if (copy_state)
|
|
|
|
|
__set_bit(i, &msg->sg.copy);
|
|
|
|
|
else
|
|
|
|
|
__clear_bit(i, &msg->sg.copy);
|
2018-10-13 03:46:01 +03:00
|
|
|
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 03:45:58 +03:00
|
|
|
static inline struct sk_psock *sk_psock(const struct sock *sk)
|
|
|
|
|
{
|
net: fix refcount bug in sk_psock_get (2)
commit 2a0133723f9ebeb751cfce19f74ec07e108bef1f upstream.
Syzkaller reports refcount bug as follows:
------------[ cut here ]------------
refcount_t: saturated; leaking memory.
WARNING: CPU: 1 PID: 3605 at lib/refcount.c:19 refcount_warn_saturate+0xf4/0x1e0 lib/refcount.c:19
Modules linked in:
CPU: 1 PID: 3605 Comm: syz-executor208 Not tainted 5.18.0-syzkaller-03023-g7e062cda7d90 #0
<TASK>
__refcount_add_not_zero include/linux/refcount.h:163 [inline]
__refcount_inc_not_zero include/linux/refcount.h:227 [inline]
refcount_inc_not_zero include/linux/refcount.h:245 [inline]
sk_psock_get+0x3bc/0x410 include/linux/skmsg.h:439
tls_data_ready+0x6d/0x1b0 net/tls/tls_sw.c:2091
tcp_data_ready+0x106/0x520 net/ipv4/tcp_input.c:4983
tcp_data_queue+0x25f2/0x4c90 net/ipv4/tcp_input.c:5057
tcp_rcv_state_process+0x1774/0x4e80 net/ipv4/tcp_input.c:6659
tcp_v4_do_rcv+0x339/0x980 net/ipv4/tcp_ipv4.c:1682
sk_backlog_rcv include/net/sock.h:1061 [inline]
__release_sock+0x134/0x3b0 net/core/sock.c:2849
release_sock+0x54/0x1b0 net/core/sock.c:3404
inet_shutdown+0x1e0/0x430 net/ipv4/af_inet.c:909
__sys_shutdown_sock net/socket.c:2331 [inline]
__sys_shutdown_sock net/socket.c:2325 [inline]
__sys_shutdown+0xf1/0x1b0 net/socket.c:2343
__do_sys_shutdown net/socket.c:2351 [inline]
__se_sys_shutdown net/socket.c:2349 [inline]
__x64_sys_shutdown+0x50/0x70 net/socket.c:2349
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x46/0xb0
</TASK>
During SMC fallback process in connect syscall, kernel will
replaces TCP with SMC. In order to forward wakeup
smc socket waitqueue after fallback, kernel will sets
clcsk->sk_user_data to origin smc socket in
smc_fback_replace_callbacks().
Later, in shutdown syscall, kernel will calls
sk_psock_get(), which treats the clcsk->sk_user_data
as psock type, triggering the refcnt warning.
So, the root cause is that smc and psock, both will use
sk_user_data field. So they will mismatch this field
easily.
This patch solves it by using another bit(defined as
SK_USER_DATA_PSOCK) in PTRMASK, to mark whether
sk_user_data points to a psock object or not.
This patch depends on a PTRMASK introduced in commit f1ff5ce2cd5e
("net, sk_msg: Clear sk_user_data pointer on clone if tagged").
For there will possibly be more flags in the sk_user_data field,
this patch also refactor sk_user_data flags code to be more generic
to improve its maintainability.
Reported-and-tested-by: syzbot+5f26f85569bd179c18ce@syzkaller.appspotmail.com
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Hawkins Jiawei <yin31149@gmail.com>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-08-05 10:48:34 +03:00
|
|
|
return __rcu_dereference_sk_user_data_with_flags(sk,
|
|
|
|
|
SK_USER_DATA_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 03:45:58 +03:00
|
|
|
}
|
|
|
|
|
|
2021-07-27 19:05:00 +03:00
|
|
|
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);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sock_drop(struct sock *sk, struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
sk_drops_add(sk, skb);
|
|
|
|
|
kfree_skb(skb);
|
|
|
|
|
}
|
|
|
|
|
|
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 03:45:58 +03:00
|
|
|
static inline void sk_psock_queue_msg(struct sk_psock *psock,
|
|
|
|
|
struct sk_msg *msg)
|
|
|
|
|
{
|
2021-03-31 05:32:23 +03:00
|
|
|
spin_lock_bh(&psock->ingress_lock);
|
2021-07-27 19:05:00 +03:00
|
|
|
if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
|
|
|
|
|
list_add_tail(&msg->list, &psock->ingress_msg);
|
2022-03-04 11:11:42 +03:00
|
|
|
else {
|
|
|
|
|
sk_msg_free(psock->sk, msg);
|
|
|
|
|
kfree(msg);
|
|
|
|
|
}
|
2021-03-31 05:32:23 +03:00
|
|
|
spin_unlock_bh(&psock->ingress_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock)
|
|
|
|
|
{
|
|
|
|
|
struct sk_msg *msg;
|
|
|
|
|
|
|
|
|
|
spin_lock_bh(&psock->ingress_lock);
|
|
|
|
|
msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);
|
|
|
|
|
if (msg)
|
|
|
|
|
list_del(&msg->list);
|
|
|
|
|
spin_unlock_bh(&psock->ingress_lock);
|
|
|
|
|
return msg;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline struct sk_msg *sk_psock_peek_msg(struct sk_psock *psock)
|
|
|
|
|
{
|
|
|
|
|
struct sk_msg *msg;
|
|
|
|
|
|
|
|
|
|
spin_lock_bh(&psock->ingress_lock);
|
|
|
|
|
msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);
|
|
|
|
|
spin_unlock_bh(&psock->ingress_lock);
|
|
|
|
|
return msg;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline struct sk_msg *sk_psock_next_msg(struct sk_psock *psock,
|
|
|
|
|
struct sk_msg *msg)
|
|
|
|
|
{
|
|
|
|
|
struct sk_msg *ret;
|
|
|
|
|
|
|
|
|
|
spin_lock_bh(&psock->ingress_lock);
|
|
|
|
|
if (list_is_last(&msg->list, &psock->ingress_msg))
|
|
|
|
|
ret = NULL;
|
|
|
|
|
else
|
|
|
|
|
ret = list_next_entry(msg, list);
|
|
|
|
|
spin_unlock_bh(&psock->ingress_lock);
|
|
|
|
|
return ret;
|
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 03:45:58 +03:00
|
|
|
}
|
|
|
|
|
|
2018-10-13 03:46:01 +03:00
|
|
|
static inline bool sk_psock_queue_empty(const struct sk_psock *psock)
|
|
|
|
|
{
|
|
|
|
|
return psock ? list_empty(&psock->ingress_msg) : true;
|
|
|
|
|
}
|
|
|
|
|
|
2021-03-31 05:32:23 +03:00
|
|
|
static inline void kfree_sk_msg(struct sk_msg *msg)
|
|
|
|
|
{
|
|
|
|
|
if (msg->skb)
|
|
|
|
|
consume_skb(msg->skb);
|
|
|
|
|
kfree(msg);
|
|
|
|
|
}
|
|
|
|
|
|
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 03:45:58 +03:00
|
|
|
static inline void sk_psock_report_error(struct sk_psock *psock, int err)
|
|
|
|
|
{
|
|
|
|
|
struct sock *sk = psock->sk;
|
|
|
|
|
|
|
|
|
|
sk->sk_err = err;
|
2021-06-28 01:48:21 +03:00
|
|
|
sk_error_report(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 03:45:58 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
struct sk_psock *sk_psock_init(struct sock *sk, int node);
|
2022-11-02 07:34:17 +03:00
|
|
|
void sk_psock_stop(struct sk_psock *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 03:45:58 +03:00
|
|
|
|
2021-02-23 21:49:26 +03:00
|
|
|
#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
|
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 03:45:58 +03:00
|
|
|
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);
|
2021-02-23 21:49:26 +03:00
|
|
|
#else
|
|
|
|
|
static inline int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
|
|
|
|
|
{
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
#endif
|
|
|
|
|
|
2020-10-11 08:09:38 +03:00
|
|
|
void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock);
|
|
|
|
|
void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *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 03:45:58 +03:00
|
|
|
|
|
|
|
|
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);
|
|
|
|
|
|
|
|
|
|
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_restore_proto(struct sock *sk,
|
|
|
|
|
struct sk_psock *psock)
|
|
|
|
|
{
|
2021-03-31 05:32:31 +03:00
|
|
|
if (psock->psock_update_sk_prot)
|
2021-04-07 06:21:11 +03:00
|
|
|
psock->psock_update_sk_prot(sk, psock, 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 03:45:58 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
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_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);
|
|
|
|
|
}
|
|
|
|
|
|
2018-12-20 22:35:33 +03:00
|
|
|
static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock)
|
|
|
|
|
{
|
2024-04-04 05:10:01 +03:00
|
|
|
read_lock_bh(&sk->sk_callback_lock);
|
2021-02-23 21:49:27 +03:00
|
|
|
if (psock->saved_data_ready)
|
|
|
|
|
psock->saved_data_ready(sk);
|
2018-12-20 22:35:33 +03:00
|
|
|
else
|
|
|
|
|
sk->sk_data_ready(sk);
|
2024-04-04 05:10:01 +03:00
|
|
|
read_unlock_bh(&sk->sk_callback_lock);
|
2018-12-20 22:35:33 +03:00
|
|
|
}
|
|
|
|
|
|
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 03:45:58 +03:00
|
|
|
static inline void psock_set_prog(struct bpf_prog **pprog,
|
|
|
|
|
struct bpf_prog *prog)
|
|
|
|
|
{
|
|
|
|
|
prog = xchg(pprog, prog);
|
|
|
|
|
if (prog)
|
|
|
|
|
bpf_prog_put(prog);
|
|
|
|
|
}
|
|
|
|
|
|
2020-06-29 12:56:28 +03:00
|
|
|
static inline int psock_replace_prog(struct bpf_prog **pprog,
|
|
|
|
|
struct bpf_prog *prog,
|
|
|
|
|
struct bpf_prog *old)
|
|
|
|
|
{
|
|
|
|
|
if (cmpxchg(pprog, old, prog) != old)
|
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
|
|
if (old)
|
|
|
|
|
bpf_prog_put(old);
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
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 03:45:58 +03:00
|
|
|
static inline void psock_progs_drop(struct sk_psock_progs *progs)
|
|
|
|
|
{
|
|
|
|
|
psock_set_prog(&progs->msg_parser, NULL);
|
2021-02-23 21:49:30 +03:00
|
|
|
psock_set_prog(&progs->stream_parser, NULL);
|
|
|
|
|
psock_set_prog(&progs->stream_verdict, NULL);
|
2021-03-31 05:32:30 +03:00
|
|
|
psock_set_prog(&progs->skb_verdict, NULL);
|
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 03:45:58 +03:00
|
|
|
}
|
|
|
|
|
|
2020-05-30 02:06:59 +03:00
|
|
|
int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb);
|
|
|
|
|
|
|
|
|
|
static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
|
|
|
|
|
{
|
|
|
|
|
if (!psock)
|
|
|
|
|
return false;
|
2021-02-23 21:49:27 +03:00
|
|
|
return !!psock->saved_data_ready;
|
2020-05-30 02:06:59 +03:00
|
|
|
}
|
2021-02-23 21:49:29 +03:00
|
|
|
|
|
|
|
|
#if IS_ENABLED(CONFIG_NET_SOCK_MSG)
|
|
|
|
|
|
2021-10-29 17:12:14 +03:00
|
|
|
#define BPF_F_STRPARSER (1UL << 1)
|
|
|
|
|
|
|
|
|
|
/* We only have two bits so far. */
|
|
|
|
|
#define BPF_F_PTR_MASK ~(BPF_F_INGRESS | BPF_F_STRPARSER)
|
|
|
|
|
|
|
|
|
|
static inline bool skb_bpf_strparser(const struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
unsigned long sk_redir = skb->_sk_redir;
|
|
|
|
|
|
|
|
|
|
return sk_redir & BPF_F_STRPARSER;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void skb_bpf_set_strparser(struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
skb->_sk_redir |= BPF_F_STRPARSER;
|
|
|
|
|
}
|
2021-02-23 21:49:29 +03:00
|
|
|
|
|
|
|
|
static inline bool skb_bpf_ingress(const struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
unsigned long sk_redir = skb->_sk_redir;
|
|
|
|
|
|
|
|
|
|
return sk_redir & BPF_F_INGRESS;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void skb_bpf_set_ingress(struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
skb->_sk_redir |= BPF_F_INGRESS;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void skb_bpf_set_redir(struct sk_buff *skb, struct sock *sk_redir,
|
|
|
|
|
bool ingress)
|
|
|
|
|
{
|
|
|
|
|
skb->_sk_redir = (unsigned long)sk_redir;
|
|
|
|
|
if (ingress)
|
|
|
|
|
skb->_sk_redir |= BPF_F_INGRESS;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline struct sock *skb_bpf_redirect_fetch(const struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
unsigned long sk_redir = skb->_sk_redir;
|
|
|
|
|
|
|
|
|
|
return (struct sock *)(sk_redir & BPF_F_PTR_MASK);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void skb_bpf_redirect_clear(struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
skb->_sk_redir = 0;
|
|
|
|
|
}
|
|
|
|
|
#endif /* CONFIG_NET_SOCK_MSG */
|
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 03:45:58 +03:00
|
|
|
#endif /* _LINUX_SKMSG_H */
|
